Electrochemical energy storage power station fault detection method, device and equipment and storage medium

Abstract

The invention provides an electrochemical energy storage power station fault detection method, device and equipment and a storage medium, and the method comprises the steps: obtaining the operation data of an electrochemical energy storage power station, carrying out the anomaly detection of the operation data, detecting the abnormal operation data, carrying out the fault detection of the abnormal operation data through a pre-trained fault detection model, and obtaining a fault detection result. And determining fault information corresponding to the abnormal operation data, generating fault prompt information according to the fault type, generating a maintenance guidance course according to the fault type and the fault reason, sending the fault prompt information and the maintenance guidance course to operation and maintenance personnel, and prompting the operation and maintenance personnel to perform field maintenance according to the maintenance guidance course. According to the embodiment of the invention, through automatic data preprocessing and intelligent monitoring, the dependence on manual operation is reduced, automatic detection, diagnosis, response and maintenance guidance of faults are realized, and the effective detection and maintenance efficiency of the electrochemical energy storage power station is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electrochemical energy storage, and in particular to a method, device, equipment and storage medium for detecting faults in an electrochemical energy storage power station. Background Art

[0002] With the rapid development of renewable energy, electrochemical energy storage power stations, as key energy regulation facilities, are crucial to the stable operation of power systems. Existing electrochemical energy storage power stations mainly rely on traditional monitoring systems and manual inspections. Specifically, the collected power station equipment operation data is transmitted to the central monitoring room, and the operation and maintenance personnel view the data in the monitoring room for monitoring. The operation and maintenance personnel judge the problem of the equipment operation data based on experience and take corresponding measures. According to the equipment manual or maintenance guide, the operation and maintenance personnel repair the faulty equipment.

[0003] However, this type of monitoring system mostly relies on manual judgment and lacks automated fault detection and diagnosis capabilities. Due to reliance on manual inspections and responses, the response time for fault detection and processing is long, which may cause the problem to worsen. Differences in experience among operation and maintenance personnel may lead to insufficient accuracy in fault diagnosis, affecting maintenance efficiency and quality. The transfer of maintenance knowledge and experience mainly relies on documents and verbal guidance, which is inefficient and difficult to standardize. A large amount of operating data has not been effectively analyzed and utilized, and cannot provide support for fault analysis and maintenance decisions, resulting in frequent equipment failures and high maintenance costs, which seriously affect the effectiveness of electrochemical energy storage power stations. Summary of the invention

[0004] In view of this, the present invention aims to propose a method, device, equipment and storage medium for electrochemical energy storage power station fault detection to solve the problem that the current power station monitoring method that relies on manual judgment, manual inspection and response leads to insufficient accuracy of power station fault diagnosis, affecting the maintenance efficiency and quality of the power station.

[0005] According to a first aspect of the present invention, a method for detecting a fault in an electrochemical energy storage power station is provided, the method comprising:

[0006] Obtaining operation data of electrochemical energy storage power stations;

[0007] Performing anomaly detection on the operation data to detect abnormal operation data;

[0008] Using a pre-trained fault detection model to perform fault detection on the abnormal operation data, and determining fault information corresponding to the abnormal operation data; wherein the fault information includes a fault type and a fault cause;

[0009] Generate fault prompt information according to the fault type, and generate a maintenance guidance tutorial according to the fault type and the fault cause;

[0010] The fault prompt information and the maintenance guide are sent to the operation and maintenance personnel, prompting the operation and maintenance personnel to perform on-site maintenance according to the maintenance guide.

[0011] Optionally, the obtaining of operation data of the electrochemical energy storage power station includes:

[0012] Collect the original data of the electrochemical energy storage station at the current moment;

[0013] Preprocessing the raw data to obtain preprocessed operating data; wherein the preprocessing includes at least one of cleaning, standardization and feature extraction;

[0014] Optionally, the performing abnormality detection on the operating data to detect abnormal operating data includes:

[0015] Performing abnormality detection on the operating data using a preset operating standard to detect whether the operating data exceeds the preset operating standard;

[0016] The operating data exceeding the preset operating standard is determined as abnormal operating data.

[0017] Optionally, the using of a pre-trained fault detection model to perform fault detection on the abnormal operation data to determine fault information corresponding to the abnormal operation data, wherein the fault information includes a fault type and a fault cause, comprises:

[0018] Using a pre-trained fault detection model to perform fault detection on the abnormal operation data, and outputting the fault type corresponding to the abnormal operation data;

[0019] The fault cause corresponding to the abnormal operation data is determined according to the fault type and pre-stored historical fault data.

[0020] Optionally, before the using of a pre-trained fault detection model to perform fault detection on the abnormal operation data and outputting a fault type corresponding to the abnormal operation data, the method further includes:

[0021] Obtain historical fault data pre-stored in the electrochemical energy storage station;

[0022] The historical fault data is used to perform deep learning on the machine learning model to obtain a fault detection model.

[0023] Optionally, after the pre-trained fault detection model is used to perform fault detection on the abnormal operation data and the fault information corresponding to the abnormal operation data is determined, the method further includes:

[0024] Update pre-stored historical fault data according to the fault information corresponding to the abnormal operation data;

[0025] The fault detection model is iteratively trained using updated historical fault data to obtain an optimized fault detection model.

[0026] Optionally, generating fault prompt information according to the fault type, and generating a maintenance guidance tutorial according to the fault type and the fault cause, includes:

[0027] Determine the fault location according to the fault type and generate fault prompt information; wherein the fault prompt information is used to prompt the operation and maintenance personnel to perform on-site maintenance;

[0028] According to the fault type and the fault cause, a pre-created maintenance knowledge base is searched to obtain maintenance methods and maintenance steps;

[0029] The maintenance method and the maintenance steps are used to generate a maintenance instruction tutorial; wherein the maintenance instruction tutorial may be in the form of any one of text, pictures and videos.

[0030] Optionally, if the maintenance guidance tutorial is in the form of a video, the use of the maintenance method and the maintenance steps to generate the maintenance guidance tutorial includes:

[0031] Filter out video materials according to the maintenance method and the maintenance steps;

[0032] The video material is edited using a pre-generated video script to generate a maintenance instruction video.

[0033] Optionally, before querying a pre-created maintenance knowledge base according to the fault type and the fault cause to obtain a maintenance method and maintenance steps, the method further includes:

[0034] Pre-build maintenance knowledge base;

[0035] The equipment information, fault cases of the electrochemical energy storage power station, and the maintenance methods and maintenance steps corresponding to the fault cases are stored in the maintenance knowledge base.

[0036] Optionally, after obtaining the operation data of the electrochemical energy storage power station, before sending the fault prompt information and the maintenance guide to the operation and maintenance personnel to prompt the operation and maintenance personnel to perform on-site maintenance according to the maintenance guide, the method further includes:

[0037] According to the operation data at the previous moment and the operation data at the current moment, the fault prediction at the next moment is performed to obtain the fault prediction result;

[0038] According to the fault prediction result, fault prompt information and maintenance guidance tutorial under the fault prediction are generated.

