Method and apparatus for recognizing faults in energy storage power plants based on knowledge graphs

Abstract

This application provides a knowledge graph-based energy storage power plant fault recognition method and apparatus for the power industry. The knowledge graph-based energy storage power plant fault recognition method includes: acquiring status data of the energy storage power plant; inputting the status data into a pre-built energy storage power plant fault recognition model based on a thermal runaway knowledge graph to characterize the correlation between the status data of the energy storage power plant and the thermal runaway process; predicting the fault status and transition path of the energy storage power plant; and determining the safety risk level of the energy storage power plant based on the fault status and transition path. This application enables comprehensive and accurate evaluation of the operating status of the energy storage power plant and realizing long-term fault warning.

Description

[Technical Field]

[0001] The present application relates to the electric power field, and in particular relates to a method and an apparatus for fault identification of energy storage power plants based on knowledge graphs. [Background Art]

[0002] With the rapid development of renewable energy, the application of energy storage power plants has become increasingly widespread. However, the problems of faults and safety risks of energy storage power plants have also become increasingly prominent. In recent years, fire incidents of energy storage power plants have occurred frequently. To ensure the safe and stable operation of energy storage power plants, it is necessary to monitor and analyze the operation status of energy storage power plants in real time and detect potential fault risks.

[0003] In the prior art, monitoring of energy storage power plants is mainly implemented by sensors and data acquisition systems, and fault conditions and safety risks of energy storage power plants are evaluated through data analysis and processing. However, such methods often only consider individual health characteristic data such as cycle time and number of cycles, and limited electrical parameters such as real-time current and voltage, making it difficult to comprehensively and accurately evaluate the overall operation status and safety risks of energy storage power plants. In addition, the available early prediction time is limited, and long-term early warning cannot be realized. [Summary of Invention] [Problem to be Solved by the Invention]

[0004] The present application provides a knowledge graph-based method and apparatus for fault identification of energy storage power plants, to comprehensively and accurately evaluate the operation status of energy storage power plants and realize long-term early fault warning. Unit for solving the problem

[0005] In a first aspect, the present application provides: acquiring status data of an energy storage power plant; The state data is input into an energy storage plant failure recognition model, which is pre-built based on a thermal runaway knowledge graph that characterizes the relationship between the state data of the energy storage plant and the thermal runaway process, in order to predict the failure status and progression path of the energy storage plant. Based on the failure status and progression path, the safety risk level of the energy storage power plant will be determined, This provides a fault detection method for energy storage power plants based on a knowledge graph that includes this information.

[0006] Based on the above method, the system predicts the failure status and progression path of an energy storage power plant based on real-time monitored status data of the energy storage power plant and an energy storage power plant failure recognition model constructed based on a thermal runaway knowledge graph that characterizes the relationship between the status data and the thermal runaway process. It comprehensively predicts the thermal runaway process that may occur in the energy storage power plant, and further determines the safety risk level of the energy storage power plant based on the failure status and progression path, thereby ensuring the safe and stable operation of the energy storage power plant. By applying status data related to the thermal runaway process to the energy storage power plant for failure prediction and progression path prediction, the system comprehensively covers various data in the thermal runaway process of the energy storage power plant, and considers various possible factors related to the thermal runaway process, it achieves accurate pre-assessment of the safety risk of the energy storage power plant, enables timely detection of potential failures and safety risks, provides long-term early warning of failures, provides reference and decision-making support to maintenance personnel, and avoids the occurrence of fire events in the energy storage power plant.

[0007] In a preferred embodiment, the step of constructing an energy storage power plant failure recognition model is: To obtain a thermal runaway knowledge graph for an energy storage power plant, which includes historical state data of the energy storage power plant, historical failure conditions corresponding to the historical state data, and historical transition paths. This includes using historical state data as input to an initial energy storage power plant failure recognition model, using historical failure conditions and historical transition paths as outputs to the initial energy storage power plant failure recognition model, and training the initial energy storage power plant failure recognition model to obtain an energy storage power plant failure recognition model.

[0008] In the above embodiment, the thermal runaway knowledge graph includes the relationship between the state data of the energy storage power plant and the thermal runaway process. By training an initial energy storage power plant failure recognition model with historical state data, historical failure conditions corresponding to the historical state data, and historical transition paths, an energy storage power plant failure recognition model can be obtained. Based on the state data related to the thermal runaway process of the energy storage power plant, various factors can be comprehensively considered to improve the prediction accuracy of the energy storage power plant failure recognition model.

