CN109596913B

CN109596913B - Charging pile fault cause diagnosis method and device

Info

Publication number: CN109596913B
Application number: CN201811416032.4A
Authority: CN
Inventors: 刘晓天; 杜维柱; 梁继清; 杨振琦; 巨汉基; 赵思翔; 杨新宇; 王杰; 袁瑞铭; 丁恒春; 易忠林; 韩迪; 刘影; 汪洋; 崔文武; 王晨; 庞富宽; 郭皎; 李守超; 李萌
Original assignee: Pns Beijing Science & Technology Co ltd; State Grid Corp of China SGCC; North China Electric Power Research Institute Co Ltd; State Grid Jibei Electric Power Co Ltd; Electric Power Research Institute of State Grid Jibei Electric Power Co Ltd
Current assignee: Pns Beijing Science & Technology Co ltd; State Grid Corp of China SGCC; North China Electric Power Research Institute Co Ltd; State Grid Jibei Electric Power Co Ltd; Electric Power Research Institute of State Grid Jibei Electric Power Co Ltd
Priority date: 2018-11-26
Filing date: 2018-11-26
Publication date: 2021-06-15
Anticipated expiration: 2038-11-26
Also published as: CN109596913A

Abstract

The application provides a charging pile fault reason diagnosis method and device, and the method comprises the following steps: the method comprises the steps that when a target charging pile breaks down, the fault type of the target charging pile is obtained; inputting the fault type of the target charging pile into a preset Bayesian network model as a prediction sample, and taking the output of the Bayesian network model as a fault cause diagnosis result corresponding to the fault type of the target charging pile; the Bayesian network model comprises a topological structure of a Bayesian network and a corresponding conditional probability table, and the topological structure of the Bayesian network is used for representing the corresponding relation between each fault type of the charging pile and each fault cause diagnosis result. The fault reason automatic diagnosis of the charging pile can be realized, the diagnosis process is efficient, the diagnosis result is accurate, the reason of the fault can be rapidly confirmed when the charging pile breaks down, and the charging pile can be timely and pertinently maintained.

Description

Charging pile fault cause diagnosis method and device

Technical Field

The application relates to the technical field of charging pile equipment, in particular to a charging pile fault cause diagnosis method and device.

Background

With the rapid development of science and technology and the increasing environmental awareness of people, more and more electrically driven vehicles are favored by people. And as the important corollary equipment of electric drive vehicle, fill electric pile and also turn into at the same time. With more and more charging piles being put into use, how to confirm the fault reason when the charging pile breaks down so as to timely maintain the charging pile also becomes an important research method in the problem of ensuring the operation quality of the charging pile.

In the prior art, a fault reason diagnosis mode of a charging pile is generally realized by adopting a mode of manually and programmatically overhauling the charging pile, if a fault is found in an inspection process, the fault reason is checked aiming at the fault, and finally the occurrence reason of the fault is confirmed.

However, the existing failure cause diagnosis method for the charging pile determines the cause of the failure through manual planned maintenance, and this method can only be confirmed after the failure cause is manually repaired and checked, so that the failure cause diagnosis process for the charging pile is passive and inefficient.

Disclosure of Invention

To the problems in the prior art, the application provides a charging pile fault reason diagnosis method and device, which can realize automatic diagnosis of the fault reason of the charging pile, have high efficiency in the diagnosis process and accurate diagnosis result, can quickly confirm the fault reason when the charging pile breaks down, and can timely and pertinently maintain the charging pile.

In order to solve the technical problem, the application provides the following technical scheme:

in a first aspect, the present application provides a method for diagnosing a cause of a fault of a charging pile, including:

the method comprises the steps that when a target charging pile breaks down, the fault type of the target charging pile is obtained;

inputting the fault type of the target charging pile into a preset Bayesian network model as a prediction sample, and taking the output of the Bayesian network model as a fault cause diagnosis result corresponding to the fault type of the target charging pile;

the Bayesian network model comprises a topological structure of a Bayesian network and a corresponding conditional probability table, and the topological structure of the Bayesian network is used for representing the corresponding relation between each fault type of the charging pile and each fault cause diagnosis result.

Further, still include:

generating a training sample set according to multiple fault types of the charging pile and known fault cause diagnosis results corresponding to the fault types;

applying the training sample set, and establishing a topological structure of the Bayesian network based on a corresponding scoring function and a search algorithm;

and determining the conditional probability of each node in the topological structure of the Bayesian network based on a maximum likelihood estimation method to obtain a conditional probability table of each node.

Further, the generating of the training sample set according to the multiple fault types of the charging pile and the known fault cause diagnosis results corresponding to the multiple fault types includes:

extracting historical operating data of the plurality of charging piles from at least one of telemetering data, remote signaling data and electric power module monitoring data and transaction data of the electric power system;

extracting charging pile fault characteristic data corresponding to multiple fault types of the charging pile from the historical operating data, and establishing a charging pile fault index system according to the dependency relationship between the charging pile fault characteristic data corresponding to the fault types;

preprocessing charging pile fault characteristic data corresponding to the charging pile fault indicator body;

and generating a training sample set according to the preprocessed charging pile fault characteristic data.

Further, to fill electric pile fault characteristic data that electric pile fault index system corresponds and carry out the preliminary treatment, include:

carrying out data cleaning and/or attribute stipulation processing on charging pile fault characteristic data corresponding to the charging pile fault index system;

and carrying out data transformation on the charging pile fault characteristic data subjected to data cleaning and/or attribute specification processing.

In a second aspect, the present application provides a charging pile fault cause diagnosis device, including:

the fault type acquisition module of the target charging pile is used for acquiring the fault type of the target charging pile when the target charging pile breaks down;

the target fault cause diagnosis module is used for inputting the fault type of the target charging pile into a preset Bayesian network model as a prediction sample, and taking the output of the Bayesian network model as a fault cause diagnosis result corresponding to the fault type of the target charging pile;

Further, still include:

the training sample set generating module is used for generating a training sample set according to the multiple fault types of the charging pile and the corresponding known fault cause diagnosis results;

the Bayesian network topology structure establishing module is used for applying the training sample set and establishing a Bayesian network topology structure based on a corresponding scoring function and a search algorithm;

and the conditional probability acquisition module is used for determining the conditional probability of each node in the topological structure of the Bayesian network based on a maximum likelihood estimation method to obtain a conditional probability table of each node.

