CN117521498A - Charging pile guide type fault diagnosis prediction method and system - Google Patents
Charging pile guide type fault diagnosis prediction method and system Download PDFInfo
- Publication number
- CN117521498A CN117521498A CN202311473075.7A CN202311473075A CN117521498A CN 117521498 A CN117521498 A CN 117521498A CN 202311473075 A CN202311473075 A CN 202311473075A CN 117521498 A CN117521498 A CN 117521498A
- Authority
- CN
- China
- Prior art keywords
- fault
- charging pile
- prediction result
- physical
- running state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000004458 analytical method Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 7
- 230000003993 interaction Effects 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000004393 prognosis Methods 0.000 claims 1
- 238000012423 maintenance Methods 0.000 abstract description 5
- 230000004044 response Effects 0.000 abstract description 5
- 230000000903 blocking effect Effects 0.000 abstract description 3
- 238000005457 optimization Methods 0.000 abstract description 3
- 238000012549 training Methods 0.000 abstract description 3
- 230000010485 coping Effects 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Animal Behavior & Ethology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a charging pile guide type fault diagnosis prediction method and a system, which belong to the technical field of fault identification and response information and comprise the following steps: establishing a physical-virtual twin model of the charging pile, importing charging pile data acquired in real time into the physical-virtual twin model, and simulating the running state of the charging pile by using the physical-virtual twin model to obtain a running state prediction result of the charging pile; and establishing a guided fault diagnosis engine, inputting the running state prediction result into the guided fault diagnosis engine, and performing fault prediction by using an analysis algorithm to obtain a fault prediction result. The invention takes the blocking grid nodes as boundaries, takes data as basic elements, combines a twin model, algorithm training and diagnosis model, realizes fault result feedback and maintenance scheme optimization based on engine diagnosis, carries out intelligent and digital management and fault early warning and coping on clustered distributed charging piles, and improves risk early warning capability.
Description
Technical Field
The invention relates to the technical field of fault identification and response information, in particular to a charging pile guide type fault diagnosis prediction method and system.
Background
Under the background of intelligent networking automobile intellectualization, networking and electric rapid development, the layout of the charging piles is continuously increased in unprecedented scale. Therefore, the practical and effective operation and maintenance management and operation state monitoring of the charging pile become particularly important in the context of digital economy.
As the utilization rate of the charging pile is higher, the probability of the charging pile failing due to environmental factors, improper use or device failure is also higher. Once a fault occurs, the current solving measures generally need to send professionals to the site for investigation by manufacturers, then feed back fault information, and repair the charging pile according to specific conditions, which is time-consuming and labor-consuming. However, when the current charging pile fault diagnosis and prediction method aims at faults of charging piles distributed in a large-scale area, the technical problems of difficult positioning of the fault problems, delayed solution measures, poor consistency, untimely maintenance feedback, poor prediction accuracy and the like exist.
Therefore, how to provide a method and a system for diagnosing and predicting the fault of the charging pile, which can rapidly locate the problem, realize an integrated quality vertical management and standardized fault management system, and improve the early warning efficiency and the fault emergency processing capability, are the problems to be solved by the technicians in the field.
Disclosure of Invention
In view of the above, the invention provides a charging pile guided fault diagnosis prediction method and a system, which are used for establishing a multi-dimensional twin model by establishing cloud service, fusing a guided fault diagnosis platform of a diagnosis engine and developing intelligent fault diagnosis and management for a charging pile. The method takes the blocking grid nodes as boundaries and takes data as basic elements, so that the problems of early warning and processing of generated chain faults of end-twin model-guided diagnosis platform-fault processing and quick positioning are solved, an integrated quality vertical management and standardized fault management system is realized, and the early warning efficiency and fault emergency processing capability are improved.
In order to achieve the above object, the present invention provides the following technical solutions:
in one aspect, the invention provides a charging pile guide type fault diagnosis prediction method, which comprises the following steps:
establishing a physical-virtual twin model of the charging pile, comprising:
acquiring position information and equipment information of each charging pile in a charging pile cluster;
dividing the charging pile cluster into a plurality of blocks according to the position information, wherein each block is provided with a block node, the block nodes interact through an intermediate node, and the data interaction among the charging pile, the block nodes and the intermediate node is realized through a dynamic real-time data information transmission chain;
constructing a physical model of the charging pile according to the position information and the equipment information;
constructing the physical-virtual twin model according to the physical model;
importing charging pile data acquired in real time into the physical-virtual twin model, and simulating the running state of the charging pile by using the physical-virtual twin model to obtain a running state prediction result of the charging pile;
and establishing a guided fault diagnosis engine, inputting the running state prediction result into the guided fault diagnosis engine, and performing fault prediction by using an analysis algorithm to obtain a fault prediction result.
Preferably, the guided fault diagnosis engine comprises a search engine and a fault knowledge graph base.
Preferably, the fault knowledge graph establishing process includes:
constructing a fault knowledge graph body;
carrying out vectorization processing on the historical fault case text, and then extracting entities and entity relations;
according to the fault knowledge graph body, correlating the entity extracted from the historical fault case text with the entity relationship to form a fault knowledge graph;
the knowledge graph base is composed of fault knowledge graphs of a plurality of different components.
Preferably, the operation state prediction result is input into a trained guided fault diagnosis engine, and the fault prediction is performed by using an analysis algorithm, including:
inputting the running state prediction result into a search engine, acquiring feature data corresponding to the running state prediction result through the search engine, and screening a fault knowledge graph set corresponding to the feature data from the fault knowledge graph base based on the feature data;
respectively calculating corresponding fault diagnosis results and fault diagnosis probabilities of the fault knowledge graph sets in the fault knowledge graph sets;
and when the fault diagnosis probability is lower than a preset threshold value, performing fault alarm and prompting a potential risk early warning and processing scheme.
Preferably, the operation state prediction result is associated with the physical-virtual twin model according to the characteristic data, when the fault diagnosis result exceeds the preset threshold value, the corresponding charging pile in the physical-virtual twin model carries out audible and visual alarm, and after the alarm charging pile is clicked, the fault mode, the fault state and the fault fusion processing scheme are displayed.
Preferably, the operation state prediction result is input into the guided fault diagnosis engine, fault prediction is performed by using an algorithm, and after obtaining the fault prediction result, the method further includes:
evaluating the accuracy of the fault result, and if the accuracy of the fault prediction result does not exceed a preset threshold value, updating the fault knowledge graph; if the accuracy of the fault result exceeds a preset threshold, the fault knowledge graph is not updated.
Preferably, the operation state prediction result is input into a search engine, and feature data corresponding to the operation state prediction result is obtained through the search engine, including:
acquiring the running state prediction result, and classifying the running state prediction data to obtain a plurality of independent single running state data;
and inputting the single running state data into a feature extraction model constructed according to the deep neural network to perform feature extraction, so as to obtain a plurality of feature data of the single running state.
In another aspect, the present invention provides a charging pile guide type fault diagnosis prediction system, comprising: the system comprises an acquisition module, a twin model platform and a diagnosis engine platform, wherein the acquisition module is connected with the twin model platform and is used for transmitting real-time data of a charging pile to the twin model platform, and the twin model platform simulates the running state of the charging pile based on a pre-constructed physical-virtual twin model to obtain a running state prediction result of the charging pile; the twin model platform is connected with the diagnosis engine platform and is used for inputting the running state prediction result into the guided fault diagnosis engine, performing fault prediction by using an analysis algorithm to obtain a fault prediction result and displaying the fault prediction result; the diagnosis engine platform is connected with the charging pile cluster and used for transmitting the prediction result to the charging pile.
Preferably, the twin platform comprises: the system comprises a physical model module, a region dividing module, a twin model module and a display module;
the area dividing module is used for dividing the charging pile cluster into a plurality of blocks according to the position information, each block is provided with a block node, and the block nodes interact through an intermediate node to realize data interaction among the charging pile, the block nodes and the intermediate node through a dynamic real-time data information transmission chain;
the physical model module is used for constructing a physical model of the charging pile according to the position information and the equipment information;
the twin model module is used for constructing the physical-virtual twin model according to the physical model;
and the display module is used for displaying the physical-virtual twin model and the fault prediction result.
Preferably, the guided fault diagnosis engine comprises a search engine and a fault knowledge graph library; the search engine is used for acquiring characteristic data of the running state prediction result according to the running state prediction result, and searching a fault knowledge graph corresponding to the characteristic data in the fault knowledge graph base based on the characteristic data; the fault knowledge graph library is used for storing fault knowledge graphs of different components.
Compared with the prior art, the invention discloses a charging pile guide type fault diagnosis prediction method and a charging pile guide type fault diagnosis prediction system, which are suitable for fault monitoring and problem early warning methods of charging piles deployed in a large-scale cluster. The method has the advantages that a clustered and meshed modular charging pile management mode is established, a fault engine is formed in the system, parameter signals are quickly obtained, system response is automatically carried out on faults, fault solving measures are intelligently provided, the fault failure event of the large-scale and clustered charging piles is effectively treated, the fault analysis efficiency and the management of an enterprise-level experience knowledge base are effectively improved, the enterprise digitization level is improved, and the cost is reduced. The method takes the blocking grid nodes as boundaries and takes data as basic elements, so that the problems of early warning and processing of generated chain faults of end-twin model-guided diagnosis platform-fault processing and quick positioning are solved, an integrated quality vertical management and standardized fault management system is realized, and the early warning efficiency and fault emergency processing capability are improved. Meanwhile, a guided fault diagnosis platform of the fusion diagnosis engine is established, and the algorithm training and diagnosis model is combined to realize fault result feedback and maintenance scheme optimization based on engine diagnosis, intelligent and digital management and fault early warning and coping are carried out on clustered distributed charging piles, so that risk early warning capability is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of the method of the present invention;
FIG. 2 is a schematic flow chart of fault knowledge base optimization according to the present invention;
fig. 3 is a schematic diagram of the system of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Aiming at the technical problems that when a large-scale regional distributed charging pile has faults, the fault problem is difficult to locate, the solution is lag, the consistency is poor, the maintenance feedback is not timely and the like, the embodiment of the invention provides a method for carrying out fault guiding diagnosis and monitoring by fusing a digital twin model, a clustered and meshed modular charging pile management mode is established, a fault engine is formed in a system, a parameter signal is quickly obtained, the system response is automatically carried out on the faults, the fault solution is intelligently provided, the fault failure event of the large-scale and clustered charging pile is effectively managed by a high-efficiency effect pair, the fault analysis efficiency and the enterprise-level experience knowledge base are effectively improved, the enterprise digital level is improved, and the cost is reduced.
In one aspect, the present invention provides a method for predicting a charging pile-guided fault diagnosis, as shown in fig. 1, including the following steps:
establishing a physical-virtual twin model of the charging pile, importing charging pile data acquired in real time into the physical-virtual twin model, and simulating the running state of the charging pile by using the physical-virtual twin model to obtain a running state prediction result of the charging pile;
and establishing a guided fault diagnosis engine, inputting the running state prediction result into the guided fault diagnosis engine, and performing fault prediction by using an analysis algorithm to obtain a fault prediction result.
Establishing a physical-virtual twin model of the charging pile, comprising:
and acquiring the position information and the equipment information of each charging pile in the charging pile cluster. The position information comprises actual position information of the charging pile and relative position information of the charging pile and other charging piles; the equipment information comprises integral information of the charging pile, and the types of all parts of the charging pile, the service time, the equipment performance, rated operation parameters and the like.
According to the method, a charging pile cluster is divided into a plurality of blocks according to position information, each block is provided with a block node, the block nodes interact through intermediate nodes, data interaction among the charging pile, the block nodes and the intermediate nodes is realized through a dynamic real-time data information transmission chain, and the physical charging pile is used for carrying out state simulation, performance prediction and operation monitoring on actual operation conditions in a whole life cycle of large-scale distribution to carry out data and information interaction. Each grid node is used as an intermediate node management platform for block management, can schedule and analyze charging pile data in blocks, and converts data among the blocks through the intermediate nodes. When the blocks are divided, a label model of the blocks and the individual charging piles is established, wherein the labels of the blocks are { A, B, C, … }, and the labels of the individual charging piles are { A, a1, a2, a3, … }, { B, B1, B2, B3, … }. When the fault diagnosis engine platform searches the corresponding fault map, preliminary searching can be performed based on the label.
Constructing a physical model of the charging pile according to the position information and the equipment information;
and constructing a physical-virtual twin model according to the physical model. The physical-virtual twin model is composed of a digital twin model of a data transmission loop, a charging loop, a control loop and an auxiliary loop.
In another embodiment, the fault diagnosis engine includes a search engine and a fault knowledge-graph library.
The knowledge graph has two construction modes of top-down and bottom-up. The bottom-up construction mode is that knowledge extraction is completed first, and then ontology information is defined; the top-down mode is to define the body information first and then complete knowledge extraction from the data. Because the fault knowledge graph of the charging pile belongs to the knowledge graph in the vertical field, and the number of the entities contained in the graph is small, the embodiment of the invention adopts a top-down construction mode, and the process for constructing the fault knowledge graph comprises the following steps:
constructing a fault knowledge graph body; the schema layer builds on top of the data layer, mainly through an ontology library to normalize a series of factual expressions of the data layer. The ontology is a template of the structured knowledge base, and the knowledge base formed by the ontology base has a strong hierarchical structure and a small redundancy degree. The embodiment of the invention mainly establishes a multi-level equipment fault diagnosis fault tree in the charging process of the charging pile based on the performance characterization of each part of the charging pile, fault states, detection tools and other entities and the relation among the parts, and comprises two primary fault sources of a power battery and a charging facility, wherein each primary fault source comprises a secondary fault source, a tertiary fault source and a specific fault type, the lower part of the multi-level equipment fault comprises specific fault types such as overvoltage, overcurrent, overtemperature and the like, and establishes a multi-level fault tree taking the charging and discharging process of the charging pile as a main body and taking part units and the fault states as branches.
Carrying out vectorization processing on the historical fault case text, and then extracting entities and entity relations; the entity extraction method can adopt a rule-based method, a statistical machine learning-based method and a deep learning-based method. The relationship is a bridge between entities, the entity relationship in the structured fault text can be directly constructed, and the semi-structured text data relationship extraction adopts a method based on pattern matching. In the extraction process, a relation expression mode between entities, such as a causal relation between a fault phenomenon and a fault reason, is constructed according to the fault text, and a relation template of the fault entity [ fault phenomenon ] reason [ fault reason ] is constructed.
According to the fault knowledge graph body, correlating the entity extracted from the historical fault case text with the entity relationship to form a fault knowledge graph;
the knowledge graph base is composed of fault knowledge graphs of a plurality of different components.
The search engine establishes an analysis algorithm based on historical data, and realizes the formal description of the case based on the characteristics through the characteristics to form a case formal characteristic library and generate a characteristic tree. The diagnostic engine is divided into case annotation, case tool analysis and characteristic automatic annotation. In the process of case labeling, the actual case is imported to develop a diagnosis training algorithm. The actual case data acquisition field comprises main fields such as a charging pile message ID, a signal name, a component unit, a fault form, an occurrence time, a number, a performance phenomenon, a parameter state, a processing measure and the like. In the process of analyzing the use case tool and automatically labeling the characteristics, a rule extraction technology is adopted to form a fault problem state description with regularity. In the use case analysis process, an expert database model is simultaneously introduced. When a fault occurs, when a corresponding field or a message ID is input, the field matching of the feature library is automatically carried out, the guided fault diagnosis is carried out, and the response of the processing measures is carried out.
In another embodiment, the method for predicting the operation state of the engine includes inputting the operation state prediction result into a trained guided fault diagnosis engine, and performing fault prediction by using an analysis algorithm, including:
inputting the running state prediction result into a search engine, acquiring characteristic data corresponding to the running state prediction result through the search engine, and screening a fault knowledge graph set corresponding to the characteristic data in a fault knowledge graph base based on the characteristic data;
respectively calculating corresponding fault diagnosis results and fault diagnosis probabilities of a fault knowledge graph set in the fault knowledge graph sets;
and when the fault diagnosis probability is lower than a preset threshold value, performing fault alarm and prompting a potential risk early warning and processing scheme.
Preferably, the fault diagnosis result is associated with the physical-virtual twin model according to the characteristic data, when the fault diagnosis result exceeds a threshold value, the corresponding charging pile in the physical-virtual twin model carries out audible and visual alarm, and after the alarm charging pile is clicked, the fault mode, the fault state and the fault processing scheme are displayed. And (3) establishing a fault diagnosis sub-engine of each part under the charging pile label according to the charging pile bill of materials (BOM), wherein the BOM bill is distributed and established under the corresponding charging pile label. When clicking a certain part of the twin model, automatically associating the historical faults and parameter thresholds which occur under the part, judging the safe running state of the current part according to the design reference, and realizing the remote running characteristic monitoring of the charging pile. When a certain part under the charging pile breaks down, or when the voltage and current signal has an abnormal value in the charging process, the corresponding part of the twin model automatically lights a yellow alarm signal, and after clicking the alarm signal, the corresponding fault mode and state can be checked, and meanwhile, the potential fault processing mode and counter-processing measures provided by the diagnosis model can be checked, so that the expected risk early warning and fault diagnosis are realized.
In another embodiment, the operation state prediction result is input to the guided fault diagnosis engine, and after the fault prediction is performed by using an analysis algorithm, as shown in fig. 2, the method further includes:
evaluating the accuracy of the fault result, and if the accuracy of the fault prediction result does not exceed a preset threshold value, updating the fault knowledge graph; if the accuracy of the fault result exceeds a preset threshold, the fault knowledge graph is not updated.
In another embodiment, the operation state prediction result is input into a search engine, and feature data corresponding to the operation state prediction result is obtained through the search engine, including:
acquiring an operation state prediction result, and classifying the operation state prediction data to obtain a plurality of independent single operation state data;
and inputting the single running state data into a feature extraction model constructed according to the deep neural network to perform feature extraction, so as to obtain feature data of a plurality of single running states.
In another embodiment, the present invention provides a charging pile guide type fault diagnosis prediction system, comprising: the system comprises an acquisition module, a twin model platform and a diagnosis engine platform, wherein the acquisition module is connected with the twin model platform and is used for transmitting real-time data of the charging pile to the twin model platform, and the twin model platform simulates the running state of the charging pile based on a pre-constructed physical-virtual twin model to obtain a running state prediction result of the charging pile; the twin model platform is connected with the diagnosis engine platform and is used for inputting the running state prediction result into the guided fault diagnosis engine, performing fault prediction by using an analysis algorithm to obtain a fault prediction result and displaying the fault prediction result; the diagnosis engine platform is connected with the charging pile cluster and used for transmitting the prediction result to the charging pile.
Preferably, the twin platform comprises: the system comprises a physical model module, a region dividing module, a twin model module and a display module;
the regional division module is used for dividing the charging pile cluster into a plurality of blocks according to the position information, each block is provided with a block node, and the block nodes interact through the intermediate nodes to realize the data interaction among the charging pile, the block nodes and the intermediate nodes through the dynamic real-time data information transmission chain;
the physical model module is used for constructing a physical model of the charging pile according to the position information and the equipment information;
the twin model module is used for constructing a physical-virtual twin model according to the physical model;
and the display module is used for displaying the physical-virtual twin model and the fault prediction result.
Preferably, the fault diagnosis engine comprises a search engine and a fault knowledge graph base; the search engine is used for acquiring characteristic data of the running state prediction result according to the running state prediction result, and searching a fault knowledge graph corresponding to the characteristic data in the fault knowledge graph base based on the characteristic data; the fault knowledge graph library is used for storing fault knowledge graphs of different components. The search engine is provided with a feature library for matching feature data corresponding to the prediction result.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. The charging pile guide type fault diagnosis and prediction method is characterized by comprising the following steps of:
establishing a physical-virtual twin model of the charging pile, comprising:
acquiring position information and equipment information of each charging pile in a charging pile cluster;
dividing the charging pile cluster into a plurality of blocks according to the position information, wherein each block is provided with a block node, the block nodes interact through an intermediate node, and the data interaction among the charging pile, the block nodes and the intermediate node is realized through a dynamic real-time data information transmission chain;
constructing a physical model of the charging pile according to the position information and the equipment information;
constructing the physical-virtual twin model according to the physical model;
importing charging pile data acquired in real time into the physical-virtual twin model, and simulating the running state of the charging pile by using the physical-virtual twin model to obtain a running state prediction result of the charging pile;
and establishing a guided fault diagnosis engine, inputting the running state prediction result into the guided fault diagnosis engine, and performing fault prediction by using an analysis algorithm to obtain a fault prediction result.
2. The method for predicting the pilot-type fault diagnosis of the charging pile according to claim 1, wherein the pilot-type fault diagnosis engine comprises a search engine and a fault knowledge graph base.
3. The method for predicting the pilot-induced fault diagnosis of the charging pile according to claim 2, wherein the process of establishing the fault knowledge base comprises the steps of:
constructing a fault knowledge graph body;
carrying out vectorization processing on the historical fault case text, and then extracting entities and entity relations;
associating the entity and the entity relationship according to the fault knowledge graph body to form a fault knowledge graph;
the fault knowledge graph library is composed of fault knowledge graphs of a plurality of different components.
4. A charging pile guide-type fault diagnosis prediction method according to claim 3, wherein the operation state prediction result is input into a trained guide-type fault diagnosis engine, and the fault prediction is performed by using an analysis algorithm, comprising:
inputting the running state prediction result into a search engine, acquiring feature data corresponding to the running state prediction result through the search engine, and screening a fault knowledge graph set corresponding to the feature data from the fault knowledge graph base based on the feature data;
respectively calculating corresponding fault diagnosis results and fault diagnosis probabilities of the fault knowledge graph sets in the fault knowledge graph sets;
and when the fault diagnosis probability is lower than a preset threshold value, performing fault alarm and prompting a potential risk early warning and processing scheme.
5. The method for predicting the guided fault diagnosis of the charging pile according to claim 4, wherein the fault diagnosis result is associated with the physical-virtual twin model according to the characteristic data, when the fault diagnosis probability exceeds the preset threshold, the corresponding charging pile in the physical-virtual twin model performs audible and visual alarm, and after clicking the alarm charging pile, the fault mode, the fault state and the fault processing scheme are displayed.
6. The method for predicting the pilot-type fault of the charging pile according to claim 1, wherein the operation state prediction result is input into the pilot-type fault diagnosis engine, the fault prediction is performed by an analysis algorithm, and the method further comprises, after obtaining the fault prediction result:
evaluating the accuracy of the fault result, and if the accuracy of the fault prediction result does not exceed a preset threshold value, updating the fault knowledge graph; if the accuracy of the fault result exceeds a preset threshold, the fault knowledge graph is not updated.
7. The method for predicting the guide type fault diagnosis of the charging pile according to claim 1, wherein the operation state prediction result is input into a search engine, and the feature data corresponding to the operation state prediction result is obtained by the search engine, comprising:
acquiring the running state prediction result, and classifying the running state prediction data to obtain a plurality of independent single running state data;
and inputting the single running state data into a feature extraction model constructed according to the deep neural network to perform feature extraction, so as to obtain a plurality of feature data of the single running state.
8. A charging pile-guided fault diagnosis prediction system, characterized by comprising: the system comprises an acquisition module, a twin model platform and a diagnosis engine platform, wherein the acquisition module is connected with the twin model platform and is used for transmitting real-time data of a charging pile to the twin model platform, and the twin model platform simulates the running state of the charging pile based on a pre-constructed physical-virtual twin model to obtain a running state prediction result of the charging pile; the twin model platform is connected with the diagnosis engine platform and is used for inputting the running state prediction result into the guided fault diagnosis engine, performing fault prediction by using an analysis algorithm to obtain a fault prediction result and displaying the fault prediction result; the diagnosis engine platform is connected with the charging pile cluster and used for transmitting the prediction result to the charging pile.
9. The charging pile-guided fault diagnosis and prognosis system according to claim 8, wherein the twin platform comprises: the system comprises a physical model module, a region dividing module, a twin model module and a display module;
the area dividing module is used for dividing the charging pile cluster into a plurality of blocks according to the position information, each block is provided with a block node, and the block nodes interact through an intermediate node to realize data interaction among the charging pile, the block nodes and the intermediate node through a dynamic real-time data information transmission chain;
the physical model module is used for constructing a physical model of the charging pile according to the position information and the equipment information;
the twin model module is used for constructing the physical-virtual twin model according to the physical model;
and the display module is used for displaying the physical-virtual twin model and the fault prediction result.
10. The method for predicting the pilot-type fault diagnosis of the charging pile according to claim 8, wherein the pilot-type fault diagnosis engine comprises a search engine and a fault knowledge graph base; the search engine is used for acquiring characteristic data of the running state prediction result according to the running state prediction result, and searching a fault knowledge graph corresponding to the characteristic data in the fault knowledge graph base based on the characteristic data; the fault knowledge graph library is used for storing fault knowledge graphs of different components.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311473075.7A CN117521498A (en) | 2023-11-07 | 2023-11-07 | Charging pile guide type fault diagnosis prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311473075.7A CN117521498A (en) | 2023-11-07 | 2023-11-07 | Charging pile guide type fault diagnosis prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117521498A true CN117521498A (en) | 2024-02-06 |
Family
ID=89741155
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311473075.7A Pending CN117521498A (en) | 2023-11-07 | 2023-11-07 | Charging pile guide type fault diagnosis prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117521498A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117991028A (en) * | 2024-04-02 | 2024-05-07 | 深圳市赛特新能科技有限公司 | Non-invasive charging pile detection platform, method and storage medium |
-
2023
- 2023-11-07 CN CN202311473075.7A patent/CN117521498A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117991028A (en) * | 2024-04-02 | 2024-05-07 | 深圳市赛特新能科技有限公司 | Non-invasive charging pile detection platform, method and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111985561B (en) | Fault diagnosis method and system for intelligent electric meter and electronic device | |
| US20220137612A1 (en) | Transformer fault diagnosis and positioning system based on digital twin | |
| CN102765643B (en) | Elevator fault diagnosis and early-warning method based on data drive | |
| CN107358366B (en) | Distribution transformer fault risk monitoring method and system | |
| CN110674189B (en) | Method for monitoring secondary state and positioning fault of intelligent substation | |
| CN102509178B (en) | Distribution network device status evaluating system | |
| CN106204330A (en) | A kind of power distribution network intelligent diagnosis system | |
| CN108537394B (en) | Real-time safety early warning method and device for smart power grid | |
| CN108336725A (en) | The management of dispatching of power netwoks monitoring of tools and intelligent analysis system | |
| CN106161138A (en) | A kind of intelligence automatic gauge method and device | |
| CN107346466A (en) | A kind of control method and device of electric power dispatching system | |
| CN112817280A (en) | Implementation method for intelligent monitoring alarm system of thermal power plant | |
| CN104363106A (en) | Electric power information communication fault early warning analysis method based on big-data technique | |
| CN109501834A (en) | A kind of point machine failure prediction method and device | |
| CN112859822A (en) | Equipment health analysis and fault diagnosis method and system based on artificial intelligence | |
| CN106650963A (en) | Electric car charging equipment detection and maintenance managing method and device | |
| CN117521498A (en) | Charging pile guide type fault diagnosis prediction method and system | |
| US11740275B2 (en) | Method for intelligent fault detection and location of power distribution network | |
| CN101833324A (en) | Intelligent fault diagnosis system in tread extrusion process and diagnosis method thereof | |
| JP7442001B1 (en) | Comprehensive failure diagnosis method for hydroelectric power generation units | |
| Eltyshev et al. | Intelligent decision support in the electrical equipment diagnostics | |
| CN116308304A (en) | New energy intelligent operation and maintenance method and system based on meta learning concept drift detection | |
| CN110968703B (en) | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm | |
| CN116720324A (en) | Traction substation key equipment fault early warning method and system based on prediction model | |
| CN114529166A (en) | Power distribution network operation safety risk early warning method and system |
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 |