[0009] In a preferred embodiment, obtaining a thermal runaway knowledge graph of an energy storage power plant is possible. Based on the thermal runaway transition mechanism of batteries, the state data type of energy storage power plants is determined, Based on the state data type, obtain historical state data for energy storage power plants, This includes obtaining historical failure status and historical transition path corresponding to the historical status data, based on the historical status data.

[0010] In a preferred embodiment, determining the state data type of an energy storage power plant based on the battery thermal runaway transition mechanism is possible. Based on the thermal runaway transition mechanism of batteries, the thermal runaway process of energy storage power plants is determined, This includes determining the state data type based on the thermal runaway process.

[0011] According to the above embodiment, the state data type of the energy storage power plant is determined based on the battery thermal runaway transition mechanism, which contributes to better analyzing the battery thermal runaway transition process. By determining the relevant data in the battery thermal runaway transition process as state data, the failure status and transition path of the energy storage power plant can be monitored and predicted more accurately.

[0012] In a preferred embodiment, the thermal runaway process includes an external process, an internal battery change process, and a thermal runaway generation process, and the state data type is determined based on the thermal runaway process. Determining the external parameters of an energy storage power plant based on an external process, Based on the internal change processes of the battery, the internal parameters of the battery in an energy storage power plant are determined, Based on the thermal runaway generation process, the thermal diffusion parameters of an energy storage power plant are determined, This includes determining the state data type based on external parameters, internal battery parameters, and thermal diffusion parameters.

[0013] The above embodiment comprehensively analyzes the thermal runaway process, divides it into an external process, an internal battery change process, and a thermal runaway occurrence process, determines external parameters based on the external process, determines internal battery parameters based on the internal battery change process, determines thermal diffusion parameters based on the thermal runaway occurrence process, determines corresponding parameters for different thermal runaway processes, and comprehensively understands the operating status and failure status of the energy storage power plant, thereby contributing to improving the prediction accuracy of the energy storage power plant failure recognition model.

[0014] In a preferred embodiment, the energy storage power plant fault recognition method based on the knowledge graph is: This further includes transmitting preventative alert information to energy storage power plants based on safety risk levels.

[0015] The above embodiment contributes to the timely transmission of preventive alarm information to energy storage power plants based on safety risk levels, alerting maintenance personnel to potential safety risks, enabling appropriate preventive and control measures, improving maintenance work efficiency, avoiding accidents, and reducing losses due to fires at energy storage power plants.

[0016] In the second embodiment, the present application is, An acquisition module for obtaining status data of an energy storage power plant, State data is input into an energy storage plant failure recognition model, which is pre-built based on a thermal runaway knowledge graph that characterizes the relationship between the state data of the energy storage plant and the thermal runaway process. A prediction module is used to predict the failure status and progression path of the energy storage plant. A determination module for determining the safety risk level of an energy storage power plant based on the failure status and progression path, Furthermore, we provide an energy storage power plant fault recognition system based on a knowledge graph that includes this.

[0017] The above device predicts the failure status and progression path of an energy storage plant based on real-time monitored status data of the energy storage plant and an energy storage plant failure recognition model constructed based on a thermal runaway knowledge graph that characterizes the relationship between the status data and the thermal runaway process. It comprehensively predicts the thermal runaway process that may occur in the energy storage plant, and further determines the safety risk level of the energy storage plant based on the failure status and progression path, thereby ensuring the safe and stable operation of the energy storage plant. It applies status data related to the thermal runaway process to the energy storage plant for failure prediction and progression path prediction, comprehensively covers various data in the thermal runaway process of the energy storage plant, and considers various possible factors related to the thermal runaway process to achieve accurate pre-assessment of the safety risk of the energy storage plant, timely detection of potential failures and safety risks, long-term early warning of failures, provides reference and decision-making support to maintenance personnel, and avoids the occurrence of fire events in the energy storage plant.

[0018] In a preferred embodiment, the prediction module comprises: an acquisition sub-module configured to acquire a thermal runaway knowledge graph of an energy storage power station, wherein the thermal runaway knowledge graph comprises historical state data of the energy storage power station, historical fault conditions corresponding to the historical state data, and historical transition paths; and a training sub-module configured to take the historical state data as input of an initial energy storage power station fault recognition model, take the historical fault conditions and the historical transition paths as output of the initial energy storage power station fault recognition model, and train the initial energy storage power station fault recognition model to obtain an energy storage power station fault recognition model.

[0019] In a third aspect, the present application further provides a computer device, comprising a memory storing computer instructions, and a processor communicatively connected to the memory, wherein the processor executes the computer instructions to perform the steps of the energy storage power station fault recognition method based on a knowledge graph according to the first aspect or any embodiment of the first aspect.

[0020] In a fourth aspect, the present application further provides a computer-readable storage medium storing a computer program, wherein when executed by a processor, the computer program implements the steps of the energy storage power station fault recognition method based on a knowledge graph according to the first aspect or any embodiment of the first aspect.

[0021] Hereinafter, in order to more clearly describe the specific embodiments of the present application or the technical solutions in the prior art, the drawings that need to be used for the description of the specific embodiments or the prior art will be briefly described. It is obvious that the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can be obtained based on these drawings without creative efforts. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] [Figure 1] It is a flowchart of an energy storage power station fault recognition method based on a knowledge graph according to an exemplary embodiment. [Figure 2] This is a schematic diagram of the structure of an energy storage power plant fault recognition device based on a knowledge graph relating to an exemplary embodiment. [Figure 3] This is a schematic diagram of the hardware structure of a computer device according to an exemplary embodiment. [Modes for carrying out the invention]

[0023] The present invention will be described clearly and completely below with reference to the drawings, and it will be clear that the described embodiments are not all embodiments but only some embodiments of the present invention. According to the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are included in the scope of the invention.

[0024] Furthermore, the technical features of the different embodiments of the present application described below can be combined with each other, as long as they do not contradict each other.

[0025] This invention provides a knowledge graph-based fault recognition method and apparatus for an energy storage power plant, in order to comprehensively and accurately evaluate the operating status of the energy storage power plant and to realize long-term fault early warning.

[0026] Figure 1 is a flowchart of a knowledge graph-based energy storage power plant fault recognition method according to an exemplary embodiment. The knowledge graph-based energy storage power plant fault recognition method includes the following steps S101 to S103, as shown in Figure 1.

[0027] Step S101: Obtain status data for the energy storage power plant.

[0028] In a preferred embodiment, an energy storage power plant is a facility system that stores, converts, and releases recyclable electrical energy using an electrochemical battery or an electromagnetic energy storage medium. It can effectively solve problems such as peak modulation of the power system, output stabilization, improvement of electrical energy quality, and peak shaving, and is of great importance in balancing load fluctuations. At the same time, energy storage power plants have economies of scale, can stabilize voltage during high load periods, suppress fluctuations in the power grid, and guarantee power supply quality. Furthermore, energy storage power plants can perform charging and discharging using an energy storage system, storing electrical energy during off-peak hours and releasing electrical energy during peak hours, thereby reducing electricity usage costs and improving energy utilization efficiency.

[0029] In a preferred embodiment, the energy storage power plant includes equipment such as a battery pack, an energy storage converter, and an isolation transformer. Here, the battery pack serves as the core equipment of the energy storage power plant and is used to store electrical energy. The battery pack typically consists of multiple battery cells, which may be lithium-ion batteries, lead-acid batteries, sodium-sulfur batteries, etc. The energy storage converter is used to perform energy conversion between the battery pack and the power grid, and includes charging and discharging. The isolation transformer isolates the energy storage power plant from the power grid, ensuring the independent operation and safety of the energy storage power plant.

[0030] In a preferred embodiment, the state data of the energy storage power plant may include external parameters, internal battery parameters, thermal diffusion parameters, etc., based on relevant factors in the thermal runaway process of the energy storage power plant.

[0031] Step S102: The state data is input into an energy storage plant failure recognition model, which is pre-built based on a thermal runaway knowledge graph that characterizes the relationship between the state data of the energy storage plant and the thermal runaway process, and the failure status and transition path of the energy storage plant are predicted.

[0032] In a preferred embodiment, the energy storage power plant fault recognition model may be constructed using algorithms such as machine learning, and is not specifically limited thereto.

[0033] In a preferred embodiment, the failure conditions predicted based on the energy storage power plant failure recognition model may be failure conditions of individual components in the energy storage power plant, failure conditions of batteries, or failure conditions of other components in the energy storage power plant, and are not specifically limited thereto.

[0034] In a preferred embodiment, the transition path predicted based on the energy storage power plant failure recognition model is the transition path of each piece of equipment in the energy storage power plant under the given state data.

[0035] Step S103: Determine the safety risk level of the energy storage power plant based on the failure status and progression path.

[0036] In a preferred embodiment, the safety risk level of an energy storage power plant is determined based on the failure conditions and the degree of loss due to the transition path. Different failure conditions and different transition paths result in different safety risk levels.

[0037] Based on the above method, the system predicts the failure status and progression path of an energy storage power plant based on real-time monitored status data of the energy storage power plant and an energy storage power plant failure recognition model constructed based on a thermal runaway knowledge graph that characterizes the relationship between the status data and the thermal runaway process. It comprehensively predicts the thermal runaway process that may occur in the energy storage power plant, and further determines the safety risk level of the energy storage power plant based on the failure status and progression path, thereby ensuring the safe and stable operation of the energy storage power plant. By applying status data related to the thermal runaway process to the energy storage power plant for failure prediction and progression path prediction, the system comprehensively covers various data in the thermal runaway process of the energy storage power plant, and considers various possible factors related to the thermal runaway process, it achieves accurate pre-assessment of the safety risk of the energy storage power plant, enables timely detection of potential failures and safety risks, provides long-term early warning of failures, provides reference and decision-making support to maintenance personnel, and avoids the occurrence of fire events in the energy storage power plant.

[0038] In one example, in step S102 above, an energy storage power plant failure recognition model is constructed by the following steps.

[0039] Step a1: Obtain a thermal runaway knowledge graph for the energy storage power plant, which includes the historical state data of the energy storage power plant, the historical failure conditions corresponding to the historical state data, and the historical transition path.

[0040] Step a2: The initial energy storage plant failure recognition model is obtained by training the initial energy storage plant failure recognition model with historical state data as input and historical failure conditions and historical transition paths as outputs.

[0041] In the embodiment of the present invention, the thermal runaway knowledge graph includes the relationship between the state data of the energy storage power plant and the thermal runaway process. An energy storage power plant failure recognition model is obtained by training an initial energy storage power plant failure recognition model with historical state data, historical failure conditions corresponding to the historical state data, and historical transition paths. Based on the state data related to the thermal runaway process of the energy storage power plant, various factors are comprehensively considered to improve the prediction accuracy of the energy storage power plant failure recognition model.

[0042] In one example, in step a1 above, the thermal runaway knowledge graph of the energy storage power plant is obtained by the following steps.

[0043] Step b1: Determine the state data type of the energy storage power plant based on the battery thermal runaway transition mechanism.

[0044] In preferred embodiments, the battery thermal runaway transition mechanism includes trigger elements, chemical reactions, heat transfer and heat storage, physical manifestations of thermal runaway, and chain reactions of thermal runaway. When determining the thermal runaway process of an energy storage power plant, it is necessary to comprehensively consider the above factors and analyze them in accordance with the actual operating conditions of the energy storage power plant. A deep understanding of the battery thermal runaway transition mechanism can lead to more accurate prediction and prevention of thermal runaway events in energy storage power plants, thereby improving the safety and stability of the energy storage power plant.

[0045] In preferred embodiments, thermal runaway of a battery can be triggered by various factors such as overcharging, over-discharging, high temperatures, and short circuits, which can accelerate chemical reactions within the battery and generate a large amount of heat.

[0046] In preferred embodiments, the chemical reactions that cause thermal runaway in a battery typically include oxidation-reduction reactions between the positive and negative electrode materials, and decomposition of the electrolyte. These reactions generate large amounts of heat and gas, increasing the temperature and pressure inside the battery.

[0047] In a preferred embodiment, heat transfer refers to the transfer of heat to the external environment through the battery housing when the internal temperature of the battery rises. If thermal control is inadequate, the battery temperature will continue to rise, leading to heat buildup.

[0048] In preferred embodiments, as the battery temperature rises, the physical properties of the battery also change, such as expansion of the housing and leakage of the electrolyte. These physical manifestations can be important evidence for determining whether or not the battery has experienced thermal runaway.

[0049] In a preferred embodiment, a thermal runaway chain reaction refers to the possibility that once a battery experiences thermal runaway, it can trigger a chain reaction including temperature increases in adjacent batteries and electrolyte leakage. These chain reactions can affect the safety of the entire energy storage power plant.

[0050] Step b2: Based on the state data type, retrieve the historical state data of the energy storage power plant.

[0051] Step b3: Based on the historical status data, obtain the historical failure status and historical transition path corresponding to the historical status data.

[0052] In one example, in step b1 above, the status data type of the energy storage power plant is determined as follows.

[0053] First, the thermal runaway process of an energy storage power plant is determined based on the battery thermal runaway transition mechanism. Exemplary examples include external processes (e.g., external usage conditions), internal battery change processes (including, but not limited to, SEI film decomposition, dendrite growth, positive electrode oxygen release, negative electrode lithium deposition, internal short circuits, and electrolyte leakage), and thermal runaway generation processes.

[0054] Then, the state data type is determined based on the thermal runaway process.

[0055] In the embodiment of the present invention, the state data type of the energy storage power plant is determined based on the battery thermal runaway transition mechanism. According to the battery thermal runaway transition mechanism, it is possible to better analyze the transition process of battery thermal runaway, and by determining the relevant data in the transition process of battery thermal runaway as state data, the failure status and transition path of the energy storage power plant can be monitored and predicted more comprehensively and accurately.