Further, the training sample set generating module includes:

the historical operating data acquisition unit is used for extracting historical operating data of the plurality of charging piles from at least one of telemetering data, remote signaling data power module monitoring data and transaction data of the power system;

the charging pile fault index system establishing unit is used for extracting charging pile fault feature data corresponding to multiple fault types of the charging piles from the historical operating data and establishing a charging pile fault index system according to the membership between the charging pile fault feature data corresponding to the fault types;

the data preprocessing unit is used for preprocessing charging pile fault characteristic data corresponding to the charging pile fault indicator body;

and the training sample set generating unit is used for generating a training sample set according to the preprocessed charging pile fault characteristic data.

Further, the data preprocessing unit is specifically configured to:

In a third aspect, the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the steps of the charging pile fault cause diagnosis method.

In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the charging pile fault cause diagnosis method.

According to the technical scheme, the fault type of the target charging pile is input into a preset Bayesian network model as a prediction sample, the output of the Bayesian network model is used as a fault cause diagnosis result corresponding to the fault type of the target charging pile, the Bayesian network model comprises a topological structure of a Bayesian network and a corresponding condition probability table, the topological structure of the Bayesian network is used for representing the corresponding relation between each fault type of the charging pile and each fault cause diagnosis result, the automatic diagnosis of the fault cause of the charging pile can be realized, the diagnosis process is efficient, the diagnosis result is accurate, the reason of the fault occurrence can be rapidly confirmed when the charging pile is in fault, and the charging pile can be timely and pertinently maintained, and can effectively improve fortune dimension personnel work efficiency, and alleviate fortune dimension operating pressure to filling electric pile, and simultaneously, fill electric pile fault cause diagnostic process simple and have a scientific foundation, can provide effectual data support for filling the daily fortune dimension work of electric pile, have very strong scientificity, reliability and maneuverability, can guide the intelligent fortune dimension of filling electric pile effectively, promote the smart level of charging facility asset management and operation maintenance work, improve the operational stability and the running life of charging facility, shorten the fault handling time length, improve asset utilization ratio and charging service level.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic flow chart of a charging pile fault cause diagnosis method in an embodiment of the present invention.

FIG. 2 is a diagram illustrating an architecture between the server S1 and the client device B1 according to an embodiment of the present invention.

Fig. 3 is a schematic diagram of the architecture among the server S1, the client device B1, and the fault detection device B2 according to the embodiment of the present invention.

Fig. 4 is a flowchart illustrating a charging pile fault cause diagnosis method including steps 001 to 003 in the embodiment of the present invention.

Fig. 5 is a schematic flowchart of step 001 in the charging pile fault cause diagnosis method in the embodiment of the present invention.

Fig. 6 is a schematic flowchart of step 001c in the charging pile fault cause diagnosis method in the embodiment of the present invention.

Fig. 7 is a schematic diagram illustrating an example structure of a charging pile fault indicator system in an embodiment of the present invention.

Fig. 8 is a schematic structural example of a topology structure of a bayesian network in the embodiment of the present invention.

Fig. 9 is a schematic structural diagram of a charging pile fault cause diagnosis device in an embodiment of the present invention.

Fig. 10 is a schematic structural diagram of a charging pile fault cause diagnosis apparatus including the model building module 00 according to an embodiment of the present invention.

Fig. 11 is a schematic structural diagram of a training sample set generating module 01 in the charging pile fault cause diagnosis method in the embodiment of the present invention.

Fig. 12 is a schematic structural diagram of an electronic device in an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Due to the fact that the reasons for forming the charging pile fault types are various, and considering that the prior art always focuses on a threshold range of a single index to determine which fault occurs in the charging pile, the fault reason diagnosis for the charging pile is passive and low in efficiency, and the problems of excessive overhaul, lack of overhaul and resource waste and mismatching are caused, the charging pile fault reason diagnosis method, the charging pile fault reason diagnosis device, the electronic equipment for realizing the charging pile fault reason diagnosis method and the computer storage medium are provided. The charging pile fault cause diagnosis method comprises the steps of inputting a fault type of a target charging pile into a preset Bayesian network model as a prediction sample, and using the output of the Bayesian network model as a fault cause diagnosis result corresponding to the fault type of the target charging pile, wherein the Bayesian network model comprises a topological structure of a Bayesian network and a corresponding condition probability table, and the topological structure of the Bayesian network is used for representing the corresponding relation between each fault type of the charging pile and each fault cause diagnosis result, so that automatic diagnosis of the fault cause of the charging pile can be realized, the diagnosis process is efficient, the diagnosis result is accurate, the fault cause of the charging pile can be quickly determined when the charging pile is in fault, the charging pile can be timely and pertinently maintained, and the working efficiency of operation and maintenance personnel can be effectively improved, the operation and maintenance work pressure for the charging pile is reduced, meanwhile, the fault reason diagnosis process of the charging pile is simple and scientific, effective data support can be provided for daily operation and maintenance work of the charging pile, the intelligent operation and maintenance system has strong scientificity, reliability and operability, intelligent operation and maintenance of the charging pile can be effectively guided, the precision level of asset management and operation maintenance work of a charging facility is improved, the operation stability and the operation life of the charging facility are improved, the fault handling time is shortened, and the asset utilization rate and the charging service level are improved.

In a model training scenario, the present application further provides a charging pile fault cause diagnosis apparatus, which may be a server S1, see fig. 2, where the server S1 may be in communication connection with at least one client device B1, the client device B1 may send historical operation data of a plurality of charging piles to the server S1 on line, and the server S1 may receive the historical operation data of the plurality of charging piles on line. The server S1 may extract charging pile fault feature data corresponding to multiple fault types of the charging pile from the historical operating data online or offline, establish a charging pile fault index system according to the membership between the charging pile fault feature data corresponding to each fault type, preprocess the charging pile fault feature data corresponding to the charging pile fault index body, generate a training sample set according to the preprocessed charging pile fault feature data, apply the training sample set, establish a topological structure of the bayesian network based on a corresponding scoring function and a search algorithm, determine conditional probabilities at each node in the topological structure of the bayesian network based on a maximum likelihood estimation method, obtain a conditional probability table of each node, and then complete establishment of a bayesian network model.

Based on the above description, the server S1 may also be replaced with a database for being accessed by the server S1, that is, the server S1 may obtain historical operation data of the charging pile from the database at different times or at regular time.

In a model prediction scenario, referring to fig. 3, the server S1 may further be in communication connection with at least one fault monitoring device B2, where the fault monitoring device B2 may be a sensor or a sensor group, such as a voltage sensor, a temperature sensor, a humidity sensor, and a current sensor, disposed on a charging pile or a related line, and when the fault monitoring device B2 monitors that a charging pile has a fault, the fault information is sent to the server S1 online, the server S1 receives the fault information online and extracts a fault type from the fault information online or offline, and then the server S1 inputs the fault type of the target charging pile as a prediction sample into a preset bayesian network model and takes an output of the bayesian network model as a fault cause diagnosis result corresponding to the fault type of the target charging pile, the Bayesian network model comprises a topological structure of a Bayesian network and a corresponding conditional probability table, the topological structure of the Bayesian network is used for representing the corresponding relation between each fault type of the charging pile and each fault reason diagnosis result, and then the server S1 sends the fault reason diagnosis result to the client device B1 on line, so that the client device B1 can timely acquire the fault reason diagnosis result of the charging pile fault, and a maintainer can rapidly and pertinently repair the corresponding charging pile fault through the client device B1.

Based on the above, the client device B1 may have a display interface, so that a user can view the fault cause diagnosis result corresponding to the charging pile fault of the target charging pile sent by the server S1 according to the interface.

It is understood that the client device B1 may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a Personal Digital Assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Wherein, intelligence wearing equipment can include intelligent glasses, intelligent wrist-watch, intelligent bracelet etc..

In practical applications, the part for diagnosing the cause of charging pile fault may be executed on the side of the server S1 as described above, that is, the architecture shown in fig. 2 or fig. 3, all operations may be completed in the client device B1, and the client device B1 may be directly connected to the fault monitoring device B2 and the power system in a communication manner. Specifically, the selection may be performed according to the processing capability of the client device B1, the limitation of the user usage scenario, and the like. This is not a limitation of the present application. If all the operations are completed in the client device B1, the client device B1 may further include a processor configured to perform specific processing for diagnosing a cause of a failure of the charging pile.

The client device may have a communication module (i.e., a communication unit), and may be in communication connection with the fault monitoring device and a server remote from the power system, so as to implement data transmission with the fault monitoring device and the server remote from the power system. For example, the communication unit acquires telemetry data, remote signaling data and power module monitoring data of the power system through a remote server of the power system, so that the client device constructs the bayesian network model of the charging pile according to the relevant data. The server may include a server on the task scheduling center side, and in other implementation scenarios, the server may also include a server on an intermediate platform, for example, a server on a third-party server platform that is communicatively linked to the task scheduling center server. The server may include a single computer device, or may include a server cluster formed by a plurality of servers, or a server structure of a distributed apparatus.

The server and the client device may communicate using any suitable network protocol, including network protocols not yet developed at the filing date of this application. The network protocol may include, for example, a TCP/IP protocol, a UDP/IP protocol, an HTTP protocol, an HTTPS protocol, or the like. Of course, the network Protocol may also include, for example, an RPC Protocol (Remote Procedure Call Protocol), a REST Protocol (Representational State Transfer Protocol), and the like used above the above Protocol.

In one or more embodiments of the present disclosure, the charging pile may be fixed on the ground or on a wall, installed in a parking lot or a charging station of a public building (a public building, a mall, a public parking lot, etc.) and a residential area, and may charge various types of electric vehicles according to different voltage levels. The input end of the charging pile is directly connected with an alternating current power grid, and the output end of the charging pile is provided with a charging plug for charging the electric drive vehicle. The electric drive vehicle may be an electric vehicle, or may be another type of vehicle driven by electric power.

The method can realize automatic diagnosis of the fault reason of the charging pile, has high efficiency in the diagnosis process and accurate diagnosis result, thereby rapidly confirming the cause of the failure when the charging pile fails, further timely and pertinently maintaining the charging pile, and can effectively improve the working efficiency of operation and maintenance personnel and reduce the operation and maintenance working pressure aiming at the charging pile, meanwhile, the fault reason diagnosis process of the charging pile is simple and scientific, effective data support can be provided for daily operation and maintenance work of the charging pile, the intelligent operation and maintenance of the charging pile can be effectively guided, the charging facility asset management and operation maintenance work fine level is improved, the operation stability and the operation service life of the charging facility are improved, the fault treatment time is shortened, and the asset utilization rate and the charging service level are improved. The following embodiments and two application scenarios are specifically described.

In order to realize automatic diagnosis of the fault reason of the charging pile and enable the diagnosis process to be more efficient and the diagnosis result to be accurate, an embodiment of the application provides a method for diagnosing the fault reason of the charging pile, and referring to fig. 1, the method for diagnosing the fault reason of the charging pile specifically includes the following steps:

step 100: the method comprises the steps that when a target charging pile breaks down, the fault type of the target charging pile is obtained;

step 200: and inputting the fault type of the target charging pile as a prediction sample into a preset Bayesian network model, and taking the output of the Bayesian network model as a fault cause diagnosis result corresponding to the fault type of the target charging pile, wherein the Bayesian network model comprises a topological structure of a Bayesian network and a corresponding conditional probability table, and the topological structure of the Bayesian network is used for representing the corresponding relation between each fault type of the charging pile and each fault cause diagnosis result.

It is understood that the bayesian network bn (bayesian network model), also called belief network, is composed of a Directed Acyclic Graph (DAG) and Conditional Probability Tables (CPT). In a bayesian network, two variables X and Y, if directly connected, indicate a direct dependency between them, and knowledge of X affects the confidence in Y and vice versa. In this sense, we mean that information can be passed between two directly connected nodes. On the other hand, if two variables X and Y are not directly connected, then information needs to pass between the two through the other variables. If all the information paths between X and Y are blocked, information cannot be passed between them. In this case, knowledge of one of the variables does not affect the confidence of the other variable, so X and Y are conditionally independent of each other. If the basic case is considered where two variables X and Y are indirectly connected through a third variable Z, the bayesian network can be decomposed into three basic structures, namely, forward, split and aggregate.

Among them, the advantages of the bayesian network are mainly reflected in:

(1) the Bayesian network describes the interrelation among the data by using a graph method, has clear semantics and is easy to understand. The graphical knowledge representation method facilitates the consistency and the integrity of the probability knowledge base, and the network module can be conveniently reconfigured according to the change of conditions.

(2) Bayesian networks are prone to handling incomplete data sets. All possible data inputs must be known for the traditional standard supervised learning algorithm, if some input is missing, the established model is biased, the method of the Bayesian network reflects a probability relation model among data in the whole database, and an accurate model can still be established if some data variable is missing.

(3) Bayesian networks allow learning causal relationships between variables. In the past data analysis, the causal relationship of a problem is that when the interference is large, the system can not make an accurate prediction. This causal relationship has been included in bayesian network models. The Bayesian method has causal and probabilistic semantics, and can be used for learning causal relationships in data and learning according to the causal relationships.

(4) The combination of Bayesian network and Bayesian statistics can make full use of domain knowledge and sample data information. The Bayesian network expresses the dependency relationship among variables by arcs, expresses the strength of the dependency relationship by a probability distribution table, organically combines the prior information with the sample knowledge, promotes the integration of the prior knowledge and the data, and is particularly effective when the sample data is sparse or the data is difficult to obtain.

As can be seen from the above description, according to the charging pile fault cause diagnosis method provided by the application, the fault type of the target charging pile is input as a prediction sample into a preset bayesian network model, and the output of the bayesian network model is used as a fault cause diagnosis result corresponding to the fault type of the target charging pile, wherein the bayesian network model comprises a topological structure of the bayesian network and a corresponding conditional probability table, and the topological structure of the bayesian network is used for representing the corresponding relationship between each fault type of the charging pile and each fault cause diagnosis result, so that automatic diagnosis of the fault cause of the charging pile can be realized, the diagnosis process is efficient, the diagnosis result is accurate, the reason of the fault occurrence can be quickly confirmed when the fault occurs, and the charging pile can be timely and pertinently maintained, and can effectively improve fortune dimension personnel work efficiency, and alleviate fortune dimension operating pressure to filling electric pile, and simultaneously, fill electric pile fault cause diagnostic process simple and have a scientific foundation, can provide effectual data support for filling the daily fortune dimension work of electric pile, have very strong scientificity, reliability and maneuverability, can guide the intelligent fortune dimension of filling electric pile effectively, promote the smart level of charging facility asset management and operation maintenance work, improve the operational stability and the running life of charging facility, shorten the fault handling time length, improve asset utilization ratio and charging service level.

In order to provide a more accurate and targeted bayesian network model to further improve the efficiency of the diagnosis process and the accuracy of the diagnosis result, in an embodiment of the present application, the method for diagnosing the cause of the fault of the charging pile further includes a model establishing step, see fig. 4, where the model establishing step specifically includes the following steps:

step 001: and generating a training sample set according to the multiple fault types of the charging pile and the corresponding known fault reason diagnosis results.

Step 002: and applying the training sample set to establish a topological structure of the Bayesian network based on the corresponding scoring function and the search algorithm.

Step 003: and determining the conditional probability of each node in the topological structure of the Bayesian network based on a maximum likelihood estimation method to obtain a conditional probability table of each node.

In order to further improve the accuracy and reliability of the diagnosis of the fault cause of the electric pile, a specific implementation manner of step 001 in the diagnosis method of the fault cause of the electric pile is further provided in an embodiment of the present application, referring to fig. 5, where the step 001 specifically includes the following contents:

step 001 a: historical operating data of the plurality of charging piles is extracted from at least one of telemetering data, remote signaling data and electric power module monitoring data and transaction data of the electric power system.

It can be understood that the historical operating data of the charging pile may be historical operating data in a preset operating period. For example, the preset operation period may be 1 month, 3 months, or 1 year, etc.

Step 001 b: and extracting charging pile fault characteristic data corresponding to multiple fault types of the charging pile from the historical operating data, and establishing a charging pile fault index system according to the dependency relationship between the charging pile fault characteristic data corresponding to the fault types.

In a specific example, the fault state of the charging pile may at least include: smoke alarm fault, ac circuit breaker fault, dc bus output fuse fault, charger fan fault, arrester fault, emergency stop button action fault, abnormal opening fault of cabinet door, dc bus output contactor fault, discharge resistance fault, electronic lock fault, insulation monitoring fault, battery reverse connection fault, control guidance fault during charging, non-homing fault of charging gun, charging pile over-temperature fault, charging gun over-temperature fault, BMS communication fault, input voltage overvoltage fault, input voltage undervoltage fault, output voltage overvoltage fault, output voltage undervoltage fault, output overcurrent fault, output short circuit fault, TCU communication fault, charging module communication alarm, charging module ac input alarm overvoltage, charging module ac input undervoltage alarm, charging module ac input phase failure alarm, etc, The fault detection method comprises the following steps of charging module direct current output short circuit fault, charging module direct current output overcurrent fault, charging module direct current output overvoltage fault, charging module direct current output undervoltage fault, charging module over-temperature fault and charging module fan fault.

Step 001 c: and preprocessing the charging pile fault characteristic data corresponding to the charging pile fault index body.

Step 001 d: and generating a training sample set according to the preprocessed charging pile fault characteristic data.

In order to further improve the accuracy and reliability of the bayesian network model building, in an embodiment of the present application, a specific implementation manner of step 001c in the charging pile fault cause diagnosis method is further provided, referring to fig. 6, where the step 001c specifically includes the following steps:

step 001 c-1: and carrying out data cleaning and/or attribute stipulation processing on the charging pile fault characteristic data corresponding to the charging pile fault index system.

Step 001 c-2: and carrying out data transformation on the charging pile fault characteristic data subjected to data cleaning and/or attribute specification processing.

Based on the above content, the charging pile fault cause diagnosis method of the present application is described in detail through the following offline model construction scenario and online model prediction scenario, and the specific content is as follows:

model training scenario

S1-feature data acquisition:

and acquiring charging pile fault characteristic data corresponding to multiple fault types of the charging pile, and establishing a charging pile fault index system according to the dependency relationship among the various charging pile fault characteristic data. It can be understood that the establishing of the charging pile fault index system may specifically be selectively extracting feature data of different fault types of the charging pile from a preset service system, and establishing the charging pile fault index system according to a dependency relationship among the fault types.

It can be understood that the data sources of the charging pile fault feature data at least include: telemetry data, module data, transaction data, and the like. An example of the charging pile fault indicator system is shown in fig. 7 and the following table 1:

TABLE 1

Based on above-mentioned table 1, fill electric pile fault index system and can include 4 one-level indexes at least, specifically do: status data a0, electrical data B0, switching value data C0, and environmental data D0.

The state data a0 further includes a secondary index, which may be: the control method comprises the following steps of A1, A2 of a vehicle, A3 of a direct current output contactor, A4 of an electronic lock of a charging interface and the like; the electrical data B0 further includes two-level indicators, which may be: an input current B1, an input voltage B2, an output current B3, an output voltage B4, an insulating state B5, a rated voltage B6, a rated current B7, and the like; the switching value state data C0 further includes two-level indicators, which may be specifically: an emergency stop C1, a door control C2, an output contactor C3, a discharge contactor C4, an auxiliary contactor C5, an electronic lock feedback point C6 and the like; the environment data D0 further includes secondary indicators, which may be specifically: the charging module temperature D1, the charging gun temperature D2, the internal temperature D3 of the charger, the internal humidity D4 of the charger and the like.

S2-data preprocessing:

and preprocessing the fault characteristic data of the charging pile. It is understood that the preprocessing may include at least data cleaning, attribute specification, and data transformation. It can be understood that the data cleansing method at least includes: abnormal value identification, missing value interpolation, data de-duplication and other processing means. Specifically, the method comprises the following steps:

(1) data cleaning:

and identifying abnormal values of the charging pile fault characteristic data, deleting the identified abnormal values from the charging pile fault characteristic data, identifying missing of the charging pile fault characteristic data, interpolating the missing values to corresponding positions in the charging pile fault characteristic data, identifying repeated data of the charging pile fault characteristic, and deleting the identified repeated data from the charging pile fault characteristic data.

(2) And (3) attribute specification:

and calculating information entropies respectively corresponding to various fault types in the charging pile fault characteristic data, and deleting data corresponding to the fault type attribute with the information entropy of 0 from the charging pile fault characteristic data. The purpose of the attribute specification is to find the smallest subset of attributes and to ensure that the probability distribution of the new data subset is as close as possible to the probability distribution of the original data set.

For example, if it is calculated that the information entropy of whether the vehicle a2, the dc output contactor state A3, the charging interface electronic lock state a4, the emergency stop C1, and the output contactor C3 in table 1 are connected is 0, the data corresponding to the fault types are deleted from the charging pile fault feature data.

(3) Data transformation:

and carrying out data transformation on the charging pile fault characteristic data subjected to the data cleaning and the attribute protocol processing, and specifically carrying out numerical processing by applying a discretization processing mode or an One-Hot-code-Encoder mode. The one-hot encoding method uses an N-bit status register to encode N states, each state having its own independent register bit and only one of which is active at any one time.

For example, the data corresponding to the operating state a1, the input voltage B2, the input current B1, the output voltage B4, the output current B3, the insulation state B5, the rated voltage B6, and the rated current B7 in the charging pile fault characteristic data shown in table 1 may be discretized, and the fault types corresponding to the output overvoltage, the output overcurrent, the insulation fault, the module warning, the charger communication abnormality, the battery pack temperature overhigh data, and the like in the charging pile fault characteristic data may be numerically processed using the unique thermal code.

S3-training sample set generation:

and generating a training sample set for training the Bayesian network according to the charging pile fault characteristic data subjected to data cleaning, attribute stipulation and data transformation.

S4-Bayesian network topology establishment:

and learning the Bayesian network topology structure based on the scoring and searching algorithm, and finding the Bayesian network structure with the best matching degree with the sample data set, namely, the Bayesian network topology structure learning aims to find the Bayesian network structure with the best matching degree with the sample data set. Learning of bayesian network structures includes scoring and search based algorithms, constraint based algorithms, and hybrid algorithms. The algorithm based on scoring and searching adopts a certain scoring standard to judge the matching degree of the independent and dependent relations and data reflected by the network structure, and then a network model with the highest score is searched by a certain searching algorithm. The algorithm process is simple and standard, and global optimization can be achieved through tabu search, so that the algorithm is selected for learning the topological structure of the Bayesian network.

Two main problems to be solved for establishing the bayesian network structure are respectively selection of a scoring function and selection of a searching method, which are specifically as follows:

(1) determining a scoring function:

and determining a scoring function corresponding to the Bayesian network according to the training sample set.

The commonly used scoring function is based on information theoretic criteria, which equates the learning problem to a data compression task, the learning objective being to find a model that describes the training data in the shortest code length, which in this case includes the byte length needed to describe the model itself and the byte length needed to describe the data using the model. For Bayesian network learning, the model is a Bayesian network, and each Bayesian network describes a probability distribution on training data, and a set of coding mechanisms can make the frequently-occurring samples shorter. Therefore, the bayesian network with the shortest overall coding Length (including the Description network and the coded data) should be selected, which is the Minimum Description Length (MDL) criterion.

Given training set D ═ x₁,x₂...,x_mA bayesian network B ═ B<G,θ>The scoring function on D can be written as:

s(B|D)＝f(θ)|B|-LL(B|D) (1)

in the formula (1), | B | is the number of parameters of the bayesian network; f (theta) represents the number of bytes required to describe each parameter theta; therein

Is the log-likelihood of the bayesian network B. Obviously, the first term f (θ) | B | of equation (1) is the number of bytes required to compute the coded bayesian network, and the second term LL (B | D) is the probability distribution P corresponding to B_BHow many bytes are needed to describe D. The learning task then translates into an optimization task, i.e. finding a bayesian network B that minimizes the scoring function s (B | D).

If f (θ) is 1, that is, each parameter is described by 1 byte, the akaike information criterion scoring function AIC (B | D) is obtained as follows:

AIC(B|D)＝|B|-LL(B|D)

if it is

I.e. for each parameter

Byte description, the Bayesian Information rule BIC (Bayesian Information criteria) scoring function BIC (B | D) is obtained as follows:

obviously, if f (θ) is 0, i.e. the length of encoding the network is not calculated, the scoring function degenerates to negative log-likelihood and, correspondingly, the learning task degenerates to maximum likelihood estimation.

(2) And (3) searching algorithm:

with the scoring function determined, the learning problem of the bayesian network becomes a search problem. The search algorithm is to search for a bayesian network structure with the highest score under a certain scoring function. As the number of variables increases, the search space will increase at an exponential level with the number of nodes, finding the optimal model is the existence of a Non-Deterministic problem NP (Non-Deterministic polymeric Problems) that the Polynomial algorithm can solve. Heuristic search such as greedy search, simulated annealing, optimal first search and the like is commonly adopted at present.

The most common search method is to continuously change the directed edge in the network structure and judge the influence of each change on the score. If a directed edge exists between the two variables, the changing direction can be deleting the directed edge or reversing the directed edge; if there is no directed edge between two variables, the change method may be to add a directed edge in any direction, but when changing, a directed loop cannot be generated.

The simplest Search algorithm is a Greedy Search (Greedy Search). Let E denote the set of all candidate edges that may be added to the network structure, and Δ (E) denotes the variation of the scoring function after the edge E in E is added to the network structure. The search algorithm can be described as:

1) selecting an initial network structure;

2) selecting an edge E in the candidate edge set, so that delta (E) > delta (E '), wherein E' is any edge except for E in E, and delta (E) >0, stopping if an edge which meets the condition cannot be found, and turning to 3 if the edge does not meet the condition;

3) adding E to the network structure, deleting the edge from the candidate set E, and turning to 2);

in the algorithm, the initial network structure may be an empty network, a random network, or a priori network built using empirical knowledge. The greedy search strategy is a local search strategy and has the problem of trapping in local extrema and saddle points. One solution is to randomly change the structure of the network when a local extremum or saddle point is trapped, possibly jumping out of the saddle point or jumping from one local extremum region to another.

(3) Determining the topological structure of the Bayesian network based on a scoring function and a search algorithm:

an example of a bayesian network topology (directed acyclic graph) DAG learned based on scoring and search algorithms is shown in fig. 8, and the bayesian network topology interpretation is shown in the pseudo-code of table 2:

TABLE 2

S5-Bayesian network parameter learning:

the Bayesian network parameters are learned based on maximum likelihood estimation, i.e. the conditional probability at each node is determined given the Bayesian network topology.

The goal of Bayesian network parameter learning is to give a network topology structure G and a training sample set D, and determine the conditional probability density of each node of the Bayesian network model by using prior knowledge, and record the conditional probability density as: p (θ | D, G). Common parameter learning methods include maximum likelihood estimation algorithms and bayesian estimation algorithms. The maximum likelihood estimation algorithm is suitable for large amount of data, and the estimated parameters can better reflect the actual situation. Thus, in one embodiment of the present application, maximum likelihood estimation is selected as the learning of the Bayesian network parameters.

(1) Maximum likelihood estimation:

in the maximum likelihood estimation process, when the parameter is the value of a given father node set through calculation, the occurrence frequency of different values of the node is taken as the conditional probability parameter of the node. The basic principle of maximum likelihood estimation is to try to find the parameters that maximize the likelihood function. The maximum likelihood estimation is to use the parameter when the likelihood function takes the maximum value as the estimation value, and the likelihood function can be expressed as:

because of the multiplication-by-multiplication operation, the calculation of taking the logarithm of the likelihood function is usually simpler, namely, the logarithm likelihood function, and the maximum likelihood estimation problem can be written as:

this is a function of theta and solving this optimization problem usually takes the derivative of theta to obtain the extreme point where the derivative is 0. When the function obtains the maximum value, the value corresponding to theta is the model parameter estimated by the user.

(2) Conditional probability table of network node CPT:

under the condition of giving a network topological structure G and a training sample set D, a conditional probability table CPT of each node of the network obtained by learning by using maximum likelihood estimation is as follows:

1) the conditional probability table CPT of the input voltage is shown in table 3:

TABLE 3

2) The conditional probability table CPT of the input current is shown in table 4:

TABLE 4

[30.7，31]	(31，91]
		0.93430657	0.06569343

3) The conditional probability table CPT of the output voltages is shown in tables 5 to 7:

see table 5 for operating state — charging:

TABLE 5

See table 6 for operating state stand-by:

TABLE 6

See table 7 for operating state — stop charging:

TABLE 7

4) The conditional probability table CPT of the output current is shown in table 8:

TABLE 8

5) The conditional probability table CPT of the running state is shown in table 9:

TABLE 9

6) The conditional probability table CPT of the insulating state is shown in table 10:

watch 10

7) The condition probability table CPT of rated voltage is shown in table 11:

TABLE 11

8) The conditional probability table CPT of rated current is shown in table 12:

TABLE 12

9) The conditional probability table CPT of the output overvoltage is shown in table 13:

watch 13

10) The conditional probability table CPT of output overcurrent is shown in table 14:

TABLE 14

11) The condition probability table CPT of insulation fault is shown in table 15:

watch 15

12) The conditional probability table CPT of the module warning is shown in tables 16 and 17:

the communication abnormality of the charger is 0, see table 16:

TABLE 16

The communication abnormality of the charger is 1, see table 17:

TABLE 17

13) The condition probability table CPT of abnormal communication of the charger is shown in table 18:

watch 18

14) The conditional probability table CPT of the battery pack over-temperature fault is shown in table 19:

watch 19

(II) model prediction scenarios

S1: and acquiring the fault type of the target charging pile when the target charging pile breaks down.

S2: and preprocessing the fault type data of the target charging pile, wherein the preprocessing comprises processing modes such as data cleaning, attribute protocol processing, data transformation and the like.

S3: and inputting the preprocessed fault type data serving as a prediction sample into a preset Bayesian network model, and taking the output of the Bayesian network model as a fault cause diagnosis result corresponding to the fault type of the target charging pile. The specific treatment method is as follows:

according to the topological structure of the Bayesian network and the conditional probability table thereof, when a fault occurs, the probability of the values of certain characteristic nodes is calculated, so that the diagnosis result of the fault reason is obtained.

The Bayesian network inference refers to calculating the probability of some node values after evidences are given by using the structure of the Bayesian network and a conditional probability table thereof.

Setting conditional reasoning parameters: the method comprises the steps of obtaining an event characteristic and an event type, wherein the event characteristic and the event type are different, namely when different fault types of a charging pile occur, the probability of each characteristic node is deduced, and therefore a fault cause diagnosis result is obtained.

Under the condition of an output overvoltage fault, the probability of the output voltage being in the (652,684) interval is 0.5350123, and the pseudo code is shown in table 20:

watch 20

Under the condition that the output overcurrent fault occurs, the probability that the output current is in the interval (85.4, 94.2) is 0.5899238, and the pseudo code is shown in table 21:

TABLE 21

Under the condition of the battery pack over-temperature fault, the probability of the output voltage being [0,652] and the output current being [0,85.4] is 0.5917889, and the pseudo code is shown in table 22:

TABLE 22

Under the condition of an insulation fault, the probability of the insulation state "abnormal" is 1, and the pseudo code is shown in table 23:

TABLE 23

Under the condition of module warning, the probability of the output current in the (85.4, 94.2) interval is 1, and the pseudo code is shown in table 24:

watch 24

Under the condition of abnormal communication of the charger, the output current is [0,85.4], the output voltage is (652,684], the probability of the operation state being "charging" is 0.3509587, and the pseudo code is shown in table 25:

TABLE 25

S4: and outputting a fault reason diagnosis result corresponding to the fault type of the target charging pile.

According to the charging pile fault reason diagnosis method, automatic diagnosis of the fault reason of the charging pile can be achieved, the diagnosis process is efficient, the diagnosis result is accurate, the fault reason can be quickly confirmed when the charging pile breaks down, and the charging pile can be timely and pertinently maintained.

In order to realize automatic diagnosis of a fault cause of a charging pile and make a diagnosis process more efficient and a diagnosis result accurate, an embodiment of the present application provides a specific embodiment of a charging pile fault cause diagnosis device for realizing all contents in the charging pile fault cause diagnosis method, and referring to fig. 9, the charging pile fault cause diagnosis device specifically includes the following contents:

the fault type obtaining module 10 of the target charging pile is used for obtaining the fault type of the target charging pile when the target charging pile breaks down.

And the target fault cause diagnosis module 20 is configured to input the fault type of the target charging pile as a prediction sample into a preset bayesian network model, and use an output of the bayesian network model as a fault cause diagnosis result corresponding to the fault type of the target charging pile, where the bayesian network model includes a topological structure of a bayesian network and a corresponding conditional probability table, and the topological structure of the bayesian network is used to represent a correspondence between each fault type of the charging pile and each fault cause diagnosis result.

The embodiment of the charging pile fault cause diagnosis device provided by the application can be specifically used for executing all processing flows of all embodiments of the charging pile fault cause diagnosis method in the embodiments, and the functions of the charging pile fault cause diagnosis device are not repeated herein, and reference can be made to the detailed description of the method embodiments.

As can be seen from the above description, according to the charging pile fault cause diagnosis device provided in the embodiment of the present application, the fault type of the target charging pile is input as a prediction sample into a preset bayesian network model by the target charging pile fault type obtaining module 10, and the output of the bayesian network model is used as a fault cause diagnosis result corresponding to the fault type of the target charging pile by the target fault cause diagnosis module 20, where the bayesian network model includes a topological structure of a bayesian network and a corresponding conditional probability table, and the topological structure of the bayesian network is used to represent a corresponding relationship between each fault type of the charging pile and each fault cause diagnosis result, so that automatic diagnosis of the fault cause of the charging pile can be achieved, a diagnosis process is efficient, a diagnosis result is accurate, and a cause of a fault occurrence of the charging pile can be quickly determined when the charging pile fails, and then can be in time and have corresponding to keep in repair filling the electric pile, and can effectively improve fortune dimension personnel work efficiency, and alleviate fortune dimension operating pressure to filling the electric pile, and simultaneously, fill electric pile fault reason diagnostic process simply and have the scientific foundation, can provide effectual data support for filling the daily fortune dimension work of electric pile, have very strong scientificity, reliability and maneuverability, can guide the intelligent fortune dimension of filling electric pile effectively, promote the smart level of benefiting of charging facility asset management and operation maintenance work, improve the operational stability and the running life of the facility of charging, it is long when shortening fault handling, improve asset utilization rate and charging service level.

In order to provide a more accurate and targeted bayesian network model to further improve the efficiency of the diagnosis process and the accuracy of the diagnosis result, in an embodiment of the present application, the charging pile fault cause diagnosis apparatus further includes a model building module 00, see fig. 10, where the model building module 00 specifically includes the following contents:

and the training sample set generating module 01 is used for generating a training sample set according to the multiple fault types of the charging pile and the corresponding known fault cause diagnosis results.

And the bayesian network topology structure establishing module 02 is used for applying the training sample set and establishing the topology structure of the bayesian network based on the corresponding scoring function and the search algorithm.

The conditional probability obtaining module 03 is configured to determine a conditional probability at each node in the topology structure of the bayesian network based on a maximum likelihood estimation method, and obtain a conditional probability table of each node.

In order to further improve the accuracy and reliability of the electric pile fault cause diagnosis, a specific implementation manner of a training sample set generating module 01 in the electric pile fault cause diagnosis device is further provided in an embodiment of the present application, referring to fig. 11, where the training sample set generating module 01 specifically includes the following contents:

the historical operating data acquisition unit 01a is used for extracting historical operating data of the plurality of charging piles from at least one of telemetering data, remote signaling data power module monitoring data and transaction data of the power system.

And the charging pile fault index system establishing unit 01b is used for extracting charging pile fault feature data corresponding to multiple fault types of the charging pile from the historical operating data, and establishing a charging pile fault index system according to the dependency relationship between the charging pile fault feature data corresponding to the fault types.

And the data preprocessing unit 01c is used for preprocessing the charging pile fault characteristic data corresponding to the charging pile fault indicator.

And the training sample set generating unit 01d is used for generating a training sample set according to the preprocessed charging pile fault characteristic data.

In order to further improve the accuracy and reliability of the bayesian network model building, an embodiment of the present application further provides a specific implementation manner of a data preprocessing unit 01c in the charging pile fault cause diagnosis apparatus, where the data preprocessing unit 01c is specifically configured to: carrying out data cleaning and/or attribute stipulation processing on charging pile fault characteristic data corresponding to the charging pile fault index system; and carrying out data transformation on the charging pile fault characteristic data subjected to data cleaning and/or attribute specification processing.

According to the charging pile fault reason diagnosis device, automatic diagnosis of the fault reason of the charging pile can be achieved, the diagnosis process is efficient, the diagnosis result is accurate, the reason of the fault can be rapidly confirmed when the charging pile breaks down, and the charging pile can be timely and pertinently maintained.

An embodiment of the present application further provides a specific implementation manner of an electronic device, which is capable of implementing all steps in the charging pile fault cause diagnosis method in the foregoing embodiment, and referring to fig. 12, the electronic device specifically includes the following contents:

a processor (processor)601, a memory (memory)602, a communication Interface (Communications Interface)603, and a bus 604;

the processor 601, the memory 602 and the communication interface 603 complete mutual communication through the bus 604; the communication interface 603 is used for realizing information transmission among a charging pile fault reason diagnosis device, a client terminal, fault monitoring equipment and other participating mechanisms;

the processor 601 is configured to call a computer program in the memory 602, and when the processor executes the computer program, the processor implements all the steps in the charging pile fault cause diagnosis method in the foregoing embodiments, for example, when the processor executes the computer program, the processor implements the following steps:

As can be seen from the above description, according to the electronic device provided by the application, the fault type of the target charging pile is input as a prediction sample into a preset bayesian network model, and the output of the bayesian network model is used as a fault cause diagnosis result corresponding to the fault type of the target charging pile, wherein the bayesian network model includes a topological structure of a bayesian network and a corresponding condition probability table, and the topological structure of the bayesian network is used for representing a corresponding relationship between each fault type of the charging pile and each fault cause diagnosis result, so that automatic diagnosis of the fault cause of the charging pile can be realized, a diagnosis process is efficient, a diagnosis result is accurate, the reason of the fault occurrence can be quickly determined when the charging pile fails, the charging pile can be timely and specifically maintained, and the work efficiency of operation and maintenance personnel can be effectively improved, the operation and maintenance work pressure for the charging pile is reduced, meanwhile, the fault reason diagnosis process of the charging pile is simple and scientific, effective data support can be provided for daily operation and maintenance work of the charging pile, the intelligent operation and maintenance system has strong scientificity, reliability and operability, intelligent operation and maintenance of the charging pile can be effectively guided, the precision level of asset management and operation maintenance work of a charging facility is improved, the operation stability and the operation life of the charging facility are improved, the fault handling time is shortened, and the asset utilization rate and the charging service level are improved.

An embodiment of the present application further provides a computer-readable storage medium capable of implementing all the steps in the charging pile fault cause diagnosis method in the foregoing embodiment, where the computer-readable storage medium stores a computer program, and the computer program, when executed by a processor, implements all the steps in the charging pile fault cause diagnosis method in the foregoing embodiment, for example, when the processor executes the computer program, the processor implements the following steps:

According to the computer-readable storage medium, automatic diagnosis of the fault reasons of the charging pile can be achieved, the diagnosis process is efficient, the diagnosis result is accurate, the fault reasons can be quickly determined when the charging pile breaks down, and the charging pile can be timely and pertinently maintained.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the hardware + program class embodiment, since it is substantially similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment. Although embodiments of the present description provide method steps as described in embodiments or flowcharts, more or fewer steps may be included based on conventional or non-inventive means. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an actual apparatus or end product executes, it may execute sequentially or in parallel (e.g., parallel processors or multi-threaded environments, or even distributed data processing environments) according to the method shown in the embodiment or the figures. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, article, or apparatus that comprises the recited elements is not excluded. For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, in implementing the embodiments of the present description, the functions of each module may be implemented in one or more software and/or hardware, or a module implementing the same function may be implemented by a combination of multiple sub-modules or sub-units, and the like. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form. The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein. The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment. In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of an embodiment of the specification. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction. The above description is only an example of the embodiments of the present disclosure, and is not intended to limit the embodiments of the present disclosure. Various modifications and variations to the embodiments described herein will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present specification should be included in the scope of the claims of the embodiments of the present specification.

Claims

1. A charging pile fault cause diagnosis method is characterized by comprising the following steps:

2. The charging pile fault cause diagnosis method according to claim 1, further comprising:

3. The charging pile fault cause diagnosis method according to claim 2, wherein the generating of the training sample set according to the plurality of fault types of the charging pile and the known fault cause diagnosis results corresponding thereto comprises:

preprocessing charging pile fault characteristic data corresponding to the charging pile fault index system;

4. The charging pile fault cause diagnosis method according to claim 3, wherein the preprocessing of the charging pile fault feature data corresponding to the charging pile fault index system comprises:

5. A charging pile fault cause diagnosis device is characterized by comprising:

6. The charging pile fault cause diagnosis device according to claim 5, further comprising:

7. The charging pile fault cause diagnosis device according to claim 6, wherein the training sample set generation module includes:

the data preprocessing unit is used for preprocessing charging pile fault characteristic data corresponding to the charging pile fault index system;

8. The charging pile fault cause diagnosis device according to claim 7, wherein the data preprocessing unit is specifically configured to:

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the charging pile fault cause diagnosis method according to any one of claims 1 to 4 when executing the program.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the charging pile fault cause diagnosis method according to any one of claims 1 to 4.