CN118051863B - Health data acquisition system and method based on digital metering technology - Google Patents
Health data acquisition system and method based on digital metering technology Download PDFInfo
- Publication number
- CN118051863B CN118051863B CN202410451477.5A CN202410451477A CN118051863B CN 118051863 B CN118051863 B CN 118051863B CN 202410451477 A CN202410451477 A CN 202410451477A CN 118051863 B CN118051863 B CN 118051863B
- Authority
- CN
- China
- Prior art keywords
- characteristic information
- parameter
- acquiring
- evaluation
- production equipment
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000036541 health Effects 0.000 title claims abstract description 38
- 238000005516 engineering process Methods 0.000 title claims abstract description 18
- 238000011156 evaluation Methods 0.000 claims abstract description 110
- 238000004519 manufacturing process Methods 0.000 claims abstract description 98
- 238000012544 monitoring process Methods 0.000 claims abstract description 55
- 238000004458 analytical method Methods 0.000 claims abstract description 26
- 230000005856 abnormality Effects 0.000 claims abstract description 17
- 230000002159 abnormal effect Effects 0.000 claims description 77
- 238000012937 correction Methods 0.000 claims description 63
- 238000005070 sampling Methods 0.000 claims description 42
- 238000000605 extraction Methods 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 20
- 230000011218 segmentation Effects 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 11
- 230000001788 irregular Effects 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 13
- 230000003862 health status Effects 0.000 description 5
- 238000013480 data collection Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 238000010223 real-time analysis Methods 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention belongs to the technical field of equipment safety production, and particularly relates to a health data acquisition system and method based on a digital metering technology. The method can obtain parallel subsets before and after the abnormality of the production equipment by segmenting the operated data of the production equipment, and then extract the second characteristic information related to the abnormality of the equipment according to the parallel subsets, so that the complexity of the data can be reduced, the analysis difficulty is reduced, the corresponding parameter characteristics of the second characteristic information can be determined by the regularity analysis of the second characteristic information, different evaluation modes are determined according to different parameter characteristics, and the operation state of the production equipment is output by adopting different evaluation modes according to the real-time monitoring characteristic information of the production equipment, so that powerful guarantee is provided for the stable production of enterprises.
Description
Technical Field
The invention belongs to the technical field of equipment safety production, and particularly relates to a health data acquisition system and method based on a digital metering technology.
Background
Along with the rapid development of industrial automation, the running state of production equipment is vital to the production efficiency and the product quality of enterprises, and in order to monitor the health condition of the production equipment in real time, a corresponding health data acquisition system is generated in time, and based on the health data of the production equipment, powerful support is provided for the health management of the production equipment, and potential hidden hazards of the production equipment can be found in time while manual overhaul is reduced.
In the prior art, for the health data acquisition of production equipment, the core is that various parameters of the running state of the equipment, such as temperature, pressure and the like, can be accurately acquired, the running state of the equipment can be directly reflected through the analysis of the data, but the running period of the equipment is long, the generated parameters are more, and the analysis result is influenced by the disordered data, so that larger deviation of the analysis result of the running state of the equipment can be caused, and based on the scheme, the health data acquisition method capable of reducing the complexity of the data and evaluating the running state of the production equipment by combining the regularity of the running data is provided.
Disclosure of Invention
The invention aims to provide a health data acquisition system and method based on a digital metering technology, which can reduce the complexity of data and improve the accuracy and efficiency of subsequent analysis.
The technical scheme adopted by the invention is as follows:
A health data acquisition method based on a digital metering technology comprises the following steps:
Acquiring operation data of production equipment, and preprocessing the operation data to obtain first characteristic information, wherein the first characteristic information comprises temperature parameters, pressure parameters and flow parameters of the production equipment;
the first characteristic information is segmented to obtain a plurality of segmented nodes, the first characteristic information between adjacent segmented nodes is summarized into parallel subsets, and then the first characteristic information in the parallel subsets is subjected to characteristic extraction to obtain second characteristic information;
The second characteristic information is subjected to sorting treatment, the second characteristic information is subjected to regular analysis according to a sorting result, the parameter characteristics of the second characteristic information are obtained, and a reference comparison library is constructed according to the parameter characteristics;
and carrying out real-time monitoring on the production equipment, carrying out feature extraction on the real-time monitoring data to obtain real-time monitoring feature information, matching the real-time monitoring feature information with a reference comparison library, and outputting the health state of the production equipment.
In a preferred scheme, the steps of acquiring operation data of production equipment and preprocessing the operation data to obtain first characteristic information include:
acquiring the operated data of the production equipment;
Cleaning the operated data, removing abnormal values, noise and filling missing values, and obtaining reference data;
acquiring a standard execution period of production equipment, and calibrating the standard execution period as a reference period;
And acquiring an acquisition period of the reference data, comparing the acquisition period with the reference period, screening out the reference data lower than the reference period, and calibrating the reference data higher than or equal to the reference period as first characteristic information.
In a preferred embodiment, the step of acquiring the acquisition period of the reference data includes:
Acquiring the reference data and arranging according to the occurrence time sequence;
Acquiring occurrence nodes of each datum, calibrating the occurrence nodes as datum nodes, and measuring and calculating time intervals between adjacent datum nodes to obtain a first evaluation parameter;
And acquiring a first evaluation threshold value, comparing the first evaluation threshold value with a first evaluation parameter, calibrating the first evaluation parameter smaller than the first evaluation threshold value as a corotation period, and calibrating a period between an ending point and a starting point of adjacent corotation periods as an acquisition period.