[0056] In one example, the thermal runaway process includes an external process, an internal battery change process, and a thermal runaway generation process.

[0057] Here, external processes refer to external usage processes. Exemplary examples include processes that mechanically trigger battery thermal runaway (for example, collisions that deform the lithium battery pack, short circuits inside the battery pack, and other actions that damage the battery pack can cause battery thermal runaway).

[0058] The internal battery change process refers to the electrochemical reactions involved in thermal runaway within the battery, such as the decomposition reactions of the positive and negative electrodes, the interactions between the positive and negative electrodes, and internal short circuits. Simultaneously, when the temperature reaches 120-130°C, the protective SEI film breaks down, the negative electrode reacts with the solvent and binder, the temperature rises, and the separator melts and closes. After the temperature continues to rise above 150°C, the internal electrolyte begins to decompose, continuously releasing heat and further heating the battery.

[0059] The thermal runaway process refers to the process where, when the battery temperature reaches 200°C or higher, the positive electrode material decomposes, releasing a large amount of heat and gas, causing the temperature to continue rising. Between 250 and 350°C, the negative electrode, in a lithium-storage state, begins to react with the electrolyte. In the final reaction, the electrolyte reacts violently with the oxygen generated by the reaction between the positive electrode and the negative electrode, further causing thermal runaway in the battery.

[0060] In the embodiments of this application, the state data type is determined according to the following:

[0061] First, the external parameters of the energy storage power plant are determined based on an external process. In the embodiments of this application, the external parameters include external usage parameters and external environmental parameters.

[0062] In preferred embodiments, external usage parameters include mechanical abuse data (needling, shock, etc.), thermal abuse data (high temperature, low temperature), electrical abuse data (overcharge, short circuit, etc.), and battery quality data. External environmental parameters include, but are not limited to, temperature, humidity, wind speed, and illuminance. These external environmental parameters reflect the environmental conditions of the energy storage power plant and can affect the operating state and lifespan of the battery. Here, the charge / discharge performance and lifespan of the battery are closely related to temperature. Excessive temperature can lead to dangers such as internal short circuits and thermal runaway in the battery. Therefore, monitoring the temperature of the energy storage power plant allows for the timely detection of potential safety risks and the implementation of appropriate countermeasures. Excessive humidity can cause problems such as internal short circuits and corrosion in the battery. Therefore, monitoring the humidity of the energy storage power plant can ensure the normal operation and lifespan of the battery. Wind speed has a significant impact on the heat dissipation and cooling effect of the energy storage power plant. In hot weather, slow wind speeds can cause the battery temperature to become too high, potentially leading to thermal runaway. Therefore, by monitoring the wind speed of an energy storage power plant, the cooling system can be adjusted in a timely manner to ensure the normal operation of the batteries. For solar energy storage power plants, light irradiation intensity is an important factor that affects the amount of power generated by the batteries. If the illumination is too strong, the batteries may overheat, potentially affecting their lifespan. Therefore, by monitoring the light irradiation intensity of an energy storage power plant, the operating conditions of the batteries can be adjusted in a timely manner to ensure the normal operation and lifespan of the batteries.

[0063] Next, the internal parameters of the battery in the energy storage power plant are determined based on the internal change process of the battery.

[0064] In a preferred embodiment, the internal parameters of the battery in the energy storage power plant include voltage, current, temperature, and charge state.

[0065] Battery voltage is an important parameter that reflects the state of electrochemical reactions inside the battery. By monitoring the battery voltage, it is possible to determine the battery's charge / discharge state and whether or not there are any abnormal conditions such as internal short circuits.

[0066] Battery current is a parameter that reflects the battery's charge and discharge capacity. By monitoring the battery current, it is possible to determine the battery's charge and discharge rate and efficiency, as well as whether or not overcharging or over-discharging is occurring.

[0067] Battery temperature is a crucial parameter that reflects the thermal equilibrium state inside the battery. By monitoring the battery temperature, it is possible to determine the battery's heat dissipation effectiveness, safety, and the presence or absence of a risk of thermal runaway.

[0068] The charge rate is a parameter that reflects the remaining capacity of the battery. By monitoring the charge rate, it is possible to determine the remaining battery capacity and whether there is a shortage of power or overcharging.

[0069] Next, the thermal diffusion parameters of the energy storage power plant are determined based on the thermal runaway generation process.

[0070] In preferred embodiments, thermal diffusion parameters include, but are not limited to, the thermal resistance between the cell and the side plate, the thermal resistance between cells, the thickness of the outer insulation pad on the side plate, and the thermal resistance between the cell and the water cooling plate. Furthermore, thermal diffusion parameters may also include trigger conditions, diffusion rate, and diffusion range. Here, trigger conditions refer to voltage drop and heating rate. > 1°C / s refers to a temperature exceeding the battery's permissible limit.

[0071] Finally, the state data type is determined based on the external parameters, internal battery parameters, and thermal diffusion parameters. For example, using the external parameters, internal battery parameters, and thermal diffusion parameters as the state data type, state data corresponding to an energy storage power plant can be collected based on the state data type.

[0072] In the embodiment of this invention, the thermal runaway process is comprehensively analyzed, divided into an external process, an internal battery change process, and a thermal runaway generation process. External parameters are determined based on the external process, internal battery parameters are determined based on the internal battery change process, and thermal diffusion parameters are determined based on the thermal runaway generation process. Corresponding parameters are determined for different thermal runaway processes, and by comprehensively understanding the operating status and failure status of the energy storage power plant, this contributes to improving the prediction accuracy of the energy storage power plant failure recognition model.

[0073] For example, the method provided in the embodiments of this application is This further includes transmitting preventative alert information to energy storage power plants based on safety risk levels.

[0074] In the embodiment of the present invention, based on the safety risk level, preventive alarm information is transmitted to the energy storage power plant in a timely manner, alerting maintenance personnel to potential safety risks, enabling appropriate preventive and control measures to be taken, thereby improving maintenance work efficiency, avoiding accidents, and contributing to reducing losses due to fires at the energy storage power plant.

[0075] Based on the same inventive concept, embodiments of the present application further provide a knowledge graph-based energy storage power plant fault recognition device. As shown in Figure 2, the device includes the following:

[0076] The acquisition module 201 is for acquiring status data of the energy storage power plant. For details, please refer to the description of step S101 in the above embodiment, and the description is omitted here.

[0077] The prediction module 202 inputs state data into a pre-built energy storage plant failure recognition model based on a thermal runaway knowledge graph that characterizes the relationship between the state data of the energy storage plant and the thermal runaway process, in order to predict the failure status and transition path of the energy storage plant. For details, please refer to the description of step S102 in the above embodiment, and the description is omitted here.

[0078] The determination module 203 is used to determine the safety risk level of the energy storage power plant based on the failure condition and transition path. For details, please refer to the description of step S103 in the above embodiment, and the explanation is omitted here.

[0079] The above device predicts the failure status and progression path of an energy storage plant based on real-time monitored status data of the energy storage plant and an energy storage plant failure recognition model constructed based on a thermal runaway knowledge graph that characterizes the relationship between the status data and the thermal runaway process. It comprehensively predicts the thermal runaway process that may occur in the energy storage plant, and further determines the safety risk level of the energy storage plant based on the failure status and progression path, thereby ensuring the safe and stable operation of the energy storage plant. It applies status data related to the thermal runaway process to the energy storage plant for failure prediction and progression path prediction, comprehensively covers various data in the thermal runaway process of the energy storage plant, and considers various possible factors related to the thermal runaway process to achieve accurate pre-assessment of the safety risk of the energy storage plant, timely detection of potential failures and safety risks, long-term early warning of failures, provides reference and decision-making support to maintenance personnel, and avoids the occurrence of fire events in the energy storage plant.

[0080] In one example, the prediction module 202 includes an acquisition submodule and a training submodule.

[0081] The acquisition submodule is for acquiring a thermal runaway knowledge graph of an energy storage power plant, which includes historical state data of the energy storage power plant, historical failure conditions corresponding to the historical state data, and historical transition paths. For details, please refer to the description in the above embodiment, and the explanation is omitted here.

[0082] The training submodule takes historical state data as input to the initial energy storage plant failure recognition model, and historical failure conditions and historical transition paths as outputs to the initial energy storage plant failure recognition model, thereby training the initial energy storage plant failure recognition model to obtain the energy storage plant failure recognition model. For details, please refer to the description in the above embodiment, and the explanation is omitted here.

[0083] In one example, the acquisition submodule includes a decision unit, a first acquisition unit, and a second acquisition unit.

[0084] The decision unit is for determining the state data type of an energy storage power plant based on the battery thermal runaway transition mechanism. For details, please refer to the description of the embodiment above, and the explanation is omitted here.

[0085] The first acquisition unit is for acquiring historical state data of an energy storage power plant based on its state data type. For details, please refer to the description of the embodiment above, and the explanation is omitted here.

[0086] The second acquisition unit is used to acquire historical failure status and historical transition path corresponding to the historical status data, based on the historical status data. For details, please refer to the description in the above embodiment, and the explanation will be omitted here.

[0087] In one example, the decision unit includes a first decision subunit and a second decision subunit.

[0088] The first determination subunit is for determining the thermal runaway process of an energy storage power plant based on the battery thermal runaway transition mechanism. For details, please refer to the description of the embodiment above, and the explanation is omitted here.

[0089] The second determination subunit is for determining the state data type based on the thermal runaway process. For details, please refer to the description in the above embodiment, and the description is omitted here.

[0090] In one example, the thermal runaway process includes an external process, an internal battery change process, and a thermal runaway generation process. The second determination subunit determines the external parameters of the energy storage power plant based on the external process, the internal battery parameters of the energy storage power plant based on the internal battery change process, and the thermal diffusion parameters of the energy storage power plant based on the thermal runaway generation process. Based on the external parameters, internal battery parameters, and thermal diffusion parameters, it determines the state data type. For further details, please refer to the description in the above embodiment, which is omitted here.

[0091] In one example, the device is The system further includes an alarm module for transmitting preventative alert information to energy storage power plants based on safety risk levels. For further details, please refer to the description in the above embodiment, which is omitted here.

[0092] For specific limitations and beneficial effects of the above-mentioned device, refer to the limitations on the energy storage power plant fault detection method based on the knowledge graph described above, and will not be explained here. All or part of each of the above modules may be implemented by software, hardware, or a combination thereof. Each of the above modules may be embedded in a processor in a computer device as hardware, or independently, or may be stored in the memory of a computer device as software so that the processor can call and execute operations corresponding to each of the above modules.

[0093] Figure 3 is a schematic diagram of the hardware structure of a computer device according to an exemplary embodiment. The device comprises one or more processors 310 and memory 320 including persistent memory, volatile memory, and a hard disk, as shown in Figure 3, with one processor 310 being used as an example. The device may further include an input device 330 and an output device 340.

[0094] The processor 310, memory 320, input device 330, and output device 340 may be connected by a bus or in other ways; Figure 3 shows a bus connection as an example.

[0095] The processor 310 may be a Central Processing Unit (CPU). The processor 310 may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, or a combination of the various chips mentioned above. The general-purpose processor may be a microprocessor or any conventional processor.

[0096] Memory 320 includes persistent memory, volatile memory, and a hard disk as a non-temporary computer-readable storage medium, and is for storing non-temporary software programs, non-temporary computer-executable programs and modules, such as program instructions / modules corresponding to the knowledge graph-based energy storage power plant fault recognition method in the embodiment of the present application. The processor 310 executes various functional applications and data processing of the server by executing the non-temporary software programs, instructions and modules stored in memory 320, that is, it realizes one of the knowledge graph-based energy storage power plant fault recognition methods described above.

[0097] The memory 320 may include an operating system, a program memory area capable of storing application programs required for at least one function, and a data memory area capable of storing data used as needed. The memory 320 may also include high-speed random-access memory and non-temporary memory such as at least one magnetic disk storage device, flash memory device, or other non-temporary solid-state storage device. In some embodiments, the memory 320 may include memory located remotely from the processor 310, and these remote memories may be connected to a data processing device via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0098] The input device 330 can receive input numerical or character information and generate signal inputs related to user settings and function control. The output device 340 may include a display device such as a display.

[0099] One or more modules are stored in memory 320 and, when executed by one or more processors 310, perform the method shown in Figure 1.

[0100] The above-described product can perform the method according to the embodiment of the present application and has a functional module and beneficial effects corresponding to performing the method. Technical details not described in detail in this embodiment can be specifically referred to in the relevant description in the embodiment shown in Figure 1.

[0101] Embodiments of the present invention further provide a non-temporary computer storage medium in which computer executable instructions capable of performing the method in any embodiment of the above-described method are stored. The storage medium may be a magnetic disk, an optical disk, read-only memory (ROM), random access memory (RAM), flash memory, a hard disk drive (HDD), or a solid-state drive (SSD), and the storage medium may further include combinations of the above-described types of memory.

[0102] In this specification, relational terms such as “First” and “Second” are merely used to distinguish one entity or operation from another, and do not necessarily require or suggest that such an actual relationship or order exists between these entities or operations. Furthermore, the terms “include,” “incorporate,” or any other variation thereof mean non-exclusive inclusion, and a process, method, article, or apparatus that includes a set of elements includes not only those elements but also other elements not explicitly listed, or elements specific to such a process, method, article, or apparatus. Unless otherwise specified, an element limited by the phrase “includes one of…” does not exclude the existence of other identical elements in a process, method, article, or apparatus that includes the element.

[0103] The above are merely specific embodiments of the present application, intended to enable those skilled in the art to understand or implement it. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Accordingly, the present application is not limited to these embodiments shown herein and should cover the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for recognizing a fault in an energy storage power plant based on a knowledge graph, which is performed by a computer device, To acquire status data of energy storage power plants, The aforementioned state data is input into an energy storage power plant failure recognition model, which is pre-constructed based on a thermal runaway knowledge graph that characterizes the relationship between the state data of the energy storage power plant and the thermal runaway process, in order to predict the failure status and progression path of the energy storage power plant. This includes determining the safety risk level of the energy storage power plant based on the failure conditions and the transition path, The aforementioned transition path refers to the thermal runaway process of the energy storage power plant, and includes the entire process from the occurrence of an abnormality inside the battery, through a gradual progression to battery pack failure, and finally to thermal runaway. The step of constructing the aforementioned energy storage power plant failure recognition model is: To obtain a thermal runaway knowledge graph of the energy storage power plant, which includes the historical state data of the energy storage power plant, the historical failure status corresponding to the historical state data, and the historical transition path, which is the thermal runaway progression process that has occurred in the energy storage power plant in the past. This includes using the historical state data as input to an initial energy storage power plant failure recognition model, using the historical failure status and the historical transition path as outputs to the initial energy storage power plant failure recognition model, and training the initial energy storage power plant failure recognition model to obtain the energy storage power plant failure recognition model. A knowledge graph-based method for recognizing failures in energy storage power plants, characterized by the features described above.

2. The step of obtaining the thermal runaway knowledge graph of the energy storage power plant is: Based on the battery thermal runaway transition mechanism, the state data type of the energy storage power plant is determined, Based on the aforementioned state data type, the historical state data of the energy storage power plant is obtained, This includes obtaining historical failure status and historical transition path corresponding to the historical status data based on the historical status data. The method for recognizing a fault in an energy storage power plant according to feature 1.

3. Determining the state data type of the energy storage power plant based on the battery thermal runaway transition mechanism is: Based on the aforementioned thermal runaway transition mechanism of the battery, the thermal runaway process of the energy storage power plant is determined, Based on the thermal runaway process, the state data type is determined, The energy storage power plant fault recognition method according to claim 2, characterized by including the following:

4. The thermal runaway process includes an external process, an internal battery change process, and a thermal runaway generation process, and the step of determining the state data type based on the thermal runaway process is: Based on the aforementioned external process, the external parameters of the energy storage power plant are determined, Based on the aforementioned internal battery change process, the internal battery parameters of the energy storage power plant are determined, Based on the aforementioned thermal runaway generation process, the thermal diffusion parameters of the energy storage power plant are determined, The state data type is determined based on the external parameters, the internal battery parameters, and the thermal diffusion parameters. The energy storage power plant fault recognition method according to claim 3, characterized by including the following:

5. The method for recognizing a fault in an energy storage power plant according to claim 1, further comprising transmitting preventive warning information to the energy storage power plant based on the safety risk level.

6. An acquisition module for obtaining status data of an energy storage power plant, The aforementioned state data is input into an energy storage power plant failure recognition model, which is pre-constructed based on a thermal runaway knowledge graph that characterizes the relationship between the state data of the energy storage power plant and the thermal runaway process, and a prediction module is used to predict the failure status and progression path of the energy storage power plant. Includes a determination module for determining the safety risk level of the energy storage power plant based on the failure conditions and the transition path, The aforementioned transition path refers to the thermal runaway process in an energy storage power plant, encompassing the entire process from an abnormality occurring inside the battery, through a gradual progression to battery pack failure, and ultimately to thermal runaway. The aforementioned prediction module is An acquisition submodule for obtaining a thermal runaway knowledge graph of the energy storage power plant, which includes historical state data of the energy storage power plant, historical failure status corresponding to the historical state data, and historical transition paths which are thermal runaway progression processes that have occurred in the energy storage power plant in the past. The system includes a training submodule for obtaining the energy storage power plant failure recognition model by using the historical state data as input to the initial energy storage power plant failure recognition model, the historical failure status and the historical transition path as outputs to the initial energy storage power plant failure recognition model, and training the initial energy storage power plant failure recognition model. A knowledge graph-based fault detection device for energy storage power plants, characterized by the following features.

7. A computer device comprising a memory in which computer instructions are stored, and a processor that is connected to the memory in a manner that allows communication between them, and which executes the computer instructions to perform the steps of the energy storage power plant fault recognition method based on a knowledge graph as described in any one of claims 1 to 5.

8. A computer-readable storage medium in which a computer program was stored, A computer-readable storage medium characterized in that, when the computer program is executed by the processor, it realizes the steps of the knowledge graph-based energy storage power plant fault recognition method described in any one of claims 1 to 5.

Images