CN116859843A - Production equipment fault monitoring method and system based on industrial big data - Google Patents
Production equipment fault monitoring method and system based on industrial big data Download PDFInfo
- Publication number
- CN116859843A CN116859843A CN202310818516.6A CN202310818516A CN116859843A CN 116859843 A CN116859843 A CN 116859843A CN 202310818516 A CN202310818516 A CN 202310818516A CN 116859843 A CN116859843 A CN 116859843A
- Authority
- CN
- China
- Prior art keywords
- equipment
- production
- data
- detection
- fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 303
- 238000012544 monitoring process Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000001514 detection method Methods 0.000 claims abstract description 286
- 230000005856 abnormality Effects 0.000 claims abstract description 97
- 238000003745 diagnosis Methods 0.000 claims abstract description 49
- 238000012545 processing Methods 0.000 claims abstract description 39
- 230000035945 sensitivity Effects 0.000 claims abstract description 24
- 238000005457 optimization Methods 0.000 claims abstract description 11
- 230000002159 abnormal effect Effects 0.000 claims description 60
- 238000009434 installation Methods 0.000 claims description 30
- 230000003993 interaction Effects 0.000 claims description 28
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000012216 screening Methods 0.000 claims description 13
- 238000010276 construction Methods 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 4
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims 2
- 230000000694 effects Effects 0.000 abstract description 20
- 238000013528 artificial neural network Methods 0.000 description 7
- 210000002569 neuron Anatomy 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000006641 stabilisation Effects 0.000 description 2
- 238000011105 stabilization Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
- G06N3/0499—Feedforward networks
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41875—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by quality surveillance of production
-
- 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
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses a production equipment fault monitoring method and system based on industrial big data, and relates to the field of data processing, wherein the method comprises the following steps: constructing a multi-level equipment association node based on the production plan and the equipment basic information; constructing a first detection data set; constructing a second detection data set; performing detection sensitivity optimization of the anomaly detection model through the fault correlation factor; inputting the first detection data set and the second detection data set into an abnormality detection model, and outputting an abnormality detection result; outputting a production abnormality detection result; fault diagnosis information is generated from the abnormality detection result and the production abnormality detection result. The technical problems of low fault monitoring and diagnosing accuracy aiming at production equipment and poor fault monitoring and diagnosing effect of the production equipment in the prior art are solved. The technical effects of improving the fault monitoring and diagnosing accuracy and comprehensiveness of the production equipment, improving the fault monitoring and diagnosing quality of the production equipment and the like are achieved.
Description
Technical Field
The invention relates to the field of data processing, in particular to a production equipment fault monitoring method and system based on industrial big data.
Background
Fault monitoring diagnostics is one of the important directions of development for industrial big data. Along with the rapid progress of the industrial production level, the precision of production equipment is higher and higher, the structure is also more and more complex, and higher-level requirements are put forward on fault monitoring and diagnosis of the production equipment. The traditional manual analysis and experience judgment can not accurately and effectively realize the fault monitoring diagnosis of production equipment. Therefore, the method for optimizing the fault monitoring and diagnosis of the production equipment is researched and designed by combining industrial big data with the fault monitoring and diagnosis of the production equipment, and has important practical significance.
In the prior art, the fault monitoring and diagnosing precision aiming at production equipment is low, and the technical problem of poor fault monitoring and diagnosing effect of the production equipment is caused.
Disclosure of Invention
The application provides a production equipment fault monitoring method and system based on industrial big data. The technical problems of low fault monitoring and diagnosing accuracy aiming at production equipment and poor fault monitoring and diagnosing effect of the production equipment in the prior art are solved. The fault monitoring and diagnosing precision and comprehensiveness of the production equipment are improved, the fault monitoring and diagnosing quality of the production equipment is improved, and the technical effect of guaranteeing the normal operation of the production equipment is achieved.
In view of the above problems, the application provides a production equipment fault monitoring method and system based on industrial big data.
In a first aspect, the present application provides a production equipment fault monitoring method based on industrial big data, wherein the method is applied to a production equipment fault monitoring system based on industrial big data, and the method comprises: device base information of the interactive production device, wherein the device base information comprises device ID information, device attribute information and a device characteristic data set; acquiring a production plan, and constructing a multi-level equipment association node based on the production plan and the equipment basic information; performing equipment operation data interaction on the production equipment to construct a first detection data set; arranging a detection sensor, detecting the production equipment through the detection sensor, and constructing a second detection data set; determining a fault correlation factor through a device characteristic data set, and optimizing the detection sensitivity of an anomaly detection model through the fault correlation factor; inputting the first detection data set and the second detection data set into the abnormality detection model, and outputting an abnormality detection result; performing data acquisition on the produced products, detecting production anomalies according to the data acquisition results of the multi-level equipment association nodes, and outputting production anomaly detection results; generating fault diagnosis information through the abnormality detection result and the production abnormality detection result.
In a second aspect, the present application also provides a production facility fault monitoring system based on industrial big data, wherein the system comprises: the device basic information acquisition module is used for interactively producing device basic information of the device, wherein the device basic information comprises device ID information, device attribute information and a device characteristic data set; the equipment association node construction module is used for collecting a production plan and constructing multi-level equipment association nodes based on the production plan and the equipment basic information; the equipment operation data interaction module is used for carrying out equipment operation data interaction on the production equipment to construct a first detection data set; the equipment detection module is used for arranging a detection sensor, carrying out equipment detection on the production equipment through the detection sensor and constructing a second detection data set; the detection sensitivity optimization module is used for determining a fault correlation factor through the equipment characteristic data set and performing detection sensitivity optimization of an abnormal detection model through the fault correlation factor; the data anomaly detection module is used for inputting the first detection data set and the second detection data set into the anomaly detection model and outputting an anomaly detection result; the production anomaly detection module is used for carrying out data acquisition on production products, carrying out production anomaly detection on data acquisition results according to the multi-level equipment association nodes and outputting production anomaly detection results; and the fault diagnosis information generation module is used for generating fault diagnosis information through the abnormal detection result and the production abnormal detection result.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
constructing multi-level equipment association nodes through equipment basic information and production plans of production equipment; constructing a first detection data set by carrying out equipment operation data interaction on production equipment; performing equipment detection on production equipment through a detection sensor to construct a second detection data set; determining a fault correlation factor through the equipment characteristic data set, and optimizing the detection sensitivity of the abnormality detection model through the fault correlation factor; inputting the first detection data set and the second detection data set into an abnormality detection model, and outputting an abnormality detection result; and executing data acquisition on the produced products, detecting production abnormality of the data acquisition result according to the multi-level equipment association nodes, outputting the production abnormality detection result, and generating fault diagnosis information by combining the abnormality detection result. The fault monitoring and diagnosing precision and comprehensiveness of the production equipment are improved, the fault monitoring and diagnosing quality of the production equipment is improved, and the technical effect of guaranteeing the normal operation of the production equipment is achieved.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly described below. It is apparent that the figures in the following description relate only to some embodiments of the present disclosure and are not limiting of the present disclosure.
FIG. 1 is a schematic flow chart of a production facility fault monitoring method based on industrial big data according to the present application;
FIG. 2 is a schematic diagram of a process for completing abnormality detection according to an abnormality detection model after database screening in a production equipment fault monitoring method based on industrial big data according to the present application;
FIG. 3 is a schematic diagram of a production facility fault monitoring system based on industrial big data.
Reference numerals illustrate: the system comprises an equipment basic information obtaining module 11, an equipment association node constructing module 12, an equipment operation data interaction module 13, an equipment detection module 14, a detection sensitivity optimizing module 15, a data abnormality detecting module 16, a production abnormality detecting module 17 and a fault diagnosis information generating module 18.
Detailed Description
The application provides a production equipment fault monitoring method and system based on industrial big data. The technical problems of low fault monitoring and diagnosing accuracy aiming at production equipment and poor fault monitoring and diagnosing effect of the production equipment in the prior art are solved. The fault monitoring and diagnosing precision and comprehensiveness of the production equipment are improved, the fault monitoring and diagnosing quality of the production equipment is improved, and the technical effect of guaranteeing the normal operation of the production equipment is achieved.
Example 1
Referring to fig. 1, the application provides a production equipment fault monitoring method based on industrial big data, wherein the method is applied to a production equipment fault monitoring system based on industrial big data, and the method specifically comprises the following steps:
step S100: device base information of the interactive production device, wherein the device base information comprises device ID information, device attribute information and a device characteristic data set;
step S200: acquiring a production plan, and constructing a multi-level equipment association node based on the production plan and the equipment basic information;
specifically, the production equipment fault monitoring system based on industrial big data can be used for product production management. The production equipment fault monitoring system based on the industrial big data can be used for carrying out intelligent fault detection on the production equipment in the production process of the product, so that the production quality of the product can be improved.
When a target product is produced, a plurality of product production devices are usually required, and basic information is acquired for the plurality of product production devices to obtain the basic information of the production devices. And then, collecting a production plan of the target product, and constructing a multi-level equipment association node by combining the equipment basic information.
The target product can be any product which is subjected to intelligent production management by using the production equipment fault monitoring system based on industrial big data. The production facility includes a plurality of product production facilities. The plurality of product production facilities includes a plurality of facilities required for the production process of the target product. The device base information includes device ID information, device attribute information, and a device feature data set corresponding to each of the production devices. The equipment ID information includes identification number information corresponding to each product production equipment. The equipment attribute information comprises equipment type, specification model, size information, position information and the like corresponding to each product production equipment. The equipment characteristic data set comprises a plurality of equipment characteristic data sequences corresponding to a plurality of product production equipment. Each equipment characteristic data sequence includes a plurality of equipment control parameter types, a plurality of equipment control parameter ranges, and a plurality of equipment failure events corresponding to each product production equipment. Each equipment fault event comprises data information such as historical equipment detection data, historical fault time, historical fault reasons, historical fault types, historical fault grades, historical fault influences, historical fault maintenance measures and the like when historical faults occur in each product production equipment. The production plan comprises the planned production quantity corresponding to the planned production period of the target product and the production flow information corresponding to the target product. The production flow information comprises a plurality of production procedure information corresponding to the target product. The multi-level device association node includes device base information arranged according to production flow information in the production plan. The method achieves the technical effect of constructing comprehensive multi-level equipment association nodes through production plans and equipment foundation information and laying a foundation for subsequent fault diagnosis of production equipment.
Step S300: performing equipment operation data interaction on the production equipment to construct a first detection data set;
step S400: arranging a detection sensor, detecting the production equipment through the detection sensor, and constructing a second detection data set;
specifically, when a target product is produced through production equipment, real-time operation data acquisition is performed on the production equipment, and a first detection data set is obtained. And arranging detection sensors based on the equipment basic information, and carrying out equipment detection on the production equipment through the arranged detection sensors to obtain a second detection data set. The first detection data set comprises a plurality of first detection data corresponding to a plurality of product production devices. Each first detection data comprises real-time equipment control parameters such as real-time voltage, real-time current and the like corresponding to each product production equipment when the target product is produced. The detection sensor comprises a temperature sensor and a noise sensor in the prior art. The second detection data set comprises a plurality of second detection data corresponding to a plurality of product production devices. Each second detection data comprises real-time temperature and real-time noise corresponding to a plurality of positions of each product production device when the target product is produced.
Illustratively, when the detection sensor is deployed, a historical data query is performed based on the device base information to obtain a device sensor deployment database. The device sensor layout database includes a plurality of device sensor layout data. Each device sensor layout data includes historical device base information, a historical device sensor layout scheme. The historical equipment sensor layout scheme comprises a historical layout type, a historical layout position and a historical layout number of the detection sensor corresponding to the historical equipment basic information. And inputting the equipment basic information into an equipment sensor layout database, performing sensor layout scheme matching on the equipment basic information through the equipment sensor layout database to obtain an equipment sensor layout scheme corresponding to the equipment basic information, and performing detection sensor layout on production equipment according to the equipment sensor layout scheme to obtain a detection sensor with the layout completed. The equipment sensor layout scheme comprises layout types, layout positions and layout quantity of detection sensors corresponding to the equipment basic information.
The method achieves the technical effects of collecting the first detection data set and the second detection data set of the production equipment and providing data support for the follow-up fault diagnosis of the production equipment.
Step S500: determining a fault correlation factor through a device characteristic data set, and optimizing the detection sensitivity of an anomaly detection model through the fault correlation factor;
specifically, based on the first detection data set and the second detection data set, the abnormality detection record inquiry of the sample production equipment is carried out through industrial big data, and an equipment abnormality detection record library is obtained. The sample production equipment comprises production equipment and a plurality of production equipment with the same type corresponding to the production equipment. The equipment abnormality detection record library comprises a plurality of groups of equipment abnormality detection records. Each group of equipment abnormality detection records comprises a historical first detection data set, a historical second detection data set and a historical abnormality detection result. And each group of equipment abnormality detection records has a production equipment identifier and a fault time identifier. The historical abnormality detection result comprises historical abnormality data in a historical first detection data set and a historical second detection data set, and a historical equipment fault type and a historical equipment fault grade corresponding to the historical abnormality data. And then, performing cross supervision training on the equipment anomaly detection record base based on the BP neural network to obtain an anomaly detection model. The BP neural network is a multi-layer feedforward neural network trained according to an error back propagation algorithm. The BP neural network can perform forward calculation and backward calculation. When calculating in the forward direction, the input information is processed layer by layer from the input layer through a plurality of layers of neurons and is turned to the output layer, and the state of each layer of neurons only affects the state of the next layer of neurons. If the expected output cannot be obtained at the output layer, the reverse calculation is carried out, the error signal is returned along the original connecting path, and the weight of each neuron is modified to minimize the error signal. The anomaly detection model comprises an input layer, an implicit layer and an output layer.
Further, on the basis of obtaining the abnormality detection model, a fault correlation factor is extracted from the device feature data set. Based on the BP neural network, the fault correlation factor is continuously self-trained and learned to a convergence state, a detection sensitivity optimization layer is obtained, and the detection sensitivity optimization layer is embedded into an abnormal detection model. Wherein the fault correlation factor comprises a plurality of device fault events in a device characteristic data set. The anomaly detection model also includes a detection sensitivity optimization layer. When fault information corresponding to the fault correlation factor exists in the first detection data set and the second detection data set of the abnormality detection model, the detection sensitivity optimization layer can perform sensitivity recognition on the fault information, so that the sensitivity, the intelligence and the efficiency of abnormality detection are improved. The technical effects of optimizing the detection sensitivity of the abnormal detection model through the fault correlation factors and improving the comprehensiveness, the accuracy and the abnormal detection sensitivity of the abnormal detection model are achieved.
Further, as shown in fig. 2, step S500 of the present application further includes:
step S510: obtaining equipment installation information of the production equipment, wherein the equipment installation information comprises equipment installation time and equipment installation positions;
Step S520: reading the using time length of the production equipment, matching the fault distribution time period of the production equipment according to the using time length, and determining a fault main period;
step S530: performing equipment stability analysis based on the equipment installation information, and determining a fault auxiliary period;
specifically, the device base information also includes device installation information of the production device. The equipment installation information comprises equipment installation time, equipment installation position and equipment installation stability time corresponding to each product production equipment in the production equipment. The equipment installation time includes a corresponding historical installation time point for each product production equipment. The equipment installation location includes installation location parameters corresponding to each of the product production equipment. The equipment installation stabilization time comprises a historical time point of starting stable operation after each product production equipment is installed and debugged. Further, a fault assistance period is determined based on the device installation time and the device installation stability time. The fault assistance period includes time range information between a device installation time and a device installation stabilization time. Then, fault distribution period extraction is performed based on the use time length of the production equipment, and a fault main period is obtained. The using time length comprises using time range information corresponding to each product production device. When the product production equipment fails, the using time range information has a corresponding equipment failure time identifier. And the failure main period comprises failure time information of failure of the product production equipment in the use duration.
Step S540: screening a model database of the abnormality detection model through the fault main period and the fault auxiliary period;
further, step S540 of the present application further includes:
step S541: reading man-machine interaction data of the production equipment, and generating equipment stability association characteristics of the production equipment according to a man-machine interaction data reading result;
step S542: the period compensation of the fault auxiliary period is carried out based on the equipment stability association characteristic, and a compensation fault auxiliary period is obtained;
step S543: and completing the model database screening of the abnormal detection model through the compensation fault auxiliary period and the fault main period.
Step S550: and finishing the abnormality detection according to the abnormality detection model after the database is screened.
Step S600: inputting the first detection data set and the second detection data set into the abnormality detection model, and outputting an abnormality detection result;
specifically, human-computer interaction data acquisition is carried out on the production equipment, a human-computer interaction data reading result is obtained, and equipment stability association characteristics of the production equipment are extracted from the human-computer interaction data reading result. The human-computer interaction data reading result comprises a plurality of pieces of equipment human-computer interaction data. Each device human-computer interaction data comprises a plurality of device human-computer interaction events corresponding to each product production device. Each equipment man-machine interaction event comprises equipment control personnel corresponding to each product production equipment, and historical stable operation time corresponding to the product production equipment when the equipment control personnel control the product production equipment to produce. The device stability association feature includes a plurality of stable run times in the human-machine interaction data reading result.
Further, the fault auxiliary period is subjected to period compensation based on the equipment stability association characteristic, and a compensation fault auxiliary period is obtained. And screening the model database based on the compensation fault auxiliary period and the fault main period to obtain a screening database. And inputting the screening database into an abnormality detection model, and updating parameters of the abnormality detection model through the screening database to improve timeliness and accuracy of the abnormality detection model. And then, inputting the first detection data set and the second detection data set into an abnormality detection model updated by parameters of the screening database to obtain an abnormality detection result.
The compensating fault auxiliary period comprises equipment stability association characteristics and a fault auxiliary period. The model database comprises a device anomaly detection record library. The screening database comprises a plurality of groups of equipment abnormality detection records corresponding to the compensation fault auxiliary period and the fault main period in the equipment abnormality detection record library. The abnormal detection result comprises abnormal data in the first detection data set and the second detection data set, and equipment fault types and equipment fault grades corresponding to the abnormal data. The method has the advantages that the first detection data set and the second detection data set are subjected to fault analysis through the abnormality detection model, reliable abnormality detection results are obtained, and the accuracy of fault monitoring and diagnosis of production equipment is improved.
Step S700: performing data acquisition on the produced products, detecting production anomalies according to the data acquisition results of the multi-level equipment association nodes, and outputting production anomaly detection results;
step S800: generating fault diagnosis information through the abnormality detection result and the production abnormality detection result.
Specifically, data acquisition is performed on a target product produced by production equipment, and production product data is obtained. And when the target product is produced by the production equipment, carrying out product data acquisition based on the multi-level equipment association nodes to obtain a data acquisition result. And carrying out production abnormality detection based on the production product data and the data acquisition result to obtain a production abnormality detection result, and combining the abnormality detection result to obtain fault diagnosis information. The production product data comprise data information such as material composition, size structure, product performance and the like corresponding to a target product produced by production equipment. The data acquisition result comprises a plurality of product production data corresponding to a plurality of production procedure information in the multi-level equipment association node. Each product production data comprises the material composition and the size structure information of the target product corresponding to each production procedure information. The production anomaly detection result comprises production product data, anomaly data information in the data acquisition result, production equipment corresponding to the anomaly data information and production anomaly grade. The production anomaly level is data information for characterizing the influence of anomaly data information on the production of a target product. The higher the influence of the abnormal data information on the production of the target product is, the larger the corresponding production abnormal grade is. The fault diagnosis information includes an abnormality detection result and a production abnormality detection result.
Illustratively, when the production anomaly detection result is obtained, industrial big data query is performed based on production product data and data acquisition results, and a plurality of groups of construction data are obtained. Each group of construction data comprises historical production product data, a historical data acquisition result, historical abnormal data information, and historical production equipment and historical production abnormal grades corresponding to the historical abnormal data information. Based on BP neural network, carrying out continuous self-training learning on multiple groups of construction data to a convergence state, and obtaining the production abnormality detection model. The production anomaly detection model comprises an input layer, an implicit layer and an output layer. And then, inputting the production product data and the data acquisition result into a production anomaly detection model, and carrying out anomaly detection and production anomaly grade identification on the production product data and the data acquisition result through the production anomaly detection model to obtain a production anomaly detection result.
The technical effect of improving the fault monitoring and diagnosing quality of the production equipment by carrying out multidimensional fault monitoring and diagnosing on the production equipment is achieved.
Further, step S800 of the present application further includes:
step S810: continuously detecting the production equipment based on the detection sensor, and recording a continuous detection result, wherein the continuous detection result corresponds to an equipment working mode identifier;
Step S820: performing continuous working time identification on the basis of the continuous detection result to generate a continuous association coefficient of each detection node;
step S830: performing data clustering of the continuous detection results based on the equipment working mode identification to generate data clustering results;
step S840: performing continuous detection equipment anomaly identification through the continuous association coefficient and the data clustering result;
step S850: and carrying out fault updating of the fault diagnosis information based on the abnormal recognition result.
Specifically, continuous detection is performed on the production equipment for a preset time interval based on the detection sensor, and a continuous detection result is obtained. The preset time interval includes a plurality of preset time points. The continuous detection result comprises a plurality of temperature parameters and a plurality of noise parameters corresponding to the production equipment in a preset time interval. And each temperature parameter and each noise parameter in the continuous detection result have corresponding equipment working mode identifiers. The equipment working mode identifier is the working mode information of the production equipment corresponding to the temperature parameter and the noise parameter.
Further, based on the continuous detection result, the continuous working time length identification of the work is carried out, and the continuous association coefficient of each detection node is obtained. The continuous association coefficient of each detection node comprises continuous working time length marks of production equipment in each preset time point. The continuous working time length identification comprises continuous working time length information of the production equipment in each preset time point. And then, carrying out data clustering on the continuous detection results based on the equipment working mode identifiers, namely classifying the continuous detection results with the same equipment working mode identifiers into one type to obtain data clustering results. The data clustering result comprises a plurality of clustering continuous detection results. Each cluster continuous detection result comprises continuous detection results with the same equipment working mode identification. And then, carrying out equipment anomaly recognition based on the continuous association coefficient and the data clustering result to obtain an anomaly recognition result, adding the anomaly recognition result into the fault diagnosis information, and carrying out data updating on the fault diagnosis information through the anomaly recognition result to improve the comprehensiveness of the fault diagnosis information. The abnormal identification result comprises continuous association coefficients, abnormal parameters in the data clustering result, production equipment corresponding to the abnormal parameters, the type of production equipment faults and the grade of production equipment faults.
Illustratively, when an anomaly identification result is obtained, industrial big data query is performed based on the continuous association coefficient and the data clustering result, and a plurality of groups of construction data sequences are obtained. Each group of construction data sequence comprises a history continuous association coefficient, a history data clustering result, a history abnormal parameter, and history production equipment, a history production equipment fault type and a history production equipment fault level corresponding to the history abnormal parameter. Based on BP neural network, carrying out continuous self-training learning on a plurality of groups of constructed data sequences to a convergence state, and obtaining the continuous detection anomaly identification model. The continuous detection anomaly identification model comprises an input layer, an implicit layer and an output layer. And then, inputting the continuous association coefficient and the data clustering result into a continuous detection abnormality recognition model, and carrying out abnormality analysis on the continuous association coefficient and the data clustering result through the continuous detection abnormality recognition model to obtain an abnormality recognition result.
The method achieves the technical effects of obtaining accurate abnormal recognition results and improving the comprehensiveness of fault monitoring and diagnosis of the production equipment by carrying out continuous detection and equipment abnormality recognition on the production equipment.
Further, after step S850 of the present application, the method further includes:
Step S860: product identification is carried out on the produced product, parameter acquisition of parameters to be processed is carried out before any procedure is carried out, and the parameters are used as first comparison data;
step S870: according to the parameters to be processed and the multi-level equipment association node, processing data of the association equipment is called and used as second comparison data, wherein the second comparison data is processed data of the production equipment of the previous node for processing the parameters to be processed;
step S880: performing data primary core on the first comparison data and the second comparison data;
step S890: if the data primary core does not pass, generating non-associated production size abnormality information of the production equipment;
step S8100: and adding the fault diagnosis information according to the non-associated production size abnormality information.
Specifically, product identification is performed on a target product produced by production equipment, and parameters to be processed of the target product before any production procedure information are acquired when the target product is produced, so that first comparison data are obtained. The first comparison data comprise processing data corresponding to parameters to be processed of the target product before any production procedure information. The parameters to be processed are the processing parameter type and the processing parameter information of the target product corresponding to any production procedure information.
Further, based on the multi-level equipment association node, processing data acquisition of the association equipment is carried out on the parameter to be processed, and second comparison data are obtained. The second comparison data is processed data of the production equipment of the last node for processing the parameters to be processed. That is, the second comparison data includes processing data of the to-be-processed parameter corresponding to the last production process information of processing the to-be-processed parameter. And then, performing data primary core on the first comparison data and the second comparison data, namely, performing data comparison on the first comparison data and the second comparison data, when the first comparison data and the second comparison data are inconsistent, the data primary core does not pass, generating uncorrelated production size abnormality information of the production equipment according to the first comparison data and the second comparison data, and adding uncorrelated production size abnormality information to the fault diagnosis information. The non-associated production size abnormality information comprises first comparison data and second comparison data which are failed in the primary core of the data, and difference information between the first comparison data and the second comparison data. The technical effect of improving the accuracy of fault monitoring and diagnosis of the production equipment by carrying out non-associated production size abnormal information analysis on the production equipment is achieved.
Further, step S890 of the present application further comprises:
step S891: if the data primary core passes, after the execution of the current procedure is completed, the data acquisition of the parameters to be processed is carried out again, and the parameters to be processed are used as third comparison data;
step S892: performing processing influence analysis on equipment through the first comparison data to generate a correlation influence coefficient;
step S893: processing and evaluating the first comparison data and the third comparison data to generate initial abnormal values of processing;
step S894: and compensating the initial abnormal value through the association influence coefficient, and adding an initial abnormal value compensation result to the fault diagnosis information.
Specifically, when the first comparison data and the second comparison data coincide, the data initially passes. And (3) producing a target product according to the parameters to be processed of any production process information, and after the current process is finished, namely, when the execution of the parameters to be processed of any production process information is finished, re-acquiring data of the parameters to be processed to obtain third comparison data. And then, processing influence analysis is carried out on the first comparison data, and a correlation influence coefficient is generated. And performing processing evaluation on the first comparison data and the third comparison data to obtain initial abnormal values. And compensating the initial abnormal value according to the associated influence coefficient to obtain an initial abnormal value compensation result, and adding the initial abnormal value compensation result to the fault diagnosis information.
The third comparison data comprise processing data of a target product corresponding to any production procedure information. The correlation influence coefficient is data information for characterizing the processing quality of the first comparison data. The worse the processing quality of the first comparison data is, the higher the processing influence of the first comparison data is, and the larger the corresponding association influence coefficient is. The initial anomaly value is data information for characterizing processing anomalies of the first comparison data and the third comparison data. The higher the processing abnormality of the first comparison data and the third comparison data, the larger the corresponding initial abnormality value. Illustratively, when the initial outlier is compensated according to the associated influence coefficient, a product of the associated influence coefficient and the initial outlier is output as an initial outlier compensation result. The technical effect of carrying out information compensation on fault diagnosis information through the initial abnormal value compensation result and improving the fault monitoring diagnosis quality of production equipment is achieved.
Further, after step S800, the method further includes:
step S910: matching an abnormal early warning grade according to the fault diagnosis information and the production plan;
step S920: and performing fault processing on the production equipment based on the abnormal early warning level.
Specifically, based on fault diagnosis information and a production plan, the abnormal early warning level is matched, the abnormal early warning level is sent to equipment maintenance personnel, the equipment maintenance personnel is reminded of timely carrying out fault treatment on production equipment through the abnormal early warning level, and therefore timeliness of fault treatment of the production equipment is improved. Illustratively, the fault levels in the fault diagnosis information are summed to obtain an anomaly early warning level. The abnormality early warning level is the sum of the failure levels in the failure diagnosis information.
In summary, the production equipment fault monitoring method based on industrial big data provided by the application has the following technical effects:
1. constructing multi-level equipment association nodes through equipment basic information and production plans of production equipment; constructing a first detection data set by carrying out equipment operation data interaction on production equipment; performing equipment detection on production equipment through a detection sensor to construct a second detection data set; determining a fault correlation factor through the equipment characteristic data set, and optimizing the detection sensitivity of the abnormality detection model through the fault correlation factor; inputting the first detection data set and the second detection data set into an abnormality detection model, and outputting an abnormality detection result; and executing data acquisition on the produced products, detecting production abnormality of the data acquisition result according to the multi-level equipment association nodes, outputting the production abnormality detection result, and generating fault diagnosis information by combining the abnormality detection result. The fault monitoring and diagnosing precision and comprehensiveness of the production equipment are improved, the fault monitoring and diagnosing quality of the production equipment is improved, and the technical effect of guaranteeing the normal operation of the production equipment is achieved.
2. And the detection sensitivity of the abnormal detection model is optimized through the fault correlation factors, so that the comprehensiveness, the accuracy and the abnormal detection sensitivity of the abnormal detection model are improved.
3. By continuously detecting production equipment and identifying equipment abnormality, an accurate abnormality identification result is obtained, and the comprehensiveness of fault monitoring and diagnosis of the production equipment is improved.
Example two
Based on the same inventive concept as the production equipment fault monitoring method based on industrial big data in the foregoing embodiment, the present invention further provides a production equipment fault monitoring system based on industrial big data, referring to fig. 3, the system includes:
an equipment basic information obtaining module 11, wherein the equipment basic information obtaining module 11 is used for interactively producing equipment basic information of equipment, and the equipment basic information comprises equipment ID information, equipment attribute information and equipment characteristic data sets;
an equipment-related node construction module 12, wherein the equipment-related node construction module 12 is used for acquiring a production plan and constructing a multi-level equipment-related node based on the production plan and the equipment basic information;
the equipment operation data interaction module 13 is used for carrying out equipment operation data interaction on the production equipment to construct a first detection data set;
The equipment detection module 14 is used for arranging a detection sensor, carrying out equipment detection on the production equipment through the detection sensor, and constructing a second detection data set;
the detection sensitivity optimization module 15 is used for determining a fault correlation factor through the equipment characteristic data set and performing detection sensitivity optimization of an abnormal detection model through the fault correlation factor;
a data anomaly detection module 16, where the data anomaly detection module 16 is configured to input the first detection data set and the second detection data set into the anomaly detection model, and output an anomaly detection result;
the production anomaly detection module 17 is used for performing data acquisition on production products, detecting production anomalies according to data acquisition results of the multi-level equipment association nodes, and outputting production anomaly detection results;
a fault diagnosis information generation module 18, wherein the fault diagnosis information generation module 18 is used for generating fault diagnosis information through the abnormality detection result and the production abnormality detection result.
Further, the system further comprises:
The equipment installation information determining module is used for obtaining equipment installation information of the production equipment, wherein the equipment installation information comprises equipment installation time and equipment installation positions;
the fault main period determining module is used for reading the using time length of the production equipment, performing fault distribution period matching of the production equipment through the using time length, and determining a fault main period;
the equipment stability analysis module is used for carrying out equipment stability analysis based on the equipment installation information and determining a fault auxiliary period;
the model database obtaining module is used for screening a model database of the abnormal detection model through the fault main period and the fault auxiliary period;
and the first execution module is used for completing abnormality detection according to the abnormality detection model after the database is screened.
Further, the system further comprises:
the equipment stability association characteristic determining module is used for reading man-machine interaction data of the production equipment and generating equipment stability association characteristics of the production equipment according to a man-machine interaction data reading result;
The period compensation module is used for compensating the period of the fault auxiliary period based on the equipment stability association characteristic to obtain a compensation fault auxiliary period;
and the second execution module is used for completing the model database screening of the abnormality detection model through the compensation fault auxiliary period and the fault main period.
Further, the system further comprises:
the equipment continuous detection module is used for continuously detecting the production equipment based on the detection sensor and recording a continuous detection result, wherein the continuous detection result corresponds to an equipment working mode identifier;
the continuous association coefficient generation module is used for carrying out continuous working time identification on the basis of the continuous detection result and generating a continuous association coefficient of each detection node;
the data clustering module is used for carrying out data clustering on the continuous detection results based on the equipment working mode identification and generating data clustering results;
the third execution module is used for executing equipment abnormality recognition of continuous detection through the continuous association coefficient and the data clustering result;
And the fault updating module is used for carrying out fault updating of the fault diagnosis information based on the abnormal identification result.
Further, the system further comprises:
the first comparison data acquisition module is used for carrying out product identification on the produced product, and carrying out parameter acquisition of parameters to be processed before any procedure is executed, and the parameters are used as first comparison data;
the second comparison data acquisition module is used for calling processing data of the associated equipment according to the parameters to be processed and the multi-level equipment associated node and taking the processing data as second comparison data, wherein the second comparison data is processed data of the production equipment of the last node for processing the parameters to be processed;
the fourth execution module is used for carrying out data primary core on the first comparison data and the second comparison data;
the fifth execution module is used for generating the non-associated production size abnormal information of the production equipment if the data primary core does not pass;
and a sixth execution module for adding to the fault diagnosis information according to the non-associated production size abnormality information.
Further, the system further comprises:
the third comparison data acquisition module is used for carrying out data acquisition on the parameters to be processed again after the execution of the current procedure is completed if the primary core of the data passes, and taking the data as third comparison data;
the processing influence analysis module is used for carrying out processing influence analysis on equipment through the first comparison data and generating a correlation influence coefficient;
the processing evaluation module is used for processing and evaluating the first comparison data and the third comparison data to generate initial abnormal values of processing;
and a seventh execution module for compensating the initial abnormal value by the association influence coefficient and adding an initial abnormal value compensation result to the fault diagnosis information.
Further, the system further comprises:
the abnormal early warning grade determining module is used for matching the abnormal early warning grade according to the fault diagnosis information and the production plan;
and the fault processing module is used for carrying out fault processing on the production equipment based on the abnormal early warning grade.
The production equipment fault monitoring system based on the industrial big data provided by the embodiment of the application can execute the production equipment fault monitoring method based on the industrial big data provided by any embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method.
All the included modules are only divided according to the functional logic, but are not limited to the above-mentioned division, so long as the corresponding functions can be realized; in addition, the specific names of the functional modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application.
The application provides a production equipment fault monitoring method based on industrial big data, wherein the method is applied to a production equipment fault monitoring system based on industrial big data, and the method comprises the following steps: constructing multi-level equipment association nodes through equipment basic information and production plans of production equipment; constructing a first detection data set by carrying out equipment operation data interaction on production equipment; performing equipment detection on production equipment through a detection sensor to construct a second detection data set; determining a fault correlation factor through the equipment characteristic data set, and optimizing the detection sensitivity of the abnormality detection model through the fault correlation factor; inputting the first detection data set and the second detection data set into an abnormality detection model, and outputting an abnormality detection result; and executing data acquisition on the produced products, detecting production abnormality of the data acquisition result according to the multi-level equipment association nodes, outputting the production abnormality detection result, and generating fault diagnosis information by combining the abnormality detection result. The technical problems of low fault monitoring and diagnosing accuracy aiming at production equipment and poor fault monitoring and diagnosing effect of the production equipment in the prior art are solved. The fault monitoring and diagnosing precision and comprehensiveness of the production equipment are improved, the fault monitoring and diagnosing quality of the production equipment is improved, and the technical effect of guaranteeing the normal operation of the production equipment is achieved.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (8)
1. A production facility fault monitoring method based on industrial big data, the method comprising:
device base information of the interactive production device, wherein the device base information comprises device ID information, device attribute information and a device characteristic data set;
acquiring a production plan, and constructing a multi-level equipment association node based on the production plan and the equipment basic information;
performing equipment operation data interaction on the production equipment to construct a first detection data set;
arranging a detection sensor, detecting the production equipment through the detection sensor, and constructing a second detection data set;
Determining a fault correlation factor through a device characteristic data set, and optimizing the detection sensitivity of an anomaly detection model through the fault correlation factor;
inputting the first detection data set and the second detection data set into the abnormality detection model, and outputting an abnormality detection result;
performing data acquisition on the produced products, detecting production anomalies according to the data acquisition results of the multi-level equipment association nodes, and outputting production anomaly detection results;
generating fault diagnosis information through the abnormality detection result and the production abnormality detection result.
2. The method of claim 1, wherein the method further comprises:
obtaining equipment installation information of the production equipment, wherein the equipment installation information comprises equipment installation time and equipment installation positions;
reading the using time length of the production equipment, matching the fault distribution time period of the production equipment according to the using time length, and determining a fault main period;
performing equipment stability analysis based on the equipment installation information, and determining a fault auxiliary period;
screening a model database of the abnormality detection model through the fault main period and the fault auxiliary period;
And finishing the abnormality detection according to the abnormality detection model after the database is screened.
3. The method of claim 2, wherein the method further comprises:
reading man-machine interaction data of the production equipment, and generating equipment stability association characteristics of the production equipment according to a man-machine interaction data reading result;
the period compensation of the fault auxiliary period is carried out based on the equipment stability association characteristic, and a compensation fault auxiliary period is obtained;
and completing the model database screening of the abnormal detection model through the compensation fault auxiliary period and the fault main period.
4. The method of claim 1, wherein the method further comprises:
continuously detecting the production equipment based on the detection sensor, and recording a continuous detection result, wherein the continuous detection result corresponds to an equipment working mode identifier;
performing continuous working time identification on the basis of the continuous detection result to generate a continuous association coefficient of each detection node;
performing data clustering of the continuous detection results based on the equipment working mode identification to generate data clustering results;
performing continuous detection equipment anomaly identification through the continuous association coefficient and the data clustering result;
And carrying out fault updating of the fault diagnosis information based on the abnormal recognition result.
5. The method of claim 1, wherein the performing data collection on the production product and detecting production anomalies from the data collection results based on the multi-level device association node further comprises:
product identification is carried out on the produced product, parameter acquisition of parameters to be processed is carried out before any procedure is carried out, and the parameters are used as first comparison data;
according to the parameters to be processed and the multi-level equipment association node, processing data of the association equipment is called and used as second comparison data, wherein the second comparison data is processed data of the production equipment of the previous node for processing the parameters to be processed;
performing data primary core on the first comparison data and the second comparison data;
if the data primary core does not pass, generating non-associated production size abnormality information of the production equipment;
and adding the fault diagnosis information according to the non-associated production size abnormality information.
6. The method of claim 5, wherein the method further comprises:
if the data primary core passes, after the execution of the current procedure is completed, the data acquisition of the parameters to be processed is carried out again, and the parameters to be processed are used as third comparison data;
Performing processing influence analysis on equipment through the first comparison data to generate a correlation influence coefficient;
processing and evaluating the first comparison data and the third comparison data to generate initial abnormal values of processing;
and compensating the initial abnormal value through the association influence coefficient, and adding an initial abnormal value compensation result to the fault diagnosis information.
7. The method of claim 1, wherein the method further comprises:
matching an abnormal early warning grade according to the fault diagnosis information and the production plan;
and performing fault processing on the production equipment based on the abnormal early warning level.
8. A production equipment fault monitoring system based on industrial big data, characterized in that the system is adapted to perform the method of any of claims 1 to 7, the system comprising:
the device basic information acquisition module is used for interactively producing device basic information of the device, wherein the device basic information comprises device ID information, device attribute information and a device characteristic data set;
the equipment association node construction module is used for collecting a production plan and constructing multi-level equipment association nodes based on the production plan and the equipment basic information;
The equipment operation data interaction module is used for carrying out equipment operation data interaction on the production equipment to construct a first detection data set;
the equipment detection module is used for arranging a detection sensor, carrying out equipment detection on the production equipment through the detection sensor and constructing a second detection data set;
the detection sensitivity optimization module is used for determining a fault correlation factor through the equipment characteristic data set and performing detection sensitivity optimization of an abnormal detection model through the fault correlation factor;
the data anomaly detection module is used for inputting the first detection data set and the second detection data set into the anomaly detection model and outputting an anomaly detection result;
the production anomaly detection module is used for carrying out data acquisition on production products, carrying out production anomaly detection on data acquisition results according to the multi-level equipment association nodes and outputting production anomaly detection results;
and the fault diagnosis information generation module is used for generating fault diagnosis information through the abnormal detection result and the production abnormal detection result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310818516.6A CN116859843B (en) | 2023-07-05 | 2023-07-05 | Production equipment fault monitoring method and system based on industrial big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310818516.6A CN116859843B (en) | 2023-07-05 | 2023-07-05 | Production equipment fault monitoring method and system based on industrial big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116859843A true CN116859843A (en) | 2023-10-10 |
| CN116859843B CN116859843B (en) | 2024-01-09 |
Family
ID=88229820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310818516.6A Active CN116859843B (en) | 2023-07-05 | 2023-07-05 | Production equipment fault monitoring method and system based on industrial big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116859843B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117172758A (en) * | 2023-11-02 | 2023-12-05 | 启东茂济医药科技有限公司 | Cloud edge fusion-based drug production line equipment fault detection method and system |
| CN117171670A (en) * | 2023-11-03 | 2023-12-05 | 海门市缔绣家用纺织品有限公司 | Textile production process fault monitoring method, device and system |
| CN117277592A (en) * | 2023-11-21 | 2023-12-22 | 西安晟昕科技股份有限公司 | Protection switching method for monitoring high-voltage circuit signals |
| CN117332360A (en) * | 2023-12-01 | 2024-01-02 | 苏州弘皓光电科技有限公司 | Greenhouse equipment fault monitoring method and system based on 5G technology |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109240258A (en) * | 2018-07-09 | 2019-01-18 | 上海万行信息科技有限公司 | Vehicle failure intelligent auxiliary diagnosis method and system based on term vector |
| CN109238727A (en) * | 2018-09-26 | 2019-01-18 | 广州文搏科技有限公司 | A kind of engine failure monitoring and warning system |
| KR20210068687A (en) * | 2019-12-02 | 2021-06-10 | 대우조선해양 주식회사 | Method for diagnosing failure and serching based on knowledge in complex facility |
| CN114282434A (en) * | 2021-12-16 | 2022-04-05 | 成都航天科工大数据研究院有限公司 | Industrial equipment health management system and method |
| CN114577470A (en) * | 2020-11-30 | 2022-06-03 | 斯凯孚公司 | Fault diagnosis method and system for fan main bearing |
| CN115833400A (en) * | 2023-02-07 | 2023-03-21 | 山东盛日电力集团有限公司 | Monitoring and early warning method and system for power equipment of transformer substation |
| CN115993807A (en) * | 2023-03-23 | 2023-04-21 | 日照鲁光电子科技有限公司 | Production monitoring optimization control method and system for silicon carbide |
| WO2023071217A1 (en) * | 2021-10-27 | 2023-05-04 | 中国华能集团清洁能源技术研究院有限公司 | Multi-working-condition process industrial fault detection and diagnosis method based on deep transfer learning |
| CN116060201A (en) * | 2023-03-08 | 2023-05-05 | 北京博数智源人工智能科技有限公司 | Deflagration monitoring abnormality positioning and identifying method and system for coal mill of thermal power station |
| CN116255344A (en) * | 2023-04-26 | 2023-06-13 | 犇流泵业科技(嘉兴)股份有限公司 | Magnetic drive pump running state online monitoring method and system |
-
2023
- 2023-07-05 CN CN202310818516.6A patent/CN116859843B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109240258A (en) * | 2018-07-09 | 2019-01-18 | 上海万行信息科技有限公司 | Vehicle failure intelligent auxiliary diagnosis method and system based on term vector |
| CN109238727A (en) * | 2018-09-26 | 2019-01-18 | 广州文搏科技有限公司 | A kind of engine failure monitoring and warning system |
| KR20210068687A (en) * | 2019-12-02 | 2021-06-10 | 대우조선해양 주식회사 | Method for diagnosing failure and serching based on knowledge in complex facility |
| CN114577470A (en) * | 2020-11-30 | 2022-06-03 | 斯凯孚公司 | Fault diagnosis method and system for fan main bearing |
| WO2023071217A1 (en) * | 2021-10-27 | 2023-05-04 | 中国华能集团清洁能源技术研究院有限公司 | Multi-working-condition process industrial fault detection and diagnosis method based on deep transfer learning |
| CN114282434A (en) * | 2021-12-16 | 2022-04-05 | 成都航天科工大数据研究院有限公司 | Industrial equipment health management system and method |
| CN115833400A (en) * | 2023-02-07 | 2023-03-21 | 山东盛日电力集团有限公司 | Monitoring and early warning method and system for power equipment of transformer substation |
| CN116060201A (en) * | 2023-03-08 | 2023-05-05 | 北京博数智源人工智能科技有限公司 | Deflagration monitoring abnormality positioning and identifying method and system for coal mill of thermal power station |
| CN115993807A (en) * | 2023-03-23 | 2023-04-21 | 日照鲁光电子科技有限公司 | Production monitoring optimization control method and system for silicon carbide |
| CN116255344A (en) * | 2023-04-26 | 2023-06-13 | 犇流泵业科技(嘉兴)股份有限公司 | Magnetic drive pump running state online monitoring method and system |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117172758A (en) * | 2023-11-02 | 2023-12-05 | 启东茂济医药科技有限公司 | Cloud edge fusion-based drug production line equipment fault detection method and system |
| CN117172758B (en) * | 2023-11-02 | 2024-03-08 | 启东茂济医药科技有限公司 | Cloud edge fusion-based drug production line equipment fault detection method and system |
| CN117171670A (en) * | 2023-11-03 | 2023-12-05 | 海门市缔绣家用纺织品有限公司 | Textile production process fault monitoring method, device and system |
| CN117171670B (en) * | 2023-11-03 | 2024-02-13 | 海门市缔绣家用纺织品有限公司 | Textile production process fault monitoring method, device and system |
| CN117277592A (en) * | 2023-11-21 | 2023-12-22 | 西安晟昕科技股份有限公司 | Protection switching method for monitoring high-voltage circuit signals |
| CN117277592B (en) * | 2023-11-21 | 2024-02-13 | 西安晟昕科技股份有限公司 | Protection switching method for monitoring high-voltage circuit signals |
| CN117332360A (en) * | 2023-12-01 | 2024-01-02 | 苏州弘皓光电科技有限公司 | Greenhouse equipment fault monitoring method and system based on 5G technology |
| CN117332360B (en) * | 2023-12-01 | 2024-02-09 | 苏州弘皓光电科技有限公司 | Greenhouse equipment fault monitoring method and system based on 5G technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116859843B (en) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116859843B (en) | Production equipment fault monitoring method and system based on industrial big data | |
| CN107358366B (en) | Distribution transformer fault risk monitoring method and system | |
| Lindemann et al. | Anomaly detection and prediction in discrete manufacturing based on cooperative LSTM networks | |
| CN107273924B (en) | Multi-data fusion power plant fault diagnosis method based on fuzzy clustering analysis | |
| CN111737909B (en) | Structural health monitoring data anomaly identification method based on space-time graph convolutional network | |
| CN111639921B (en) | Intelligent equipment fault judgment and auxiliary disposal method based on expert system | |
| TW201615844A (en) | Method and system of cause analysis and correction for manufacturing data | |
| CN112101431A (en) | Electronic equipment fault diagnosis system | |
| CN116448419A (en) | Zero sample bearing fault diagnosis method based on depth model high-dimensional parameter multi-target efficient optimization | |
| CN114386312A (en) | Equipment fault diagnosis method | |
| CN116467674B (en) | Intelligent fault processing fusion updating system and method for power distribution network | |
| CN105975797A (en) | Product early-fault root cause recognition method based on fuzzy data processing | |
| CN111898673A (en) | Dissolved oxygen content prediction method based on EMD and LSTM | |
| Kao et al. | Deep learning based positioning error fault diagnosis of wire bonding equipment and an empirical study for IC packaging | |
| Xie et al. | Fault diagnosis of multistage manufacturing systems based on rough set approach | |
| CN116577653A (en) | Fault detection method and system for energy storage motor | |
| CN116662925A (en) | Industrial process soft measurement method based on weighted sparse neural network | |
| KR101137318B1 (en) | System and method for dignosis of semiconduct manufacturing apparatus | |
| CN114676887A (en) | River water quality prediction method based on graph convolution STG-LSTM | |
| Escobar et al. | Augmentation of body-in-white dimensional quality systems through artificial intelligence | |
| CN114779739A (en) | Fault monitoring method for industrial process under cloud edge end cooperation based on probability map model | |
| CN112036727A (en) | Method for positioning risk degree of gas pipeline | |
| Puig et al. | Diagnosis and Fault-tolerant Control 1: Data-driven and Model-based Fault Diagnosis Techniques | |
| Dash et al. | A Comparison of Model-Based and Machine Learning Techniques for Fault Diagnosis | |
| Khalyasmaa et al. | Fuzzy inference algorithms for power equipment state assessment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |