CN116401614B - Equipment fault identification method and system - Google Patents
Equipment fault identification method and system Download PDFInfo
- Publication number
- CN116401614B CN116401614B CN202310661096.5A CN202310661096A CN116401614B CN 116401614 B CN116401614 B CN 116401614B CN 202310661096 A CN202310661096 A CN 202310661096A CN 116401614 B CN116401614 B CN 116401614B
- Authority
- CN
- China
- Prior art keywords
- fault
- gluing
- node
- equipment
- obtaining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 239000003292 glue Substances 0.000 claims abstract description 70
- 238000004364 calculation method Methods 0.000 claims abstract description 48
- 238000012544 monitoring process Methods 0.000 claims abstract description 33
- 230000007480 spreading Effects 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000004026 adhesive bonding Methods 0.000 claims description 207
- 239000000306 component Substances 0.000 claims description 66
- 238000012360 testing method Methods 0.000 claims description 45
- 230000035945 sensitivity Effects 0.000 claims description 32
- 230000004927 fusion Effects 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 13
- 230000000712 assembly Effects 0.000 claims description 10
- 238000000429 assembly Methods 0.000 claims description 10
- 239000008358 core component Substances 0.000 claims description 10
- 150000001875 compounds Chemical class 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 8
- 230000010354 integration Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 238000012098 association analyses Methods 0.000 claims description 3
- 239000003822 epoxy resin Substances 0.000 abstract description 12
- 229920000647 polyepoxide Polymers 0.000 abstract description 12
- 230000000694 effects Effects 0.000 abstract description 4
- 239000011248 coating agent Substances 0.000 description 15
- 238000000576 coating method Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 5
- 238000005507 spraying Methods 0.000 description 5
- 239000002131 composite material Substances 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 239000003795 chemical substances by application Substances 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000009413 insulation Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000002910 structure generation Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a fault identification method and a fault identification system of equipment, which relate to the technical field of data processing, and the method comprises the following steps: obtaining a target equipment assembly set of a target glue spreader, constructing a glue spreading topological structure, calculating fault analysis calculation force, obtaining T node fault analysis calculation force, further obtaining T node fault record data sets, combining the glue spreading topological structure to perform fault sensitive feature learning, obtaining an equipment fault recognition model, monitoring the target glue spreader in real time, obtaining an equipment monitoring data set, performing fault analysis on the equipment monitoring data set based on the equipment fault recognition model, obtaining an equipment fault recognition result, integrating the data, and obtaining an equipment fault recognition report. The invention solves the technical problems of incomplete fault recognition range and low recognition accuracy of the epoxy resin glue spreader in the prior art, and achieves the technical effects of improving the comprehensiveness and accuracy of the fault recognition of the epoxy resin glue spreader.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a fault identification method and system of equipment.
Background
The epoxy resin glue spreader is professional equipment for building an LNG liquid cargo containment system, and the equipment can mix high-viscosity bi-component epoxy resin and a hardening agent, coat the bi-component epoxy resin and the hardening agent on a heat insulation and insulation module according to requirements, and then install the bi-component epoxy resin and the hardening agent on a steel plate of an inner cabin of the containment system. Mainly comprises a glue supply system, a coating robot assembly line and an electric control integrated system.
However, when the existing epoxy resin gumming machine fails, accurate and comprehensive fault identification is difficult to perform, and the fault maintenance efficiency is affected.
Disclosure of Invention
The application provides a fault identification method and a fault identification system for equipment, which are used for solving the technical problems of incomplete fault identification range and low identification accuracy of an epoxy resin glue spreader in the prior art.
In a first aspect of the present application, there is provided a fault identification method for a device, the method comprising: obtaining a target equipment assembly set of a target glue spreader, wherein the target equipment assembly set comprises T equipment assemblies of the target glue spreader, and T is a positive integer greater than 1; constructing a gluing topological structure based on the target equipment assembly set, wherein the gluing topological structure comprises T gluing topological nodes, and the T gluing topological nodes comprise gluing core nodes and T-1 gluing cooperative nodes; performing fault analysis calculation force calculation based on the gluing topological structure to obtain T node fault analysis calculation forces; based on the T node fault analysis calculation forces, T node fault record data sets are obtained; based on the T node fault record data sets, performing fault sensitive feature learning according to the gluing topological structure to obtain an equipment fault recognition model; real-time monitoring is carried out on the target glue spreader based on the glue spreading topological structure, and a device monitoring data set is obtained; performing fault analysis on the equipment monitoring data set based on the equipment fault recognition model to obtain equipment fault recognition results; and carrying out data integration based on the equipment fault recognition result to obtain an equipment fault recognition report.