[0039] Optionally, performing fault prediction at the next moment based on the historical fault data at the previous moment and the operation data at the current moment to obtain a fault prediction result includes:

[0040] Use the pre-trained fault prediction model to determine the data change trend between the historical fault data at the previous moment and the operating data at the current moment;

[0041] Fault prediction is performed on the data change trend to determine the probability of fault occurrence at the next moment, and the fault prediction result of the electrochemical energy storage power station at the next moment is obtained.

[0042] Optionally, the performing abnormality detection on the operating data, after detecting abnormal operating data, further comprises:

[0043] Displaying operation data to operation and maintenance personnel through a pre-created multimodal interface, and receiving multimodal input from the operation and maintenance personnel;

[0044] In response to the fault description content input by the operation and maintenance personnel, a pre-trained fault detection model is used to perform fault detection on the fault description information to determine the fault information corresponding to the fault description content.

[0045] According to a second aspect of the present invention, there is provided a fault detection device for an electrochemical energy storage power station, the device comprising:

[0046] A data acquisition module is used to acquire the operation data of the electrochemical energy storage power station;

[0047] A data processing module, used for performing anomaly detection on the operation data to detect abnormal operation data;

[0048] A fault detection module, used to perform fault detection on the abnormal operation data using a pre-trained fault detection model, and determine fault information corresponding to the abnormal operation data; wherein the fault information includes a fault type and a fault cause;

[0049] An information generation module is used to generate fault prompt information according to the fault type, and to generate a maintenance guidance tutorial according to the fault type and fault cause;

[0050] The maintenance prompt module is used to send the fault prompt information and the maintenance guidance tutorial to the operation and maintenance personnel, prompting the operation and maintenance personnel to perform on-site maintenance according to the maintenance guidance tutorial.

[0051] According to another aspect of the present invention, there is also provided an electronic device, comprising:

[0052] processor;

[0053] a memory for storing instructions executable by the processor;

[0054] Wherein, the processor is configured to execute the instructions to implement the electrochemical energy storage power station fault detection method as described above.

[0055] According to another aspect of the present invention, a readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the electrochemical energy storage power station fault detection method as described above are implemented.

[0056] The electrochemical energy storage power station fault detection method provided by the embodiment of the present invention obtains the operation data of the electrochemical energy storage power station, performs anomaly detection on the operation data, detects abnormal operation data, uses a pre-trained fault detection model to perform fault detection on the abnormal operation data, determines the fault information corresponding to the abnormal operation data, generates fault prompt information according to the fault type, and generates a maintenance guide tutorial according to the fault type and the fault cause, sends the fault prompt information and the maintenance guide tutorial to the operation and maintenance personnel, and prompts the operation and maintenance personnel to perform on-site maintenance according to the maintenance guide tutorial. The embodiment of the present invention conducts in-depth analysis of a large amount of operation data, provides data support for fault prediction and maintenance decision-making, realizes the maximum utilization of data, automatically identifies anomalies in the power station operation data, realizes fault detection and accurate diagnosis, reduces dependence on manual operation through automated data preprocessing and intelligent monitoring, improves operation and maintenance efficiency and response speed, can automatically trigger maintenance processes and response measures according to fault information, ensures that faults can be handled promptly and effectively, and the maintenance guide tutorial can be quickly and standardizedly delivered to the operation and maintenance personnel, realizes automatic detection, diagnosis, response and maintenance guidance of faults, and further improves the effective detection and maintenance efficiency of electrochemical energy storage power stations.

[0057] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0059] Figure 1 It is a flowchart of the steps of a method for detecting a fault in an electrochemical energy storage power station provided by an embodiment of the present invention;

[0060] Figure 2 yes Figure 1A flowchart of step 101 in the electrochemical energy storage power station fault detection method provided by an embodiment of the present invention;

[0061] Figure 3 yes Figure 1 A flowchart of step 102 in the electrochemical energy storage power station fault detection method provided in an embodiment of the present invention;

[0062] Figure 4 yes Figure 1 A flowchart of step 103 in the electrochemical energy storage power station fault detection method provided by an embodiment of the present invention;

[0063] Figure 5 yes Figure 1 A flowchart of step 104 in the electrochemical energy storage power station fault detection method provided by an embodiment of the present invention;

[0064] Figure 6 is a flowchart of another electrochemical energy storage power station fault detection method provided by an embodiment of the present invention;

[0065] Figure 7 is a schematic diagram of a scenario of a method for detecting a fault in an electrochemical energy storage power station provided by an embodiment of the present invention;

[0066] Figure 8 It is a data transmission schematic diagram of the electrochemical energy storage power station fault detection method provided by an embodiment of the present invention;

[0067] Fig. 9 It is a functional diagram of the interface of the electrochemical energy storage power station fault detection method provided by an embodiment of the present invention;

[0068] Fig.10 It is a structural schematic diagram of a fault detection device for an electrochemical energy storage power station provided by an embodiment of the present invention;

[0069] Fig.11 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0070] To make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. However, it will be appreciated by those skilled in the art that in the embodiments of the present invention, many technical details are proposed in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed in the present application can be implemented. The division of the following embodiments is for the convenience of description, and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined and referenced with each other without contradiction.

[0071] Most existing monitoring systems rely on manual judgment and lack automated fault detection and diagnosis capabilities. They rely on manual inspections and responses, which results in long response times for fault detection and processing, and in severe cases, worsens the fault problem. Secondly, differences in experience among operation and maintenance personnel lead to insufficient accuracy in fault diagnosis, affecting maintenance efficiency and quality. The transfer of maintenance knowledge and experience mainly relies on documents and verbal guidance, which is inefficient and difficult to standardize. There is a lack of preventive maintenance, and equipment failures occur frequently. Operation and maintenance personnel are unable to prepare in advance, resulting in high maintenance costs. A large amount of operating data has not been effectively analyzed and utilized, and cannot provide support for fault prediction and maintenance decisions. These problems limit the operation and maintenance management level of electrochemical energy storage power stations.

[0072] In view of this, the embodiments of the present disclosure provide a method, device, equipment and storage medium for detecting faults in an electrochemical energy storage power station.

[0073] Reference Figure 1 , shows a flowchart of the steps of the electrochemical energy storage power station fault detection method provided by an embodiment of the present invention, the method may include:

[0074] Step 101, obtaining operation data of an electrochemical energy storage power station.

[0075] In the embodiment of the present invention, referring to Figure 7 , showing a scenario schematic diagram of the electrochemical energy storage power station fault detection method provided by an embodiment of the present invention, by installing high-precision sensors and cameras in the electrochemical energy storage power station, using high-precision sensors and / or cameras to collect the on-site operating status and operating video data of the power station in real time, etc., because the collected raw data may contain a large amount of useless information, the raw data can be pre-processed by cleaning, standardization and feature extraction to obtain the operating data of the electrochemical energy storage power station, and the operating data is used to perform effective fault detection and analysis on the electrochemical energy storage power station.

