CN117270479A - Method and system for monitoring multi-working-procedure production line of molding plate - Google Patents
Method and system for monitoring multi-working-procedure production line of molding plate Download PDFInfo
- Publication number
- CN117270479A CN117270479A CN202311549084.XA CN202311549084A CN117270479A CN 117270479 A CN117270479 A CN 117270479A CN 202311549084 A CN202311549084 A CN 202311549084A CN 117270479 A CN117270479 A CN 117270479A
- Authority
- CN
- China
- Prior art keywords
- monitoring data
- comparison
- production line
- data set
- analyzed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 725
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 450
- 238000000034 method Methods 0.000 title claims abstract description 99
- 238000000465 moulding Methods 0.000 title claims description 21
- 239000013598 vector Substances 0.000 claims abstract description 395
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000005259 measurement Methods 0.000 claims description 97
- 238000003860 storage Methods 0.000 claims description 79
- 230000015654 memory Effects 0.000 claims description 26
- 238000007405 data analysis Methods 0.000 claims description 19
- 238000011156 evaluation Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 16
- 238000009412 basement excavation Methods 0.000 abstract 3
- 238000005065 mining Methods 0.000 description 51
- 230000005291 magnetic effect Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005265 energy consumption Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 230000004927 fusion Effects 0.000 description 3
- 238000012806 monitoring device Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000005266 casting Methods 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012731 temporal analysis Methods 0.000 description 2
- 238000000700 time series analysis Methods 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005294 ferromagnetic effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000010422 painting Methods 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 238000004381 surface treatment Methods 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/4183—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by data acquisition, e.g. workpiece identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Software Systems (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Automation & Control Theory (AREA)
- Computational Linguistics (AREA)
- Fuzzy Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The utility model provides a template multi-procedure processing production line monitoring method and system, through a plurality of monitoring data clusters that obtain the production line monitoring dataset that is to analyze, can carry out whole operation data vector description excavation, local operation data vector description excavation and equipment operation log excavation to each monitoring data cluster respectively, in carrying out the dataset matching process, can carry out the matching according to the above three types of eigenvectors that excavate, and confirm whether the production line monitoring dataset that is to analyze is the production line monitoring dataset that reproduces based on the matching result of three types of eigenvectors, because with the joint matching comparison of the three types of characteristics of dataset, confirm whether the production line monitoring dataset that is to analyze is the production line monitoring dataset that reproduces, can make the comparison result more reliable.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a method and a system for monitoring a multi-working-procedure processing production line of a molding plate.
Background
The intelligent factory is a manufacturing mode for realizing automation, high efficiency and intellectualization of the production process by utilizing advanced information technology and Internet of things technology. In plate processing, especially in a multi-procedure molding plate processing production line, more and more enterprises begin to introduce intelligent factories to help intelligent production and monitor the production state of the production line. Which can help to obtain real-time production data and metrics such as the operating conditions of the production line, the operating status of the equipment, the production progress of the product, etc. Based on the data, real-time analysis and monitoring can be performed, decision support is provided for a management layer, the management layer is helped to adjust a production plan in time, and the production flow is optimized, so that the production efficiency and quality are improved, and the intelligent development of the manufacturing industry is further promoted. How to quickly and accurately determine the production state of a multi-procedure processing production line of a molding plate is a technical problem which needs attention.
Disclosure of Invention
In view of the foregoing, embodiments of the present application provide at least a method and a system for monitoring a multi-process manufacturing line of a molding board.
The technical scheme of the embodiment of the application is realized as follows: in one aspect, an embodiment of the present application provides a method for monitoring a multi-process manufacturing line of a molding board, which is applied to a monitoring system, and the method includes: acquiring a monitoring data set of a production line to be analyzed, wherein the monitoring data set of the production line to be analyzed comprises Q monitoring data clusters, each monitoring data cluster is monitoring data of one production line in a multi-procedure processing production line of a corresponding molding plate, and Q is more than or equal to 1; respectively acquiring the overall operation data vector description of the Q monitoring data clusters and the local operation data vector description of the Q monitoring data clusters, and acquiring the equipment operation log of the monitoring data set of the production line to be analyzed; respectively comparing the overall operation data vector description of the Q monitoring data clusters with the comparison overall operation data vector description corresponding to the monitoring data sets of the comparison production line to obtain an overall vector description comparison result; respectively comparing the local operation data vector descriptions of the Q monitoring data clusters with the comparison local operation data vector descriptions corresponding to the monitoring data sets of the comparison production lines to obtain local vector description comparison results; respectively carrying out log comparison on the equipment operation log of the monitoring data set of the production line to be analyzed and the comparison equipment operation logs of the monitoring data sets of the comparison production lines to obtain log comparison results; determining a data analysis result of the to-be-analyzed production line monitoring dataset according to the overall vector description comparison result, the local vector description comparison result and the log comparison result, wherein the data analysis result represents whether the to-be-analyzed production line monitoring dataset is a recurrence production line monitoring dataset or not; if the to-be-analyzed production line monitoring data set is a reproduction production line monitoring data set, determining a target comparison production line monitoring data set for reproduction of the to-be-analyzed production line monitoring data set, and taking a production state evaluation result corresponding to the target comparison production line monitoring data set as a production state evaluation result of the to-be-analyzed production line monitoring data set.
In some embodiments, any one of the Q monitoring data clusters is considered an xth monitoring data cluster, any one of the plurality of control line monitoring data sets is considered a yth control line monitoring data set, the yth control line monitoring data set comprising P control monitoring data clusters, wherein x is greater than or equal to 1, y is greater than or equal to 1, and P is greater than or equal to 1; and comparing the overall operation data vector description of the Q monitoring data clusters with the comparison overall operation data vector description corresponding to the monitoring data sets of the comparison production line to obtain an overall vector description comparison result, wherein the overall vector description comparison result comprises: respectively determining overall commonality measurement results between the overall operation data vector description of the x-th monitoring data cluster and the comparison overall operation data vector description corresponding to the P comparison monitoring data clusters, and taking the overall commonality measurement result with the largest numerical value as the overall commonality measurement result of the x-th monitoring data cluster and the y-th comparison production line monitoring data set until determining the overall commonality measurement result of each monitoring data cluster in the Q monitoring data clusters and the y-th comparison production line monitoring data set respectively; determining an overall commonality measurement result between the to-be-analyzed production line monitoring dataset and the y-th control production line monitoring dataset according to the overall commonality measurement result of each of the Q monitoring data clusters and the y-th control production line monitoring dataset respectively until determining an overall commonality measurement result between the to-be-analyzed production line monitoring dataset and the plurality of control production line monitoring datasets; and determining the overall vector description comparison result according to the overall commonality measurement result between the to-be-analyzed production line monitoring data set and the plurality of comparison production line monitoring data sets.
In some embodiments, any one of the Q monitoring data clusters is considered an xth monitoring data cluster, any one of the plurality of control line monitoring data sets is considered a yth control line monitoring data set, the yth control line monitoring data set comprising P control monitoring data clusters, wherein x is greater than or equal to 1, y is greater than or equal to 1, and P is greater than or equal to 1; the local vector description comparison is performed on the local operation data vector descriptions of the Q monitoring data clusters and the comparison local operation data vector descriptions corresponding to the plurality of comparison production line monitoring data sets, so as to obtain local vector description comparison results, including: respectively determining local commonality measurement results between the local operation data vector descriptions of the x-th monitoring data cluster and the comparison local operation data vector descriptions corresponding to the P comparison monitoring data clusters, and taking the local commonality measurement result with the largest numerical value as the local commonality measurement result of the monitoring data clusters of the x-th monitoring data cluster and the monitoring data sets of the y-th comparison production line until determining the local commonality measurement result of each monitoring data cluster in the Q monitoring data clusters and the monitoring data sets of the y-th comparison production line; determining a local commonality measurement result between the monitoring data set of the production line to be analyzed and the monitoring data set of the y-th control production line according to the local commonality measurement result of each monitoring data cluster in the Q monitoring data clusters and the monitoring data set of the y-th control production line respectively until determining a local commonality measurement result between the monitoring data set of the production line to be analyzed and the monitoring data sets of the plurality of control production lines; and determining the local vector description comparison result according to the local commonality measurement result between the to-be-analyzed production line monitoring data set and the plurality of control production line monitoring data sets.
In some embodiments, the log comparing the device running log of the to-be-analyzed production line monitoring dataset with the comparison device running logs of the plurality of comparison production line monitoring datasets to obtain log comparison results respectively includes: determining log commonality measurement results between the equipment running logs of the production line monitoring data set to be analyzed and the comparison equipment running logs of each comparison production line monitoring data set respectively; and determining the log comparison result according to the log commonality measurement result.
In some embodiments, the method further comprises: obtaining a plurality of control line monitoring data sets, wherein each control line monitoring data set comprises P control monitoring data clusters; respectively acquiring comparison overall operation data vector descriptions of P comparison monitoring data clusters of each comparison production line monitoring data set and comparison local operation data vector descriptions of the P comparison monitoring data clusters, and respectively acquiring comparison equipment operation logs of each comparison production line monitoring data set; and correspondingly storing the comparison whole operation data vector description of the P comparison monitoring data clusters of each comparison production line monitoring data set, the comparison local operation data vector description of the P comparison monitoring data clusters and the comparison equipment operation log of each comparison production line monitoring data set in a storage space, wherein the storage space comprises the comparison whole operation data vector description, the comparison local operation data vector description and the comparison equipment operation log corresponding to the plurality of comparison production line monitoring data sets.