In a second aspect of the present application, there is provided a fault identification system for a device, the system comprising: the device comprises a target device component set acquisition module, a target device component set acquisition module and a target device component set processing module, wherein the target device component set acquisition module is used for acquiring a target device component set of a target glue spreader, the target device component set comprises T device components of the target glue spreader, and T is a positive integer greater than 1; the gluing topological structure construction module is used for constructing a gluing topological structure based on the target equipment assembly set, wherein the gluing topological structure comprises T gluing topological nodes, and the T gluing topological nodes comprise gluing core nodes and T-1 gluing cooperative nodes; the node fault analysis computing power obtaining module is used for carrying out fault analysis computing power calculation based on the gluing topological structure to obtain T node fault analysis computing powers; the node fault record data set obtaining module is used for obtaining T node fault record data sets based on the T node fault analysis calculation forces; the equipment fault identification model obtaining module is used for carrying out fault sensitive feature learning according to the gluing topological structure based on the T node fault record data sets to obtain an equipment fault identification model; the device monitoring data set obtaining module is used for monitoring the target glue spreader in real time based on the glue spreading topological structure to obtain a device monitoring data set; the equipment fault identification result obtaining module is used for carrying out fault analysis on the equipment monitoring data set based on the equipment fault identification model to obtain an equipment fault identification result; and the equipment fault identification report acquisition module is used for carrying out data integration based on the equipment fault identification result to acquire an equipment fault identification report.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
the application provides a fault identification method of equipment, which relates to the technical field of data processing, and aims at solving the technical problems of incomplete fault identification range and low identification accuracy of an epoxy resin glue spreader in the prior art by obtaining a target equipment assembly set of a target glue spreader, constructing a glue spreading topological structure, calculating fault analysis calculation force, obtaining T node fault analysis calculation force, further obtaining T node fault record data sets, carrying out fault sensitive feature learning by combining the glue spreading topological structure, obtaining an equipment fault identification model, carrying out real-time monitoring on the target glue spreader, obtaining an equipment monitoring data set, carrying out fault analysis on the equipment monitoring data set based on the equipment fault identification model, obtaining an equipment fault identification result, integrating data, and obtaining an equipment fault identification report.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a fault identification method of a device according to an embodiment of the present application;
fig. 2 is a schematic flow chart of constructing a gummed topology architecture in a fault recognition method of a device according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of obtaining a device fault recognition model in a device fault recognition method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a fault recognition system of a device according to an embodiment of the present application.
Reference numerals illustrate: the device comprises a target device component set acquisition module 11, a gluing topological structure construction module 12, a node fault analysis calculation power acquisition module 13, a node fault record data set acquisition module 14, a device fault identification model acquisition module 15, a device monitoring data set acquisition module 16, a device fault identification result acquisition module 17 and a device fault identification report acquisition module 18.
Detailed Description
The application provides a fault identification method of equipment, which is used for solving the technical problems of incomplete fault identification range and low identification accuracy of an epoxy resin glue spreader in the prior art.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above-described drawings are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
As shown in fig. 1, the present application provides a fault identification method for a device, the method comprising:
s100: obtaining a target equipment assembly set of a target glue spreader, wherein the target equipment assembly set comprises T equipment assemblies of the target glue spreader, and T is a positive integer greater than 1;
specifically, the types of equipment components contained in the target glue spreader are extracted by reading the specification of the target glue spreader, including equipment such as a glue supply pump, a glue gun, a pressure sensor, an oil-water separator and the like, and the equipment components are taken as a target equipment component set, wherein it is assumed that T equipment components of the target glue spreader are extracted altogether, and a positive integer of T being greater than 1 means that the number of extracted equipment components is more than 1. The target device component set may be used as basic data for subsequent construction of a rubberized topology architecture.
S200: constructing a gluing topological structure based on the target equipment assembly set, wherein the gluing topological structure comprises T gluing topological nodes, and the T gluing topological nodes comprise gluing core nodes and T-1 gluing cooperative nodes;
specifically, the connection relation of all devices in the target device assembly set and the role of the connection relation in each link of the gluing operation are combed, and a gluing topological structure is constructed by combining the working principle of a target gluing machine. The topology structure, namely, a network topology structure, refers to a network structure formed by network node equipment and communication media, and can represent the layout of cables and network equipment and data adopted in data transmission. The gluing topological structure comprises T gluing topological nodes, the T gluing topological nodes further comprise gluing core nodes with core functions and T-1 gluing cooperative nodes for assisting the core nodes to work, and the gluing topological structure can represent connection and data transmission relations between the core nodes of the T equipment components and the T-1 gluing cooperative nodes and can be used as basic data for subsequent fault analysis.
Further, as shown in fig. 2, step S200 of the embodiment of the present application further includes:
S210: performing gluing value degree identification based on the T equipment components to obtain T component gluing value degrees;
s220: based on the gluing value of the T assemblies, a gluing core assembly and T-1 gluing cooperative assemblies are obtained according to the T equipment assemblies;
s230: based on the gluing working principle of the target gluing machine, carrying out gluing association analysis on the T equipment components to obtain a component-gluing association relation;
s240: based on the gluing core component and the T-1 gluing cooperative components, the gluing core node and the T-1 gluing cooperative nodes are obtained;
s250: and generating the gluing topological structure according to the gluing core node and the T-1 gluing cooperative nodes based on the component-gluing association relation.
Specifically, according to the role played by the T devices in each link of the target gumming machine, the importance of the gumming role of the T device components is identified, and according to the importance degree of each device component, the corresponding value grade is set, and the higher the importance is, the higher the corresponding value is. And extracting a gluing core component with the largest gluing value of the components according to the T component gluing values, for example, when the gluing core component with the largest gluing value of the components is a coating unit of a target gluing machine, wherein a gluing core node comprises a plurality of coating nozzles in the coating unit. And taking other T-1 equipment components except the gluing core component as a gluing cooperative component for performing gluing work in cooperation with the core component. Based on the glue application working principle of the target glue applicator, the glue application working principle of the target glue applicator may be: the coating machine is used for conveying coating materials to a coating unit through a higher feeding system, the coating unit is a core component of the coating machine and is usually composed of a series of nozzles, the coating unit uniformly covers the coating materials on the surface of a product by controlling the positions and the numbers of the nozzles, and an electric control integrated system of the coating machine can comprehensively control the numbers, the positions, the spraying speeds and other parameters of the nozzles so as to ensure the quality and the efficiency of coating. According to the gluing working principle of the target gluing machine, the action relation of the T equipment components in each link of gluing work is analyzed to obtain a component-gluing association relation, for example, the working task of a coating unit of the target gluing machine in gluing work is to uniformly cover a coating material on the surface of a product. And dividing the T equipment components into a gluing core node and T-1 gluing cooperative nodes according to the connection relation between the gluing core components and the T-1 gluing cooperative components. Based on the action relation of the T equipment components in each link of the gluing operation, the gluing core nodes and the T-1 gluing cooperative nodes are connected to generate the gluing topological structure which can be used as basic data for subsequent fault analysis.
S300: performing fault analysis calculation force calculation based on the gluing topological structure to obtain T node fault analysis calculation forces;
specifically, based on the gluing topological architecture, calculating the ratio of the gluing value degree of T components to the gluing value degree of the total components, wherein the gluing value degree of the total components is the sum of the gluing value degrees of the T components, the ratio of the gluing value degrees of the T components to the gluing value degree of the total components is taken as the fault analysis calculation force of each component node, the calculation force is the calculation capacity for realizing the output of a target result by processing information data, the node fault analysis calculation force refers to the calculation capacity required when each component node performs fault analysis, and the node fault analysis calculation force is the highest as the importance degree of each component node in the whole gluing work is different, the corresponding gluing value degrees are different, the calculation force for performing fault analysis allocated by a system is also different, the higher the gluing value degree is, the higher the corresponding node fault analysis calculation force is, and the value degree of the gluing core node is the highest. The node fault analysis calculation force can be used for representing the importance degree of fault identification of each gluing node.
S400: based on the T node fault analysis calculation forces, T node fault record data sets are obtained;
specifically, according to the fault analysis calculation force of a certain node in the T node fault analysis calculation forces, fault records and analysis are performed on the corresponding node to obtain a fault record data set of the node, the larger the node fault analysis calculation force is, the more corresponding node fault record data are extracted, and the like, the T node fault record data sets are extracted and can be used as basic data for sensitive feature learning of subsequent faults.
S500: based on the T node fault record data sets, performing fault sensitive feature learning according to the gluing topological structure to obtain an equipment fault recognition model;
specifically, the T node fault record data sets are used as training data, and the gluing topological architecture is combined to perform fault sensitive feature learning, that is, equipment fault recognition training, so as to obtain an equipment fault recognition model, where the equipment fault recognition model includes T node fault recognition units corresponding to the T gluing topological nodes and can be used to perform equipment fault recognition on the gluing equipment of the T gluing topological nodes respectively.
Further, as shown in fig. 3, step S500 of the embodiment of the present application further includes:
s510: traversing the gluing topological structure to obtain a first gluing topological node;
s520: based on the first gluing topological node, obtaining a first node fault record data set and a first node fault analysis computing force according to the T node fault record data sets and the T node fault analysis computing forces;
specifically, each gluing topological node in the gluing topological structure is set as a first gluing topological node, and correspondingly, the first node fault record data set and the first node fault analysis calculation force corresponding to the first gluing topological node are extracted from the T node fault record data sets and the T node fault analysis calculation forces corresponding to the T gluing topological nodes and can be used as basic data for the subsequent sensitive feature learning of faults.
S530: and performing fault sensitive feature learning based on the first node fault record data set and the first node fault analysis calculation force to obtain a first node fault identification unit, and adding the first node fault identification unit into the equipment fault identification model.
Further, step S530 of the embodiment of the present application further includes:
s531: obtaining a plurality of same-group glue spreading machines based on the target glue spreading machine;
s532: obtaining a multi-dimensional preset fault characteristic index, wherein the multi-dimensional preset fault characteristic index comprises a fault type, a fault reason and a fault influence;
s533: obtaining a first retrieval constraint characteristic according to the first gluing topological node;
s534: acquiring a second retrieval constraint characteristic according to the multidimensional preset fault characteristic index;
s535: obtaining a third retrieval constraint characteristic according to the first node fault analysis calculation force;
s536: obtaining a plurality of retrieval entities according to the plurality of the same-group glue spreading machines;
s537: obtaining a plurality of fault identification record data sets according to the plurality of retrieval entities based on the first retrieval constraint feature, the second retrieval constraint feature and the third retrieval constraint feature;
s538: the first node failure recognition unit is acquired based on the plurality of failure recognition record data sets.
Specifically, according to the parameter model of the target glue spreader, selecting a plurality of glue spreaders with the same model, and taking the glue spreaders with the same model as the glue spreaders with the same group. Selecting fault characteristics of multiple dimensions, including fault types, fault reasons and fault influences, taking the fault characteristics as multidimensional preset fault characteristic indexes, taking the first gluing topological node as a first retrieval constraint characteristic, taking the multidimensional preset fault characteristic indexes as a second retrieval constraint characteristic, taking the first node fault analysis calculation force as a third retrieval constraint characteristic, taking the multiple same group of glue spreading machines as multiple retrieval entities, and retrieving data of the multiple retrieval entities according to the first retrieval constraint characteristic, the second retrieval constraint characteristic and the third retrieval constraint characteristic to obtain data including information of each gluing topological node, fault types, fault reasons, fault influences, fault analysis calculation force of each gluing topological node and the like, and taking the data as multiple fault identification record data sets. Taking the plurality of fault identification record data sets as construction data, and training the first node fault identification unit by combining the architecture of the neural network model, wherein the training process can be as follows: dividing each fault identification record data set identifier into a training data set, a verification data set and a test data set, sequentially inputting all data in the training data set into the first node fault identification unit, adjusting network parameters according to output results until convergence, and finally verifying and testing the first node fault identification unit by using the verification data set and the test data set until a preset accuracy requirement is met to obtain the first node fault identification unit which can be used for carrying out fault identification of the first node. And by analogy, a second node fault recognition unit and a second node fault recognition unit … … are obtained, the first node fault recognition unit and the second node fault recognition unit … … are added into the equipment fault recognition model, the construction of the equipment fault recognition model is completed, and the equipment fault recognition model can be used for performing gluing equipment fault recognition.
