CN111582516A - Equipment maintenance method and device based on big data analysis - Google Patents
Equipment maintenance method and device based on big data analysis Download PDFInfo
- Publication number
- CN111582516A CN111582516A CN202010354271.2A CN202010354271A CN111582516A CN 111582516 A CN111582516 A CN 111582516A CN 202010354271 A CN202010354271 A CN 202010354271A CN 111582516 A CN111582516 A CN 111582516A
- Authority
- CN
- China
- Prior art keywords
- equipment
- state
- fault
- state data
- data
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000012423 maintenance Methods 0.000 title claims abstract description 38
- 238000007405 data analysis Methods 0.000 title claims abstract description 20
- 230000036541 health Effects 0.000 claims abstract description 41
- 238000004458 analytical method Methods 0.000 claims abstract description 25
- 238000007621 cluster analysis Methods 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims description 25
- 230000015654 memory Effects 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 16
- 238000007781 pre-processing Methods 0.000 claims description 13
- 238000004140 cleaning Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 10
- 238000010219 correlation analysis Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 7
- 230000003862 health status Effects 0.000 claims description 3
- 230000002035 prolonged effect Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000008014 freezing Effects 0.000 description 1
- 238000007710 freezing Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- 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
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a device maintenance method and a device based on big data analysis. And performing cluster analysis on the plurality of descriptors of the state data to determine the fault state of the equipment. And determining the health state of the equipment according to the fault state of the equipment, and pushing the health state to a customer service system so that customer service personnel can perform maintenance-related operations on the equipment according to the health state of the equipment. The fault state of the equipment is determined after the status data are preprocessed, a plurality of descriptors are obtained and then clustering analysis is carried out, so that the health state of the equipment can be obtained based on the fault state of the equipment, customer service staff can timely carry out corresponding maintenance operation according to the health state of the equipment, the service life of the equipment is prolonged, and the user experience is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of data processing, in particular to a device maintenance method and device based on big data analysis.
Background
There are generally three modes of equipment maintenance: post-hoc maintenance, preventive maintenance and predictive maintenance, wherein the value of predictive maintenance is most obvious: in a short period: enterprises can obtain secondary marketing benefits; and (3) long-term observation: better provides high-quality service for customers, improves the product quality and improves the user satisfaction.
The pain points of the equipment maintenance in the industry at present are as follows:
(1) the accuracy is insufficient: the conclusion of machine learning is often one-sided due to the lack of sufficient data available to the industry, resulting in the models used not being sufficiently validated.
(2) The knowledge system is complex: the method needs big data algorithm engineers and engineers in the fields of machinery, automation and the like in the professional field to participate together.
(3) Poor landing property: the equipment failure has the characteristics of complexity, diversity, susceptibility to external factors and the like, so that the current equipment maintenance scheme can only solve individual problems and has no universality.
Disclosure of Invention
The embodiment of the invention provides a device maintenance method and device based on big data analysis, which are used for predicting faults in time, maintaining the devices, prolonging the service life of the devices and improving user experience.
In a first aspect, an embodiment of the present invention provides an apparatus maintenance method based on big data analysis, including:
acquiring state data of equipment;
carrying out data preprocessing on the state data, and extracting features of the preprocessed state data to obtain a plurality of descriptors of the state data;
performing cluster analysis on a plurality of descriptors of the state data to determine the fault state of the equipment;
and determining the health state of the equipment according to the fault state of the equipment, and pushing the health state to a customer service system so that customer service personnel can perform maintenance-related operations on the equipment according to the health state of the equipment.
According to the technical scheme, the fault state of the equipment is determined after the status data are preprocessed to obtain the descriptors and then subjected to clustering analysis, so that the health state of the equipment can be obtained based on the fault state of the equipment, and customer service staff can timely perform corresponding maintenance operation according to the health state of the equipment, so that the service life of the equipment is prolonged, and the user experience is improved.
Optionally, the performing data preprocessing on the state data includes:
performing an ETL process on the state data;
denoising the state data;
and performing a cleaning operation based on model specific requirements on the state data.
Optionally, the extracting features from the preprocessed state data to obtain a plurality of descriptors of the state data includes:
performing single-feature extraction on the preprocessed state data to obtain a descriptor;
performing correlation analysis on the preprocessed state data to obtain a descriptor;
and generating abstract features of the preprocessed state data to obtain a descriptor.
Optionally, the determining the health status of the device according to the fault status of the device includes:
when the fault state of the equipment is a fault machine, determining the equipment as fault equipment and determining the fault level of the equipment by diagnosing the fault state of the equipment through an expert library;
when the fault state of the equipment is a non-fault machine, performing predictive analysis according to the current state data of the equipment to obtain the predicted state data of the equipment; re-clustering and analyzing the predicted state data to determine a predicted fault state of the equipment, if the predicted fault state of the equipment is a fault machine, determining the equipment to be sub-healthy equipment, and diagnosing the predicted fault state of the equipment by the expert database to determine the fault level of the equipment; and if the predicted fault state of the equipment is a non-fault machine, determining that the equipment is healthy equipment.
Optionally, the performing predictive analysis according to the current state data of the device to obtain the predicted state data of the device includes:
and carrying out predictive analysis on the current state data of the equipment by using an LSTM algorithm to obtain the predicted state data of the equipment.
In a second aspect, an embodiment of the present invention provides an apparatus for maintaining a device based on big data analysis, including:
an acquisition unit configured to acquire status data of a device;
the processing unit is used for carrying out data preprocessing on the state data and extracting features of the preprocessed state data to obtain a plurality of descriptors of the state data; performing cluster analysis on a plurality of descriptors of the state data to determine the fault state of the equipment; and determining the health state of the equipment according to the fault state of the equipment, and pushing the health state to a customer service system so that customer service personnel can perform maintenance-related operations on the equipment according to the health state of the equipment.
Optionally, the processing unit is specifically configured to:
performing an ETL process on the state data;
denoising the state data;
and performing a cleaning operation based on model specific requirements on the state data.
Optionally, the processing unit is specifically configured to:
performing single-feature extraction on the preprocessed state data to obtain a descriptor;
performing correlation analysis on the preprocessed state data to obtain a descriptor;
and generating abstract features of the preprocessed state data to obtain a descriptor.
Optionally, the processing unit is specifically configured to:
when the fault state of the equipment is a fault machine, determining the equipment as fault equipment and determining the fault level of the equipment by diagnosing the fault state of the equipment through an expert library;
when the fault state of the equipment is a non-fault machine, performing predictive analysis according to the current state data of the equipment to obtain the predicted state data of the equipment; re-clustering and analyzing the predicted state data to determine a predicted fault state of the equipment, if the predicted fault state of the equipment is a fault machine, determining the equipment to be sub-healthy equipment, and diagnosing the predicted fault state of the equipment by the expert database to determine the fault level of the equipment; and if the predicted fault state of the equipment is a non-fault machine, determining that the equipment is healthy equipment.
Optionally, the processing unit is specifically configured to:
and carrying out predictive analysis on the current state data of the equipment by using an LSTM algorithm to obtain the predicted state data of the equipment.
In a third aspect, an embodiment of the present invention further provides a computing device, including:
a memory for storing program instructions;
and the processor is used for calling the program instructions stored in the memory and executing the equipment maintenance method based on the big data analysis according to the obtained program.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable non-volatile storage medium, which includes computer-readable instructions, and when the computer reads and executes the computer-readable instructions, the computer is caused to execute the above device maintenance method based on big data analysis.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic diagram of a system architecture according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of an apparatus maintenance method based on big data analysis according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating a system architecture according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a device maintenance based on big data analysis according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a health status analysis provided by an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an apparatus maintenance device based on big data analysis according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a system architecture provided in an embodiment of the present invention. Referring to fig. 1, the system architecture may be a server 100 including a processor 110, a communication interface 120, and a memory 130.
The communication interface 120 is used for communicating with a terminal device, and transceiving information transmitted by the terminal device to implement communication.
The processor 110 is a control center of the server 100, connects various parts of the entire server 100 using various interfaces and lines, performs various functions of the server 100 and processes data by running or executing software programs and/or modules stored in the memory 130 and calling data stored in the memory 130. Alternatively, processor 110 may include one or more processing units.
The memory 130 may be used to store software programs and modules, and the processor 110 executes various functional applications and data processing by operating the software programs and modules stored in the memory 130. The memory 130 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to a business process, and the like. Further, the memory 130 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
It should be noted that the structure shown in fig. 1 is only an example, and the embodiment of the present invention is not limited thereto.
Based on the above description, fig. 2 shows in detail a flow of the device maintenance method based on big data analysis according to the embodiment of the present invention, where the flow may be executed by the device maintenance apparatus based on big data analysis.
As shown in fig. 2, the process specifically includes:
The state data may be continuous data such as an actual temperature of the freezing chamber, an actual temperature of the refrigerating chamber, an actual temperature of the temperature-changing chamber, an environmental temperature, and the like, or discontinuous data such as a user-set temperature, door opening and closing information, and the like.
When the data preprocessing is performed on the state data, the ETL (extract, transform, load) process is mainly performed on the state data, and the noise removal is performed on the state data; and performing a cleaning operation based on model-specific requirements on the state data.
The preprocessing step is mainly a three-layer cleaning process for the state data, and the first-layer ETL mainly performs operations such as conversion of data formats, addition of data information and the like, for example, according to the IP information of the equipment, obtaining the regional information of the equipment and adding the information into the state data. The second time is to remove the noise, mainly using the extreme value to remove the dispersion, such as interpolation to complement the missing data. The third time is based on model specific requirements for cleaning, such as variance, deviation based filtering.
In the process of extracting the features, the following methods can be specifically used for processing:
in a first mode
And performing single-feature extraction on the preprocessed state data to obtain a descriptor.
The method is to directly extract features of certain state data, such as temperature data, and the temperature data can be directly used as a descriptor.
Mode two
And performing correlation analysis on the preprocessed state data to obtain a descriptor.
This method is a relational feature extraction, for example, when a door of a refrigerating chamber door of a refrigerator is opened, the temperature of the refrigerating chamber rises, in which case a correlation exists between a temperature sensor of the refrigerating chamber and a door opening and closing sensor, and the correlation of the sensors can be used as a descriptor.
Mode III
And generating abstract features of the preprocessed state data to obtain a descriptor.
This way, features other than the surface features are abstracted out: such as variance, kurtosis, periodicity, etc. In general, the state data is subjected to FFT (Fast Fourier Transform), and information such as variance, peak, and period can be obtained by the FFT, and these information can be used as a descriptor.
Step 203, performing cluster analysis on the multiple descriptors of the state data to determine the fault state of the equipment.
After obtaining a plurality of descriptors, cluster analysis can be performed to obtain the fault state of the device, and the fault state can include a fault machine and a non-fault machine. The method of cluster analysis is general cluster analysis, and is not described in detail.
And 204, determining the health state of the equipment according to the fault state of the equipment, and pushing the health state to a customer service system so that customer service personnel can perform maintenance-related operations on the equipment according to the health state of the equipment.
The fault states are divided into fault machines and non-fault machines, and the health states are fault equipment, sub-health equipment and health equipment respectively.
After the fault state of the equipment is obtained, the health state of the equipment can be determined, and the method specifically includes the following steps according to the classification of the fault state:
and when the fault state of the equipment is a fault machine, determining the equipment as fault equipment, diagnosing the fault state of the equipment through an expert library, and determining the fault level of the equipment.
When the fault state of the equipment is a non-fault machine, firstly, prediction analysis is carried out according to the current state data of the equipment to obtain the predicted state data of the equipment. And then, clustering and analyzing the predicted state data again to determine the predicted fault state of the equipment. If the predicted fault state of the equipment is a fault machine, determining the equipment as sub-health equipment, diagnosing the predicted fault state of the equipment through an expert library, and finally determining the fault level of the equipment; and if the predicted fault state of the equipment is a non-fault machine, determining that the equipment is healthy equipment.
When the predicted state data of the device is obtained by performing predictive analysis according to the current state data of the device, the current state data of the device may be specifically subjected to predictive analysis by using a Long Short-Term Memory (LSTM) algorithm to obtain the predicted state data of the device.
For the non-fault machine to enter into the predictive analysis, the LSTM algorithm predicts the state data of the non-fault machine in the future days through the current data, and then obtains the fault machine and the non-fault machine based on the predicted data through the cluster analysis again for the state data of the future days. It is to be emphasized that: at this time, the fault machine based on the prediction data is obtained based on the analysis of the prediction data, and the fault state of the fault machine based on the prediction data in the current data is represented as a non-fault machine, that is, the fault machine based on the prediction data can be positioned as a sub-health device in the non-fault machine, the sub-health device also carries out fault level positioning on the pushed expert database, and then a Customer Relationship Management (CRM) system is pushed to carry out subsequent processing. Correspondingly, after the fault machine obtained through the first clustering analysis is determined to be fault equipment, the fault machine is also pushed to an expert database for fault grading, and then the fault machine is pushed to a CRM system for subsequent processing. The CRM system is a customer service system. It should be noted that, the health device may also be simultaneously pushed to the CRM system, and the CRM system performs corresponding processing on the health device at its discretion.
In order to better explain the embodiment of the present invention, the process of the above-mentioned equipment maintenance will be described in a specific implementation scenario.
Fig. 3 is an overall architecture diagram, and as shown in fig. 3, sensor data of a device, such as a refrigerator, an air conditioner, or a washing machine, of a user is uploaded to a big data platform through a wifi module, where the sensor data includes (taking the refrigerator as an example): continuous data such as freezer actual temperature, walk-in actual temperature, temperature-changing room actual temperature, ambient temperature still include: the user sets discontinuous data such as temperature, door opening and closing information and the like.
After data access is carried out on a big data platform, the big data platform is stored in an HBASE (database), data preprocessing is carried out before entering a model, the data preprocessing is a three-layer cleaning process for original data, the first layer is an ETL (extract, transform and load) process, mainly conversion of data formats and addition of data information are carried out, for example, equipment region information is obtained according to equipment IP information, and the information is added into equipment data; the second layer is basic noise removal, and mainly removes dispersion by using an extreme value and completes missing data by using interpolation; the third layer is based on model-specific requirements for cleaning, such as variance, bias based filtering, etc.
After the data enters the model, feature extraction is carried out, and descriptors (such as variance, kurtosis and the like) of machine learning are extracted and used as input of the machine learning. The method comprises the following steps that two health models are mainly used and respectively comprise a diagnosis model and a prediction model, wherein the diagnosis model is used for carrying out cluster analysis on current data to obtain a fault machine and a non-fault machine, and the fault machine is fault equipment; and the prediction model is to perform clustering analysis on the non-fault machine again to obtain sub-health equipment and health equipment. And finally, fault grading is carried out on the unhealthy equipment (sub-health equipment and fault equipment) through an expert library, then the unhealthy equipment and the health equipment are released, and then the unhealthy equipment and the health equipment are pushed to a CRM system, and customer service in the CRM system can carry out subsequent operation, such as informing a user or promoting operation and maintenance products.
Fig. 4 is a specific explanation of the health model. The current data is subjected to feature extraction (descriptors), which mainly comprise three types of descriptors: single feature extraction (direct features such as temperature are directly used as descriptors); correlation analysis (taking the correlation of sensors as descriptors); and (4) feature generation (abstracting other features except the surface features, such as variance, kurtosis, period and the like). And carrying out cluster analysis on the obtained multi-angle descriptors to obtain a fault machine and a non-fault machine. The fault machine enters an expert database (expert diagnosis database), identifies faults and finally determines the grade. For a non-failure machine to enter into prediction analysis, the LSTM algorithm predicts state data of the non-failure machine in the next several days through current data, and then the prediction data is divided into a failure machine and a non-failure machine based on the prediction data again through a cluster analysis mode, and it needs to be emphasized that: the fault machine based on the prediction data is obtained based on the analysis of the prediction data, the fault state of the fault machine based on the prediction data in the current data is represented as a non-fault machine, namely the fault machine based on the prediction data can be positioned as sub-health equipment in the non-fault machine, the sub-health equipment is pushed to an expert database for fault level positioning, and then the fault machine is pushed to a CRM system for subsequent processing.
Fig. 5 is a filtering process of healthy equipment, sub-healthy equipment, and faulty equipment, where after performing cluster analysis on current data, a faulty machine and a non-faulty machine are obtained, and the faulty machine is determined to be the faulty equipment. The method comprises the steps of carrying out prediction analysis on current data of a non-fault machine to obtain prediction data, then carrying out clustering analysis on the prediction data again to obtain a fault machine and a non-fault machine based on the prediction data, wherein the fault machine obtained based on the prediction data belongs to sub-health equipment, and the non-fault machine obtained based on the prediction data is real health equipment.
The above embodiment shows that the state data of the device is acquired, the data preprocessing is performed on the state data, and the features are extracted from the preprocessed state data to obtain a plurality of descriptors of the state data. And performing cluster analysis on the plurality of descriptors of the state data to determine the fault state of the equipment. And determining the health state of the equipment according to the fault state of the equipment, and pushing the health state to a customer service system so that customer service personnel can perform maintenance-related operations on the equipment according to the health state of the equipment. The fault state of the equipment is determined after the status data are preprocessed, a plurality of descriptors are obtained and then clustering analysis is carried out, so that the health state of the equipment can be obtained based on the fault state of the equipment, customer service staff can timely carry out corresponding maintenance operation according to the health state of the equipment, the service life of the equipment is prolonged, and the user experience is improved.
Based on the same technical concept, fig. 6 exemplarily shows a structure of a device maintenance apparatus based on big data analysis according to an embodiment of the present invention, and the apparatus may perform a device maintenance flow based on big data analysis.
As shown in fig. 6, the apparatus specifically includes:
an acquisition unit 601 configured to acquire status data of a device;
a processing unit 602, configured to perform data preprocessing on the state data, and extract features from the preprocessed state data to obtain multiple descriptors of the state data; performing cluster analysis on a plurality of descriptors of the state data to determine the fault state of the equipment; and determining the health state of the equipment according to the fault state of the equipment, and pushing the health state to a customer service system so that customer service personnel can perform maintenance-related operations on the equipment according to the health state of the equipment.
Optionally, the processing unit 602 is specifically configured to:
performing an ETL process on the state data;
denoising the state data;
and performing a cleaning operation based on model specific requirements on the state data.
Optionally, the processing unit 602 is specifically configured to:
performing single-feature extraction on the preprocessed state data to obtain a descriptor;
performing correlation analysis on the preprocessed state data to obtain a descriptor;
and generating abstract features of the preprocessed state data to obtain a descriptor.
Optionally, the processing unit 602 is specifically configured to:
when the fault state of the equipment is a fault machine, determining the equipment as fault equipment and determining the fault level of the equipment by diagnosing the fault state of the equipment through an expert library;
when the fault state of the equipment is a non-fault machine, performing predictive analysis according to the current state data of the equipment to obtain the predicted state data of the equipment; re-clustering and analyzing the predicted state data to determine a predicted fault state of the equipment, if the predicted fault state of the equipment is a fault machine, determining the equipment to be sub-healthy equipment, and diagnosing the predicted fault state of the equipment by the expert database to determine the fault level of the equipment; and if the predicted fault state of the equipment is a non-fault machine, determining that the equipment is healthy equipment.
Optionally, the processing unit 602 is specifically configured to:
and carrying out predictive analysis on the current state data of the equipment by using an LSTM algorithm to obtain the predicted state data of the equipment.
Based on the same technical concept, an embodiment of the present invention further provides a computing device, including:
a memory for storing program instructions;
and the processor is used for calling the program instructions stored in the memory and executing the equipment maintenance method based on the big data analysis according to the obtained program.
Based on the same technical concept, an embodiment of the present invention further provides a computer-readable non-volatile storage medium, which includes computer-readable instructions, and when the computer reads and executes the computer-readable instructions, the computer is enabled to execute the above device maintenance method based on big data analysis.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A device maintenance method based on big data analysis is characterized by comprising the following steps:
acquiring state data of equipment;
carrying out data preprocessing on the state data, and extracting features of the preprocessed state data to obtain a plurality of descriptors of the state data;
performing cluster analysis on a plurality of descriptors of the state data to determine the fault state of the equipment;
and determining the health state of the equipment according to the fault state of the equipment, and pushing the health state to a customer service system so that customer service personnel can perform maintenance-related operations on the equipment according to the health state of the equipment.
2. The method of claim 1, wherein the data preprocessing the state data comprises:
performing an ETL process on the state data;
denoising the state data;
and performing a cleaning operation based on model specific requirements on the state data.
3. The method of claim 1, wherein said extracting features from said preprocessed state data to obtain a plurality of descriptors of said state data comprises:
performing single-feature extraction on the preprocessed state data to obtain a descriptor;
performing correlation analysis on the preprocessed state data to obtain a descriptor;
and generating abstract features of the preprocessed state data to obtain a descriptor.
4. The method of any one of claims 1 to 3, wherein said determining the health status of the device based on the fault status of the device comprises:
when the fault state of the equipment is a fault machine, determining the equipment as fault equipment and determining the fault level of the equipment by diagnosing the fault state of the equipment through an expert library;
when the fault state of the equipment is a non-fault machine, performing predictive analysis according to the current state data of the equipment to obtain the predicted state data of the equipment; re-clustering and analyzing the predicted state data to determine a predicted fault state of the equipment, if the predicted fault state of the equipment is a fault machine, determining the equipment to be sub-healthy equipment, and diagnosing the predicted fault state of the equipment by the expert database to determine the fault level of the equipment; and if the predicted fault state of the equipment is a non-fault machine, determining that the equipment is healthy equipment.
5. The method of claim 4, wherein the performing predictive analysis based on the current state data of the device to obtain predicted state data of the device comprises:
and carrying out predictive analysis on the current state data of the equipment by using an LSTM algorithm to obtain the predicted state data of the equipment.
6. An apparatus for maintaining equipment based on big data analysis, comprising:
an acquisition unit configured to acquire status data of a device;
the processing unit is used for carrying out data preprocessing on the state data and extracting features of the preprocessed state data to obtain a plurality of descriptors of the state data; performing cluster analysis on a plurality of descriptors of the state data to determine the fault state of the equipment; and determining the health state of the equipment according to the fault state of the equipment, and pushing the health state to a customer service system so that customer service personnel can perform maintenance-related operations on the equipment according to the health state of the equipment.
7. The apparatus as claimed in claim 6, wherein said processing unit is specifically configured to:
performing an ETL process on the state data;
denoising the state data;
and performing a cleaning operation based on model specific requirements on the state data.
8. The apparatus as claimed in claim 6, wherein said processing unit is specifically configured to:
performing single-feature extraction on the preprocessed state data to obtain a descriptor;
performing correlation analysis on the preprocessed state data to obtain a descriptor;
and generating abstract features of the preprocessed state data to obtain a descriptor.
9. A computing device, comprising:
a memory for storing program instructions;
a processor for calling program instructions stored in said memory to execute the method of any one of claims 1 to 5 in accordance with the obtained program.
10. A computer-readable non-transitory storage medium including computer-readable instructions which, when read and executed by a computer, cause the computer to perform the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010354271.2A CN111582516A (en) | 2020-04-29 | 2020-04-29 | Equipment maintenance method and device based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010354271.2A CN111582516A (en) | 2020-04-29 | 2020-04-29 | Equipment maintenance method and device based on big data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111582516A true CN111582516A (en) | 2020-08-25 |
Family
ID=72122593
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010354271.2A Pending CN111582516A (en) | 2020-04-29 | 2020-04-29 | Equipment maintenance method and device based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111582516A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102509178A (en) * | 2011-11-25 | 2012-06-20 | 江苏省电力公司淮安供电公司 | Distribution network device status evaluating system |
| CN109872003A (en) * | 2019-03-06 | 2019-06-11 | 中国科学院软件研究所 | Obj State prediction technique, system, computer equipment and storage medium |
| CN110046562A (en) * | 2019-04-01 | 2019-07-23 | 湖南大学 | A kind of wind power system health monitor method and device |
| CN110861123A (en) * | 2019-11-14 | 2020-03-06 | 华南智能机器人创新研究院 | Method and device for visually monitoring and evaluating running state of robot |
-
2020
- 2020-04-29 CN CN202010354271.2A patent/CN111582516A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102509178A (en) * | 2011-11-25 | 2012-06-20 | 江苏省电力公司淮安供电公司 | Distribution network device status evaluating system |
| CN109872003A (en) * | 2019-03-06 | 2019-06-11 | 中国科学院软件研究所 | Obj State prediction technique, system, computer equipment and storage medium |
| CN110046562A (en) * | 2019-04-01 | 2019-07-23 | 湖南大学 | A kind of wind power system health monitor method and device |
| CN110861123A (en) * | 2019-11-14 | 2020-03-06 | 华南智能机器人创新研究院 | Method and device for visually monitoring and evaluating running state of robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11187446B2 (en) | Anomaly detection in a refrigeration condensor system | |
| EP3588283A1 (en) | System and method for recommending service experience package | |
| US20170315855A1 (en) | Method of detecting anomalies on appliances and system thereof | |
| CN110837852A (en) | Fault diagnosis method and device for rolling mill gearbox and terminal equipment | |
| CN113010389A (en) | Training method, fault prediction method, related device and equipment | |
| CN114267178B (en) | Intelligent operation maintenance method and device for station | |
| CN104516808A (en) | Data preprocessing device and method thereof | |
| CN114324368B (en) | Modified plastic production detection method and system based on mechanical vision detection | |
| US20200242493A1 (en) | Operational energy consumption anomalies in intelligent energy consumption systems | |
| CN110059069A (en) | System and method for detecting and predicting the behavior of goal systems | |
| US20200143294A1 (en) | Automatic classification of refrigeration states using in an internet of things computing environment | |
| CN114528942A (en) | Construction method of data sample library of engineering machinery, failure prediction method and engineering machinery | |
| CN111582516A (en) | Equipment maintenance method and device based on big data analysis | |
| CN109698026B (en) | Component identification in fault handling of medical devices | |
| CN108664696B (en) | Method and device for evaluating running state of water chiller | |
| CN106485526A (en) | A kind of diagnostic method of data mining model and device | |
| CN114925674A (en) | File compliance checking method and device, electronic equipment and storage medium | |
| Van Beek et al. | A CPU contention predictor for business-critical workloads in cloud datacenters | |
| CN111582343B (en) | Equipment fault prediction method and device | |
| CN113361811A (en) | Method, system, device and computer readable storage medium for predicting operation state | |
| CN112395167A (en) | Operation fault prediction method and device and electronic equipment | |
| CN111428886A (en) | Fault diagnosis deep learning model self-adaptive updating method and device | |
| CN110413482A (en) | Detection method and device | |
| CN115080445B (en) | Game test management method and system | |
| CN116627761B (en) | PHM modeling and modeling auxiliary system and method based on big data frame |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200825 |