In some embodiments, the method further comprises: acquiring a comparison data set label of each comparison production line monitoring data set and a comparison whole operation data vector description of each comparison production line monitoring data set in the storage space; establishing a lookup table according to the control data set labels of the monitoring data sets of each control production line and the storage positions; and comparing the overall operation data vector description of the Q monitoring data clusters with the comparison overall operation data vector description corresponding to the monitoring data sets of the comparison production line to obtain an overall vector description comparison result, wherein the overall vector description comparison result comprises: acquiring a data set label of the monitoring data set of the production line to be analyzed, and matching a selected data set label set from the lookup table according to the data set label of the monitoring data set of the production line to be analyzed; retrieving a comparison overall operation data vector description corresponding to the alternative data set tag set from a storage location associated with the alternative data set tag set in the lookup table; and respectively comparing the overall operation data vector description of the Q monitoring data clusters with the comparison overall operation data vector description corresponding to the alternative data set label set to obtain an overall vector description comparison result.
In some embodiments, the lookup table includes a total lookup table and a sub-lookup table, the total lookup table having an update duration interval greater than an update duration interval of the sub-lookup table.
In some embodiments, the determining the data analysis result of the line monitoring dataset to be analyzed according to the overall vector description comparison result, the local vector description comparison result and the log comparison result comprises: acquiring production process parameters of the monitoring data set of the production line to be analyzed, and determining target emphasis elements corresponding to the monitoring data set of the production line to be analyzed according to the production process parameters; acquiring a first eccentric weight corresponding to the overall operation data vector description, a second eccentric weight corresponding to the local operation data vector description and a third eccentric weight corresponding to the equipment operation log under the target weight element; and determining a data analysis result of the monitoring data set of the production line to be analyzed according to the first eccentric weight, the overall vector description comparison result, the second eccentric weight, the local vector description comparison result, the third eccentric weight and the log comparison result.
In some embodiments, the method further comprises: and if the data analysis result of the to-be-analyzed production line monitoring data set indicates that the to-be-analyzed production line monitoring data set is not a reproduction production line monitoring data set, carrying out manual auditing on the to-be-analyzed production line monitoring data set, determining a production state evaluation result of the to-be-analyzed production line monitoring data set, and taking the audited to-be-analyzed production line monitoring data set as a new comparison to the to-be-analyzed production line monitoring data set.
In another aspect, the present application provides a monitoring system comprising a memory and a processor, the memory storing a computer program executable on the processor, the processor implementing the steps of the method described above when the program is executed.
The beneficial effects of this application include at least: according to the method for monitoring the multi-procedure processing production line of the molding plate, through the acquisition of the plurality of monitoring data clusters of the monitoring data set of the production line to be analyzed, the overall operation data vector description mining, the local operation data vector description mining and the equipment operation log mining can be respectively carried out on each monitoring data cluster, so that in the data set matching process, matching comparison can be carried out according to the three types of the feature vectors which are mined, and whether the monitoring data set of the production line to be analyzed is a monitoring data set of the production line to be analyzed is determined based on the matching results of the three types of the feature vectors.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the aspects of the present application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and, together with the description, serve to explain the technical aspects of the application.
Fig. 1 is a schematic implementation flow chart of a method for monitoring a multi-process processing line of a molding plate according to an embodiment of the present application;
fig. 2 is a schematic diagram of a composition structure of a monitoring device according to an embodiment of the present application;
fig. 3 is a schematic hardware entity diagram of a monitoring system according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application are further elaborated below in conjunction with the accompanying drawings and examples, which should not be construed as limiting the present application, and all other embodiments obtained by those skilled in the art without making inventive efforts are within the scope of protection of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with one another without conflict. The term "first/second/third" is merely to distinguish similar objects and does not represent a specific ordering of objects, it being understood that the "first/second/third" may be interchanged with a specific order or sequence, as permitted, to enable embodiments of the present application described herein to be practiced otherwise than as illustrated or described herein.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing the present application only and is not intended to be limiting of the present application.
Embodiments of the present application provide a method for monitoring a multi-process manufacturing line of a molding plate, which may be performed by a processor of a monitoring system. The monitoring system may refer to a device with data processing capabilities such as a server, a notebook computer, a tablet computer, a desktop computer, a mobile device (e.g., a mobile phone, a portable video player, a personal digital assistant, a dedicated messaging device, a portable gaming device), etc.
Fig. 1 is a schematic implementation flow chart of a method for monitoring a multi-process processing production line of a molding plate according to an embodiment of the present application, as shown in fig. 1, the method includes the following steps: step S110, a production line monitoring data set to be analyzed is obtained.
The data in the production line monitoring data set may include one or more of sensor data, production data, energy data, equipment status data, log data and the like in the production process, for example, various parameters such as temperature, humidity, pressure, vibration and the like can be collected and monitored through sensors arranged on the multi-process production line of the molding plate, the production data may include data such as production speed, cycle time, yield and the like, the energy data includes the use condition of energy such as electric power, water, gas and the like, the equipment status data includes the operation time, failure times, maintenance records and the like of equipment, and the log data includes various log data such as equipment operation log, operator operation log and the like generated in the operation process of the production line. The monitoring data set of the production line to be analyzed can comprise Q monitoring data clusters, wherein Q is more than or equal to 1. Each monitoring data cluster is the monitoring data of one production line in the multi-procedure processing production line of the corresponding molding plate. For example, in a multi-process manufacturing line for a molding board, multiple processes such as cutting, trimming, cleaning, grooving, bending, connecting and fixing, surface treatment (such as polishing, spraying, painting, film pasting, etc.) are involved, each process involves related manufacturing equipment, i.e. a separate manufacturing line, and then a monitoring data cluster is generated corresponding to each separate manufacturing line, and all the monitoring data clusters form a monitoring data set of the manufacturing line to be analyzed. For discrete data, such as running state (on, off, alarm, etc.) data of the device, the discrete data may be encoded to obtain numerical data for subsequent operation, where the encoding mode is, for example, single-heat encoding.
If one line monitoring data set to be analyzed is included, Q monitoring data clusters of the line monitoring data set to be analyzed are extracted. If a plurality of line monitoring data sets to be analyzed are included, respectively carrying out consistent operation on each line monitoring data set to be analyzed to obtain Q monitoring data clusters of each line monitoring data set to be analyzed, subsequently respectively processing each line monitoring data set to be analyzed and Q monitoring data clusters of each line monitoring data set to be analyzed, determining the data analysis result of each line monitoring data set to be analyzed, and determining whether each line monitoring data set to be analyzed is a reproduction line monitoring data set (namely, a reappearance data set similar to a historical line monitoring data set).
Step S120, respectively obtaining the overall operation data vector descriptions of the Q monitoring data clusters and the local operation data vector descriptions of the Q monitoring data clusters, and obtaining the device operation log of the monitoring data set of the production line to be analyzed.
In the embodiment of the application, the Q monitoring data clusters can be processed respectively to obtain the overall operation data vector description of each monitoring data cluster, the Q monitoring data clusters are processed respectively to obtain the local operation data vector description of each monitoring data cluster, and the monitoring data set of the production line to be analyzed is processed to obtain the equipment operation log of the monitoring data set of the production line to be analyzed. The overall operation data vector description may be used to describe operation characteristics of the production line in the monitored data cluster, for example, the overall operation data vector description may reflect a production state corresponding to the monitored data cluster, and may include production efficiency information (e.g., yield utilization qualification index, such as disqualification, general, qualification, and excellent), energy consumption information (e.g., high energy consumption, medium energy consumption, low energy consumption, etc.), and production abnormality evaluation information (e.g., fault early warning, fault reminding, normal state, etc.). By obtaining the overall operational data vector description, it can be determined to which production state the monitoring data cluster belongs. The local run data vector description may be used to describe data detail features in the monitoring data cluster, e.g., the local run data vector description may include core data in the monitoring data cluster, such as abrupt temperature data, peak power consumption data, etc., with prominent features, typically maxima, minima, inflection points, etc. The equipment operation log is an operation log of equipment of a production line involved in the production line monitoring dataset to be analyzed, and can comprise operation records and personnel maintenance records so as to ensure consistency of operation basis of the equipment when subsequent comparison matches.
Optionally, when the overall operation data vector description of the Q monitoring data clusters is obtained, vector description mining may be performed on the Q monitoring data clusters according to the overall operation data vector description mining network, so as to obtain an overall operation data vector description of each monitoring data cluster in the Q monitoring data clusters. For example, the overall operational data vector describes that the mining network is a CNN (convolutional neural network, such as a residual network), or RNN (recurrent neural network).
Before vector description mining is carried out on Q monitoring data clusters based on the whole operation data vector description mining network, the whole operation data vector description mining network is debugged, so that the debugged whole operation data vector description mining network has the capability of carrying out vector description mining on Q monitoring data clusters to obtain the whole operation data vector description of the Q monitoring data clusters.
As one embodiment, Q monitoring data cluster samples of the monitoring data set samples of the production line and global vector description tag samples of the Q monitoring data cluster samples are obtained, the Q monitoring data cluster samples are respectively input into a global operation data vector description mining network, global operation data vector description output samples of each monitoring data cluster sample in the Q monitoring data cluster samples are respectively output, and the global operation data vector description mining network is trained according to the global operation data vector description output samples of the Q monitoring data cluster samples and the global vector description tag samples of the Q monitoring data cluster samples. The overall vector description label sample of the Q monitoring data cluster samples is a real overall operation data vector description of the monitoring data cluster sample obtained in advance, and the overall operation data vector description output sample is an overall operation data vector description sample output by mining a network according to the overall operation data vector description, namely, the output of the network. The desire to debug the whole run data vector description mining network is to have the output result of the network (i.e., the whole run data vector description output sample) and the whole vector description tag sample converge. If the network output result is the same as the overall vector description label sample, the overall operation data vector description mining network at the moment is stored, and when the overall operation data vector description mining network is applied, vector description mining is carried out on Q monitoring data clusters based on the overall operation data vector description mining network, so that overall operation data vector descriptions of the Q monitoring data clusters are obtained. When the whole operation data vector description mining network is debugged, a large number of monitoring data clusters corresponding to the production line monitoring data set samples can be used for debugging the whole operation data vector description mining network, so that the network debugging quality is improved.
Optionally, when the local operation data vector descriptions of the Q monitoring data clusters are obtained, vector description mining may be performed on the Q monitoring data clusters according to the local operation data vector description mining network, so as to obtain the local operation data vector description of each monitoring data cluster in the Q monitoring data clusters. The local run data vector description mining network may be, for example, any viable neural network such as a convolutional self-encoder (Convolutional Autoencoder) or time series analysis network (Time Series Analysis) or LSTM (long short-term memory network).
Before vector description mining is carried out on Q monitoring data clusters based on the local operation data vector description mining network, debugging is carried out on the local operation data vector description mining network, so that the debugged local operation data vector description mining network can have the capability of carrying out vector description mining on Q monitoring data clusters to obtain the local operation data vector description of the Q monitoring data clusters. As one embodiment, Q monitoring data cluster samples of the monitoring data set samples of the production line and local operation data vector description tag samples of the Q monitoring data cluster samples are obtained, the Q monitoring data cluster samples are respectively input into a local operation data vector description mining network, local operation data vector description output samples of each monitoring data cluster sample in the Q monitoring data cluster samples are respectively output, and the local operation data vector description mining network is trained according to the local operation data vector description tag samples of the Q monitoring data cluster samples and the local operation data vector description output samples of the Q monitoring data cluster samples. The local operation data vector description label samples of the Q monitoring data cluster samples refer to real local operation data vector description samples of the monitoring data cluster samples obtained in advance, and the local operation data vector description output samples refer to local operation data vector description samples output by mining a network according to the local operation data vector description, namely, output of the network. And debugging the local operation data vector description mining network according to the output of the local operation data vector description mining network and the real local operation data vector description sample. Debugging a local run data vector description mining network is expected to converge the output of the network with the actual local run data vector description samples (local run data vector description tag samples). And if the output of the network is consistent with the real local operation data vector description sample, storing a local operation data vector description mining network, and carrying out vector description mining on Q monitoring data clusters based on the local operation data vector description mining network to obtain local operation data vector descriptions of the Q monitoring data clusters when the local operation data vector description mining network is applied. Similarly, when the local operation data vector description mining network is debugged, the local operation data vector description mining network is debugged based on monitoring data clusters corresponding to a large number of production line monitoring data set samples, and network performance is improved.
After the whole operation data vector description, the local operation data vector description and the equipment operation log of each production line monitoring data set are mined, the above data are stored (for example, cloud loading) to determine the storage positions (i.e. addresses) of the whole operation data vector description, the local operation data vector description and the equipment operation log in a storage system, and the storage spaces of the storage positions in the storage system are recorded, so that the extraction is convenient.
And step S130, carrying out overall vector description comparison on the overall operation data vector descriptions of the Q monitoring data clusters and the comparison overall operation data vector descriptions corresponding to the monitoring data sets of the comparison production lines respectively, and obtaining an overall vector description comparison result.
In this embodiment of the present application, because the overall operation data vector descriptions of Q monitoring data clusters are obtained, overall vector description comparison may be performed according to the overall operation data vector description of each monitoring data cluster in Q monitoring data clusters and comparison overall operation data vector descriptions corresponding to a plurality of comparison production line monitoring data sets, so as to obtain an overall vector description comparison result. The comparison production line monitoring data sets can correspond to Q comparison monitoring data clusters, and the comparison overall operation data vector description of each comparison monitoring data cluster can be obtained by carrying out overall operation data vector description mining on each comparison monitoring data cluster. And carrying out overall vector description comparison on the overall operation data vector descriptions of the Q monitoring data clusters and the comparison overall operation data vector descriptions corresponding to the comparison production line monitoring data sets to obtain overall vector description comparison results, namely carrying out overall vector description comparison on the overall operation data vector descriptions of the Q monitoring data clusters and the comparison overall operation data vector descriptions corresponding to the comparison production line monitoring data sets respectively to obtain overall vector description comparison results between the to-be-analyzed production line monitoring data sets and the comparison production line monitoring data sets.
As one implementation, any one of the Q monitoring data clusters is regarded as an xth monitoring data cluster, any one of the plurality of control line monitoring data sets is regarded as a yth control line monitoring data set, the yth control line monitoring data set comprises P control monitoring data clusters, wherein x is greater than or equal to 1, y is greater than or equal to 1, and P is greater than or equal to 1, and the overall vector description comparison process comprises: respectively determining overall commonality measurement results between the overall operation data vector description of the x-th monitoring data cluster and the comparison overall operation data vector description corresponding to the P comparison monitoring data clusters, and taking the overall commonality measurement result with the largest numerical value as the overall commonality measurement result of the x-th monitoring data cluster and the y-th comparison production line monitoring data set until determining the overall commonality measurement result of each monitoring data cluster in the Q monitoring data clusters and the y-th comparison production line monitoring data set respectively; determining an overall commonality measurement result between the monitoring data set of the production line to be analyzed and the monitoring data set of the y-th control production line according to the overall commonality measurement result of each monitoring data cluster in the Q monitoring data clusters and the monitoring data set of the y-th control production line respectively until determining the overall commonality measurement result between the monitoring data set of the production line to be analyzed and the monitoring data sets of the plurality of control production lines; and determining an overall vector description comparison result according to the overall commonality measurement result between the to-be-analyzed production line monitoring data set and the plurality of comparison production line monitoring data sets. The similarity between the two vectors is represented by the commonality measurement result, and the determination mode of the overall commonality measurement result may be that the distance between the vectors is calculated, such as euclidean distance, cosine distance, and the like.
In addition, the overall commonality measurement result between the monitoring data set of the production line to be analyzed and the monitoring data set of the y-th control production line can be determined according to the overall commonality measurement result between each monitoring data cluster in the Q monitoring data clusters and the monitoring data set of the y-th control production line, so that the overall commonality measurement result between the monitoring data set of the production line to be analyzed and each monitoring data set of the plurality of monitoring data sets of the control production line can be determined. For example, the overall commonality measurement result of the three comparison monitoring data clusters corresponding to the y-th comparison production line monitoring data set by the Q monitoring data clusters is 0.7, 0.5 and 0.64 respectively, and then, according to the average value of the overall commonality measurement results of the Q monitoring data clusters and the y-th comparison production line monitoring data set, determining the overall commonality measurement result between the to-be-analyzed production line monitoring data set and the y-th comparison production line monitoring data set, for example, the overall commonality measurement result between the to-be-analyzed production line monitoring data set and the y-th comparison production line monitoring data set is (0.7+0.5+0.64) +.3=0.61. And respectively carrying out overall vector description comparison on each comparison production line monitoring dataset and the to-be-analyzed production line monitoring dataset to obtain overall commonality measurement results between each comparison production line monitoring dataset and the to-be-analyzed production line monitoring dataset in the comparison production line monitoring datasets, wherein the overall vector description comparison results comprise overall commonality measurement results between each comparison production line monitoring dataset and the to-be-analyzed production line monitoring dataset in the comparison production line monitoring datasets, namely overall commonality measurement results between the to-be-analyzed production line monitoring datasets and each comparison production line monitoring dataset.
And step S140, carrying out local vector description comparison on the local operation data vector descriptions of the Q monitoring data clusters and the comparison local operation data vector descriptions corresponding to the monitoring data sets of the comparison production line respectively, and obtaining a local vector description comparison result.
In this embodiment of the present application, because the local operation data vector descriptions of Q monitoring data clusters are obtained, local vector description comparison may be performed according to the local operation data vector description of each monitoring data cluster in Q monitoring data clusters and the comparison local operation data vector descriptions corresponding to the multiple comparison production line monitoring data sets, so as to obtain a local vector description comparison result. The method comprises the steps that each comparison production line monitoring data set can correspond to Q comparison monitoring data clusters, and the comparison local operation data vector description of each comparison monitoring data cluster can be obtained based on the local operation data vector description mining of each comparison monitoring data cluster. And comparing the local operation data vector descriptions of the Q monitoring data clusters with the contrast local operation data vector descriptions corresponding to the monitoring data sets of the contrast production line to obtain local vector description comparison results, for example, comparing the local operation data vector descriptions of the Q monitoring data clusters with the contrast local operation data vector descriptions corresponding to the monitoring data sets of each contrast production line respectively to obtain local vector description comparison results between the monitoring data sets of the production line to be analyzed and the monitoring data sets of each contrast production line.