[0076] It should be noted that an electrochemical energy storage power station is a facility that uses electrochemical reactions to store and release electrical energy. It achieves the storage and dispatch of electrical energy by converting electrical energy into chemical energy and storing it in batteries, and converting chemical energy back into electrical energy when needed. The electrochemical energy storage power station specifically includes energy storage battery systems, battery management systems, energy management systems, power conversion systems and other equipment, among which the energy storage battery system is the core of the electrochemical energy storage power station and is used for the storage and release of electrical energy; the battery management system is used to monitor and manage the status of the battery to ensure the safe operation and efficient use of the battery; the energy management system is used to coordinate and manage the operation of the entire power station; the power conversion system is used to convert the DC power of the battery into AC power, or to convert AC power into DC power to meet the needs of the power grid. In this embodiment, the operating data of the electrochemical energy storage power station includes equipment images and equipment sounds. The equipment images may include images obtained by collecting the entire equipment, key components of the equipment, operating parameters and / or operation panels, etc. The equipment sounds are obtained by collecting the sounds emitted by the equipment, but are not limited to this.

[0077] The executor of this embodiment is an integrated AIGC multimodal intelligent operation and maintenance system. AIGC integrates advanced artificial intelligence technology to achieve real-time monitoring, fault detection and diagnosis of power station equipment, improve the operation and maintenance efficiency and safety of electrochemical energy storage power stations, and use advanced AI technology (such as machine learning, natural language processing, computer vision, augmented reality, etc.) combined with multimodal data (such as sensor data, video data, text data, etc.) to achieve real-time monitoring, fault detection and maintenance guidance of electrochemical energy storage power station equipment.

[0078] Step 102: Perform anomaly detection on the operation data to detect abnormal operation data.

[0079] In an embodiment of the present invention, the operating data is compared with the corresponding device threshold in the preset operating standard to determine whether it exceeds the standard, and the operating data exceeding the preset operating standard is marked as abnormal operating data. The abnormal operating data can also be marked with abnormality according to the degree of abnormality of the abnormal operating data, and the determined abnormal operating data is stored.

[0080] Step 103, using a pre-trained fault detection model to perform fault detection on the abnormal operation data, and determining fault information corresponding to the abnormal operation data; wherein the fault information includes the fault type and the fault cause.

[0081] In an embodiment of the present invention, a pre-trained fault detection model is used to perform fault detection on abnormal operation data, and the abnormal operation data of the power station is input into the pre-trained fault detection model, that is, the abnormal operation data is input into the fault detection model, and the fault detection model infers the abnormal operation data and outputs fault information corresponding to the abnormal operation data, and the fault information includes the fault type and the fault cause.

[0082] Specifically, the machine learning model is used to analyze historical fault data, analyze the correlation between fault type and fault cause, compare and match the fault type corresponding to the abnormal operation data with the historical fault data, match similar fault cases, and determine the cause of the fault.

[0083] Step 104, generating fault prompt information according to the fault type, and generating a maintenance guidance tutorial according to the fault type and the fault cause.

[0084] Specifically, fault prompt information is generated according to the fault type, and a maintenance guide is generated according to the fault type and the fault cause. The fault location can be determined according to the fault type in the fault information, and fault prompt information is generated. The fault prompt information is used to prompt the operation and maintenance personnel to perform on-site maintenance. According to the fault type and the fault cause, a pre-created maintenance knowledge base is queried to obtain the maintenance method and maintenance steps, and the maintenance method and maintenance steps are used to generate a maintenance guide; wherein the maintenance guide includes any one of text, pictures and videos

[0085] It should be noted that the maintenance knowledge base includes equipment information, fault cases, maintenance methods, maintenance steps, etc. The maintenance knowledge base adopts structured storage to facilitate quick query and analysis. According to the type of fault, the corresponding maintenance methods and steps in the knowledge base are queried. According to the cause of the fault, the maintenance methods and steps are further refined, and the maintenance methods and maintenance steps are used to generate maintenance guidance tutorials. The maintenance guidance tutorials include any one of text, pictures and videos, which will not be repeated here.

[0086] Step 105: Send the fault prompt information and the maintenance guide to the operation and maintenance personnel, prompting the operation and maintenance personnel to perform on-site maintenance according to the maintenance guide.

[0087] Specifically, the system automatically sends notifications to operation and maintenance personnel and related manufacturers, and sends fault prompt information and maintenance instructions to operation and maintenance personnel. Operation and maintenance personnel can use AR devices to view the maintenance instructions and perform on-site repairs.

[0088] The electrochemical energy storage power station fault detection method provided by the embodiment of the present invention obtains the operation data of the electrochemical energy storage power station, performs anomaly detection on the operation data, detects abnormal operation data, uses a pre-trained fault detection model to perform fault detection on the abnormal operation data, determines the fault information corresponding to the abnormal operation data, generates fault prompt information according to the fault type, and generates a maintenance guide tutorial according to the fault type and the fault cause, sends the fault prompt information and the maintenance guide tutorial to the operation and maintenance personnel, and prompts the operation and maintenance personnel to perform on-site maintenance according to the maintenance guide tutorial. The embodiment of the present invention conducts in-depth analysis of a large amount of operation data, provides data support for fault prediction and maintenance decision-making, realizes the maximum utilization of data, automatically identifies anomalies in the power station operation data, realizes fault detection and accurate diagnosis, reduces dependence on manual operation through automated data preprocessing and intelligent monitoring, improves operation and maintenance efficiency and response speed, can automatically trigger maintenance processes and response measures according to fault information, ensures that faults can be handled promptly and effectively, and the maintenance guide tutorial can be quickly and standardizedly delivered to the operation and maintenance personnel, realizes automatic detection, diagnosis, response and maintenance guidance of faults, and further improves the effective detection and maintenance efficiency of electrochemical energy storage power stations.

[0089] Further, see Figure 2 , showing Figure 1 A flowchart of step 101 in a method for detecting a fault in an electrochemical energy storage power station is provided. The method is substantially the same as the method for detecting a fault in an electrochemical energy storage power station provided in the first embodiment of the present invention. Step 101 may include:

[0090] Step 1011, collecting the original data of the electrochemical energy storage station at the current moment;

[0091] Step 1012, preprocessing the original data to obtain preprocessed operating data; wherein the preprocessing includes at least one of cleaning, standardization and feature extraction.

[0092] It should be noted that, in the embodiments of the present invention, Figure 8 , shows a schematic diagram of data transmission of the electrochemical energy storage station in this embodiment, using data acquisition equipment to collect the original data of the electrochemical energy storage station at the current moment, wherein the data acquisition equipment includes high-precision sensors and cameras, sensors are installed on key equipment of the energy storage power station, such as battery packs, PCS (power conversion system), cooling system, etc., for collecting operating data such as temperature, voltage, current, pressure, etc., cameras are installed around the equipment to monitor the operating status of the equipment in real time and capture abnormal phenomena (such as equipment overheating, smoke, etc.)

[0093] Specifically, the raw data of high-precision sensors and cameras are transmitted to the intelligent monitoring system in real time through wired or wireless networks, and various types of collected data, such as sensor data, video data, and environmental data, are used to ensure the comprehensiveness and diversity of the data. For key parameters (such as battery temperature and voltage), high-frequency collection (such as once per second) is used to ensure the real-time and accuracy of the data; for non-critical parameters (such as ambient temperature), low-frequency collection (such as once per minute) is used to reduce the amount of data and system load. Through high-precision sensors and cameras, the collected data has high accuracy and reliability, providing a solid foundation for subsequent analysis and processing.

[0094] In this embodiment, the raw data is preprocessed to obtain preprocessed operating data; wherein, the preprocessing includes at least one of cleaning, standardization and feature extraction, data cleaning includes noise removal, processing missing values ​​and removing outliers, etc., noise removal data can remove noise in sensor data by filtering algorithm, and for missing data, interpolation method is used to fill, and outliers are detected and removed by statistical methods or machine learning algorithms. The data of different sensors are normalized to the same range, and the data is converted into a standard normal distribution with a mean of 0 and a variance of 1 to eliminate dimensional differences. Feature extraction includes extracting statistical features of data, such as mean, variance, peak value, peak-to-peak value, etc., or extracting time series features of data, such as trend, periodicity, autocorrelation, etc. For video data, the features of the image are extracted for anomaly detection. It should be noted that in this embodiment, the transmitted data is encrypted to ensure the security and privacy of the data.

[0095] The embodiment of the present invention preprocesses the operating data so that the preprocessed data has higher quality and consistency, can significantly improve the accuracy of fault detection and diagnosis, and provide more information support for fault detection and diagnosis.

[0096] Further, see Figure 3 , showing Figure 1 A flowchart of step 102 in a method for detecting a fault in an electrochemical energy storage power station is provided. The method is substantially the same as the method for detecting a fault in an electrochemical energy storage power station provided in the first embodiment of the present invention. Step 102 may include:

[0097] Step 1021, using a preset operating standard to perform an abnormality detection on the operating data to detect whether the operating data exceeds the preset operating standard.

[0098] Step 1022: determining the operating data exceeding the preset operating standard as abnormal operating data.

[0099] Specifically, the operating data is compared with the device threshold corresponding to the preset operating standard to determine whether it exceeds the standard. In some embodiments, statistical methods can be used to detect whether the data deviates from the normal range, and the mean and standard deviation of the data can be calculated to determine whether the operating data is within the deviation range. Specifically, a pre-trained machine learning model is used to detect anomalies in the operating data, and through multimodal data fusion, a training model is used to identify abnormal patterns in the fused multimodal data, and sensor data is fused with video data to improve the accuracy of anomaly detection. For example, temperature sensor data and video monitoring data are combined to determine whether the device is overheated. Alternatively, historical operating data and real-time operating data are combined to determine whether the current operating data is abnormal. For example, by comparing historical temperature data with current temperature data, it is determined whether there is an abnormal fluctuation.

[0100] It should be noted that in the embodiment of the present invention, the preset operating standard is to formulate the operating parameter range of the equipment according to the specifications of the equipment and the historical operating data, wherein the preset operating standard can be dynamically adjusted according to the actual operating conditions of the equipment and environmental changes, and this embodiment does not make specific limitations on this.

[0101] In this embodiment, the operating data that exceeds the preset operating standards is marked as abnormal operating data. The abnormal operating data can also be marked according to the degree of abnormality of the abnormal operating data. The determined abnormal operating data is stored. Local storage or cloud storage can be used to store the abnormal data in a local server or edge computing device, or the abnormal data can be uploaded to a cloud platform to provide data support for fault prediction and maintenance decisions.

[0102] The embodiment of the present invention utilizes a machine learning model to perform anomaly detection on power plant operation data, which can automatically identify abnormal conditions in the power plant and reduce reliance on manual experience. By using preset operation standards and a variety of anomaly detection methods, it can accurately identify whether the operation data exceeds the standards, thereby improving the accuracy and real-time performance of anomaly detection.

[0103] Further, see Figure 4 , showing Figure 1 A flowchart of step 103 in a method for detecting a fault in an electrochemical energy storage power station is provided. The method is substantially the same as the method for detecting a fault in an electrochemical energy storage power station provided in the first embodiment of the present invention. Step 103 may include:

[0104] Step 1031, using a pre-trained fault detection model to perform fault detection on the abnormal operation data, and outputting the fault type corresponding to the abnormal operation data;

[0105] Step 1032: Determine the fault cause corresponding to the abnormal operation data according to the fault type and pre-stored historical fault data.

[0106] It should be noted that in the embodiment of the present invention, a pre-trained model suitable for electrochemical energy storage power station fault detection is selected as a fault detection model, such as a deep learning model or a machine learning model, to perform fault detection on abnormal operation data. Specifically, the pre-trained model is usually trained based on a large amount of historical fault data and can identify common fault modes. In this embodiment, the abnormal operation data of the power station is input into the pre-trained fault detection model, that is, the abnormal operation data is input into the fault detection model, and the fault detection model infers the abnormal operation data and outputs the fault type corresponding to the abnormal operation data. For example, the model outputs fault types such as "battery overheating" and "voltage abnormality". If the system collects multimodal data (such as sensor data and video data), these data can be fused and input into the fault detection model to improve the accuracy of fault detection.

[0107] In the embodiment of the present invention, the information such as the fault type, fault cause, and maintenance record of the power station in the past is stored as historical fault data, and the historical fault data can be stored in a structured manner for quick query and analysis. The historical fault data is analyzed using a machine learning model, and the correlation between the fault type and the fault cause is analyzed. The fault type is compared and matched with the historical fault data, and similar fault cases are matched to determine the fault cause. The historical fault data is analyzed using a machine learning model, and the correlation between the fault type and the fault cause is analyzed.

[0108] The embodiments of the present invention can accurately analyze the cause of the fault through historical fault data and machine learning models, reduce reliance on manual experience, and quickly determine the cause of the fault so as to provide clear maintenance guidance to operation and maintenance personnel and improve the efficiency of fault handling.

[0109] Specifically, step 1031 uses a pre-trained fault detection model to perform fault detection on the abnormal operation data, and before outputting the fault type corresponding to the abnormal operation data, it may also include:

[0110] First, historical fault data pre-stored in the electrochemical energy storage station is obtained;

[0111] Secondly, the historical fault data is used to perform deep learning on the machine learning model to obtain a fault detection model.

[0112] It should be noted that, in the embodiment of the present invention, the historical fault data pre-stored in the electrochemical energy storage station is obtained, and specifically, the historical fault data can be extracted from the equipment operation log of the electrochemical energy storage station, including the fault type, fault time, fault cause, maintenance record, etc., and the data related to the fault, such as temperature, voltage, current, etc., can be extracted from the historical data of the sensor; video materials related to the fault can be extracted from the video monitoring system, such as video clips of abnormal operation of the equipment; and fault information can be extracted from the daily records of the operation and maintenance personnel, such as fault description, maintenance steps, etc. The historical fault data is stored in a local server or cloud database to facilitate subsequent analysis and processing. Through historical fault data from multiple sources (equipment operation log, sensor data, video monitoring data, operation and maintenance personnel records), the system can fully understand the fault history of the energy storage power station and provide rich training data for the fault detection model.

[0113] Specifically, this embodiment selects a machine learning model suitable for fault detection of an electrochemical energy storage power station, such as a deep learning model or a traditional machine learning model, divides historical fault data into a training set, a validation set, and a test set to ensure the generalization ability of the model, trains the machine learning model using the training set, adjusts the parameters of the model so that it can accurately identify the fault type, verifies the model using the validation set, evaluates the performance of the model, optimizes the model based on the verification results, and obtains a fault detection model. The fault detection model can output the corresponding fault type based on the input abnormal operation data, and deploys the trained fault detection model to the operation and maintenance system of the electrochemical energy storage station for real-time fault detection. In some embodiments, the fault detection model can output the probability of the fault type to facilitate the operation and maintenance personnel to judge the severity of the fault.

[0114] The embodiment of the present invention performs deep learning on the machine learning model through historical fault data. The model can accurately identify the fault type and improve the accuracy of fault detection. By using the machine learning model for fault detection, the system can automatically identify the fault type, reduce dependence on manual experience, and improve the intelligence level of the system.

[0115] Specifically, step 103 uses a pre-trained fault detection model to perform fault detection on the abnormal operation data, and after determining the fault information corresponding to the abnormal operation data, it also includes:

[0116] Update pre-stored historical fault data according to the fault information corresponding to the abnormal operation data;

[0117] The fault detection model is iteratively trained using updated historical fault data to obtain an optimized fault detection model.

[0118] It should be noted that, in an embodiment of the present invention, new fault information is stored in a historical fault database to ensure the integrity and timeliness of the data, the updated historical fault data is divided into a training set, a validation set and a test set, the training set is used to iteratively train the fault detection model, the parameters of the model are adjusted so that it can accurately identify new fault types, the validation set is used to verify the model, and the model is optimized based on the verification results. An incremental learning method is used to gradually add new fault data to the model training to avoid retraining the entire model, the model is regularly updated in batches to ensure the timeliness and accuracy of the model, and the model is updated immediately after the fault detection is completed to ensure the real-time performance of the model.

[0119] Further, see Figure 5 , showing Figure 1 A flowchart of step 104 in a method for detecting a fault in an electrochemical energy storage power station is provided. The method is substantially the same as the method for detecting a fault in an electrochemical energy storage power station provided in the first embodiment of the present invention. Step 104 may include:

[0120] Step 1041, determine the fault location according to the fault type, and generate fault prompt information; wherein the fault prompt information is used to prompt the operation and maintenance personnel to perform on-site maintenance.

[0121] Step 1042, query the pre-created maintenance knowledge base according to the fault type and fault cause to obtain the maintenance method and maintenance steps.

[0122] Step 1043, using the maintenance method and maintenance steps to generate a maintenance guidance tutorial; wherein the maintenance guidance tutorial may be in the form of any one of text, pictures and videos.

[0123] It should be noted that in the embodiment of the present invention, the specific device location where the fault occurs is determined according to the fault type, and fault prompt information is generated. For example, if the fault type is "battery overheating", the specific battery pack is located. Among them, the fault prompt information can be a text prompt information, a voice prompt or a multi-modal interface prompt. According to the severity of the fault, a suitable notification method (such as SMS, email, voice broadcast, etc.) is selected. This embodiment does not make specific limitations on this. After the fault detection is completed, the fault prompt information is immediately generated to ensure that the operation and maintenance personnel can receive the notification in time.

[0124] Specifically, the maintenance knowledge base includes equipment information, fault cases, maintenance methods, maintenance steps, etc. The maintenance knowledge base adopts structured storage to facilitate quick query and analysis. According to the fault type, the corresponding maintenance methods and steps in the knowledge base are queried. According to the cause of the fault, the maintenance methods and steps are further refined, and the maintenance methods and maintenance steps are used to generate maintenance guidance tutorials; among them, the maintenance guidance tutorials include any one of text, pictures and videos.

[0125] It should be noted that the maintenance guide tutorial can include fields such as fault type, fault cause, maintenance steps, images, videos, etc., and display the maintenance guide tutorial in a multi-modal manner, supporting multiple forms of display such as text, pictures, videos and AR to enhance the user experience. Specifically, it can be a detailed text description to help the operation and maintenance personnel more intuitively understand the maintenance images of the maintenance steps or a maintenance video that dynamically displays the maintenance process. In some embodiments, AR technology can be used to display the maintenance steps and operating instructions in real time on the equipment of the operation and maintenance personnel, and the fault location and maintenance path can be displayed in real time through AR glasses or mobile phone cameras.

[0126] The embodiment of the present invention combines the fault type and the fault cause to perform multi-condition query to obtain more accurate maintenance methods and steps. The maintenance knowledge base provides a standardized maintenance process, reduces human errors, and ensures the safety and reliability of the maintenance process. By querying the maintenance knowledge base, operation and maintenance personnel can quickly and accurately obtain maintenance methods and steps, reduce maintenance time, and improve maintenance efficiency.

[0127] Specifically, if the maintenance guidance tutorial is in the form of a video, step 1043 uses the maintenance method and the maintenance steps to generate a maintenance guidance tutorial, including:

[0128] First, video materials are selected according to the maintenance method and the maintenance steps;

[0129] Secondly, the video material is edited using a pre-generated video script to generate a maintenance instruction video.

[0130] It should be noted that, in the embodiments of the present invention, video materials are screened out according to the maintenance method and the maintenance steps. The video materials may be relevant video materials extracted from historical maintenance records, such as equipment disassembly, component replacement, troubleshooting, etc., or relevant video materials may be extracted from equipment operation manuals, such as equipment assembly, component installation, etc., or video materials may be generated through simulated operations, such as maintenance processes simulated by virtual reality (VR) or augmented reality (AR). Relevant video materials are screened out according to the fault type, and by matching the fault type and maintenance steps, it is ensured that the screened video materials are highly relevant to the actual maintenance needs, thereby improving the accuracy of video guidance.

[0131] In this embodiment, a detailed video script is generated according to the maintenance method and maintenance steps. The video script adopts a structured format to facilitate video editing. The screened video material is imported into the video editing software. According to the video script, the video material is edited, spliced, and narration and subtitles are added. After the video editing is completed, the final maintenance instruction video is generated, and the generated video is output to a common video format (such as MP4, AVI) for easy playback on different devices. After the fault detection is completed, the maintenance instruction video is generated immediately to ensure that the operation and maintenance personnel can obtain video guidance in time. According to the new fault data, the video script and video material are dynamically updated to ensure the timeliness and accuracy of the video guidance.

[0132] Specifically, before step 1042 searches a pre-created maintenance knowledge base according to the fault type and the fault cause to obtain a maintenance method and maintenance steps, it also includes:

[0133] First, build a maintenance knowledge base in advance;

[0134] Secondly, the equipment information, fault cases of the electrochemical energy storage power station, and the maintenance methods and maintenance steps corresponding to the fault cases are stored in the maintenance knowledge base.

[0135] It should be noted that in the embodiment of the present invention, a database type suitable for storing maintenance knowledge is selected, such as a relational database or a NoSQL database, and the architecture of the maintenance knowledge base is designed based on the database, including data table structure, field definition, index design, etc. The equipment information, fault cases of the electrochemical energy storage power station, and the maintenance methods and maintenance steps corresponding to the fault cases are stored in the maintenance knowledge base. The maintenance knowledge base may include the following tables: an equipment information table for storing equipment model, specification, installation location and other information; a fault case table for storing historical fault cases, including fault type, fault cause, fault time, etc.; a maintenance method table for storing maintenance methods for different fault types; a maintenance step table for storing detailed maintenance steps, etc. The equipment information, fault cases, maintenance methods and maintenance steps are stored in the knowledge base to ensure the integrity and consistency of the data, and the data in the knowledge base is stored in a structured manner for quick query and analysis.

[0136] It should be noted that in this embodiment, the access rights of the knowledge base are set to ensure that only authorized personnel can access and modify the data in the knowledge base. For example, operation and maintenance personnel can query the knowledge base, but only administrators can modify the knowledge base. Through structured storage and permission management, the integrity and consistency of the data in the knowledge base are ensured to avoid data loss or tampering.

[0137] Reference Figure 6, shows a flowchart of the steps of another electrochemical energy storage power station fault detection method provided by an embodiment of the present invention, which method is basically the same as the electrochemical energy storage power station fault detection method provided by the first embodiment of the present invention, except that the method may further include:

[0138] Step 101, obtaining operation data of an electrochemical energy storage power station.

[0139] Step 106, performing fault prediction at the next moment based on the operation data at the previous moment and the operation data at the current moment, and obtaining a fault prediction result.

[0140] Step 107: Generate fault prompt information and maintenance guidance tutorials under the fault prediction according to the fault prediction result.

[0141] In an embodiment of the present invention, in an embodiment of the present invention, the operation data of the electrochemical energy storage station is collected, a machine learning model suitable for fault prediction is selected, such as a time series prediction model, a regression model or a deep learning model, and the fault prediction model is trained using historical operation data, and the parameters of the model are adjusted so that it can accurately predict the future state of the equipment. The operation data at the previous moment is used as historical data and input into the fault prediction model, and the operation data at the current moment is used as real-time data and input into the fault prediction model. The model outputs the fault prediction result at the next moment. Through the combination of historical data and current data, the fault prediction model can accurately predict the future state of the equipment and improve the accuracy of fault prediction. Real-time prediction can timely discover potential faults and avoid fault deterioration. Fault prediction information is extracted from the results output by the fault prediction model, and fault prompt information is generated. After the fault prediction is completed, a maintenance guide is immediately generated. According to the fault prediction results, the fault prompt information and the maintenance guide under the fault prediction are generated. Refer to the foregoing description, and no further description is given here.

[0142] Step 105: Send the fault prompt information and the maintenance guide to the operation and maintenance personnel, prompting the operation and maintenance personnel to perform on-site maintenance according to the maintenance guide.

[0143] The above steps 101 and 105 are as described above and will not be repeated here.

[0144] Specifically, step 106 performs fault prediction at the next moment based on the historical fault data at the previous moment and the operation data at the current moment to obtain a fault prediction result, which may specifically include:

[0145] First, a pre-trained fault prediction model is used to determine the data change trend between the historical fault data at the previous moment and the operating data at the current moment;

[0146] Secondly, a fault prediction is performed on the data change trend to determine the probability of a fault occurring at the next moment, and a fault prediction result of the electrochemical energy storage power station at the next moment is obtained.

[0147] It should be noted that in the embodiment of the present invention, through the pre-trained fault prediction model, it is possible to accurately identify the change trend between historical fault data and current operating data, improve the accuracy of fault prediction, automatically identify fault trends, reduce dependence on manual experience, and input the data change trend into the pre-trained fault prediction model. The model infers the data, determines the probability of fault occurrence at the next moment, and obtains the fault prediction result of the electrochemical energy storage power station at the next moment.

[0148] Compared with the prior art, the implementation mode of the present invention, on the basis of achieving the beneficial effects brought by the first implementation mode, through the combination of historical data and current data, the system can accurately and timely predict the future status of the equipment, and through real-time generation of fault prompt information and detailed maintenance guidance tutorials, ensure that the operation and maintenance personnel can obtain maintenance guidance in time, so that the operation and maintenance personnel can understand potential faults in advance, quickly perform preventive maintenance, avoid fault deterioration, and reduce the fault maintenance cost of the power station. Through predictive maintenance and intelligent resource scheduling, it can reduce unplanned downtime and extend the service life of equipment, thereby reducing operation and maintenance costs and improving the overall reliability of equipment.

[0149] In some embodiments, the performing abnormality detection on the operating data, after detecting abnormal operating data, further comprises:

[0150] First, the operation data is displayed to the operation and maintenance personnel through a pre-created multimodal interface, and the multimodal input of the operation and maintenance personnel is received;

[0151] Secondly, in response to the fault description content input by the operation and maintenance personnel, a pre-trained fault detection model is used to perform fault detection on the fault description information to determine the fault information corresponding to the fault description content.

[0152] Reference Fig. 9, showing an interface function diagram of the electrochemical energy storage power station fault detection method provided by an embodiment of the present invention. It should be noted that, in an embodiment of the present invention, operation data is displayed to operation and maintenance personnel through a pre-created multimodal interface, and multimodal input of the operation and maintenance personnel is received. Specifically, a multimodal interface is designed to support multiple input and output methods, such as voice, text, image, video and augmented reality (AR). Operation data and fault information are displayed on the interface, and multiple interaction methods are supported, such as voice input, text input, image upload, video playback and AR interaction. The operation and maintenance personnel can input the fault description content by voice, text, image upload, etc. In response to the fault description content input by the operation and maintenance personnel, the fault description content is input into the pre-trained fault detection model, and the model infers the data and outputs the fault detection result. Through the multimodal interface, the embodiment of the present invention enables the operation and maintenance personnel to obtain operation data and input fault description content in the most convenient way, thereby improving user experience and interactivity.

[0153] The embodiments of the present invention provide data support for fault prediction and maintenance decision-making by deeply analyzing a large amount of operation data, thereby maximizing the use of data, automatically identifying anomalies in power station operation data, and realizing fault detection and accurate diagnosis. Through automated data preprocessing and intelligent monitoring, the reliance on manual operations is reduced, and the operation and maintenance efficiency and response speed are improved. The maintenance process and response measures can be automatically triggered according to the fault information to ensure that the fault can be handled in a timely and effective manner. The maintenance guidance tutorial can be quickly and standardizedly delivered to the operation and maintenance personnel, realizing automatic detection, diagnosis, response and maintenance guidance of faults, and further improving the effective detection and maintenance efficiency of electrochemical energy storage power stations.

[0154] Reference Fig.10 , shows a schematic structural diagram of a fault detection device for an electrochemical energy storage power station provided by an embodiment of the present invention, the device comprising:

[0155] The data acquisition module 201 is used to acquire the operation data of the electrochemical energy storage power station;

[0156] The data processing module 202 is used to perform anomaly detection on the operation data and detect abnormal operation data;

[0157] A fault detection module 203 is used to perform fault detection on the abnormal operation data using a pre-trained fault detection model to determine fault information corresponding to the abnormal operation data; wherein the fault information includes a fault type and a fault cause;

[0158] An information generation module 204 is used to generate fault prompt information according to the fault type, and to generate a maintenance guidance tutorial according to the fault type and fault cause;

[0159] The maintenance prompt module 205 is used to send the fault prompt information and the maintenance guidance tutorial to the operation and maintenance personnel, prompting the operation and maintenance personnel to perform on-site maintenance according to the maintenance guidance tutorial.

[0160] Furthermore, the data acquisition module 201 includes:

[0161] The acquisition submodule is used to collect the raw data of the electrochemical energy storage station at the current moment;

[0162] The preprocessing submodule is used to preprocess the raw data to obtain preprocessed operating data; wherein the preprocessing includes at least one of cleaning, standardization and feature extraction.

[0163] Furthermore, the data processing module 202 includes:

[0164] A first detection submodule, configured to perform abnormality detection on the operation data using a preset operation standard to detect whether the operation data exceeds the preset operation standard;

[0165] The first determining submodule is used to determine the operating data exceeding the preset operating standard as abnormal operating data.

[0166] Furthermore, the fault detection module 203 includes:

[0167] A second detection submodule, configured to perform fault detection on the abnormal operation data using a pre-trained fault detection model, and output a fault type corresponding to the abnormal operation data;

[0168] The second determination submodule is used to determine the fault cause corresponding to the abnormal operation data according to the fault type and pre-stored historical fault data.

[0169] Furthermore, the fault detection module 203 also includes:

[0170] An acquisition submodule, used to acquire historical fault data pre-stored in the electrochemical energy storage station;

[0171] The first training submodule is used to use the historical fault data to perform deep learning on the machine learning model to obtain a fault detection model.

[0172] Furthermore, the fault detection module 203 also includes:

[0173] An updating submodule, used for updating pre-stored historical fault data according to the fault information corresponding to the abnormal operation data;

[0174] The second training submodule is used to iteratively train the fault detection model using the updated historical fault data to obtain an optimized fault detection model.

[0175] Furthermore, the information generation module 204 includes:

[0176] A first generating submodule is used to determine the fault location according to the fault type and generate fault prompt information; wherein the fault prompt information is used to prompt the operation and maintenance personnel to perform on-site maintenance;

[0177] A query submodule, used to query a pre-created maintenance knowledge base according to the fault type and the fault cause, and obtain maintenance methods and maintenance steps;

[0178] The second generation submodule is used to generate a maintenance guidance tutorial using the maintenance method and the maintenance steps; wherein the maintenance guidance tutorial is in the form of any one of text, pictures and videos.

[0179] Furthermore, if the maintenance guidance tutorial is in the form of a video, the second generation submodule includes:

[0180] A screening unit, used for screening out video materials according to the maintenance method and the maintenance steps;

[0181] The editing unit is used to edit the video material using a pre-generated video script to generate a maintenance guidance video.

[0182] Furthermore, the information generation module 204 further includes:

[0183] Build submodules for pre-building maintenance knowledge base;

[0184] The storage submodule is used to store the equipment information, fault cases of the electrochemical energy storage power station, and the maintenance methods and maintenance steps corresponding to the fault cases in the maintenance knowledge base.

[0185] Furthermore, the device also includes:

[0186] The fault prediction module is used to predict the fault at the next moment based on the operation data at the previous moment and the operation data at the current moment, and obtain the fault prediction result;

[0187] The second information generation module is used to generate fault prompt information and maintenance guidance tutorials under the fault prediction according to the fault prediction result.

[0188] Furthermore, the fault prediction module includes:

[0189] The third determination submodule is used to determine the data change trend between the historical fault data at the previous moment and the operation data at the current moment by using the pre-trained fault prediction model;

[0190] The fourth determination submodule is used to perform fault prediction on the data change trend, determine the probability of fault occurrence at the next moment, and obtain the fault prediction result of the electrochemical energy storage power station at the next moment.

[0191] Furthermore, the device also includes:

[0192] A multimodal interface module, used to display operation data to operation and maintenance personnel through a pre-created multimodal interface, and to receive multimodal input from the operation and maintenance personnel;

[0193] The fault input module is used to respond to the fault description content input by the operation and maintenance personnel, use a pre-trained fault detection model to perform fault detection on the fault description information, and determine the fault information corresponding to the fault description content.

[0194] The electrochemical energy storage power station fault detection device provided by the embodiment of the present invention obtains the operation data of the electrochemical energy storage power station, performs abnormal detection on the operation data, detects abnormal operation data, uses a pre-trained fault detection model to perform fault detection on the abnormal operation data, determines the fault information corresponding to the abnormal operation data, generates fault prompt information according to the fault type, and generates a maintenance guide tutorial according to the fault type and the fault cause, and sends the fault prompt information and the maintenance guide tutorial to the operation and maintenance personnel, prompting the operation and maintenance personnel to perform on-site maintenance according to the maintenance guide tutorial. The embodiment of the present invention performs in-depth analysis on a large amount of operation data, provides data support for fault prediction and maintenance decision-making, realizes the maximum utilization of data, automatically identifies abnormalities in the power station operation data, realizes fault detection and accurate diagnosis, reduces dependence on manual operation through automated data preprocessing and intelligent monitoring, improves operation and maintenance efficiency and response speed, can automatically trigger maintenance processes and response measures according to fault information, ensures that faults can be handled promptly and effectively, and the maintenance guide tutorial can be quickly and standardizedly delivered to the operation and maintenance personnel, realizes automatic detection, diagnosis, response and maintenance guidance of faults, and further improves the effective detection and maintenance efficiency of electrochemical energy storage power stations.

[0195] Reference Fig.11 , an embodiment of the present invention further provides an electronic device, such as Fig.11 As shown, it includes a processor 301, a communication interface 302, a memory 303 and a communication bus 304, wherein the processor 301, the communication interface 302, and the memory 303 communicate with each other through the communication bus 304.

[0196] A processor 301, a memory 303 for storing processor executable instructions;

[0197] The processor 301 is configured to execute the instructions to implement the electrochemical energy storage power station fault detection method as described above:

[0198] Obtaining operation data of electrochemical energy storage power stations;

[0199] Performing anomaly detection on the operation data to detect abnormal operation data;

[0200] Using a pre-trained fault detection model to perform fault detection on the abnormal operation data, and determining fault information corresponding to the abnormal operation data; wherein the fault information includes a fault type and a fault cause;

[0201] Generate fault prompt information according to the fault type, and generate a maintenance guidance tutorial according to the fault type and the fault cause;

[0202] The fault prompt information and the maintenance guide are sent to the operation and maintenance personnel, prompting the operation and maintenance personnel to perform on-site maintenance according to the maintenance guide.

[0203] The communication bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0204] The communication interface is used for communication between the above terminal and other devices.

[0205] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0206] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0207] In another embodiment provided by the present invention, a computer-readable storage medium is also provided, on which a computer program is stored. When the computer program is executed by a processor, the electrochemical energy storage power station fault detection method described in any of the above embodiments is implemented.

[0208] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0209] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0210] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0211] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A method for detecting faults in an electrochemical energy storage power station, characterized in that: The method comprises: Obtaining operation data of electrochemical energy storage power stations; Performing anomaly detection on the operation data to detect abnormal operation data; Using a pre-trained fault detection model to perform fault detection on the abnormal operation data, and determining fault information corresponding to the abnormal operation data; wherein the fault information includes a fault type and a fault cause; Generate fault prompt information according to the fault type, and generate a maintenance guidance tutorial according to the fault type and the fault cause; The fault prompt information and the maintenance guide are sent to the operation and maintenance personnel, prompting the operation and maintenance personnel to perform on-site maintenance according to the maintenance guide.

2. The method according to claim 1, characterized in that The obtaining of the operation data of the electrochemical energy storage power station includes: Collect the original data of the electrochemical energy storage station at the current moment; The raw data is preprocessed to obtain preprocessed operating data; wherein the preprocessing includes at least one of cleaning, standardization and feature extraction.

3. The method according to claim 1, characterized in that The performing abnormality detection on the operation data to detect abnormal operation data includes: Performing abnormality detection on the operating data using a preset operating standard to detect whether the operating data exceeds the preset operating standard; The operating data exceeding the preset operating standard is determined as abnormal operating data.

4. The method according to claim 1, characterized in that: The method of using a pre-trained fault detection model to perform fault detection on the abnormal operation data to determine fault information corresponding to the abnormal operation data, wherein the fault information includes a fault type and a fault cause, includes: Using a pre-trained fault detection model to perform fault detection on the abnormal operation data, and outputting the fault type corresponding to the abnormal operation data; The fault cause corresponding to the abnormal operation data is determined according to the fault type and pre-stored historical fault data.

5. The method according to claim 4, characterized in that The method further comprises: performing fault detection on the abnormal operation data by using a pre-trained fault detection model and outputting a fault type corresponding to the abnormal operation data. Obtain historical fault data pre-stored in the electrochemical energy storage station; The historical fault data is used to perform deep learning on the machine learning model to obtain a fault detection model.

6. The method according to claim 4, characterized in that After the pre-trained fault detection model is used to perform fault detection on the abnormal operation data and the fault information corresponding to the abnormal operation data is determined, the method further includes: Update pre-stored historical fault data according to the fault information corresponding to the abnormal operation data; The fault detection model is iteratively trained using updated historical fault data to obtain an optimized fault detection model.

7. The method according to claim 1, characterized in that Generating fault prompt information according to the fault type, and generating a maintenance guidance tutorial according to the fault type and the fault cause, include: Determine the fault location according to the fault type and generate fault prompt information; wherein the fault prompt information is used to prompt the operation and maintenance personnel to perform on-site maintenance; According to the fault type and the fault cause, a pre-created maintenance knowledge base is searched to obtain maintenance methods and maintenance steps; The maintenance method and the maintenance steps are used to generate a maintenance instruction tutorial; wherein the maintenance instruction tutorial may be in the form of any one of text, pictures and videos.

8. The method according to claim 7, characterized in that If the maintenance guidance tutorial is in the form of a video, the maintenance method and the maintenance steps are used to generate the maintenance guidance tutorial, including: Filter out video materials according to the maintenance method and the maintenance steps; The video material is edited using a pre-generated video script to generate a maintenance instruction video.

9. The method according to claim 7, characterized in that: Before querying the pre-created maintenance knowledge base according to the fault type and the fault cause to obtain the maintenance method and maintenance steps, the method further includes: Pre-build maintenance knowledge base; The equipment information, fault cases of the electrochemical energy storage power station, and the maintenance methods and maintenance steps corresponding to the fault cases are stored in the maintenance knowledge base.

10. The method according to claim 1, characterized in that After obtaining the operation data of the electrochemical energy storage power station, before sending the fault prompt information and the maintenance guide to the operation and maintenance personnel to prompt the operation and maintenance personnel to perform on-site maintenance according to the maintenance guide, the method further includes: According to the operation data at the previous moment and the operation data at the current moment, the fault prediction at the next moment is performed to obtain the fault prediction result; According to the fault prediction result, fault prompt information and maintenance guidance tutorial under the fault prediction are generated.

11. The method according to claim 10, characterized in that The method of performing fault prediction at the next moment based on the historical fault data at the previous moment and the operation data at the current moment to obtain the fault prediction result includes: Use the pre-trained fault prediction model to determine the data change trend between the historical fault data at the previous moment and the operating data at the current moment; Fault prediction is performed on the data change trend to determine the probability of fault occurrence at the next moment, and the fault prediction result of the electrochemical energy storage power station at the next moment is obtained.

12. The method according to claim 1, characterized in that After performing abnormality detection on the operation data and detecting abnormal operation data, the method further includes: Displaying operation data to operation and maintenance personnel through a pre-created multimodal interface, and receiving multimodal input from the operation and maintenance personnel; In response to the fault description content input by the operation and maintenance personnel, a pre-trained fault detection model is used to perform fault detection on the fault description information to determine the fault information corresponding to the fault description content.

13. A fault detection device for an electrochemical energy storage power station, characterized in that: The device comprises: A data acquisition module is used to acquire the operation data of the electrochemical energy storage power station; A data processing module, used for performing anomaly detection on the operation data to detect abnormal operation data; A fault detection module, configured to perform fault detection on the abnormal operation data using a pre-trained fault detection model, and determine fault information corresponding to the abnormal operation data; wherein the fault information includes a fault type and a fault cause; An information generation module is used to generate fault prompt information according to the fault type, and to generate a maintenance guidance tutorial according to the fault type and fault cause; The maintenance prompt module is used to send the fault prompt information and the maintenance guidance tutorial to the operation and maintenance personnel, prompting the operation and maintenance personnel to perform on-site maintenance according to the maintenance guidance tutorial.

14. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to execute the instructions to implement the electrochemical energy storage power station fault detection method according to any one of claims 1 to 12.

15. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the electrochemical energy storage power station fault detection method according to any one of claims 1 to 12 is implemented.

Images