Fault diagnosis method and device for energy storage system and medium

Abstract

The embodiment of the invention discloses a fault diagnosis method and device for an energy storage system and a medium. The method comprises the steps of obtaining a target device type of a target device in the energy storage system and current device operation data corresponding to the target device; performing data preprocessing on the current equipment operation data to obtain standard equipment operation data; determining a target fault diagnosis mode corresponding to the target equipment based on an association relationship between the target equipment type and a preset fault diagnosis mode; and based on the target fault diagnosis mode and the standard equipment operation data, determining a target fault diagnosis result corresponding to the target equipment. Through the technical scheme of the embodiment of the invention, the fault diagnosis of the energy storage system can be realized, the fault diagnosis result can be accurately and conveniently determined, and the fault diagnosis efficiency of the energy storage system is improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the technical field of fault diagnosis, and in particular to a fault diagnosis method, device, and medium for an energy storage system. Background Art

[0002] Energy storage systems are technical devices used to store and release electrical energy. They are widely used in power systems, renewable energy utilization, and power supply and demand regulation. With the booming development of renewable energy, energy storage systems are increasingly demonstrating their irreplaceable importance as a bridge between energy production and consumption.

[0003] Currently, energy storage system failures typically manifest in multiple ways, including equipment anomalies, battery cell anomalies, and network anomalies. Traditional fault diagnosis and location methods often rely on manual inspections and single-system alarms, resulting in low efficiency and difficulty in locating faults. These methods are unable to accurately diagnose and locate faults during real-time operation of energy storage systems, and often require lengthy troubleshooting times, increasing system downtime and impacting the safety and economic efficiency of energy storage. Summary of the Invention

[0004] Embodiments of the present invention provide a method, device, and medium for diagnosing faults in an energy storage system, thereby enabling fault diagnosis of the energy storage system and avoiding shutdown inspection of the energy storage system. The method can accurately and conveniently determine the fault diagnosis results without manual inspection, thereby improving the efficiency of fault diagnosis in the energy storage system.

[0005] In a first aspect, an embodiment of the present invention provides a method for diagnosing a fault of an energy storage system, comprising:

[0006] Obtaining a target device type of a target device in the energy storage system and current device operation data corresponding to the target device;

[0007] Performing data preprocessing on the current equipment operation data to obtain standard equipment operation data;

[0008] Determining a target fault diagnosis method corresponding to the target device based on an association relationship between the target device type and a preset fault diagnosis method;

[0009] Based on the target fault diagnosis mode and the standard equipment operation data, a target fault diagnosis result corresponding to the target equipment is determined.

[0010] Optionally, the method further includes: the target device includes at least one of: a temperature control device, an energy management system, a battery cluster, a power system, a single battery cell, an energy conversion system, a battery management system and a power environment monitoring system.

[0011] Optionally, the method also includes: the target fault diagnosis method corresponding to the temperature control device is a temperature control over-limit fault diagnosis method; the target fault diagnosis method corresponding to the energy management system is a network delay over-limit fault diagnosis method; the target fault diagnosis method corresponding to the battery cluster is a cell voltage difference over-limit fault diagnosis method; the target fault diagnosis method corresponding to the power system is a grid frequency fault diagnosis method; the target fault diagnosis method corresponding to the single cell is a cell voltage and temperature index fault diagnosis method; the target fault diagnosis method corresponding to the energy conversion system is a diagnosis method based on the PCS expert model; the target fault diagnosis method corresponding to the battery management system is a diagnosis method based on the BMS expert model; the target fault diagnosis method corresponding to the power environment monitoring system is a diagnosis method based on the dynamic environment expert model.

[0012] Optionally, the method also includes: performing fault diagnosis on the standard equipment operating data based on the target fault diagnosis method to obtain the fault level and target fault operating parameters corresponding to the target equipment; if the fault level is a preset level, determining the fault description, fault location and fault occurrence time corresponding to the target equipment based on the target fault operating parameters and the standard equipment operating data.

[0013] Optionally, the method also includes: if the target fault diagnosis method is a parameter over-limit diagnosis method, then based on the equipment operating parameters in the standard equipment operation data and the preset parameter limit interval, determining the target fault operating parameters and fault level corresponding to the target equipment; if the target fault diagnosis method is a hybrid expert model diagnosis method, then inputting the standard equipment operation data into the preset hybrid expert model for feature extraction and fault diagnosis to determine the target fault operating parameters and fault level corresponding to the target equipment.

[0014] Optionally, the method also includes: determining the fault location and fault occurrence time corresponding to the target fault operating parameters from the standard equipment operating data based on the target fault operating parameters; and determining the fault description corresponding to the target fault operating parameters based on the association relationship between the target fault operating parameters and the preset fault description.

[0015] Optionally, the method further includes: the target fault diagnosis result includes at least one of a fault description, a fault level, a fault location, and a fault occurrence time.

[0016] Optionally, the method also includes: categorizing and counting the target fault diagnosis results of each target device, and displaying the statistical results on the interface; wherein the statistical results include the proportion of the number of target devices corresponding to each fault level; and the display method of the statistical results includes at least one of a bar chart and a pie chart.

[0017] In a second aspect, an embodiment of the present invention further provides a fault diagnosis device for an energy storage system, the device comprising:

[0018] A current device operation data acquisition module is used to acquire a target device type of a target device in the energy storage system and current device operation data corresponding to the target device;

[0019] a standard equipment operation data determination module, configured to perform data preprocessing on the current equipment operation data to obtain standard equipment operation data;

[0020] A target fault diagnosis mode determination module is used to determine a target fault diagnosis mode corresponding to the target device based on an association relationship between the target device type and the preset fault diagnosis mode;

[0021] The target fault diagnosis result determination module is used to determine the target fault diagnosis result corresponding to the target device based on the target fault diagnosis method and the standard device operation data.

[0022] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising:

[0023] one or more processors;

[0024] a memory for storing one or more programs;

[0025] When the one or more programs are executed by the one or more processors, the one or more processors implement the fault diagnosis method for the energy storage system provided by any embodiment of the present invention.

[0026] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a fault diagnosis method for an energy storage system as provided in any embodiment of the present invention.

[0027] In a fifth aspect, an embodiment of the present invention provides a computer program product, including a computer program, which, when executed by a processor, implements the fault diagnosis method for an energy storage system provided by any embodiment of the present invention.

[0028] The technical solution of the embodiment of the present invention obtains the target device type of the target device in the energy storage system and the current device operation data corresponding to the target device; performs data preprocessing on the current device operation data to obtain standard device operation data; determines the target fault diagnosis method corresponding to the target device based on the association relationship between the target device type and the preset fault diagnosis method; determines the target fault diagnosis result corresponding to the target device based on the target fault diagnosis method and the standard device operation data, thereby realizing fault diagnosis of the energy storage system, avoiding shutdown inspection of the energy storage system, and accurately and conveniently determining the fault diagnosis result without manual inspection, thereby improving the fault diagnosis efficiency of the energy storage system.

[0029] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0031] Figure 1 This is a flow chart of a fault diagnosis method for an energy storage system provided in Example 1 of the present invention;

[0032] Figure 2 This is a flow chart of a fault diagnosis method for an energy storage system provided in the second embodiment of the present invention;

[0033] Figure 3 1 is a schematic structural diagram of a fault diagnosis device for an energy storage system provided in a third embodiment of the present invention;

[0034] Figure 4 It is a structural diagram of an electronic device for implementing the fault diagnosis method of the energy storage system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0036] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0037] Example 1

[0038] Figure 1 A flowchart of a method for diagnosing a fault in an energy storage system is provided for the first embodiment of the present invention. This embodiment is applicable to the case where fault diagnosis is performed in real-time operation of an energy storage system. The method can be executed by a fault diagnosis device for an energy storage system. The fault diagnosis device for an energy storage system can be implemented in the form of hardware and / or software, and the fault diagnosis device for an energy storage system can be configured in an electronic device. Figure 1 As shown, the method includes:

[0039] S110 : Acquire a target device type of a target device in the energy storage system and current device operation data corresponding to the target device.

[0040] The current device operating data may refer to the collection of device operating parameters collected by each target sensor on the target device at the current moment. The target device may refer to the device selected by the user for fault diagnosis. The target device is any device or system that comprises an energy storage system. The energy storage system may be, but is not limited to, an electrochemical energy storage system. Target devices include at least one of: a temperature control device, an energy management system (EMS), a battery cluster, a power system, a single cell, a power conversion system (PCS), a battery management system (BMS), and a power environment monitoring system. The target sensor may refer to a sensor installed on the target device that collects device operating parameters required for device fault diagnosis. Each device operating parameter collected by the target sensor has a corresponding collection time. For example, each device operating parameter in the current device operating data corresponds to the current moment. The target device type can be understood as a pre-set identifier used to distinguish different types of identification.

[0041] In an embodiment of the present invention, a server can be used for fault diagnosis of an energy storage system. The server can be a local server or a cloud server. The following description takes a cloud server as an example, and cloud servers are collectively referred to as the cloud. Fault diagnosis of the energy storage system is performed in the cloud instead of at the local end of the energy storage system, so that the energy storage system at the local end can be continuously monitored without shutting down, and there is no need to shut down for fault diagnosis. Data communication between the energy management system and all other devices in the energy storage system is established in advance at the local end through a multi-source acquisition protocol, so that the energy management system can receive multi-source data, that is, the current device operation data uploaded simultaneously by target devices of different device types.

[0042] Specifically, the user sends a fault diagnosis instruction of the energy storage system to the cloud, such as selecting the target device in the fault diagnosis interface and clicking the fault diagnosis control, so that the cloud can obtain the target device type of the target device in the energy storage system and the current device operation data corresponding to the target device through the energy management system in the energy storage system. If there are target devices of different device types that need to be diagnosed at the same time, the energy management system can upload the data to the cloud through multi-threading technology. Among them, each topic can upload the current device operation data of a type of target device. The energy management system can support the simultaneous upload of multiple topics, that is, the current device operation data of target devices of different device types can be uploaded at the same time.

[0043] S120: Preprocess the current equipment operation data to obtain standard equipment operation data.

[0044] The standard device operation data may refer to valid device operation data without redundancy and in a unified format.

[0045] Specifically, after obtaining the current device operation data of the target device in the cloud, the current device operation data can be preprocessed based on the preset data processing method to obtain standard device operation data. For example, the preset data processing method may include but is not limited to error data elimination, redundant data deduplication and data format standardization. Exemplarily, the abnormal parameter values collected by the target sensor are filtered through a rule engine (such as regular expressions, range thresholds), so as to achieve the elimination of error data in the current device operation data. For example, data with a voltage value exceeding the rated range of ±10% is directly marked as invalid and eliminated. For multiple target devices with the same timestamp (collection time) that repeatedly report data, hash comparison or primary key conflict detection mechanism can be used to deduplicate. Data of different protocols (such as Modbus, OPC UA) can also be uniformly converted into JSON format to achieve data preprocessing to obtain standard device operation data.

[0046] S130: Determine a target fault diagnosis method corresponding to the target device based on an association relationship between the target device type and a preset fault diagnosis method.

[0047] Each device type has an associated preset fault diagnosis method. For example, a temperature control device has a corresponding temperature limit overrun fault diagnosis method. A targeted fault diagnosis method can be a personalized method specifically designed for diagnosing faults on a target device.

[0048] Specifically, the target device type of the target device is used to determine the target fault diagnosis method associated with the target device type from the association between the target device type and the preset fault diagnosis method, and the target fault diagnosis method is used as the target fault diagnosis method corresponding to the target device. This can be understood as obtaining the target fault diagnosis method set by the user based on the target device type.

[0049] S140: Determine a target fault diagnosis result corresponding to the target device based on the target fault diagnosis method and standard device operation data.

[0050] Among them, the target fault diagnosis result includes: at least one of: fault description, fault level, fault location and fault occurrence time. The fault description may refer to a text description of the current fault condition of the target device. If the target device is a temperature control device, the fault description may be, but is not limited to, the liquid cooler temperature exceeding the limit. The fault level may refer to the severity of the current fault condition of the target device. For example, the fault level may include, but is not limited to, a minor fault, a moderate fault and a major fault. The fault location may refer to the location where the current fault condition of the target device occurs. For example, the fault location can be represented by the device number of the target device, or by the sensor position of the target sensor. The fault occurrence time may refer to the time when the current fault condition of the target device occurs. The target fault diagnosis result can be displayed on the fault diagnosis result display interface of the cloud. In an embodiment of the present invention, after the user clicks the fault diagnosis control, he waits for the cloud to complete the fault diagnosis process and views the fault diagnosis result of the target device on the fault diagnosis result display interface that jumps to after the fault diagnosis is completed. For example, when multiple target devices are simultaneously undergoing fault diagnosis, the cloud can statistically display the target fault diagnosis results of all target devices by category, thereby determining the proportion of target devices corresponding to each fault level and displaying them using a bar chart or a fan chart.

[0051] For example, consider a temperature control device as the target device. This device corresponds to the temperature control over-limit fault diagnosis method. This method analyzes and processes standard device operating data to determine the target fault diagnosis result for the temperature control device. Specifically, for temperature control devices such as liquid chillers, condition monitoring and threshold comparison methods can be used to identify and categorize liquid chiller faults.

[0052] Preset water temperature ranges for normal operation, minor faults, moderate faults, and severe faults of the liquid cooler are defined. For example, normal operation: [25, 35]°C, minor fault: [35, 40]°C, moderate fault: [40, 45]°C, and severe fault: water temperature > 45°C. If the current water temperature detected by the temperature sensor in the current device operating data falls within the water temperature range corresponding to a moderate fault, the fault level of the liquid cooler where the temperature sensor is installed is determined to be a moderate fault. The current time the current water temperature is detected is determined as the time the liquid cooler fault occurred. The device ID of the liquid cooler or the location of the temperature sensor is determined as the location of the fault. Fault descriptions corresponding to each fault condition can be predefined based on predefined rules. For example, the fault description for a minor liquid cooler fault can be preset as "liquid cooler temperature under-limit exceeded," the fault description for a moderate liquid cooler fault can be preset as "liquid cooler temperature medium-limit exceeded," and the fault description for a severe liquid cooler fault can be preset as "liquid cooler temperature over-limit exceeded." On this basis, the above-mentioned liquid cooler fault is described as the liquid cooler temperature exceeding the limit.

[0053] It should be noted that the temperature control device can also perform fault diagnosis based on the device operating status and / or water temperature. For example, the current device operating status of the liquid cooler is obtained (normal, alarm or fault). If the current device operating status is an alarm, the liquid cooler fault level is determined to be a moderate fault and a moderate alarm is triggered. If the current device operating status is a fault, the liquid cooler fault level is determined to be a severe fault and a severe alarm is triggered. For fault diagnosis based on both the device operating status and water temperature, triggering any of the above will trigger an alarm, and the priority is: severe > moderate > mild. For example, if the water temperature is 37°C and the liquid cooler status is a fault, the liquid cooler should be judged to be a severe fault and a severe alarm should be triggered.

[0054] On the basis of the above technical solution, "determining the target fault diagnosis result corresponding to the target equipment based on the target fault diagnosis method and the standard equipment operation data" may include: performing fault diagnosis on the standard equipment operation data based on the target fault diagnosis method to obtain the fault level and target fault operation parameters corresponding to the target equipment; if the fault level is a preset level, determining the fault description, fault location and fault occurrence time corresponding to the target equipment based on the target fault operation parameters and the standard equipment operation data.

[0055] The target fault operating parameters may refer to the current fault operating parameters of the target device when a fault occurs. The preset level may refer to the fault level of the target device when a fault occurs. The preset level may include, but is not limited to, a mild fault, a moderate fault, and a severe fault.

[0056] For example, using an energy management system as the target device, the energy management system supports the network delay exceeding limit fault diagnosis method. This method analyzes and processes standard device operating data to determine the target fault diagnosis result for the energy management system. Specifically, the energy management system uploads ping communication delay values when communicating with the cloud, and fault diagnosis is performed through threshold comparison testing.

[0057] Preset ranges for communication delay values for normal operation, minor faults, moderate faults, and severe faults of the energy management system are provided. For example, normal operation is [1, 50] ms, minor faults are {50, 100] ms, moderate faults are {100, 200] ms, and severe faults are >200 ms or the energy management system loses communication with the cloud. If the current network delay collected by the sensor in the current device operation data falls within the communication delay value range corresponding to a moderate fault, the energy management system fault level is determined to be a severe fault. The current time at which the current network delay is collected is determined as the time of occurrence of the energy management system fault. The device number of the energy management system is determined as the location of the energy management system fault. Fault descriptions corresponding to each fault condition can be predefined based on predefined rules. For example, the fault description for a minor fault in the energy management system can be preset as "EMS communication network delay low limit exceeded," the fault description for a moderate fault in the energy management system can be preset as "EMS communication network delay medium limit exceeded," and the fault description for a severe fault in the energy management system can be preset as "EMS communication network delay high limit exceeded." Based on this, the fault description for the energy management system is "EMS communication network delay high limit exceeded."

[0058] On the basis of the above technical solution, "determining the fault description, fault location and fault occurrence time corresponding to the target equipment based on the target fault operating parameters and standard equipment operating data" may include: determining the fault location and fault occurrence time corresponding to the target fault operating parameters from the standard equipment operating data based on the target fault operating parameters; determining the fault description corresponding to the target fault operating parameters based on the association between the target fault operating parameters and the preset fault description.

[0059] Specifically, based on the target fault operating parameters, the target sensor that collects the target fault operating parameters can be determined from the standard equipment operating data, and the installation location of the target sensor is determined as the fault location. The time of fault occurrence is determined based on the time when the target fault operating parameters were collected. Based on the association between the target fault operating parameters and the preset fault description, the fault description corresponding to the target fault operating parameters is determined.

[0060] It should be noted that for energy management systems, if the cloud and energy management system lose communication for 5 minutes or longer, it is considered a severe fault, and if the corresponding target fault operating parameters exist at the current moment, it is necessary to trace back the historical device operating data collected for the target device at a historical moment, and determine the time when the energy management system fault occurred based on the historical moment corresponding to the target fault operating parameters of the energy management system in the historical device operating data. Therefore, for target devices that require fault diagnosis based on historical device operating data collected at a historical moment, the time when the target device fault occurred is the historical moment when the target fault operating parameters first appeared when the target device continuously failed, further improving the accuracy of fault diagnosis.

[0061] The technical solution of the embodiment of the present invention obtains the target device type of the target device in the energy storage system and the current device operation data corresponding to the target device; performs data preprocessing on the current device operation data to obtain standard device operation data; determines the target fault diagnosis method corresponding to the target device based on the association between the target device type and the preset fault diagnosis method; determines the target fault diagnosis result corresponding to the target device based on the target fault diagnosis method and the standard device operation data, thereby realizing fault diagnosis of the energy storage system in the cloud, avoiding shutdown inspection of the energy storage system, and without manual inspection, and can accurately and conveniently determine the fault diagnosis result, thereby improving the fault diagnosis efficiency of the energy storage system.

[0062] Building on the aforementioned technical solution, a pre-built and trained dynamic causal inference model based on a Bayesian network is utilized, combined with the energy storage system's operational data (such as temperature chains, current fluctuations, and network topology changes), to automatically identify the root cause of a fault, rather than just the symptoms. For example, when a cell voltage exceeds a certain limit, the dynamic causal inference model analyzes whether the cause is a temperature control failure (a direct cause) or a BMS misjudgment (an indirect cause), and generates a causal path diagram to assist in determining the root cause of the fault.

[0063] Among them, the model construction process includes: Bayesian network structure design and dynamic characteristic embedding. In the Bayesian network structure design process, node variables are defined, which include observable variables (such as battery cell voltage, temperature chain data, current fluctuations) and hidden variables (such as temperature control failure, BMS misjudgment, electrolyte leakage and other potential fault causes). Establish a causal relationship network: determine the directed edge relationship between nodes through the expert knowledge base and historical fault data. For example, a temperature sensor anomaly may point to temperature control failure, and a BMS misjudgment may affect the voltage readings of multiple batteries at the same time. In the dynamic characteristic embedding process, a time slicing mechanism is introduced, so that time series data can be processed through a dynamic Bayesian network (DBN).

[0064] The data-driven reasoning process includes multi-source data fusion and fault tracing algorithms. Three data sources—real-time energy storage system data (temperature, voltage, etc.) collected from the cloud, BMS status messages, and network topology change logs—are integrated to establish a joint probability distribution model. Maximum a posteriori probability estimation (MAP) is used to locate the most likely root cause of the fault. For example, when a cell voltage exceeds a certain limit, the following calculations are performed: P(temperature control failure | voltage anomaly) = 0.72; P(BMS misjudgment | voltage anomaly) = 0.25. Markov chain Monte Carlo (MCMC) methods can also be used to handle uncertainty in high-dimensional parameter spaces.

[0065] Causal paths can be generated using backpropagation tracing, starting from the observed fault symptom node and performing backward probability propagation along the directed edges of the Bayesian network to generate a causal chain with confidence. For example, voltage limit violation → temperature anomaly (confidence 82%) → cooling pump failure (confidence 68%); voltage limit violation → BMS calibration deviation (confidence 31%).

[0066] Example 2

[0067] Figure 2 This is a flowchart of a fault diagnosis method for an energy storage system provided by the second embodiment of the present invention. Based on the above embodiments, this embodiment describes in detail the process of determining the target fault diagnosis result for each type of target device. The explanations of the terms that are the same or corresponding to the above embodiments are not repeated here. Figure 2 As shown, the method includes:

[0068] S210: Obtain a target device type of a target device in the energy storage system and current device operation data corresponding to the target device.

[0069] S220: Preprocess the current equipment operation data to obtain standard equipment operation data.

[0070] S230: Determine a target fault diagnosis method corresponding to the target device based on an association relationship between the target device type and a preset fault diagnosis method.

[0071] S240: If the target fault diagnosis mode is the parameter limit-crossing diagnosis mode, the target fault operating parameters and fault level corresponding to the target device are determined based on the device operating parameters in the standard device operating data and the preset parameter limit intervals.

[0072] The parameter limit diagnosis method may refer to a parameter threshold comparison diagnosis method. In embodiments of the present invention, the parameter limit diagnosis method is applicable to temperature control equipment, energy management systems (EMS), battery clusters, power systems, and single cells. The preset parameter limit range may refer to a threshold range corresponding to each fault level pre-set for each target device.

[0073] For example, taking a battery cluster as the target device, the battery cluster corresponds to a cell voltage differential over-limit fault diagnosis method. During charging and discharging, the energy storage system needs to monitor the inter-cluster and intra-cluster voltage differentials of each battery cluster. Pre-set ranges are defined for mild, moderate, and severe inter-cluster voltage differential faults. For example, if the rated voltage is 800V, the mild fault voltage differential values are [0.5%, 1%]*800V, the moderate fault voltage differential values are {1%, 2%]*800V, and the severe fault voltage differential values are >2%*800V. Furthermore, pre-set ranges are defined for mild, moderate, and severe intra-cluster voltage differential faults. For example, the mild fault voltage differential values are [100, 200]mV, the moderate fault voltage differential values are {200, 500%]mV, and the severe fault voltage differential values are >500mV. Triggering any of the above two items will determine the fault and issue an alarm, and the alarm priority is: severe > moderate > mild.

[0074] For example, taking the power system as the target device, the power system corresponds to the grid frequency fault diagnosis method. Based on power system stability requirements, the nominal frequency of my country's power grid is 50Hz. Pre-set ranges are defined for minor, moderate, and severe power system faults. For example, the deviation value for a minor fault is ±0.2Hz to ±0.5Hz; the deviation value for a moderate fault is ±0.5Hz to ±1.0Hz; and the deviation value for a severe fault is > ±1.0Hz.

[0075] For example, taking a single battery cell as the target device, a single battery cell corresponds to a single voltage and temperature indicator fault diagnosis method. The voltage and temperature ranges for mild, moderate, and severe faults are pre-set. For example, a voltage over-limit mild fault is: {3.65, 3.8]V or [2.5, 2.8}V; a voltage over-limit moderate fault is: {3.8, 4.0]V or [2.0, 2.5}V; a voltage over-limit severe fault is: >4.0V or <2.0V. Another example is a temperature over-limit mild fault is: {45, 55]V or [-10, 0}°C; a temperature over-limit moderate fault is: {55, 65]V or [-20, -10}°C; a temperature over-limit severe fault is: >65°C or <-20°C.

[0076] S250: If the target fault diagnosis method is a hybrid expert model diagnosis method, the standard equipment operation data is input into a preset hybrid expert model for feature extraction and fault diagnosis, and the target fault operation parameters and fault level corresponding to the target equipment are determined.

[0077] Among them, the preset hybrid expert model is constructed by a convolutional neural network and a gating network. For example, a hybrid expert model (Mixture of Experts, MoE) is constructed using a convolutional neural network (CNN) architecture and a gating network to achieve fault classification of PCS, BMS, and dynamic environment. The hybrid expert model diagnosis method may refer to a method of using a hybrid expert model for fault diagnosis. The hybrid expert model diagnosis method is applicable to energy conversion systems, battery management systems, and power environment monitoring systems. Based on empirical data and operation and maintenance records, a BMS / PCS / dynamic environment fault level diagnosis training set with level labels is constructed, and a rule engine is formulated for model training. In an embodiment of the present invention, independent expert networks (expert models) in the hybrid expert model are designed according to the equipment type. For example, according to the needs of fault diagnosis, multiple expert knowledge systems are established for different equipment types and fields. Each expert system consists of a group of related experts, and each expert is responsible for fault diagnosis of a specific type of equipment.

[0078] Specifically, if the target fault diagnosis method is a hybrid expert model, the standard device operating data is input into a preset hybrid expert model for feature extraction to obtain device operating characteristics. Based on the extracted device operating characteristics, the target expert model corresponding to the target device type is determined from the hybrid expert model. The device operating characteristics are input into the target expert model for fault diagnosis, and the fault level and target fault operating parameters used to derive the fault level are obtained. The target fault operating parameters and fault level corresponding to the target device are then output.

[0079] For example, let's take the PCS expert model as the target expert model. The PCS expert model can be used to address power conversion issues such as inverters and abnormal charging and discharging. For example, the PCS expert model can detect insulated gate bipolar transistor (IGBT) failures, IGBT overtemperature, and AC bus overvoltage, and diagnose them as moderate faults to trigger a moderate alarm. It can also detect AC module group insulation detection anomalies or DC module group insulation detection anomalies and diagnose them as severe faults to trigger a severe alarm.

[0080] For example, the target expert model is a BMS expert model. The BMS expert model can be used to analyze battery management issues such as battery pack voltage balancing and SOC jumps. For example, it can detect inter-cluster current imbalance alarms, a summary of mild under-temperature alarms for modules within the stack, and a summary of mild over-temperature alarms for modules within the stack, and diagnose them as mild faults to trigger mild alarms. It can also detect a summary of moderate low insulation resistance alarms for modules within the stack, abnormal closing of the stack contactor, and abnormal opening of the stack contactor, and diagnose them as moderate faults to trigger moderate alarms. It can also detect abnormal system status and abnormal cluster status, and diagnose them as severe faults to trigger severe alarms.

[0081] For example, let's take the dynamic environment expert model as an example. The dynamic environment expert model can be used to focus on environmental alarms such as temperature and humidity, water intrusion, and smoke. For example, it can detect a transformer dehumidifier fan failure or a transformer dehumidifier communication failure and diagnose it as a minor fault, triggering a minor alarm. It can also detect a transformer overtemperature trip, transformer overtemperature alarm, or transformer core overtemperature alarm and diagnose it as a moderate fault, triggering a moderate alarm. It can also detect single fire alarms, multiple fire alarms, and box transformer measurement and control-smoke signals and diagnose them as severe faults, triggering a severe alarm.

[0082] It should be noted that for complex diagnostic alert scenarios that cannot be matched by rules, machine learning models can be introduced for classification and analysis of abnormal patterns in time series data. Dynamic weight adjustment enables the rule engine and machine learning model to work in tandem. A lightweight inference model can be deployed locally to implement low-latency hierarchical classification preprocessing. The cloud is responsible for model training, rule table updates, and expert weight adjustment. For example, for battery life model testing, the corresponding life analysis model can be selected based on the cell model. For example, for an LF-280K cell, the model predicts that after two years of energy storage system operation and 1500 cycles, the cell's state of health (SOH) will be 95.65%. Therefore, SOH alarm ranges can be set for minor, moderate, and severe faults. For example: Minor fault alarm value: [0, 10%] * 95.65%; moderate fault alarm value: {10%, 20%] * 95.65%; severe fault alarm value: voltage differential > 20% * 95.65%.

[0083] S260: If the fault level is a preset level, determine the fault description, fault location, and fault occurrence time corresponding to the target device based on the target fault operating parameters and the standard device operating data.

[0084] Exemplarily, the target fault diagnosis result may also include the fault type. The fault type may be determined by the target device type. For example, if the target device is an energy conversion system, the fault type of the energy conversion system is a PCS abnormality. If the target device is a power environment monitoring system, the fault type of the power environment monitoring system is a dynamic environment system abnormality. When multiple target devices are simultaneously undergoing fault diagnosis, the cloud can statistically display the target fault diagnosis results of all target devices by category, thereby determining the proportion of target devices corresponding to each fault type and displaying them using a bar chart or a fan chart.

[0085] The technical solution of the embodiment of the present invention is that if the target fault diagnosis method is a parameter over-limit diagnosis method, the target fault operation parameters and fault level corresponding to the target device are determined based on the device operation parameters in the standard device operation data and the preset parameter limit interval. Therefore, for the target device applicable to the parameter over-limit diagnosis method, the device operation data can be directly compared through the preset parameter limit interval (such as voltage, temperature threshold) to achieve rapid identification and classification of faults; if the target fault diagnosis method is a hybrid expert model diagnosis method, the standard device operation data is input into the preset hybrid expert model for feature extraction and fault diagnosis, and the target fault operation parameters and fault level corresponding to the target device are determined. Therefore, for the target device applicable to the hybrid expert model diagnosis method, the gated network can be used to dynamically select the expert sub-model (target expert model), and multi-dimensional feature extraction and fault diagnosis can be performed for complex fault modes, further improving the accuracy of fault diagnosis. Multiple target devices of different device types can use their respective applicable target fault diagnosis methods for fault diagnosis in parallel, further improving the efficiency of fault diagnosis.

[0086] It should be noted that when the parameter out-of-limit diagnosis method cannot clearly identify the root cause of the fault (such as BMS misjudgment or actual temperature control failure), the hybrid expert model can also distinguish direct / indirect causes through multi-expert collaborative reasoning.

[0087] The following is an embodiment of a fault diagnosis device for an energy storage system provided by an embodiment of the present invention. This device and the fault diagnosis method for an energy storage system in each of the above embodiments belong to the same inventive concept. For details not fully described in the embodiment of the fault diagnosis device for an energy storage system, reference can be made to the embodiment of the fault diagnosis method for an energy storage system described above.

[0088] Example 3

[0089] Figure 3 This is a schematic diagram of the structure of a fault diagnosis device for an energy storage system provided by the third embodiment of the present invention. Figure 3As shown, the apparatus includes: a current equipment operation data acquisition module 310 , a standard equipment operation data determination module 320 , a target fault diagnosis method determination module 330 and a target fault diagnosis result determination module 340 .

[0090] Among them, the current device operation data acquisition module 310 is used to obtain the target device type of the target device in the energy storage system and the current device operation data corresponding to the target device; the standard device operation data determination module 320 is used to perform data preprocessing on the current device operation data to obtain standard device operation data; the target fault diagnosis method determination module 330 is used to determine the target fault diagnosis method corresponding to the target device based on the association relationship between the target device type and the preset fault diagnosis method; the target fault diagnosis result determination module 340 is used to determine the target fault diagnosis result corresponding to the target device based on the target fault diagnosis method and the standard device operation data.

[0091] The technical solution of the embodiment of the present invention obtains the target device type of the target device in the energy storage system and the current device operation data corresponding to the target device; performs data preprocessing on the current device operation data to obtain standard device operation data; determines the target fault diagnosis method corresponding to the target device based on the association between the target device type and the preset fault diagnosis method; determines the target fault diagnosis result corresponding to the target device based on the target fault diagnosis method and the standard device operation data, thereby realizing fault diagnosis of the energy storage system, avoiding shutdown inspection of the energy storage system, and without manual inspection, and can accurately and conveniently determine the fault diagnosis result, thereby improving the fault diagnosis efficiency of the energy storage system.

[0092] Based on the above technical solution, the target equipment includes: at least one of: temperature control equipment, energy management system, battery cluster, power system, single battery cell, energy conversion system, battery management system and power environment monitoring system.

[0093] On the basis of the above technical solutions, the target fault diagnosis method corresponding to the temperature control equipment is the temperature control over-limit fault diagnosis method; the target fault diagnosis method corresponding to the energy management system is the network delay over-limit fault diagnosis method; the target fault diagnosis method corresponding to the battery cluster is the cell voltage difference over-limit fault diagnosis method; the target fault diagnosis method corresponding to the power system is the grid frequency fault diagnosis method; the target fault diagnosis method corresponding to the single cell is the cell voltage and temperature index fault diagnosis method; the target fault diagnosis method corresponding to the energy conversion system is the diagnosis method based on the PCS expert model; the target fault diagnosis method corresponding to the battery management system is the diagnosis method based on the BMS expert model; the target fault diagnosis method corresponding to the power environment monitoring system is the diagnosis method based on the dynamic environment expert model.

[0094] Based on the above technical solution, the target fault diagnosis result determination module 340 may include:

[0095] A first fault diagnosis result determination submodule is configured to perform fault diagnosis on the standard equipment operating data based on a target fault diagnosis method to obtain a fault level and target fault operating parameters corresponding to the target equipment;

[0096] The second fault diagnosis result determination submodule is used to determine the fault description, fault location and fault occurrence time corresponding to the target device based on the target fault operating parameters and standard device operating data if the fault level is a preset level.

[0097] On the basis of the above technical solution, the first fault diagnosis result determination submodule is specifically used for: if the target fault diagnosis method is the parameter over-limit diagnosis method, then based on the equipment operating parameters in the standard equipment operation data and the preset parameter limit interval, determine the target fault operating parameters and fault level corresponding to the target equipment; if the target fault diagnosis method is the hybrid expert model diagnosis method, then input the standard equipment operation data into the preset hybrid expert model for feature extraction and fault diagnosis to determine the target fault operating parameters and fault level corresponding to the target equipment.

[0098] Based on the above technical solution, the second fault diagnosis result determination submodule is specifically used to: determine the fault location and fault occurrence time corresponding to the target fault operating parameters from the standard equipment operation data based on the target fault operating parameters; determine the fault description corresponding to the target fault operating parameters based on the association relationship between the target fault operating parameters and the preset fault description.

[0099] On the basis of the above technical solution, the target fault diagnosis result includes at least one of: fault description, fault level, fault location and fault occurrence time.

[0100] On the basis of the above technical solution, the device further comprises: a statistical result display module;

[0101] The statistical result display module is used to categorize and count the target fault diagnosis results of each target device and display the statistical results on the interface; wherein, the statistical results include the proportion of the number of target devices corresponding to each fault level; the display method of the statistical results includes at least one of a bar chart and a fan chart.

[0102] The energy storage system fault diagnosis device provided in the embodiment of the present invention can execute the energy storage system fault diagnosis method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the energy storage system fault diagnosis method.

[0103] It is worth noting that in the above-mentioned embodiment of fault diagnosis of the energy storage system, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present invention.

[0104] Example 4

[0105] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0106] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0107] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0108] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the energy storage system fault diagnosis method.

[0109] In some embodiments, the fault diagnosis method for the energy storage system may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the fault diagnosis method for the energy storage system described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the fault diagnosis method for the energy storage system in any other appropriate manner (e.g., by means of firmware).

[0110] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0111] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0112] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0113] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0114] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0115] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0116] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the fault diagnosis method for the energy storage system provided in any embodiment of the present application.

[0117] During the implementation of the computer program product, the computer program code for performing the operations of the present invention can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and also conventional procedural programming languages such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). The program product and the fault diagnosis method for the energy storage system disclosed in each embodiment of the present application belong to the same inventive concept, and therefore will not be described in detail here.

[0118] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0119] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A fault diagnosis method for an energy storage system, characterized in that: include: Obtaining a target device type of a target device in the energy storage system and current device operation data corresponding to the target device; Performing data preprocessing on the current equipment operation data to obtain standard equipment operation data; Determining a target fault diagnosis method corresponding to the target device based on an association relationship between the target device type and a preset fault diagnosis method; Based on the target fault diagnosis mode and the standard equipment operation data, a target fault diagnosis result corresponding to the target equipment is determined.

2. The method according to claim 1, characterized in that The target device includes: at least one of a temperature control device, an energy management system, a battery cluster, a power system, a single battery cell, an energy conversion system, a battery management system and a power environment monitoring system.

3. The method according to claim 2, characterized in that The target fault diagnosis method corresponding to the temperature control device is the temperature control over-limit fault diagnosis method; the target fault diagnosis method corresponding to the energy management system is the network delay over-limit fault diagnosis method; the target fault diagnosis method corresponding to the battery cluster is the cell voltage difference over-limit fault diagnosis method; the target fault diagnosis method corresponding to the power system is the grid frequency fault diagnosis method; the target fault diagnosis method corresponding to the single cell is the cell voltage and temperature index fault diagnosis method; the target fault diagnosis method corresponding to the energy conversion system is the diagnosis method based on the PCS expert model; the target fault diagnosis method corresponding to the battery management system is the diagnosis method based on the BMS expert model; the target fault diagnosis method corresponding to the power environment monitoring system is the diagnosis method based on the dynamic environment expert model.

4. The method according to claim 1, wherein The determining, based on the target fault diagnosis mode and the standard equipment operation data, a target fault diagnosis result corresponding to the target equipment includes: Performing fault diagnosis on the standard equipment operating data based on the target fault diagnosis method to obtain the fault level and target fault operating parameters corresponding to the target equipment; If the fault level is a preset level, the fault description, fault location, and fault occurrence time corresponding to the target device are determined based on the target fault operating parameters and the standard device operating data.

5. The method according to claim 4, characterized in that The performing fault diagnosis on the standard equipment operating data based on the target fault diagnosis method to obtain the fault level and target fault operating parameters corresponding to the target equipment includes: If the target fault diagnosis mode is a parameter limit-crossing diagnosis mode, determining the target fault operating parameters and fault level corresponding to the target device based on the device operating parameters in the standard device operating data and the preset parameter limit intervals; If the target fault diagnosis method is a hybrid expert model diagnosis method, the standard equipment operation data is input into a preset hybrid expert model for feature extraction and fault diagnosis to determine the target fault operation parameters and fault level corresponding to the target equipment.

6. The method according to claim 4, characterized in that The determining, based on the target fault operating parameters and the standard equipment operating data, a fault description, a fault location, and a fault occurrence time corresponding to the target equipment includes: Determining, based on the target fault operating parameters, from the standard equipment operating data, a fault occurrence location and a fault occurrence time corresponding to the target fault operating parameters; Based on the association relationship between the target fault operating parameter and the preset fault description, the fault description corresponding to the target fault operating parameter is determined.

7. The method according to any one of claims 1 to 6, characterized in that The target fault diagnosis result includes at least one of a fault description, a fault level, a fault location, and a fault occurrence time.

8. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Analyze the target fault diagnosis results of each target device by category and display the statistical results on the interface; The statistical results include the proportion of target devices corresponding to each fault level; and the statistical results are displayed in at least one of a bar chart and a fan chart.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; a memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the fault diagnosis method for the energy storage system as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the fault diagnosis method for the energy storage system as described in any one of claims 1 to 8 is implemented.

Images