As one embodiment, any one of the Q monitoring data clusters is considered as an xth monitoring data cluster, any one of the plurality of control line monitoring data sets is considered as a yth control line monitoring data set, the yth control line monitoring data set comprises P control monitoring data clusters, wherein x is greater than or equal to 1, y is greater than or equal to 1, and P is greater than or equal to 1, and the process of comparing the local vector descriptions can comprise: respectively determining local commonality measurement results between the local operation data vector description of the x-th monitoring data cluster and the comparison local operation data vector description corresponding to the P comparison monitoring data clusters, and taking the local commonality measurement result with the largest numerical value as the local commonality measurement result of the x-th monitoring data cluster and the y-th comparison production line monitoring data set until determining the local commonality measurement result of each monitoring data cluster in the Q monitoring data clusters and the y-th comparison production line monitoring data set respectively; determining a local commonality measurement result between the monitoring data set of the production line to be analyzed and the monitoring data set of the y-th control production line according to the local commonality measurement result of each monitoring data cluster in the Q monitoring data clusters and the monitoring data set of the y-th control production line respectively until determining the local commonality measurement result between the monitoring data set of the production line to be analyzed and the monitoring data sets of the plurality of control production lines; and determining a local vector description comparison result according to the local commonality measurement result between the to-be-analyzed production line monitoring data set and the plurality of control production line monitoring data sets. The determining manner of the local commonality measurement result can refer to the determining manner of the whole commonality measurement result.
In addition, a local commonality measurement result between the monitoring data set of the production line to be analyzed and the monitoring data set of the y-th control production line can be determined according to the local commonality measurement result between each monitoring data cluster in the Q monitoring data clusters and each monitoring data set of the y-th control production line, so that a local commonality measurement result between the monitoring data set of the production line to be analyzed and each monitoring data set of the plurality of monitoring data sets of the control production line can be determined. For example, the local commonality measurement results of the Q monitoring data clusters and the three comparison monitoring data clusters corresponding to the y-th comparison production line monitoring data set are sequentially 0.7, 0.5 and 0.64, and the local commonality measurement result between the to-be-analyzed production line monitoring data set and the y-th comparison production line monitoring data set can be determined according to the average value of the local commonality measurement results of the Q monitoring data clusters and the y-th comparison production line monitoring data set. For example, the local commonality measurement result between the monitoring data set of the to-be-analyzed production line and the monitoring data set of the y-th comparison production line is (0.7+0.5+0.64)/(3=0.61), and local vector description comparison is performed on each monitoring data set of the comparison production line and the monitoring data set of the to-be-analyzed production line respectively to obtain local commonality measurement results between each monitoring data set of the comparison production line and the monitoring data set of the to-be-analyzed production line respectively, and then the local vector description comparison results may include local commonality measurement results between each monitoring data set of the comparison production line and the monitoring data set of the to-be-analyzed production line respectively, i.e. local commonality measurement results between the monitoring data set of the to-be-analyzed production line and each monitoring data set of the comparison production line respectively.
And step S150, respectively carrying out log comparison on the equipment operation logs of the production line monitoring data set to be analyzed and the comparison equipment operation logs of the comparison production line monitoring data sets to obtain log comparison results.
In the embodiment of the application, the equipment operation log of the production line monitoring data set to be analyzed is respectively compared with the comparison equipment operation log of each comparison production line monitoring data set in the plurality of comparison production line monitoring data sets, so that a log comparison result is obtained. For example, determining a log commonality metric result between a device running log of a production line monitoring dataset to be analyzed and a collation device running log of each collation production line monitoring dataset, respectively; and determining a log comparison result according to the log commonality measurement result. For example, device running logs of the production line monitoring data set to be analyzed and comparison device running logs of the production line monitoring data set can be respectively mined, so that a log commonality measurement result between the two device running logs is determined. For example, if the production line monitoring dataset includes a device log, and the comparison production line monitoring dataset includes a comparison device log, then a log commonality metric between the device log and the comparison device log may be determined.
In the device running log, text data describing the maintenance record of the device is generally recorded, as a specific implementation manner, the device running log and the comparison device running log can be vectorized respectively, for example, text is embedded and encoded based on a word bag model and TF-IDF to obtain text vectors, and then a commonality measurement result between the text vectors corresponding to the device running log and the comparison device running log respectively is calculated based on a cosine similarity algorithm to be used as a log commonality measurement result.
Step S160, determining a data analysis result of the to-be-analyzed production line monitoring data set according to the overall vector description comparison result, the local vector description comparison result and the log comparison result, wherein the data analysis result represents whether the to-be-analyzed production line monitoring data set is a recurring production line monitoring data set.
In this embodiment of the present application, since the overall vector description comparison result, the local vector description comparison result, and the log comparison result between the line monitoring data set to be analyzed and each of the plurality of line monitoring data sets to be compared are obtained, it may be determined whether the line monitoring data set to be analyzed and each of the line monitoring data sets to be analyzed are recurring line monitoring data sets (i.e., similar line monitoring data sets that reappear, i.e., the common measurement result of one line monitoring data set and the line monitoring data set to be analyzed in the line monitoring data sets to be analyzed is greater than the threshold value) by combining the overall vector description comparison result, the local vector description comparison result, and the log comparison result. For example, when two or more of the overall vector description comparison result, the local vector description comparison result, and the log comparison result indicate that the line monitoring data set to be analyzed matches the control line monitoring data set, the line monitoring data set to be analyzed is determined to be a recurring line monitoring data set. Or when the whole vector description comparison result, the local vector description comparison result and the log comparison result all indicate that the to-be-analyzed production line monitoring data set is matched with the control production line monitoring data set, determining that the to-be-analyzed production line monitoring data set is a reproduction production line monitoring data set.
As one embodiment, because the global vector description comparison result includes global commonality measurement results between the to-be-analyzed line monitoring dataset and each of the control line monitoring datasets, the local vector description comparison result includes local commonality measurement results between the to-be-analyzed line monitoring dataset and each of the control line monitoring datasets, and the log comparison result includes log commonality measurement results between the to-be-analyzed line monitoring dataset and each of the control line monitoring datasets. Then, a fusion commonality measurement result between the to-be-analyzed production line monitoring dataset and each control production line monitoring dataset is determined according to three commonality measurement results (an overall commonality measurement result, a local commonality measurement result and a device running log commonality measurement result), and whether the to-be-analyzed production line monitoring dataset is matched with the control production line monitoring dataset is determined according to a fusion commonality measurement result between the to-be-analyzed production line monitoring dataset and each control production line monitoring dataset and a commonality measurement result threshold value, so that whether the to-be-analyzed production line monitoring dataset is a reproduction production line monitoring dataset is determined. For example, if the overall commonality measurement result between the to-be-analyzed line monitoring dataset and each control line monitoring dataset is S1, the local commonality measurement result is S2, and the log commonality measurement result is S3, the fusion commonality measurement result between the to-be-analyzed line monitoring dataset and the control line monitoring dataset may be s= (s1+s2+s3)/(3). And if S is greater than the commonality measurement result threshold value, the data set of the to-be-analyzed production line is matched with the data set of the control production line, and the data set of the to-be-analyzed production line is the data set of the reproduction production line. If S is not greater than the commonality measurement result threshold, the data set is not matched with the reference data set, and the data set is not a duplicate data set.
In other embodiments, different eccentric weights (i.e., weights) may be determined according to the emphasis factors corresponding to the line monitoring data set to be analyzed, and the matching determination result of the line monitoring data set to be analyzed and the control line monitoring data set may be determined in combination with the eccentric weights, so as to determine whether the line monitoring data set to be analyzed is a recurring line monitoring data set. For example, obtaining production process parameters (such as a mold material, a friction coefficient of a separating agent, a type proportion of a mold base, a shape and a size of a sand core, a casting temperature and a casting speed, a release agent and the like) of a monitoring dataset of a production line to be analyzed, wherein different production process parameters have different influences on the production line of different links, for example, factors with higher requirements on equipment maintenance, such as the shape of the sand core and the type of the mold base, and a running log can occupy larger eccentric weight value), and determining a target weight factor corresponding to the monitoring dataset of the production line to be analyzed according to the production process parameters; acquiring a first eccentric weight corresponding to the overall operation data vector description, a second eccentric weight corresponding to the local operation data vector description and a third eccentric weight corresponding to the equipment operation log under the target weight element; and determining a data analysis result of the monitoring data set of the production line to be analyzed according to the first eccentric weight, the overall vector description comparison result, the second eccentric weight, the local vector description comparison result, the third eccentric weight and the log comparison result.
Because the target emphasis factors corresponding to the line monitoring data set to be analyzed are different, when whether the line monitoring data set to be analyzed is a reproduction line monitoring data set under the target emphasis factors is analyzed, the concerned layers of the line monitoring data set are different. And determining the target emphasis element of the monitoring data set of the production line to be analyzed by combining the production process parameters of the monitoring data set of the production line to be analyzed, and then evaluating whether the monitoring data set of the production line to be analyzed is a repeated monitoring data set of the production line by combining the eccentric weight of each aspect under the target emphasis element, so that the accuracy of matching is improved.
Optionally, after determining the data analysis result of the line monitoring data set to be analyzed, the line monitoring data set to be analyzed may also be processed for a specific data analysis result. For example, if the data analysis result of the line monitoring data set to be analyzed indicates that the line monitoring data set to be analyzed is not a recurring line monitoring data set, the line monitoring data set to be analyzed is manually audited, the production state evaluation result of the line monitoring data set to be analyzed is determined, and the audited line monitoring data set to be analyzed is used as a new comparison line monitoring data set to be analyzed.
Step S170, if the monitoring data set of the production line to be analyzed is a reproduction monitoring data set of the production line, determining a target comparison monitoring data set of the production line to be analyzed, and taking the production state evaluation result corresponding to the target comparison monitoring data set as the production state evaluation result of the monitoring data set of the production line to be analyzed.