Further, step S538 of the embodiment of the present application further includes:
s538-1: performing supervised training based on the plurality of fault identification record data sets to obtain a plurality of fault calibrators;
s538-2: traversing the plurality of fault calibrators to test based on the first node fault record data set to obtain a plurality of calibrator test results, wherein the plurality of calibrator test results comprise a plurality of fault calibration sensitivities and a plurality of fault calibration loss data sets;
s538-3: setting a first fault calibration sensitivity constraint characteristic corresponding to the first gluing topological node based on a first gluing value corresponding to the first gluing topological node;
s538-4: screening the plurality of fault calibrators based on the first fault calibration sensitivity constraint characteristic to obtain a plurality of winning fault calibrators meeting the first fault calibration sensitivity constraint characteristic;
s538-5: based on the plurality of winning fault demanders, obtaining a plurality of characteristic fault calibration loss data sets according to the plurality of fault calibration loss data sets;
s538-6: and performing incremental feature fusion on the plurality of winning fault demanders based on the plurality of feature fault scaling loss data sets to obtain the first node fault identification unit.
Specifically, the multiple fault identification record data sets are used as construction data, each fault identification record data set identifier is divided into a training data set, a verification data set and a test data set, and the supervised training of the fault calibrator is performed by combining the architecture of the neural network model, wherein the training process can be as follows: firstly, inputting all data of a training data set into the fault calibrator in sequence, adjusting network parameters according to output results until convergence, then verifying and testing the fault calibrator by using a verification data set and a test data set until preset requirements are met, obtaining the fault calibrator, and the like, and obtaining a plurality of fault calibrators.
Further, all data in the first node fault record data set are substituted into the plurality of fault calibrators in sequence to test, a plurality of calibrator test results are output by the plurality of fault calibrators, and the plurality of calibrator test results comprise a plurality of fault calibration sensitivities and a plurality of fault calibration loss data sets. The plurality of fault calibration sensitivities are the accuracy of fault identification of the plurality of fault calibrators, and the plurality of fault calibration loss data sets are data sets of fault calibration failure. And setting a first fault calibration sensitivity constraint characteristic corresponding to the first gluing topological node based on the first gluing value degree corresponding to the first gluing topological node, wherein the first fault calibration sensitivity constraint characteristic is a first fault calibration sensitivity threshold, and the higher the gluing value degree of the first gluing topological node is, the higher the corresponding first fault calibration sensitivity threshold is. Comparing a plurality of fault calibration sensitivities in a plurality of calibrator test results of the plurality of fault calibrators with the first fault calibration sensitivity constraint feature one by one, screening out a plurality of fault calibrators with fault calibration sensitivities meeting the first fault calibration sensitivity constraint feature, taking the plurality of fault calibrators as a plurality of winning fault calibrators, taking a plurality of fault calibration loss data sets corresponding to the plurality of winning fault calibrators as a plurality of characteristic fault calibration loss data sets, performing incremental learning on the plurality of winning fault calibrators by using the plurality of characteristic fault calibration loss data sets, obtaining a new rule from the plurality of characteristic fault calibration loss data sets, and performing feature fusion with the corresponding winning fault calibrators to obtain the first node fault identification unit which can be used for carrying out fault identification of the first node.
Further, step S538-2 of the embodiment of the present application further comprises:
s538-21: traversing the plurality of fault calibrators to obtain a first fault calibrator;
s538-22: testing the first fault calibrator based on the first node fault record data set to obtain a first fault calibration accurate index, a first fault calibration accurate index and a first fault calibration loss data set;
s538-23: setting an index fusion constraint characteristic based on the first glue spreading value;
s538-24: weighting and fusing the first fault calibration accurate index and the first fault calibration accurate index based on the index fusion constraint characteristic to obtain a first fault calibration sensitivity;
s538-25: and generating a first calibrator test result based on the first fault calibration sensitivity and the first fault calibration loss data set, and adding the first calibrator test result to the plurality of calibrator test results.
Specifically, the plurality of fault calibrators are used as first fault calibrators, the data in the first node fault record data set is used for testing the first fault calibrators, a plurality of test results of the plurality of fault calibrators are obtained, a first fault calibration accurate index and a first fault calibration accurate index of each fault calibrator are calculated through the accuracy of the test results, the first fault calibration accurate index refers to the proportion of the number of all the predicted correct fault calibration test results to the total number of the test results, the first fault calibration accurate index refers to the proportion of all the completely correct fault calibration test results to all the predicted correct fault calibration test results, and the fault calibration failure data is used as the first fault calibration loss data set. And setting index fusion constraint characteristics, namely weight coefficients of the first fault calibration accurate index and the first fault calibration accurate index, on the basis of the first glue spreading value, wherein the higher the glue spreading value is, the larger the corresponding weight coefficient is, carrying out weighted calculation on the first fault calibration accurate index and the first fault calibration accurate index by using the index fusion constraint characteristics, taking the calculated weighted average value as first fault calibration sensitivity, taking the first fault calibration sensitivity and the first fault calibration loss data set as first calibrator test results, and adding the first calibrator test results to the plurality of calibrator test results. The multiple calibrator test results can be used as basic data for subsequent calibrator screening.
S600: real-time monitoring is carried out on the target glue spreader based on the glue spreading topological structure, and a device monitoring data set is obtained;
specifically, monitoring devices are installed at each gluing node of the target gluing machine based on the gluing topological structure, real-time monitoring is performed on real-time operation data of each gluing node device, and data such as the spraying radius, the spraying speed, whether the spraying unit can normally spray, the position of the spraying unit cannot normally work and the like are monitored, so that the data are used as a device monitoring data set and can be used as basic data for performing fault identification on the current target gluing machine.
S700: performing fault analysis on the equipment monitoring data set based on the equipment fault recognition model to obtain equipment fault recognition results;
specifically, the monitoring data of each glue spreading node in the equipment monitoring data set is respectively input into the fault recognition unit of the corresponding node of the equipment fault recognition model, and the equipment fault recognition result of each glue spreading node is output by the equipment fault recognition model, so that fault information such as fault type, fault reason, fault influence and the like of each glue spreading node can be represented.
S800: and carrying out data integration based on the equipment fault recognition result to obtain an equipment fault recognition report.
Specifically, the data such as fault type, fault cause, fault influence and the like in the equipment fault identification result are subjected to fault influence sorting, fault classification, fault treatment scheme generation, fault prevention measure generation and the like, and finally are arranged into an equipment fault identification report, wherein the equipment fault identification report comprises the data such as fault type, fault cause, fault influence and the like, and also comprises fault prevention measures, fault treatment scheme, system optimization scheme and the like, and the equipment fault identification report can be used for fault treatment, fault prevention, coater system optimization and the like.
Further, the embodiment of the present application further includes step S900, where step S900 further includes:
s910: judging whether the equipment fault identification result is a multi-node fault identification result or not;
s920: when the equipment fault identification result is the multi-node fault identification result, connecting a fault collaborative analysis network, and analyzing the fault collaborative influence of the equipment fault identification result based on the fault collaborative analysis network to obtain a fault compound risk index;
s930: and adding the fault compound risk index to the equipment fault identification report.
Specifically, whether the equipment fault recognition result is a composite fault caused by faults of components of a plurality of nodes is judged, if yes, a fault collaborative analysis network is connected, fault collaborative influence analysis is conducted on the equipment fault recognition result based on the fault collaborative analysis network, the fault collaborative analysis network comprises preset fault collaborative influence weights according to the gluing topological structure, corresponding fault risk indexes are determined according to the fault collaborative influence weights of each failed node, then the fault collaborative influence weight coefficient of each node and the corresponding fault risk coefficient are subjected to weighted calculation, the obtained weighted average value is used as a fault composite risk index, the fault composite risk index can reflect the fault influence degree when the plurality of node components are simultaneously in fault, and the fault composite risk index is added into the equipment fault recognition report, so that the comprehensiveness and the accuracy of fault recognition of the epoxy resin glue spreader can be improved.
In summary, the embodiment of the application has at least the following technical effects:
according to the application, a gluing topological structure is constructed by obtaining a target equipment assembly set of a target gluing machine, fault analysis calculation force is calculated based on the gluing topological structure, T node fault analysis calculation force is obtained, T node fault record data sets are further obtained, fault sensitive feature learning is carried out by combining the gluing topological structure, an equipment fault recognition model is obtained, the target gluing machine is monitored in real time, an equipment monitoring data set is obtained, fault analysis is carried out on the equipment monitoring data set based on the equipment fault recognition model, an equipment fault recognition result is obtained, data integration is carried out, and an equipment fault recognition report is obtained.
The technical effects of improving the comprehensiveness and accuracy of fault identification of the epoxy resin glue spreader are achieved.
Example two
Based on the same inventive concept as the fault recognition method of the device in the foregoing embodiment, as shown in fig. 4, the present application provides a fault recognition system of the device, and the system and method embodiments in the embodiments of the present application are based on the same inventive concept. Wherein the system comprises:
the target equipment assembly set acquisition module 11 is used for acquiring a target equipment assembly set of the target glue spreader, wherein the target equipment assembly set comprises T equipment assemblies of the target glue spreader, and T is a positive integer greater than 1;
a gluing topology construction module 12, configured to construct a gluing topology based on the target device component set, where the gluing topology includes T gluing topology nodes, and the T gluing topology nodes include a gluing core node and T-1 gluing cooperative nodes;
the node fault analysis computing power obtaining module 13 is used for carrying out fault analysis computing power calculation based on the gluing topological structure to obtain T node fault analysis computing powers;
A node fault record dataset acquisition module 14 for acquiring T node fault record datasets based on the T node fault analysis algorithms;
the equipment fault identification model obtaining module 15 is used for carrying out fault sensitive feature learning according to the gluing topological structure based on the T node fault record data sets to obtain an equipment fault identification model;
the device monitoring data set obtaining module 16 is configured to monitor the target glue spreader in real time based on the glue topology architecture, so as to obtain a device monitoring data set;
the device fault recognition result obtaining module 17 is used for performing fault analysis on the device monitoring data set based on the device fault recognition model to obtain a device fault recognition result;
and an equipment fault identification report obtaining module 18, configured to integrate data based on the equipment fault identification result, and obtain an equipment fault identification report.
Further, the system further comprises:
The component gluing value obtaining module is used for identifying the gluing value based on the T equipment components to obtain T component gluing values;
the gluing component dividing module is used for obtaining a gluing core component and T-1 gluing cooperative components according to the T equipment components based on the gluing value of the T components;
the component-gluing association relation obtaining module is used for carrying out gluing association analysis on the T equipment components based on a gluing working principle of the target gluing machine to obtain a component-gluing association relation;
the gluing node obtaining module is used for obtaining the gluing core node and the T-1 gluing cooperative nodes based on the gluing core component and the T-1 gluing cooperative components;
the gluing topology structure generation module is used for generating the gluing topology structure according to the gluing core node and the T-1 gluing cooperative nodes based on the component-gluing association relation;
further, the system further comprises:
The first gluing topological node obtaining module is used for traversing the gluing topological architecture to obtain a first gluing topological node;
the first node fault parameter obtaining module is used for obtaining a first node fault record data set and a first node fault analysis computing force according to the T node fault record data sets and the T node fault analysis computing forces based on the first gluing topological node;
the first node fault identification unit obtaining module is used for carrying out sensitive feature learning of faults based on the first node fault record data set and the first node fault analysis calculation force, obtaining a first node fault identification unit and adding the first node fault identification unit into the equipment fault identification model;
further, the system further comprises:
a plurality of same-group coater acquisition modules for acquiring a plurality of same-group coaters based on the target coater;
the system comprises a multidimensional preset fault characteristic index obtaining module, a fault analysis module and a fault analysis module, wherein the multidimensional preset fault characteristic index obtaining module is used for obtaining multidimensional preset fault characteristic indexes, and the multidimensional preset fault characteristic indexes comprise fault types, fault reasons and fault influences;
The first retrieval constraint feature acquisition module is used for acquiring first retrieval constraint features according to the first gluing topological node;
the second retrieval constraint characteristic obtaining module is used for obtaining second retrieval constraint characteristics according to the multidimensional preset fault characteristic indexes;
the third retrieval constraint characteristic obtaining module is used for obtaining a third retrieval constraint characteristic according to the first node fault analysis calculation force;
the plurality of retrieval entity obtaining modules are used for obtaining a plurality of retrieval entities according to the plurality of same-group glue spreading machines;
the fault identification record data set obtaining module is used for obtaining a plurality of fault identification record data sets according to the plurality of retrieval entities based on the first retrieval constraint feature, the second retrieval constraint feature and the third retrieval constraint feature;
a first node failure recognition unit obtaining module configured to obtain the first node failure recognition unit based on the plurality of failure recognition record data sets;
Further, the system further comprises:
the fault calibrator acquisition modules are used for performing supervised training based on the fault identification record data sets to acquire a plurality of fault calibrators;
the calibrator test result obtaining module is used for traversing the plurality of fault calibrators to test based on the first node fault record data set to obtain a plurality of calibrator test results, wherein the plurality of calibrator test results comprise a plurality of fault calibration sensitivities and a plurality of fault calibration loss data sets;
the first fault calibration sensitivity constraint feature acquisition module is used for setting first fault calibration sensitivity constraint features corresponding to the first gluing topological nodes based on first gluing value degrees corresponding to the first gluing topological nodes;
the winning fault calibrator obtaining module is used for screening the plurality of fault calibrators based on the first fault calibration sensitivity constraint characteristic to obtain a plurality of winning fault calibrators meeting the first fault calibration sensitivity constraint characteristic;
The characteristic fault calibration loss data set obtaining module is used for obtaining a plurality of characteristic fault calibration loss data sets according to the plurality of fault calibration loss data sets based on the plurality of winning fault calibrators;
the first node fault identification unit obtaining module is used for carrying out incremental feature fusion on the plurality of winning fault calibrators based on the plurality of feature fault calibration loss data sets to obtain the first node fault identification unit;
further, the system further comprises:
the first fault calibrator obtaining module is used for traversing the plurality of fault calibrators to obtain a first fault calibrator;
the first fault calibrator test module is used for testing the first fault calibrator based on the first node fault record data set to obtain a first fault calibration accurate index, a first fault calibration accurate index and a first fault calibration loss data set;
the index fusion constraint feature setting module is used for setting index fusion constraint features based on the first glue spreading value;
The first fault calibration sensitivity obtaining module is used for carrying out weighted fusion on the first fault calibration accurate index and the first fault calibration accurate index based on the index fusion constraint characteristic to obtain first fault calibration sensitivity;
the first calibrator test result generation module is used for generating a first calibrator test result based on the first fault calibration sensitivity and the first fault calibration loss data set, and adding the first calibrator test result to the plurality of calibrator test results;
further, the system further comprises:
the multi-node fault identification result judging module is used for judging whether the equipment fault identification result is a multi-node fault identification result or not;
the fault compound risk index obtaining module is used for connecting a fault collaborative analysis network when the equipment fault identification result is the multi-node fault identification result, and carrying out fault collaborative influence analysis on the equipment fault identification result based on the fault collaborative analysis network to obtain a fault compound risk index;
And the fault compound risk index adding module is used for adding the fault compound risk index into the equipment fault identification report.
It should be noted that the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing description of the preferred embodiments of the application is not intended to limit the application to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the application are intended to be included within the scope of the application.
The specification and figures are merely exemplary illustrations of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (6)
1. A method for fault identification of a device, the method comprising:
obtaining a target equipment assembly set of a target glue spreader, wherein the target equipment assembly set comprises T equipment assemblies of the target glue spreader, and T is a positive integer greater than 1;
constructing a gluing topological structure based on the target equipment assembly set, wherein the gluing topological structure comprises T gluing topological nodes, and the T gluing topological nodes comprise gluing core nodes and T-1 gluing cooperative nodes;
performing fault analysis calculation force calculation based on the gluing topological structure to obtain T node fault analysis calculation forces;
based on the T node fault analysis calculation forces, T node fault record data sets are obtained;
based on the T node fault record data sets, performing fault sensitive feature learning according to the gluing topological structure to obtain an equipment fault recognition model;
real-time monitoring is carried out on the target glue spreader based on the glue spreading topological structure, and a device monitoring data set is obtained;
performing fault analysis on the equipment monitoring data set based on the equipment fault recognition model to obtain equipment fault recognition results;
data integration is carried out based on the equipment fault recognition result, and an equipment fault recognition report is obtained;
Based on the target device component set, constructing a gluing topological architecture, including:
performing gluing value degree identification based on the T equipment components to obtain T component gluing value degrees;
based on the gluing value of the T assemblies, a gluing core assembly and T-1 gluing cooperative assemblies are obtained according to the T equipment assemblies;
based on the gluing working principle of the target gluing machine, carrying out gluing association analysis on the T equipment components to obtain a component-gluing association relation;
based on the gluing core component and the T-1 gluing cooperative components, the gluing core node and the T-1 gluing cooperative nodes are obtained;
generating the gluing topological structure according to the gluing core node and the T-1 gluing cooperative nodes based on the component-gluing association relation;
based on the T node fault record data sets, performing fault sensitive feature learning according to the gluing topological architecture to obtain an equipment fault identification model, wherein the equipment fault identification model comprises the following steps:
traversing the gluing topological structure to obtain a first gluing topological node;
based on the first gluing topological node, obtaining a first node fault record data set and a first node fault analysis computing force according to the T node fault record data sets and the T node fault analysis computing forces;
And performing fault sensitive feature learning based on the first node fault record data set and the first node fault analysis calculation force to obtain a first node fault identification unit, and adding the first node fault identification unit into the equipment fault identification model.
2. The method of claim 1, wherein the obtaining a first node failure recognition unit comprises:
obtaining a plurality of same-group glue spreading machines based on the target glue spreading machine;
obtaining a multi-dimensional preset fault characteristic index, wherein the multi-dimensional preset fault characteristic index comprises a fault type, a fault reason and a fault influence;
obtaining a first retrieval constraint characteristic according to the first gluing topological node;
acquiring a second retrieval constraint characteristic according to the multidimensional preset fault characteristic index;
obtaining a third retrieval constraint characteristic according to the first node fault analysis calculation force;
obtaining a plurality of retrieval entities according to the plurality of the same-group glue spreading machines;
obtaining a plurality of fault identification record data sets according to the plurality of retrieval entities based on the first retrieval constraint feature, the second retrieval constraint feature and the third retrieval constraint feature;
The first node failure recognition unit is acquired based on the plurality of failure recognition record data sets.
3. The method of claim 2, wherein obtaining the first node failure recognition unit based on the plurality of failure recognition record data sets comprises:
performing supervised training based on the plurality of fault identification record data sets to obtain a plurality of fault calibrators;
traversing the plurality of fault calibrators to test based on the first node fault record data set to obtain a plurality of calibrator test results, wherein the plurality of calibrator test results comprise a plurality of fault calibration sensitivities and a plurality of fault calibration loss data sets;
setting a first fault calibration sensitivity constraint characteristic corresponding to the first gluing topological node based on a first gluing value corresponding to the first gluing topological node;
screening the plurality of fault calibrators based on the first fault calibration sensitivity constraint characteristic to obtain a plurality of winning fault calibrators meeting the first fault calibration sensitivity constraint characteristic;
based on the plurality of winning fault demanders, obtaining a plurality of characteristic fault calibration loss data sets according to the plurality of fault calibration loss data sets;
And performing incremental feature fusion on the plurality of winning fault demanders based on the plurality of feature fault scaling loss data sets to obtain the first node fault identification unit.
4. A method according to claim 3, characterized in that the method comprises:
traversing the plurality of fault calibrators to obtain a first fault calibrator;
testing the first fault calibrator based on the first node fault record data set to obtain a first fault calibration accurate index, a first fault calibration accurate index and a first fault calibration loss data set;
setting an index fusion constraint characteristic based on the first glue spreading value;
weighting and fusing the first fault calibration accurate index and the first fault calibration accurate index based on the index fusion constraint characteristic to obtain a first fault calibration sensitivity;
and generating a first calibrator test result based on the first fault calibration sensitivity and the first fault calibration loss data set, and adding the first calibrator test result to the plurality of calibrator test results.
5. The method of claim 1, wherein the method comprises:
Judging whether the equipment fault identification result is a multi-node fault identification result or not;
when the equipment fault identification result is the multi-node fault identification result, connecting a fault collaborative analysis network, and analyzing the fault collaborative influence of the equipment fault identification result based on the fault collaborative analysis network to obtain a fault compound risk index;
and adding the fault compound risk index to the equipment fault identification report.
6. A fault identification system for a device, characterized in that the system is adapted to perform the method of any of claims 1 to 5, the system comprising:
the device comprises a target device component set acquisition module, a target device component set acquisition module and a target device component set processing module, wherein the target device component set acquisition module is used for acquiring a target device component set of a target glue spreader, the target device component set comprises T device components of the target glue spreader, and T is a positive integer greater than 1;
the gluing topological structure construction module is used for constructing a gluing topological structure based on the target equipment assembly set, wherein the gluing topological structure comprises T gluing topological nodes, and the T gluing topological nodes comprise gluing core nodes and T-1 gluing cooperative nodes;
The node fault analysis computing power obtaining module is used for carrying out fault analysis computing power calculation based on the gluing topological structure to obtain T node fault analysis computing powers;
the node fault record data set obtaining module is used for obtaining T node fault record data sets based on the T node fault analysis calculation forces;
the equipment fault identification model obtaining module is used for carrying out fault sensitive feature learning according to the gluing topological structure based on the T node fault record data sets to obtain an equipment fault identification model;
the device monitoring data set obtaining module is used for monitoring the target glue spreader in real time based on the glue spreading topological structure to obtain a device monitoring data set;
the equipment fault identification result obtaining module is used for carrying out fault analysis on the equipment monitoring data set based on the equipment fault identification model to obtain an equipment fault identification result;
and the equipment fault identification report acquisition module is used for carrying out data integration based on the equipment fault identification result to acquire an equipment fault identification report.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310661096.5A CN116401614B (en) | 2023-06-06 | 2023-06-06 | Equipment fault identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310661096.5A CN116401614B (en) | 2023-06-06 | 2023-06-06 | Equipment fault identification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116401614A CN116401614A (en) | 2023-07-07 |
| CN116401614B true CN116401614B (en) | 2023-08-18 |
Family
ID=87016447
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310661096.5A Active CN116401614B (en) | 2023-06-06 | 2023-06-06 | Equipment fault identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116401614B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117540337B (en) * | 2023-11-15 | 2024-04-16 | 中国铁塔股份有限公司辽宁省分公司 | Multi-source fusion intelligent regional safety and precision sensing method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103001811A (en) * | 2012-12-31 | 2013-03-27 | 北京启明星辰信息技术股份有限公司 | Method and device for fault locating |
| WO2015176565A1 (en) * | 2014-05-22 | 2015-11-26 | 袁志贤 | Method for predicting faults in electrical equipment based on multi-dimension time series |
| CN113505458A (en) * | 2021-07-26 | 2021-10-15 | 中国电力科学研究院有限公司 | Cascading failure key trigger branch prediction method, system, equipment and storage medium |
| CN115146074A (en) * | 2022-07-08 | 2022-10-04 | 北京航空航天大学杭州创新研究院 | Fault diagnosis map construction method and related device |
| CN115225463A (en) * | 2022-09-21 | 2022-10-21 | 江苏牛掌柜科技有限公司 | Hardware fault monitoring method and system based on IT operation and maintenance |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US12008298B2 (en) * | 2020-10-26 | 2024-06-11 | Duke University | Evaluating functional fault criticality of structural faults for circuit testing |
-
2023
- 2023-06-06 CN CN202310661096.5A patent/CN116401614B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103001811A (en) * | 2012-12-31 | 2013-03-27 | 北京启明星辰信息技术股份有限公司 | Method and device for fault locating |
| WO2015176565A1 (en) * | 2014-05-22 | 2015-11-26 | 袁志贤 | Method for predicting faults in electrical equipment based on multi-dimension time series |
| CN113505458A (en) * | 2021-07-26 | 2021-10-15 | 中国电力科学研究院有限公司 | Cascading failure key trigger branch prediction method, system, equipment and storage medium |
| CN115146074A (en) * | 2022-07-08 | 2022-10-04 | 北京航空航天大学杭州创新研究院 | Fault diagnosis map construction method and related device |
| CN115225463A (en) * | 2022-09-21 | 2022-10-21 | 江苏牛掌柜科技有限公司 | Hardware fault monitoring method and system based on IT operation and maintenance |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116401614A (en) | 2023-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105117602B (en) | A kind of metering device running status method for early warning | |
| CN104732276B (en) | One kind metering production facility on-line fault diagnosis method | |
| Harris et al. | A review of performance monitoring and assessment techniques for univariate and multivariate control systems | |
| CN116401614B (en) | Equipment fault identification method and system | |
| Lindemann et al. | Anomaly detection and prediction in discrete manufacturing based on cooperative LSTM networks | |
| CN108830325A (en) | A kind of vibration information classification of landform recognition methods based on study | |
| CN116467674B (en) | Intelligent fault processing fusion updating system and method for power distribution network | |
| CN110580577A (en) | Intelligent substation secondary system operation quality multi-layer evaluation method based on weight coefficient correction | |
| CN109409780B (en) | Change processing method, device, computer equipment and storage medium | |
| CN118037014A (en) | Road construction monitoring system based on Internet of things | |
| Wanner et al. | Quality modelling in battery cell manufacturing using soft sensoring and sensor fusion-A review | |
| CN111537888A (en) | Data-driven echelon battery SOC prediction method | |
| CN114583767B (en) | Data-driven wind power plant frequency modulation response characteristic modeling method and system | |
| CN109324591B (en) | fault diagnosis device and method of stochastic hybrid system based on robust estimator | |
| CN113486926B (en) | Automatic change pier equipment anomaly detection system | |
| CN110766248B (en) | Workshop artificial factor reliability assessment method based on SHEL and interval intuitionistic fuzzy assessment | |
| CN117200449B (en) | Multi-dimensional algorithm analysis-based power grid monitoring management method and system | |
| Li et al. | Predicting Software Quality by Optimized BP Network Based on PSO. | |
| Tiwary et al. | Multi-dimensional ANN application for active power flow state classification on a utility system | |
| CN115267409A (en) | Power equipment fault detection method, device and equipment | |
| Wang et al. | Complex equipment diagnostic reasoning based on neural network algorithm | |
| CN111553565B (en) | Performance evaluation method and system for online monitoring device of transformer substation | |
| CN118311379B (en) | High-voltage power cable online monitoring fault positioning method and system | |
| Fallahpour et al. | Supplier selection under fuzzy environment: a hybrid model using KAM in DEA | |
| CN116823215B (en) | Intelligent operation and maintenance management and control method and system for power station |
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 |