In a preferred embodiment, the step of performing segmentation processing on the first feature information to obtain a plurality of segment nodes includes:
acquiring abnormal parameters in the first characteristic information, and calibrating an occurrence node of the abnormal parameters as an abnormal node;
Taking the occurrence interval of adjacent abnormal nodes as an abnormal interval, counting the length of the abnormal interval, and calibrating the length as a second evaluation parameter;
Acquiring a second evaluation threshold value and comparing the second evaluation threshold value with the second evaluation parameter;
If the second evaluation parameter is larger than a second evaluation threshold, indicating that the corresponding abnormal parameter is accidental abnormality, and marking the corresponding abnormal node as a segmented node;
And if the second evaluation parameter is smaller than or equal to a second evaluation threshold, indicating that the corresponding abnormal parameter is continuous abnormality, and marking the last abnormal node in the continuous abnormality as a segmented node, wherein the abnormal nodes before the last abnormal node in the continuous abnormality are marked as invalid nodes.
In a preferred scheme, the step of summarizing the first feature information between adjacent segment nodes into parallel subsets, and then performing feature extraction on the first feature information in the parallel subsets to obtain second feature information includes:
Acquiring each segment node, and performing backtracking offset processing on each segment node to obtain a sampling interval;
Acquiring a first measuring and calculating function;
Collecting first characteristic information in each sampling interval from the parallel subsets, respectively inputting the first characteristic information into a first measuring and calculating function, and calibrating an output result into first calibration parameters, wherein each sampling interval corresponds to one first calibration parameter;
performing difference on the first correction parameters one by one to obtain deviation parameters;
And acquiring an allowable deviation threshold, counting the occupation ratio of the deviation parameter higher than the allowable deviation threshold, calibrating the occupation ratio as an evaluation parameter, and extracting second characteristic information from the parallel subset according to the evaluation parameter.
In a preferred embodiment, the step of extracting the second characteristic information from the parallel subset according to the evaluation parameter comprises:
Acquiring the evaluation parameters;
Acquiring an evaluation threshold value, and comparing the evaluation threshold value with an evaluation parameter;
If the evaluation threshold is greater than or equal to the evaluation parameter, indicating that the first characteristic information corresponding to the sampling interval cannot be used as the second characteristic information, synchronously updating the sampling interval, and re-acquiring the first characteristic information in the updated sampling interval;
if the evaluation threshold is smaller than the evaluation parameter, the first characteristic information in the corresponding sampling interval is directly calibrated to be the second characteristic information.
In a preferred embodiment, the step of sorting the second feature information, and performing rule analysis on the second feature information according to the sorting result to obtain the parameter characteristics of the second feature information includes:
Respectively acquiring second characteristic information of each sampling interval after sequencing, and sequentially performing difference processing to obtain fluctuation parameters, wherein the fluctuation parameters comprise positive fluctuation parameters and negative fluctuation parameters;
acquiring continuous time lengths of the positive fluctuation parameter and the negative fluctuation parameter, and calibrating the continuous time lengths as a second calibration parameter and a third calibration parameter respectively;
Acquiring a correction threshold value, and comparing the correction threshold value with a second correction parameter and a third correction parameter;
If the second correction parameter or the third correction parameter is larger than or equal to the correction threshold value, screening out the second characteristic information corresponding to the third correction parameter or the second correction parameter smaller than the correction threshold value, and outputting the parameter characteristic of the second characteristic information as regularity;
And if the second correction parameter and the third correction parameter are smaller than the correction threshold, directly outputting the parameter characteristics of the second characteristic information as irregularity.
In a preferred scheme, after the parameter characteristics of the second characteristic information are output, risk prediction is performed on the production equipment according to the output result of the parameter characteristics;
If the output result of the parameter characteristic is regular, a second measuring and calculating function is obtained, the second characteristic information is input into the second measuring and calculating function, the output result is calibrated to be the risk duration, and the risk duration and the corresponding second characteristic parameter are added into a reference comparison library;
If the output result of the parameter characteristics is irregular, the parameter with the largest value in the corresponding second characteristic information is marked as a risk threshold value, the risk threshold value is downwards offset, the offset result is marked as a risk parameter, and the risk parameter is added into a reference comparison library.
In a preferred scheme, the step of matching the real-time monitoring characteristic information with a reference comparison library and outputting the health status of production equipment comprises the following steps:
Acquiring real-time monitoring characteristic information, and arranging according to acquisition time sequence;
If the real-time monitoring characteristic information is regular and the corresponding safety execution duration is smaller than the risk duration, the health state of the production equipment is indicated to be normal, the irregularity is abnormal, and an alarm signal is synchronously sent;
If the real-time monitoring characteristic information is irregular, when the real-time monitoring characteristic information is continuously larger than or equal to the risk parameter, judging that the health state of the production equipment is abnormal, synchronously sending out an alarm signal, and otherwise, judging that the production equipment is normal.
The invention also provides a health data acquisition system based on the digital metering technology, which is applied to the health data acquisition method based on the digital metering technology, and comprises the following steps:
The data acquisition module is used for acquiring the operation data of the production equipment and preprocessing the operation data to obtain first characteristic information, wherein the first characteristic information comprises temperature parameters, pressure parameters and flow parameters of the production equipment;
The segmentation extraction module is used for carrying out segmentation processing on the first characteristic information to obtain a plurality of segmentation nodes, summarizing the first characteristic information between adjacent segmentation nodes into parallel subsets, and carrying out characteristic extraction on the first characteristic information in the parallel subsets to obtain second characteristic information;
The rule analysis module is used for carrying out sorting processing on the second characteristic information, carrying out rule analysis on the second characteristic information according to a sorting result to obtain parameter characteristics of the second characteristic information, and constructing a reference comparison library according to the parameter characteristics;
The real-time monitoring module is used for carrying out real-time monitoring on the production equipment, carrying out feature extraction on the real-time monitoring data to obtain real-time monitoring feature information, matching the real-time monitoring feature information with the reference comparison library, and outputting the health state of the production equipment.
The invention has the technical effects that:
The invention can obtain a plurality of parallel subsets before and after the abnormality of the production equipment by segmenting the running data of the production equipment, and then extracts the second characteristic information related to the abnormality of the equipment according to the parallel subsets, thereby reducing the complexity of the data, reducing the analysis difficulty, determining the corresponding parameter characteristics of the second characteristic information by the regularity analysis of the second characteristic information, determining different evaluation modes according to different parameter characteristics, and outputting the running state of the production equipment by adopting different evaluation modes according to the real-time monitoring characteristic information of the production equipment, thereby providing powerful guarantee for the stable production of enterprises.
Drawings
FIG. 1 is a flow chart of a method according to a first embodiment of the invention;
fig. 2 is a system block diagram in a second embodiment of the invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one preferred embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Example 1
Referring to fig. 1, a first embodiment of the present invention provides a health data acquisition method based on digital metering technology, which includes:
s1, acquiring operation data of production equipment, and preprocessing the operation data to obtain first characteristic information, wherein the first characteristic information comprises temperature parameters, pressure parameters and flow parameters of the production equipment;
S2, carrying out segmentation processing on the first characteristic information to obtain a plurality of segment nodes, summarizing the first characteristic information among adjacent segment nodes into parallel subsets, and carrying out characteristic extraction on the first characteristic information in the parallel subsets to obtain second characteristic information;
S3, sorting the second characteristic information, performing rule analysis on the second characteristic information according to a sorting result to obtain parameter characteristics of the second characteristic information, and constructing a reference comparison library according to the parameter characteristics;
And S4, carrying out real-time monitoring on the production equipment, carrying out feature extraction on the real-time monitoring data to obtain real-time monitoring feature information, matching the real-time monitoring feature information with a reference comparison library, and outputting the health state of the production equipment.
As described in the above steps S1-S4, with the continuous development of industrial automation, the health status monitoring and management of the production equipment becomes an indispensable loop in enterprise operation, in this embodiment, firstly, operation data of the production equipment are obtained through corresponding sensor equipment, these data cover a plurality of key parameters such as temperature, pressure and flow of the production equipment, after raw data are obtained, preprocessing is required to be performed to eliminate interference factors such as abnormal values and noise, first feature information reflecting the operation status of the production equipment is extracted, then the first feature information is processed in sections and extracted in features, and is divided into a plurality of section nodes, data between adjacent section nodes are parallel subsets, by feature extraction of data in these subsets, second feature information with more representativeness is obtained, these second feature information can more accurately reflect the operation status before abnormality of the production equipment, then the second feature information is sequenced, after the original data are obtained, change of the equipment parameters and feature information are reflected by analysis of sequencing results, thus the second feature information is extracted, the quality of the production equipment is compared with the real-time feature information is extracted, and the real-time quality information is compared with the real-time information is detected, and the quality of the production equipment is continuously monitored, and the quality is better than the real-time information is found, and the quality of the quality information is better than the quality of the production equipment, the efficiency of equipment management is improved.
In a preferred embodiment, the steps of acquiring operation data of the production equipment and preprocessing the operation data to obtain the first characteristic information include:
S101, acquiring running data of production equipment;
S102, cleaning the operated data, removing abnormal values, noise and filling missing values, and obtaining reference data;
s103, acquiring a standard execution period of production equipment, and calibrating the standard execution period as a reference period;
S104, acquiring an acquisition period of the reference data, comparing the acquisition period with the reference period, screening out the reference data lower than the reference period, and calibrating the reference data higher than or equal to the reference period as first characteristic information.
After the running data of the production equipment is output as described in the above steps S101-S104, the running data is cleaned first, during the data collection process, abnormal values, noise or missing values may occur due to various reasons (such as sensor faults, data transmission errors, etc.), these bad data may interfere with subsequent data analysis and even lead to erroneous conclusion, so that data cleaning techniques such as filtering, interpolation, etc. need to be used to remove the abnormal values, noise and fill the missing values, so as to obtain more accurate and reliable reference data, then the standard execution period of the production equipment is obtained and calibrated as a reference period, the reference period generally represents the working period after the production equipment is put into operation, the standard execution period of the equipment can be found out through analyzing the historical running data of the equipment, and is used as the reference for subsequent data processing, then the collection period of the reference data needs to be obtained and compared with the reference period, and the reference data lower than the reference period needs to be screened out, because these data may represent the test process of the production equipment or a temporary enabled time period, and the corresponding data higher than or equal to the first calibration period is provided as the support information of the first data.
In a preferred embodiment, the step of acquiring the acquisition period of the reference data includes:
step1, acquiring reference data, and arranging according to the occurrence time sequence;
Step2, obtaining occurrence nodes of each datum, calibrating the occurrence nodes as datum nodes, and measuring and calculating time intervals between adjacent datum nodes to obtain a first evaluation parameter;
Step3, acquiring a first evaluation threshold value, comparing the first evaluation threshold value with a first evaluation parameter, calibrating the first evaluation parameter smaller than the first evaluation threshold value as a turning period, and calibrating a period between the ending point and the starting point of the adjacent turning period as an acquisition period.
After the reference data are determined, the arrangement is performed according to the time sequence of occurrence of the reference data, the occurrence nodes of each reference data are counted and calibrated as reference nodes, then the time interval between the adjacent reference nodes is measured to obtain a first evaluation parameter, the time interval reflects the execution time of the production equipment, after the first evaluation parameter is obtained, a first evaluation threshold is obtained and compared with the first evaluation parameter, the first evaluation threshold is set according to the production requirement and purpose, and the first evaluation parameter smaller than the first evaluation threshold is calibrated as a turning period, and the period between the ending point and the starting point of the adjacent turning period is calibrated as an acquisition period.
In a preferred embodiment, the step of performing segmentation processing on the first feature information to obtain a plurality of segment nodes includes:
S201, acquiring an abnormal parameter in the first characteristic information, and calibrating an occurrence node of the abnormal parameter as an abnormal node;
s202, taking the occurrence interval of adjacent abnormal nodes as an abnormal interval, counting the length of the abnormal interval, and calibrating the length as a second evaluation parameter;
s203, acquiring a second evaluation threshold value and comparing the second evaluation threshold value with a second evaluation parameter;
if the second evaluation parameter is larger than the second evaluation threshold, indicating that the corresponding abnormal parameter is accidental abnormality, and marking the corresponding abnormal node as a segmented node;
If the second evaluation parameter is smaller than or equal to the second evaluation threshold, the corresponding abnormal parameter is indicated to be continuous abnormality, the last abnormal node in the continuous abnormality is marked as a segmented node, and all the abnormal nodes before the last abnormal node in the continuous abnormality are marked as invalid nodes.
As described in the above steps S201-S203, when the first feature information is processed in a segmentation manner, firstly, the abnormal parameters in the first feature information need to be acquired, which may be caused by errors, equipment faults or other factors in the data collection process, once the abnormal parameters are identified, the nodes where the abnormal parameters occur are marked as abnormal nodes, then the occurrence intervals of adjacent abnormal nodes are used as abnormal intervals, the lengths of the abnormal intervals are counted and used as second evaluation parameters, then a second evaluation threshold is acquired and compared with the second evaluation parameters, the second evaluation threshold is a preset reference value for judging the nature of the abnormal parameters, if the second evaluation parameters are greater than the second evaluation threshold, the abnormal parameters corresponding to the second evaluation threshold can be regarded as accidental abnormal nodes, in this case, the abnormal nodes corresponding to the abnormal parameters are marked as segmented nodes because the abnormal nodes do not affect the distribution and the characteristics of the whole data set, if the second evaluation parameters are smaller than or equal to the second evaluation threshold, then the second evaluation threshold is acquired, and then the second evaluation threshold is compared with the second evaluation threshold, in this case, the abnormal nodes corresponding to the abnormal nodes are marked as the abnormal nodes because the abnormal nodes do not contribute to the continuous distribution and the abnormal nodes, in this case, the abnormal node is not marked as the abnormal nodes, and the abnormal nodes can be marked as the abnormal nodes, and the abnormal nodes are not being the abnormal nodes.
In a preferred embodiment, the step of summarizing the first feature information between adjacent segment nodes into parallel subsets, and then performing feature extraction on the first feature information in the parallel subsets to obtain second feature information includes:
S204, acquiring each segment node, and performing backtracking offset processing on each segment node to obtain a sampling interval;
s205, acquiring a first measuring and calculating function;
s206, collecting first characteristic information in each sampling interval from the parallel subsets, respectively inputting the first characteristic information into a first measuring and calculating function, and calibrating an output result as a first calibration parameter, wherein each sampling interval corresponds to one first calibration parameter;
s207, performing difference on each first correction parameter one by one to obtain a deviation parameter;
s208, acquiring an allowable deviation threshold, counting the occupation ratio of the deviation parameters higher than the allowable deviation threshold, calibrating the occupation ratio as an evaluation parameter, and extracting second characteristic information from the parallel subset according to the evaluation parameter.
As described in the above steps S204 to S208, after the segmentation processing of the first feature information is completed, backtracking offset processing is performed according to the segmented nodes to obtain a sampling interval, that is, offset is performed towards the historical direction of the segmented nodes, and then a first measuring function is obtained, where an expression of the first measuring function is: in which, in the process, A first calibration parameter is indicated and is used to determine,Representing the amount of first characteristic information within the sampling interval,The method comprises the steps of representing first characteristic information in sampling intervals, outputting output results corresponding to each sampling interval by collecting the first characteristic information in each sampling interval and inputting the first characteristic information into a first measuring and calculating function, calibrating the output results to be first calibration parameters, performing difference operation on each first calibration parameter to output deviation parameters, wherein the deviation parameters reflect the difference degree of data among different intervals, acquiring an allowable deviation threshold value, calculating the occupation ratio of the deviation parameters higher than the allowable deviation threshold value, and obtaining a more representative second characteristic information according to the evaluation parameters.
In a preferred embodiment, the step of extracting the second characteristic information from the parallel subset according to the evaluation parameter comprises:
acquiring evaluation parameters;
Acquiring an evaluation threshold value, and comparing the evaluation threshold value with an evaluation parameter;
If the evaluation threshold value is greater than or equal to the evaluation parameter, the first characteristic information in the corresponding sampling interval cannot be used as the second characteristic information, the sampling interval is synchronously updated, and the first characteristic information in the updated sampling interval is acquired again;
If the evaluation threshold is smaller than the evaluation parameter, the first characteristic information in the corresponding sampling interval is directly calibrated as the second characteristic information.
In this embodiment, when the second characteristic information is extracted, the evaluation parameter and the evaluation threshold are first acquired, the evaluation threshold is a reference standard for comparing the magnitude of the evaluation parameter, the evaluation threshold is compared with the evaluation parameter, it can be judged whether the first characteristic information in the sampling interval can be used as the second characteristic information, if the evaluation threshold is greater than or equal to the evaluation parameter, it means that the first characteristic information in the current sampling interval cannot be used as the second characteristic information, because the first correction parameter in the different sampling interval deviates too much, in this case, the sampling interval needs to be updated, and the first characteristic information in the updated sampling interval needs to be acquired again, and this process can be performed again by adjusting the sampling range, increasing or decreasing the number of samples, and the like, and then repeating the above process, otherwise, if the evaluation threshold is smaller than the evaluation parameter, the first characteristic information in the corresponding sampling interval can be directly calibrated as the second characteristic information, which indicates that the first characteristic information in the corresponding sampling interval can be extracted as the second characteristic information.
In a preferred embodiment, the step of sorting the second feature information, and performing rule analysis on the second feature information according to the sorting result to obtain the parameter characteristics of the second feature information includes:
S301, respectively acquiring second characteristic information of each sampling interval after sequencing, and sequentially performing difference processing to obtain fluctuation parameters, wherein the fluctuation parameters comprise positive fluctuation parameters and negative fluctuation parameters;
S302, acquiring continuous time lengths of a positive fluctuation parameter and a negative fluctuation parameter, and calibrating the continuous time lengths as a second correction parameter and a third correction parameter respectively;
s303, acquiring a correction threshold value, and comparing the correction threshold value with the second correction parameter and the third correction parameter;
If the second correction parameter or the third correction parameter is larger than or equal to the correction threshold value, screening out the second characteristic information corresponding to the third correction parameter or the second correction parameter smaller than the correction threshold value, and outputting the parameter characteristic of the second characteristic information as regularity;
And if the second correction parameter and the third correction parameter are smaller than the correction threshold value, directly outputting the parameter characteristics of the second characteristic information as irregularity.
As described in the above steps S301 to S303, after the second feature information is output, the second feature information is sequenced, and after the sequenced second feature information is obtained, a difference process needs to be sequentially performed, so that a fluctuation parameter can be obtained, where the fluctuation parameter includes a correction fluctuation parameter and a negative fluctuation parameter, which respectively represent an increase and decrease of the second feature information in a sampling interval, then a continuous duration of the correction fluctuation parameter and a continuous duration of the negative fluctuation parameter are obtained, and are respectively calibrated into a second correction parameter and a third correction parameter, then a correction threshold value is obtained, and the correction threshold value is compared with the second correction parameter and the third correction parameter, where setting of the correction threshold value is determined according to an actual situation, and by comparing the correction threshold value with the correction parameter, a parameter characteristic of the second feature information can be determined, and if the second correction parameter or the third correction parameter is greater than or equal to the correction threshold value, then the second feature information corresponding to the second correction parameter is continuously increased or decreased in the sampling interval, and if the second feature information corresponding to the second correction parameter or the third correction parameter is less than the correction threshold value, and the second feature information is not considered to have no influence on the second feature information, and the second feature information is directly analyzed.
In a preferred embodiment, after outputting the parameter characteristics of the second characteristic information, performing risk prediction on the production equipment according to the output result of the parameter characteristics;
If the output result of the parameter characteristic is regular, a second measuring and calculating function is obtained, second characteristic information is input into the second measuring and calculating function, the output result is calibrated to be the risk duration, and the risk duration and the corresponding second characteristic parameter are added into a reference comparison library;
If the output result of the parameter characteristics is irregular, the parameter with the largest value in the corresponding second characteristic information is marked as a risk threshold value, the risk threshold value is shifted downwards, the shifting result is marked as a risk parameter, and the risk parameter is added into a reference comparison library.
In this embodiment, after the parameter characteristic of the second characteristic information is output, risk prediction may be performed on the parameter characteristic, if the output result of the parameter characteristic is regular, which indicates that the operation state of the production apparatus exhibits a certain stability in a period of time, where the stability includes stability of a forward trend and stability of a reverse trend, and at this time, a second measuring and calculating function is obtained, where an expression of the second measuring and calculating function is: in which, in the process, Representing the duration of the risk,The standard operation information is represented by a table,Representing the current operational information of the vehicle,Indicating the length of time of the sampling interval,Representing the amount of second characteristic information within the sampling interval,AndThe second characteristic information in the sampling interval is represented, corresponding risk duration under different operation information can be determined by inputting the second characteristic information into the function, then the risk duration and corresponding second characteristic parameters are added into a reference comparison library together, after the real-time characteristic information of the production equipment is acquired, the real-time characteristic information can be regarded as current operation information and matched with the corresponding risk duration, the method is only suitable for the condition that the operation information of the production equipment is greater than or equal to the second characteristic information, however, if the output result of the parameter characteristic is irregular, the parameter with the maximum value in the second characteristic information can be calibrated as a risk threshold, so that the abnormal operation phenomenon of the production equipment is ensured to be found in advance, the safety of the production equipment is further ensured, the risk threshold is downwards offset, the offset result is calibrated as the risk parameter, and the risk parameter is added into the reference comparison library for subsequent analysis and comparison.
In a preferred embodiment, the step of matching the real-time monitoring feature information with the reference comparison library and outputting the health status of the production facility includes:
S401, acquiring real-time monitoring characteristic information, and arranging according to acquisition time sequence;
s402, if the real-time monitoring characteristic information is regular and the corresponding safety execution duration is smaller than the risk duration, indicating that the health state of the production equipment is normal, the irregularity is abnormal, and synchronously sending out an alarm signal;
S403, if the real-time monitoring characteristic information is irregular, judging that the health state of the production equipment is abnormal when the real-time monitoring characteristic information is continuously larger than or equal to the risk parameter, synchronously sending out an alarm signal, and otherwise judging that the production equipment is normal.
As described in the foregoing steps S401-S403, in the actual running process of the production device, real-time monitoring feature information is collected and arranged according to the collection time sequence, if the real-time monitoring feature information shows regularity and the corresponding safe execution time length is smaller than the risk time length, then the health status of the production device can be judged to be normal, however, if the safe execution time length is longer than the risk time length, the operation of the production device tends to be abnormal, at this time, an alarm signal is sent synchronously, so that a worker is prompted to timely perform maintenance processing on the production device, and for irregular real-time monitoring feature information, whether the real-time monitoring feature information is continuously greater than or equal to the risk parameter is required to be concerned, if the real-time monitoring feature information is continuously greater than or equal to the risk parameter, the health status of the production device is judged to be abnormal, and the alarm signal is sent synchronously, because the feature information continuously exceeding the risk parameter usually indicates that the potential fault or potential safety hazard exists, and when the real-time monitoring feature information does not exceed the risk parameter, the production device is considered to be running normally, so that the comprehensive evaluation on the production device is realized.
Example 2
Referring to fig. 2, a second embodiment of the present invention, based on the previous embodiment, provides a health data collection system based on digital metering technology, which is applied to the above health data collection method based on digital metering technology, and includes:
The data acquisition module is used for acquiring the operation data of the production equipment and preprocessing the operation data to obtain first characteristic information, wherein the first characteristic information comprises temperature parameters, pressure parameters and flow parameters of the production equipment;
The segmentation extraction module is used for carrying out segmentation processing on the first characteristic information to obtain a plurality of segmentation nodes, summarizing the first characteristic information among adjacent segmentation nodes into parallel subsets, and carrying out characteristic extraction on the first characteristic information in the parallel subsets to obtain second characteristic information;
the rule analysis module is used for carrying out sequencing treatment on the second characteristic information, carrying out rule analysis on the second characteristic information according to a sequencing result to obtain the parameter characteristics of the second characteristic information, and constructing a reference comparison library according to the parameter characteristics;
the real-time monitoring module is used for carrying out real-time monitoring on the production equipment, carrying out feature extraction on the real-time monitoring data to obtain real-time monitoring feature information, matching the real-time monitoring feature information with the reference comparison library, and outputting the health state of the production equipment.
In the above, the system comprises a data acquisition module, a segment extraction module, a rule analysis module and a real-time monitoring module, wherein the data acquisition module is responsible for acquiring the running data of the production equipment and preprocessing the data, extracting first characteristic information comprising temperature parameters, pressure parameters, flow parameters and the like, the parameters directly reflect the running state of the equipment, the segment extraction module further processes the first characteristic information, the system can identify abnormal nodes in the data, namely the segment nodes, the data between adjacent segment nodes are summarized into parallel subsets through segment processing of the data, then the data in the subsets are subjected to characteristic extraction to obtain second characteristic information, the rule analysis module is responsible for sequencing the second characteristic information after the second characteristic information is obtained, the system can reveal the potential characteristic of the second characteristic information through analysis, the parameter characteristics are responsible for constructing a reference comparison library, and finally, the data in the subsets are subjected to characteristic extraction, the real-time analysis is performed on the data by the monitoring module, and the real-time analysis is performed on the data by the basis of the real-time analysis of the normal condition of the data, and the real-time condition is found out by the real-time monitoring equipment, the abnormal condition is better, the production equipment is better, the accuracy and the efficiency is improved, the accuracy of the subsequent analysis is improved, the second characteristic information is judged, the system can realize real-time monitoring and early warning of the health condition of production equipment, and provides powerful guarantee for stable production of enterprises.
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, apparatus, article, or method 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, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that comprises the element.
The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention. Structures, devices and methods of operation not specifically described and illustrated herein, unless otherwise indicated and limited, are implemented according to conventional means in the art.
Claims (6)
1. A health data acquisition method based on a digital metering technology is characterized by comprising the following steps of: comprising the following steps:
Acquiring operation data of production equipment, and preprocessing the operation data to obtain first characteristic information, wherein the first characteristic information comprises temperature parameters, pressure parameters and flow parameters of the production equipment;
the first characteristic information is segmented to obtain a plurality of segmented nodes, the first characteristic information between adjacent segmented nodes is summarized into parallel subsets, and then the first characteristic information in the parallel subsets is subjected to characteristic extraction to obtain second characteristic information;
The second characteristic information is subjected to sorting treatment, the second characteristic information is subjected to regular analysis according to a sorting result, the parameter characteristics of the second characteristic information are obtained, and a reference comparison library is constructed according to the parameter characteristics;
Real-time monitoring is carried out on production equipment, feature extraction is carried out on real-time monitoring data, real-time monitoring feature information is obtained, the real-time monitoring feature information is matched with a reference comparison library, and the health state of the production equipment is output;
the step of performing segmentation processing on the first characteristic information to obtain a plurality of segment nodes includes:
acquiring abnormal parameters in the first characteristic information, and calibrating an occurrence node of the abnormal parameters as an abnormal node;
Taking the occurrence interval of adjacent abnormal nodes as an abnormal interval, counting the length of the abnormal interval, and calibrating the length as a second evaluation parameter;
Acquiring a second evaluation threshold value and comparing the second evaluation threshold value with the second evaluation parameter;
If the second evaluation parameter is larger than a second evaluation threshold, indicating that the corresponding abnormal parameter is accidental abnormality, and marking the corresponding abnormal node as a segmented node;
If the second evaluation parameter is smaller than or equal to a second evaluation threshold, indicating that the corresponding abnormal parameter is continuous abnormality, and marking the last abnormal node of the continuous abnormality as a segmented node, wherein all the abnormal nodes before the last abnormal node of the continuous abnormality are marked as invalid nodes;
The step of summarizing the first characteristic information between adjacent segment nodes into parallel subsets, and then carrying out characteristic extraction on the first characteristic information in the parallel subsets to obtain second characteristic information comprises the following steps:
Acquiring each segment node, and performing backtracking offset processing on each segment node to obtain a sampling interval;
Acquiring a first measuring and calculating function;
Collecting first characteristic information in each sampling interval from the parallel subsets, respectively inputting the first characteristic information into a first measuring and calculating function, and calibrating an output result into first calibration parameters, wherein each sampling interval corresponds to one first calibration parameter;
performing difference on the first correction parameters one by one to obtain deviation parameters;
acquiring an allowable deviation threshold, counting the occupation ratio of deviation parameters higher than the allowable deviation threshold, calibrating the occupation ratio as an evaluation parameter, and extracting second characteristic information from the parallel subset according to the evaluation parameter;
the step of extracting second characteristic information from the parallel subset according to the evaluation parameter includes:
Acquiring the evaluation parameters;
Acquiring an evaluation threshold value, and comparing the evaluation threshold value with an evaluation parameter;
If the evaluation threshold is greater than or equal to the evaluation parameter, indicating that the first characteristic information corresponding to the sampling interval cannot be used as the second characteristic information, synchronously updating the sampling interval, and re-acquiring the first characteristic information in the updated sampling interval;
If the evaluation threshold is smaller than the evaluation parameter, directly calibrating the first characteristic information in the corresponding sampling interval as second characteristic information;
the step of sorting the second characteristic information, and performing rule analysis on the second characteristic information according to the sorting result to obtain the parameter characteristics of the second characteristic information comprises the following steps:
Respectively acquiring second characteristic information of each sampling interval after sequencing, and sequentially performing difference processing to obtain fluctuation parameters, wherein the fluctuation parameters comprise positive fluctuation parameters and negative fluctuation parameters;
acquiring continuous time lengths of the positive fluctuation parameter and the negative fluctuation parameter, and calibrating the continuous time lengths as a second calibration parameter and a third calibration parameter respectively;
Acquiring a correction threshold value, and comparing the correction threshold value with a second correction parameter and a third correction parameter;
If the second correction parameter or the third correction parameter is larger than or equal to the correction threshold value, screening out the second characteristic information corresponding to the third correction parameter or the second correction parameter smaller than the correction threshold value, and outputting the parameter characteristic of the second characteristic information as regularity;
And if the second correction parameter and the third correction parameter are smaller than the correction threshold, directly outputting the parameter characteristics of the second characteristic information as irregularity.
2. The method for collecting health data based on digital metering technology according to claim 1, wherein the method comprises the following steps: the method comprises the steps of obtaining operation data of production equipment, preprocessing the operation data to obtain first characteristic information, and comprises the following steps:
acquiring the operated data of the production equipment;
Cleaning the operated data, removing abnormal values, noise and filling missing values, and obtaining reference data;
acquiring a standard execution period of production equipment, and calibrating the standard execution period as a reference period;
And acquiring an acquisition period of the reference data, comparing the acquisition period with the reference period, screening out the reference data lower than the reference period, and calibrating the reference data higher than or equal to the reference period as first characteristic information.
3. The method for collecting health data based on digital metering technology according to claim 2, wherein: the step of acquiring the acquisition period of the reference data includes:
Acquiring the reference data and arranging according to the occurrence time sequence;
Acquiring occurrence nodes of each datum, calibrating the occurrence nodes as datum nodes, and measuring and calculating time intervals between adjacent datum nodes to obtain a first evaluation parameter;
And acquiring a first evaluation threshold value, comparing the first evaluation threshold value with a first evaluation parameter, calibrating the first evaluation parameter smaller than the first evaluation threshold value as a corotation period, and calibrating a period between an ending point and a starting point of adjacent corotation periods as an acquisition period.
4. The method for collecting health data based on digital metering technology according to claim 1, wherein the method comprises the following steps: after the parameter characteristics of the second characteristic information are output, carrying out risk prediction on the production equipment according to the output result of the parameter characteristics;
If the output result of the parameter characteristic is regular, a second measuring and calculating function is obtained, the second characteristic information is input into the second measuring and calculating function, the output result is calibrated to be the risk duration, and the risk duration and the corresponding second characteristic parameter are added into a reference comparison library;
If the output result of the parameter characteristics is irregular, the parameter with the largest value in the corresponding second characteristic information is marked as a risk threshold value, the risk threshold value is downwards offset, the offset result is marked as a risk parameter, and the risk parameter is added into a reference comparison library.
5. The method for collecting health data based on digital metering technology according to claim 4, wherein: the step of matching the real-time monitoring characteristic information with a reference comparison library and outputting the health state of production equipment comprises the following steps:
Acquiring real-time monitoring characteristic information, and arranging according to acquisition time sequence;
If the real-time monitoring characteristic information is regular and the corresponding safety execution duration is smaller than the risk duration, the health state of the production equipment is indicated to be normal, the irregularity is abnormal, and an alarm signal is synchronously sent;
If the real-time monitoring characteristic information is irregular, when the real-time monitoring characteristic information is continuously larger than or equal to the risk parameter, judging that the health state of the production equipment is abnormal, synchronously sending out an alarm signal, and otherwise, judging that the production equipment is normal.
6. A health data acquisition system based on digital metering technology, which is applied to the health data acquisition method based on digital metering technology as set forth in any one of claims 1 to 5, and is characterized in that: comprising the following steps:
The data acquisition module is used for acquiring the operation data of the production equipment and preprocessing the operation data to obtain first characteristic information, wherein the first characteristic information comprises temperature parameters, pressure parameters and flow parameters of the production equipment;
The segmentation extraction module is used for carrying out segmentation processing on the first characteristic information to obtain a plurality of segmentation nodes, summarizing the first characteristic information between adjacent segmentation nodes into parallel subsets, and carrying out characteristic extraction on the first characteristic information in the parallel subsets to obtain second characteristic information;
The rule analysis module is used for carrying out sorting processing on the second characteristic information, carrying out rule analysis on the second characteristic information according to a sorting result to obtain parameter characteristics of the second characteristic information, and constructing a reference comparison library according to the parameter characteristics;
The real-time monitoring module is used for carrying out real-time monitoring on the production equipment, carrying out feature extraction on the real-time monitoring data to obtain real-time monitoring feature information, matching the real-time monitoring feature information with the reference comparison library, and outputting the health state of the production equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410451477.5A CN118051863B (en) | 2024-04-16 | 2024-04-16 | Health data acquisition system and method based on digital metering technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410451477.5A CN118051863B (en) | 2024-04-16 | 2024-04-16 | Health data acquisition system and method based on digital metering technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118051863A CN118051863A (en) | 2024-05-17 |
| CN118051863B true CN118051863B (en) | 2024-07-02 |
Family
ID=91050301
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410451477.5A Active CN118051863B (en) | 2024-04-16 | 2024-04-16 | Health data acquisition system and method based on digital metering technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118051863B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118067204B (en) * | 2024-04-22 | 2024-06-25 | 南京市计量监督检测院 | Safety production data acquisition system based on digital metering technology |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117077893A (en) * | 2023-08-30 | 2023-11-17 | 浙江瞭望神州科技有限公司 | Method and device for analyzing intelligent data of cultivated land |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9558056B2 (en) * | 2013-07-28 | 2017-01-31 | OpsClarity Inc. | Organizing network performance metrics into historical anomaly dependency data |
| CN115328733A (en) * | 2022-08-15 | 2022-11-11 | 北京百度网讯科技有限公司 | Alarm method and device applied to business system, electronic equipment and storage medium |
| CN116911824A (en) * | 2023-07-13 | 2023-10-20 | 郑州电力高等专科学校 | Intelligent decision method and system based on electric power big data |
| CN117579401A (en) * | 2024-01-17 | 2024-02-20 | 北京九建科技有限公司 | Energy data analysis method based on edge calculation |
| CN117719385B (en) * | 2024-02-18 | 2024-05-03 | 弘安天启(南京)科技有限公司 | Intelligent charging pile control system and method |
-
2024
- 2024-04-16 CN CN202410451477.5A patent/CN118051863B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117077893A (en) * | 2023-08-30 | 2023-11-17 | 浙江瞭望神州科技有限公司 | Method and device for analyzing intelligent data of cultivated land |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118051863A (en) | 2024-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118051863B (en) | Health data acquisition system and method based on digital metering technology | |
| CN113344134B (en) | Low-voltage distribution monitoring terminal data acquisition abnormality detection method and system | |
| US10852357B2 (en) | System and method for UPS battery monitoring and data analysis | |
| CN111984705B (en) | Precision evaluation management method and device for power quality monitoring device | |
| CN110703214A (en) | Weather radar state evaluation and fault monitoring method | |
| CN118067204B (en) | Safety production data acquisition system based on digital metering technology | |
| CN115454778A (en) | Intelligent monitoring system for abnormal time sequence indexes in large-scale cloud network environment | |
| CN116304957A (en) | On-line identification method for monitoring state mutation of power supply and transformation equipment | |
| CN115689396A (en) | Pollutant discharge control method, device, equipment and medium | |
| CN112215307B (en) | Method for automatically detecting signal abnormality of earthquake instrument by machine learning | |
| CN114065509A (en) | Fault troubleshooting method of crack meter for geological disaster prevention and control | |
| CN117171366A (en) | Knowledge graph construction method and system for power grid dispatching operation situation | |
| CN117761416A (en) | Bus duct on-line monitoring system | |
| CN116628609A (en) | Intelligent monitoring method and system for multi-source data analysis | |
| CN114938339B (en) | Data processing method and related device | |
| CN115163195A (en) | Coal mine coal face gas sensor numerical value distortion identification method and system | |
| CN114202209A (en) | Water quality abnormity identification method and device | |
| CN116878728B (en) | Pressure sensor fault detection analysis processing system | |
| CN117978628B (en) | Communication control method and system based on intelligent park | |
| CN117420811B (en) | Production line quality monitoring method and system for automatic production | |
| CN117273221B (en) | River reach abnormal emission early warning method and device based on adjacent discontinuities feature analysis | |
| CN117783792B (en) | Valve side sleeve insulation state detection method and system based on multiparameter real-time monitoring | |
| CN117951455B (en) | On-line monitoring method for operation faults of scraper conveyor | |
| CN116448062B (en) | Bridge settlement deformation detection method, device, computer and storage medium | |
| CN117950947A (en) | Computer fault monitoring system and method based on Internet |
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 |