It can be understood that each of the pre-stored control line monitoring data sets is matched with corresponding production state evaluation result information in advance, and after the target control line monitoring data set is determined, the production state evaluation result corresponding to the target control line monitoring data set is directly used as the production state evaluation result of the production line monitoring data set, so that the production state evaluation result of the production line monitoring data set can be obtained quickly and accurately.
According to the embodiment of the application, through obtaining the plurality of monitoring data clusters of the monitoring data set of the production line to be analyzed, the overall operation data vector description mining, the local operation data vector description mining and the equipment operation log mining can be respectively carried out on each monitoring data cluster, so that in the data set matching process, matching can be carried out according to three types of information obtained through mining, and whether the monitoring data set of the production line to be analyzed is a monitoring data set of the production line to be analyzed is determined based on the matching results of the three types of feature vectors. When the integral vector description comparison is performed by acquiring the integral operation data vector description corresponding to the plurality of comparison production line monitoring data sets, the integral vector description comparison can be performed by firstly acquiring the comparison integral operation data vector description, the comparison local operation data vector description and the comparison equipment operation log of the plurality of comparison production line monitoring data sets so as to directly acquire the comparison integral operation data vector description corresponding to the plurality of comparison production line monitoring data sets.
As another embodiment, the method for monitoring a multi-process manufacturing line of a molding plate provided in the examples of the present application may include the steps of: step S210, obtaining a reference data set label of each reference production line monitoring data set and a reference overall operation data vector description of each reference production line monitoring data set in a storage space.
According to the embodiment of the application, as the storage position of the comparison data set label of each comparison production line monitoring data set and the comparison whole operation data vector description of each comparison production line monitoring data set in the storage space is required to be obtained, the comparison whole operation data vector description of each comparison production line monitoring data set is stored in the storage space, vector description mining processing is carried out on a plurality of comparison production line monitoring data sets in advance, and the whole operation data vector description, the local operation data vector description and the equipment operation log of a plurality of comparison production line monitoring data sets corresponding to the comparison production line monitoring data sets are obtained, so that the acquisition and the matching according to the acquired data are facilitated.
As one embodiment, a method for storing in a storage space a global operational data vector description, a local operational data vector description, and a device operational log of a plurality of control line monitoring data sets, corresponding to the plurality of control line monitoring data sets, includes: acquiring a plurality of control production line monitoring data sets and P control monitoring data clusters of each control production line monitoring data set; respectively acquiring comparison overall operation data vector descriptions of P comparison monitoring data clusters and comparison local operation data vector descriptions of P comparison monitoring data clusters of each comparison production line monitoring data set, and respectively acquiring comparison equipment operation logs of each comparison production line monitoring data set; and correspondingly storing the comparison whole operation data vector description of the P comparison monitoring data clusters contained in each comparison production line monitoring data set, the comparison local operation data vector description of the P comparison monitoring data clusters and the comparison equipment operation log of each comparison production line monitoring data set in a storage space. When overall vector description comparison is carried out by using the overall operation data vector descriptions of the Q monitoring data clusters to obtain overall vector description comparison results, obtaining comparison overall operation data vector descriptions corresponding to a plurality of comparison production line monitoring data sets in a storage space; and respectively comparing the overall operation data vector description of the Q monitoring data clusters with the comparison overall operation data vector description corresponding to the monitoring data sets of the comparison production line to obtain an overall vector description comparison result. The storage space comprises a plurality of comparison whole operation data vector descriptions, comparison local operation data vector descriptions and comparison equipment operation logs corresponding to the comparison production line monitoring data sets.
By acquiring the comparison overall operation data vector description of the P comparison monitoring data clusters corresponding to the comparison production line monitoring data set, the comparison local operation data vector description of the P comparison monitoring data clusters, and the comparison equipment operation log of the comparison production line monitoring data set, the comparison overall operation data vector description of the P comparison monitoring data clusters corresponding to the comparison production line monitoring data set, the comparison local operation data vector description of the P comparison monitoring data clusters, and the comparison equipment operation log of the comparison production line monitoring data set can be correspondingly stored in the storage space. In one embodiment, since the plurality of cross-reference line monitoring data sets of cross-reference global operational data vector descriptions, cross-reference local operational data vector descriptions and cross-reference device operational logs are stored in the storage space, when the cross-reference global operational data vector descriptions are obtained to compare the global operational data vector descriptions with the global operational data vector descriptions of the Q monitoring data clusters, the cross-reference global operational data vector descriptions, the cross-reference local operational data vector descriptions and the cross-reference device operational logs of each cross-reference line monitoring data set may be obtained to match, which causes additional calculation overhead, but only the cross-reference global operational data vector descriptions of each cross-reference line monitoring data set need to be obtained to match when the cross-reference global operational data vector descriptions are compared. In order to reduce the matching time of the overall operation data vector description, a lookup table can be built only based on the comparison overall operation data vector description, and the lookup table (i.e. index catalog) is not built by using the comparison overall operation data vector description, the comparison local operation data vector description and the comparison equipment operation log, so that the comparison overall operation data vector description can be quickly acquired at the corresponding storage position according to the lookup table, and the efficiency is improved.
As an embodiment, a collation data set label for each collation line monitoring data set and a collation overall operation data vector description for each collation line monitoring data set in a plurality of collation line monitoring data sets may be obtained. The control data set label can comprise an ID of the control production line monitoring data set, a process parameter type of the control production line monitoring data set and a classification label of the control production line monitoring data set. The classification label of the control line monitoring dataset is, for example, a preset operation state classification label of the control line monitoring dataset. The storage location is a fetch address in the storage space for a reference global operational data vector description of the reference line monitoring dataset, based on which the reference global operational data vector description of the reference line monitoring dataset may be fetched.
Step S220, a lookup table is established according to the control data set labels and the storage positions of each control production line monitoring data set.
In the embodiment of the application, because the comparison data set label of each comparison production line monitoring data set and the comparison overall operation data vector of each comparison production line monitoring data set are obtained to describe the storage position in the storage space, the lookup table can be established according to the comparison data set label and the storage position of each comparison production line monitoring data set. The position of the comparison whole operation data vector description of the comparison production line monitoring data set corresponding to each comparison data set label in the storage space can be quickened through the lookup table, so that the comparison whole operation data vector description can be quickened to be obtained.
As one implementation mode, because the storage space comprises the comparison whole operation data vector description, the comparison local operation data vector description and the comparison equipment operation log corresponding to the comparison production line monitoring data sets, the lookup table can be established according to at least one of the comparison whole operation data vector description, the comparison local operation data vector description and the comparison equipment operation log corresponding to the comparison production line monitoring data sets, so that the query efficiency is improved. For example, acquiring a comparison data set label of each comparison production line monitoring data set and a comparison data set vector description of each comparison production line monitoring data set in a storage position in a storage space, and establishing a lookup table according to the comparison data set label and the storage position of each comparison production line monitoring data set; acquiring a data set label of a monitoring data set of the production line to be analyzed, and matching a selected data set label set from a lookup table according to the data set label of the monitoring data set of the production line to be analyzed; and retrieving the comparison data set vector description corresponding to the alternative data set label set from the storage position associated with the alternative data set label set in the lookup table, and respectively carrying out data set vector description matching on the data set vector description of the Q monitoring data clusters and the comparison data set vector description corresponding to the alternative data set label set to obtain a data set vector description matching result. The cross-reference data set vector description of the cross-reference line monitoring data set includes at least one of a cross-reference global operational data vector description of the cross-reference line monitoring data set, a cross-reference local operational data vector description, and a cross-reference equipment operational log. The data set vector description of the production line monitoring data set to be analyzed includes one or more of an overall operational data vector description, a local operational data vector description, and a device operational log of the production line monitoring data set to be analyzed.
In other words, when the collation global operation data vector description, the collation local operation data vector description and the collation equipment operation log of the collation line monitoring data set are mined, a lookup table is established according to at least one of the collation global operation data vector description, the collation local operation data vector description and the collation equipment operation log of the collation line monitoring data set, and the storage location of the corresponding information can be obtained from the lookup table later. For example, the lookup table includes a storage location described with respect to the local operation data vector, and when the local vector description comparison is performed, the storage location described with respect to the local operation data vector in the lookup table may be acquired, and the local vector description comparison with respect to the local operation data vector description may be invoked from the storage location.
Step S230, acquiring the data set label of the monitoring data set of the production line to be analyzed, and matching the selected data set label set from the lookup table according to the data set label of the monitoring data set of the production line to be analyzed.
In this embodiment of the present application, the description of the reference data set vector of the reference line monitoring data set includes description of the reference overall operation data vector, in other words, description of the reference overall operation data vector according to the reference overall operation data vector of the reference line monitoring data set is described by creating a lookup table, because the lookup table is generated, when the reference overall operation data vector descriptions corresponding to the reference line monitoring data sets are obtained from the storage space, the data set label of the line monitoring data set to be analyzed can be obtained, and the set of the selected data set label is matched from the lookup table according to the data set label of the line monitoring data set to be analyzed. The data set label of the to-be-analyzed production line monitoring data set can comprise an ID of the to-be-analyzed production line monitoring data set, a production process parameter type of the to-be-analyzed production line monitoring data set, a classification label of the to-be-analyzed production line monitoring data set and the like. When the data set label of the monitoring data set of the production line to be analyzed is matched with the selected data set label set from the lookup table, all the comparison data set labels in the lookup table are determined to be matched candidate data set label sets, or the comparison data set label matched with the data set label of the monitoring data set of the production line to be analyzed is determined to be candidate data set label sets, and is matched with the data set label of the monitoring data set of the production line to be analyzed, for example, the data set label of the monitoring data set of the production line to be analyzed is the same as the comparison data set label, or the data set label of the monitoring data set of the production line to be analyzed is the same as the classification label of the comparison data set label. Matching the selected data set label set from the lookup table according to the data set label of the to-be-analyzed production line monitoring data set, obtaining a plurality of candidate data set label sets matched with the data set label of the to-be-analyzed production line monitoring data set, comparing the whole vector description with the whole operation data vector description of the comparison production line monitoring data set in the candidate data set label sets, and determining the comparison production line monitoring data set which is the recurrence production line monitoring data set with the to-be-analyzed production line monitoring data set.
Step S240, retrieving the description of the reference whole operation data vector corresponding to the candidate data set label set from the storage position associated with the candidate data set label set in the lookup table.
In this embodiment, because the lookup table includes the storage locations of the descriptions of the reference whole operation data vectors of the reference line monitoring data sets and the reference data set label of each reference line monitoring data set, the descriptions of the reference whole operation data vectors of the reference line monitoring data sets corresponding to the reference line monitoring data set identification can be retrieved from the storage locations associated with the reference line monitoring data sets.
Step S250, the overall operation data vector description of the Q monitoring data clusters is compared with the comparison overall operation data vector description corresponding to the label set of the alternative data set, and an overall vector description comparison result is obtained.
In the embodiment of the present application, the comparison overall operation data vector description corresponding to the label set of the candidate data set is namely comparison overall operation data vector descriptions corresponding to the plurality of comparison production line monitoring data sets, and then overall operation data vector descriptions of the Q monitoring data clusters and the comparison overall operation data vector descriptions corresponding to the label set of the candidate data set are subjected to overall vector description comparison to obtain an overall vector description comparison result.
In this embodiment of the present application, because the overall operation data vector description is easier to mine than the local operation data vector description, and meanwhile, the overall operation data vector description is simpler to match with the operation log of the comparison device, the matching relationship between the monitoring data set of the production line to be analyzed and the monitoring data set of the comparison production line can be determined by performing rapid feature comparison according to the overall operation data vector description. If the overall operational data vector description matches between the two production line monitoring data sets, then the local operational data vector description is reused with the equipment operation log for matching. If the overall operation data vector description between the two production line monitoring data sets is not matched, the to-be-analyzed production line monitoring data set is determined to be not matched with the comparison production line monitoring data set, so that the to-be-analyzed production line monitoring data set is rapidly determined not to be the reproduction production line monitoring data set, and the efficiency is improved. And establishing a lookup table according to the storage position of the comparison whole operation data vector description of the comparison production line monitoring data set, and rapidly determining the comparison whole operation data vector description by adopting the lookup table, so that the speed of acquiring the comparison whole operation data vector description is improved.
As an implementation mode, if the overall operation data vector description between the two production line monitoring data sets is not matched, comparing the local operation data vector description of the production line monitoring data set to the comparison local operation data vector description of the comparison production line monitoring data set according to the local operation data vector description of the production line monitoring data set to be analyzed, determining whether the production line monitoring data set to be analyzed is matched with the comparison production line monitoring data set or comparing the equipment operation log of the production line monitoring data set to be analyzed with the comparison equipment operation log of the comparison production line monitoring data set according to the equipment operation log of the production line monitoring data set to be analyzed, and determining whether the production line monitoring data set to be analyzed is matched with the comparison production line monitoring data set again. And when the two production line monitoring data sets are not matched according to the comparison of the whole operation data vector description, the accuracy and the reliability are improved based on the comparison of the local operation data vector description or the equipment operation log again.
In one embodiment, considering that the purpose of creating the lookup table is to quickly determine a reference global operational data vector description that is close to the global operational data vector description of the line monitoring data set to be analyzed when the data sets are aligned to determine a recurring line monitoring data set of the line monitoring data set to be analyzed, the information of the mined reference global operational data vector description (e.g., the storage location of the reference global operational data vector description in the storage space) may be incorporated into the lookup table, i.e., the lookup table is created, prior to the data set alignment. In order to effectively update the lookup table in real time, the description of the comparison whole operation data vector of the newly obtained comparison production line monitoring data set is quickly saved in the storage space, because the data volume saved in the whole storage space is large, the whole storage space needs to consume a long time when being updated, and at the moment, if the new comparison production line monitoring data set is available, the storage failure is likely to be caused, because the time length for updating the global lookup table is large, when the new comparison production line monitoring data set is obtained when the global lookup table is updated, the new comparison production line monitoring data set needs to be firstly mined for describing the comparison whole operation data vector, then the mined information is stored, and then the description of the lookup table is updated according to the storage position saved in the storage space, so that the comparison whole operation data vector of the new comparison production line monitoring data set can be queried based on the lookup table.
Based on this, the embodiments of the present application propose to generate two lookup tables, one of which is a global updated total lookup table and the other is a sub-lookup table constructed when a new line monitoring dataset is obtained at the time of total lookup table creation. The total lookup table has longer updating time interval, the updating time interval of the sub lookup table is shorter than the updating time interval of the total lookup table, so long as the updating time interval of the sub lookup table is reasonably set and is mainly short, the vector characterization of the monitoring data set of the production line can be completely mined and stored, the total lookup table and the sub lookup table are generated, when the total lookup table is updated, the data set vector description of the monitoring data set of the new production line is ensured to be mined, the sub lookup table can be constructed according to the data set vector description of the monitoring data set of the new production line, and the data set vector description of the monitoring data set of the new production line is obtained according to the sub lookup table, so that the efficiency is improved.
In the embodiment of the application, when the monitoring data set of the production line to be analyzed is obtained, the whole operation data vector description of the monitoring data set of the production line to be analyzed is pulled in batches from the storage space, the whole operation data vector description is used for searching in the packed lookup table, and the comparison whole operation data vector description matched with the whole operation data vector description of the monitoring data set of the production line to be analyzed is found from the storage space according to the retrieval address in the lookup table, so that the comparison production line monitoring data set corresponding to the comparison whole operation data vector description is determined. In addition, the comparison production line monitoring data set can be judged according to the local vector description comparison and the equipment operation log matching, so that the comparison production line monitoring data set similar to the data in the production line monitoring data set to be analyzed is selected again.
According to the embodiment of the application, through obtaining the plurality of monitoring data clusters of the monitoring data set of the production line to be analyzed, the overall operation data vector description mining, the local operation data vector description mining and the equipment operation log mining can be respectively carried out on each monitoring data cluster, so that in the data set matching process, comparison can be carried out according to three mined features, whether the monitoring data set of the production line to be analyzed is a monitoring data set of the production line to be analyzed is determined based on the matching results of the three types of feature vectors, and because the three types of features of the data set are subjected to joint matching comparison, whether the monitoring data set of the production line to be analyzed is determined, and the comparison results can be more reliable. In addition, based on obtaining a plurality of comparison production line monitoring data sets in advance and processing each comparison production line monitoring data set to obtain comparison overall operation data vector description, comparison local operation data vector description and comparison equipment operation log of each comparison production line monitoring data set, the above information can be stored in a storage space, when obtaining the production line monitoring data set to be analyzed, corresponding information is obtained in the storage space to be matched, and whether the production line monitoring data set to be analyzed is a reproduction production line monitoring data set is determined. Furthermore, in the embodiment of the application, because the lookup table for comparing the description of the whole operation data vector is established in advance, the description of the whole operation data vector can be quickly checked according to the lookup table, and the comparison efficiency of the data set is improved.
Based on the foregoing embodiments, the embodiments of the present application provide a monitoring apparatus, where each unit included in the apparatus, and each module included in each unit may be implemented by a processor in a computer device; of course, the method can also be realized by a specific logic circuit; in practice, the processor may be a central processing unit (Central Processing Unit, CPU), microprocessor (Microprocessor Unit, MPU), digital signal processor (Digital Signal Processor, DSP) or field programmable gate array (Field Programmable Gate Array, FPGA), etc.
Fig. 2 is a schematic structural diagram of a monitoring device according to an embodiment of the present application, and as shown in fig. 2, a monitoring device 200 includes: the data acquisition module 210 is configured to acquire a to-be-analyzed production line monitoring data set, where the to-be-analyzed production line monitoring data set includes Q monitoring data clusters, each monitoring data cluster is monitoring data of one production line in a corresponding multi-procedure processing production line of a molding plate, and Q is greater than or equal to 1; the feature extraction module 220 is configured to obtain an overall operation data vector description of the Q monitoring data clusters and a local operation data vector description of the Q monitoring data clusters, and obtain an equipment operation log of the monitoring data set of the production line to be analyzed; the overall characteristic comparison module 230 is configured to compare the overall operation data vector descriptions of the Q monitoring data clusters with the comparison overall operation data vector descriptions corresponding to the multiple comparison production line monitoring data sets, so as to obtain overall vector description comparison results; the local feature comparison module 240 is configured to compare the local operation data vector descriptions of the Q monitoring data clusters with the local operation data vector descriptions of the corresponding comparison local operation data vector descriptions of the multiple comparison production line monitoring data sets, so as to obtain a local vector description comparison result; the log comparison module 250 is configured to perform log comparison on the device running log of the to-be-analyzed production line monitoring dataset and the comparison device running logs of the plurality of comparison production line monitoring datasets, respectively, to obtain a log comparison result; the recurrence evaluation module 260 is configured to determine a data analysis result of the to-be-analyzed line monitoring dataset according to the overall vector description comparison result, the local vector description comparison result, and the log comparison result, where the data analysis result characterizes whether the to-be-analyzed line monitoring dataset is a recurrence line monitoring dataset; the state determining module 270 is configured to determine a target control line monitoring dataset for the line monitoring dataset to be analyzed to be repeated if the line monitoring dataset to be analyzed is a repeated line monitoring dataset, and take a production state evaluation result corresponding to the target control line monitoring dataset as a production state evaluation result of the line monitoring dataset to be analyzed.
The description of the apparatus embodiments above is similar to that of the method embodiments above, with similar advantageous effects as the method embodiments. In some embodiments, functions or modules included in the apparatus provided in the embodiments of the present application may be used to perform the methods described in the embodiments of the methods, and for technical details that are not disclosed in the embodiments of the apparatus of the present application, please refer to the description of the embodiments of the methods of the present application for understanding.
It should be noted that, in the embodiment of the present application, if the above-mentioned method for monitoring the multi-process line of the molding board is implemented in the form of a software functional module, and sold or used as an independent product, the method may also be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application may be essentially or portions contributing to the related art, and the software product may be stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read Only Memory (ROM), a magnetic disk, an optical disk, or other various media capable of storing program codes. Thus, embodiments of the present application are not limited to any specific hardware, software, or firmware, or to any combination of hardware, software, and firmware.
The embodiment of the application provides a monitoring system, which comprises a memory and a processor, wherein the memory stores a computer program capable of running on the processor, and the processor realizes part or all of the steps in the method when executing the program.
Embodiments of the present application provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs some or all of the steps of the above-described method. The computer readable storage medium may be transitory or non-transitory.
Embodiments of the present application provide a computer program comprising computer readable code which, when run in a computer device, performs some or all of the steps for implementing the above method.
Embodiments of the present application provide a computer program product comprising a non-transitory computer-readable storage medium storing a computer program which, when read and executed by a computer, performs some or all of the steps of the above-described method. The computer program product may be realized in particular by means of hardware, software or a combination thereof. In some embodiments, the computer program product is embodied as a computer storage medium, in other embodiments the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), or the like.
It should be noted here that: the above description of various embodiments is intended to emphasize the differences between the various embodiments, the same or similar features being referred to each other. The above description of apparatus, storage medium, computer program and computer program product embodiments is similar to that of method embodiments described above, with similar advantageous effects as the method embodiments. For technical details not disclosed in the embodiments of the apparatus, storage medium, computer program and computer program product of the present application, please refer to the description of the method embodiments of the present application.
Fig. 3 is a schematic diagram of a hardware entity of a monitoring system according to an embodiment of the present application, as shown in fig. 3, the hardware entity of the monitoring system 1000 includes: a processor 1001 and a memory 1002, wherein the memory 1002 stores a computer program executable on the processor 1001, the processor 1001 implementing the steps in the method of any of the embodiments described above when the program is executed.
The memory 1002 stores a computer program executable on the processor, and the memory 1002 is configured to store instructions and applications executable by the processor 1001, and may also cache data (e.g., image data, audio data, voice communication data, and video communication data) to be processed or already processed by each module in the processor 1001 and the monitoring system 1000, which may be implemented by a FLASH memory (FLASH) or a random access memory (Random Access Memory, RAM).
The processor 1001 executes a program to implement the steps of the method for monitoring a multi-step molding board processing line according to any one of the above. The processor 1001 generally controls the overall operation of the monitoring system 1000.
Embodiments of the present application provide a computer storage medium storing one or more programs executable by one or more processors to implement the steps of the method for monitoring a multi-process manufacturing line for a modeling board according to any of the embodiments above.
It should be noted here that: the description of the storage medium and apparatus embodiments above is similar to that of the method embodiments described above, with similar benefits as the method embodiments. For technical details not disclosed in the embodiments of the storage medium and the apparatus of the present application, please refer to the description of the method embodiments of the present application for understanding. The processor may be at least one of a target application integrated circuit (Application Specific Integrated Circuit, ASIC), a digital signal processor (Digital Signal Processor, DSP), a digital signal processing device (Digital Signal Processing Device, DSPD), a programmable logic device (Programmable Logic Device, PLD), a field programmable gate array (Field Programmable Gate Array, FPGA), a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, and a microprocessor. It will be appreciated that the electronic device implementing the above-mentioned processor function may be other, and embodiments of the present application are not specifically limited.
The computer storage medium/Memory may be a Read Only Memory (ROM), a programmable Read Only Memory (Programmable Read-Only Memory, PROM), an erasable programmable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), an electrically erasable programmable Read Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), a magnetic random access Memory (Ferromagnetic Random Access Memory, FRAM), a Flash Memory (Flash Memory), a magnetic surface Memory, an optical disk, or a Read Only optical disk (Compact Disc Read-Only Memory, CD-ROM); but may also be various terminals such as mobile phones, computers, tablet devices, personal digital assistants, etc., that include one or any combination of the above-mentioned memories.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in various embodiments of the present application, the sequence number of each step/process described above does not mean that the execution sequence of each step/process should be determined by the function and the internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read Only Memory (ROM), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the integrated units described above may be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the related art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a removable storage device, a ROM, a magnetic disk, or an optical disk.
The foregoing is merely an embodiment of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered in the protection scope of the present application.
Claims (10)
1. A method for monitoring a multi-working-line processing production line of a molding plate, which is applied to a monitoring system, the method comprising: acquiring a monitoring data set of a production line to be analyzed, wherein the monitoring data set of the production line to be analyzed comprises Q monitoring data clusters, each monitoring data cluster is monitoring data of one production line in a multi-procedure processing production line of a corresponding molding plate, and Q is more than or equal to 1; respectively acquiring the overall operation data vector description of the Q monitoring data clusters and the local operation data vector description of the Q monitoring data clusters, and acquiring the equipment operation log of the monitoring data set of the production line to be analyzed; respectively comparing the overall operation data vector description of the Q monitoring data clusters with the comparison overall operation data vector description corresponding to the monitoring data sets of the comparison production line to obtain an overall vector description comparison result; respectively comparing the local operation data vector descriptions of the Q monitoring data clusters with the comparison local operation data vector descriptions corresponding to the monitoring data sets of the comparison production lines to obtain local vector description comparison results; respectively carrying out log comparison on the equipment operation log of the monitoring data set of the production line to be analyzed and the comparison equipment operation logs of the monitoring data sets of the comparison production lines to obtain log comparison results; determining a data analysis result of the to-be-analyzed production line monitoring dataset according to the overall vector description comparison result, the local vector description comparison result and the log comparison result, wherein the data analysis result represents whether the to-be-analyzed production line monitoring dataset is a recurrence production line monitoring dataset or not; if the to-be-analyzed production line monitoring data set is a reproduction production line monitoring data set, determining a target comparison production line monitoring data set for reproduction of the to-be-analyzed production line monitoring data set, and taking a production state evaluation result corresponding to the target comparison production line monitoring data set as a production state evaluation result of the to-be-analyzed production line monitoring data set.
2. The method of claim 1, wherein any one of the Q monitoring data clusters is considered an xth monitoring data cluster, any one of the plurality of control line monitoring data sets is considered a yth control line monitoring data set, the yth control line monitoring data set comprising P control monitoring data clusters, wherein x is ≡1, y is ≡1, and P is ≡1; and comparing the overall operation data vector description of the Q monitoring data clusters with the comparison overall operation data vector description corresponding to the monitoring data sets of the comparison production line to obtain an overall vector description comparison result, wherein the overall vector description comparison result comprises: respectively determining overall commonality measurement results between the overall operation data vector description of the x-th monitoring data cluster and the comparison overall operation data vector description corresponding to the P comparison monitoring data clusters, and taking the overall commonality measurement result with the largest numerical value as the overall commonality measurement result of the x-th monitoring data cluster and the y-th comparison production line monitoring data set until determining the overall commonality measurement result of each monitoring data cluster in the Q monitoring data clusters and the y-th comparison production line monitoring data set respectively; determining an overall commonality measurement result between the to-be-analyzed production line monitoring dataset and the y-th control production line monitoring dataset according to the overall commonality measurement result of each of the Q monitoring data clusters and the y-th control production line monitoring dataset respectively until determining an overall commonality measurement result between the to-be-analyzed production line monitoring dataset and the plurality of control production line monitoring datasets; and determining the overall vector description comparison result according to the overall commonality measurement result between the to-be-analyzed production line monitoring data set and the plurality of comparison production line monitoring data sets.
3. The method of claim 1, wherein any one of the Q monitoring data clusters is considered an xth monitoring data cluster, any one of the plurality of control line monitoring data sets is considered a yth control line monitoring data set, the yth control line monitoring data set comprising P control monitoring data clusters, wherein x is ≡1, y is ≡1, and P is ≡1; the local vector description comparison is performed on the local operation data vector descriptions of the Q monitoring data clusters and the comparison local operation data vector descriptions corresponding to the plurality of comparison production line monitoring data sets, so as to obtain local vector description comparison results, including: respectively determining local commonality measurement results between the local operation data vector descriptions of the x-th monitoring data cluster and the comparison local operation data vector descriptions corresponding to the P comparison monitoring data clusters, and taking the local commonality measurement result with the largest numerical value as the local commonality measurement result of the monitoring data clusters of the x-th monitoring data cluster and the monitoring data sets of the y-th comparison production line until determining the local commonality measurement result of each monitoring data cluster in the Q monitoring data clusters and the monitoring data sets of the y-th comparison production line; determining a local commonality measurement result between the monitoring data set of the production line to be analyzed and the monitoring data set of the y-th control production line according to the local commonality measurement result of each monitoring data cluster in the Q monitoring data clusters and the monitoring data set of the y-th control production line respectively until determining a local commonality measurement result between the monitoring data set of the production line to be analyzed and the monitoring data sets of the plurality of control production lines; and determining the local vector description comparison result according to the local commonality measurement result between the to-be-analyzed production line monitoring data set and the plurality of control production line monitoring data sets.
4. A method according to any one of claims 1 to 3, wherein the log comparing the device running log of the to-be-analyzed production line monitoring dataset with the comparison device running logs of the plurality of comparison production line monitoring datasets to obtain log comparison results respectively includes: determining log commonality measurement results between the equipment running logs of the production line monitoring data set to be analyzed and the comparison equipment running logs of each comparison production line monitoring data set respectively; and determining the log comparison result according to the log commonality measurement result.
5. The method according to claim 4, wherein the method further comprises: obtaining a plurality of control line monitoring data sets, wherein each control line monitoring data set comprises P control monitoring data clusters; respectively acquiring comparison overall operation data vector descriptions of P comparison monitoring data clusters of each comparison production line monitoring data set and comparison local operation data vector descriptions of the P comparison monitoring data clusters, and respectively acquiring comparison equipment operation logs of each comparison production line monitoring data set; and correspondingly storing the comparison whole operation data vector description of the P comparison monitoring data clusters of each comparison production line monitoring data set, the comparison local operation data vector description of the P comparison monitoring data clusters and the comparison equipment operation log of each comparison production line monitoring data set in a storage space, wherein the storage space comprises the comparison whole operation data vector description, the comparison local operation data vector description and the comparison equipment operation log corresponding to the plurality of comparison production line monitoring data sets.
6. The method of claim 5, wherein the method further comprises: acquiring a comparison data set label of each comparison production line monitoring data set and a comparison whole operation data vector description of each comparison production line monitoring data set in the storage space; establishing a lookup table according to the control data set labels of the monitoring data sets of each control production line and the storage positions; and comparing the overall operation data vector description of the Q monitoring data clusters with the comparison overall operation data vector description corresponding to the monitoring data sets of the comparison production line to obtain an overall vector description comparison result, wherein the overall vector description comparison result comprises: acquiring a data set label of the monitoring data set of the production line to be analyzed, and matching a selected data set label set from the lookup table according to the data set label of the monitoring data set of the production line to be analyzed; retrieving a comparison overall operation data vector description corresponding to the alternative data set tag set from a storage location associated with the alternative data set tag set in the lookup table; and respectively comparing the overall operation data vector description of the Q monitoring data clusters with the comparison overall operation data vector description corresponding to the alternative data set label set to obtain an overall vector description comparison result.
7. The method of claim 6, wherein the lookup table comprises a total lookup table and a sub-lookup table, wherein the total lookup table has an update duration interval that is greater than the update duration interval of the sub-lookup table.
8. The method of claim 1, wherein the determining the data analysis result of the line monitoring dataset to be analyzed based on the global vector description comparison result, the local vector description comparison result, and the log comparison result comprises: acquiring production process parameters of the monitoring data set of the production line to be analyzed, and determining target emphasis elements corresponding to the monitoring data set of the production line to be analyzed according to the production process parameters; acquiring a first eccentric weight corresponding to the overall operation data vector description, a second eccentric weight corresponding to the local operation data vector description and a third eccentric weight corresponding to the equipment operation log under the target weight element; and determining a data analysis result of the monitoring data set of the production line to be analyzed according to the first eccentric weight, the overall vector description comparison result, the second eccentric weight, the local vector description comparison result, the third eccentric weight and the log comparison result.
9. The method according to claim 1, wherein the method further comprises: and if the data analysis result of the to-be-analyzed production line monitoring data set indicates that the to-be-analyzed production line monitoring data set is not a reproduction production line monitoring data set, carrying out manual auditing on the to-be-analyzed production line monitoring data set, determining a production state evaluation result of the to-be-analyzed production line monitoring data set, and taking the audited to-be-analyzed production line monitoring data set as a new comparison to the to-be-analyzed production line monitoring data set.
10. A monitoring system comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that the processor implements the steps of the method of any one of claims 1 to 9 when the program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311549084.XA CN117270479B (en) | 2023-11-21 | 2023-11-21 | Method and system for monitoring multi-working-procedure production line of molding plate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311549084.XA CN117270479B (en) | 2023-11-21 | 2023-11-21 | Method and system for monitoring multi-working-procedure production line of molding plate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117270479A true CN117270479A (en) | 2023-12-22 |
| CN117270479B CN117270479B (en) | 2024-02-06 |
Family
ID=89204711
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311549084.XA Active CN117270479B (en) | 2023-11-21 | 2023-11-21 | Method and system for monitoring multi-working-procedure production line of molding plate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117270479B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108229444A (en) * | 2018-02-09 | 2018-06-29 | 天津师范大学 | A kind of pedestrian's recognition methods again based on whole and local depth characteristic fusion |
| CN109344841A (en) * | 2018-08-10 | 2019-02-15 | 北京华捷艾米科技有限公司 | A kind of clothes recognition methods and device |
| CN112714288A (en) * | 2020-12-24 | 2021-04-27 | 冯丽琴 | Intelligent monitoring method and device and monitoring equipment |
| CN113537087A (en) * | 2021-07-20 | 2021-10-22 | 蒋金强 | Intelligent traffic information processing method and device and server |
| CN114019927A (en) * | 2021-11-05 | 2022-02-08 | 江苏电子信息职业学院 | Supervision feedback control system based on intelligent precision die manufacturing |
| CN116361351A (en) * | 2022-12-01 | 2023-06-30 | 重庆科创职业学院 | Data mining method for health management of industrial equipment |
| CN116540584A (en) * | 2023-03-13 | 2023-08-04 | 重庆大学 | Intelligent management and control system of unmanned production line of fusion-cast charging |
-
2023
- 2023-11-21 CN CN202311549084.XA patent/CN117270479B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108229444A (en) * | 2018-02-09 | 2018-06-29 | 天津师范大学 | A kind of pedestrian's recognition methods again based on whole and local depth characteristic fusion |
| CN109344841A (en) * | 2018-08-10 | 2019-02-15 | 北京华捷艾米科技有限公司 | A kind of clothes recognition methods and device |
| CN112714288A (en) * | 2020-12-24 | 2021-04-27 | 冯丽琴 | Intelligent monitoring method and device and monitoring equipment |
| CN113537087A (en) * | 2021-07-20 | 2021-10-22 | 蒋金强 | Intelligent traffic information processing method and device and server |
| CN114019927A (en) * | 2021-11-05 | 2022-02-08 | 江苏电子信息职业学院 | Supervision feedback control system based on intelligent precision die manufacturing |
| CN116361351A (en) * | 2022-12-01 | 2023-06-30 | 重庆科创职业学院 | Data mining method for health management of industrial equipment |
| CN116540584A (en) * | 2023-03-13 | 2023-08-04 | 重庆大学 | Intelligent management and control system of unmanned production line of fusion-cast charging |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117270479B (en) | 2024-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111078479B (en) | Memory detection model training method, memory detection method and device | |
| CN107025154B (en) | Disk failure prediction method and device | |
| CN111522704A (en) | Alarm information processing method, device, computer device and storage medium | |
| CN111158977A (en) | Abnormal event root cause positioning method and device | |
| CN110705598B (en) | Intelligent model management method, intelligent model management device, computer equipment and storage medium | |
| Almeida et al. | Smart at what cost? characterising mobile deep neural networks in the wild | |
| CN111949646B (en) | Equipment running condition analysis method, device, equipment and medium based on big data | |
| CN113284002A (en) | Power consumption data anomaly detection method and device, computer equipment and storage medium | |
| CN117170915A (en) | Data center equipment fault prediction method and device and computer equipment | |
| CN108733694B (en) | Retrieval recommendation method and device | |
| CN115905990A (en) | Transformer oil temperature abnormity monitoring method based on density aggregation algorithm | |
| CN117270479B (en) | Method and system for monitoring multi-working-procedure production line of molding plate | |
| CN115062200A (en) | User behavior mining method and system based on artificial intelligence | |
| CN113946983A (en) | Method and device for evaluating weak links of product reliability and computer equipment | |
| CN116883181B (en) | Financial service pushing method based on user portrait, storage medium and server | |
| CN113220551A (en) | Index trend prediction and early warning method and device, electronic equipment and storage medium | |
| CN117312825A (en) | Target behavior detection method and device, electronic equipment and storage medium | |
| WO2023116816A1 (en) | Protein sequence alignment method and apparatus, and server and storage medium | |
| CN115964470A (en) | Service life prediction method and system for motorcycle accessories | |
| CN113296990B (en) | Method and device for recognizing abnormity of time sequence data | |
| CN109491844B (en) | Computer system for identifying abnormal information | |
| CN113469237A (en) | User intention identification method and device, electronic equipment and storage medium | |
| Fahrudin et al. | Implementation of Big Data Analytics for Machine Learning Model Using Hadoop and Spark Environment on Resizing Iris Dataset | |
| CN117270476B (en) | Production control method and system based on intelligent factory | |
| CN112183644B (en) | Index stability monitoring method and device, computer equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |