Knowledge graph-based energy storage power station fault identification method and apparatus

Abstract

The present application relates to the field of electric power, and provides a knowledge graph-based energy storage power station fault identification method and apparatus. The knowledge graph-based energy storage power station fault identification method comprises: acquiring state data of an energy storage power station; inputting the state data into a pre-constructed energy storage power station fault identification model, and predicting a fault condition and an evolution path of the energy storage power station, wherein the energy storage power station fault identification model is constructed on the basis of a thermal runaway knowledge graph, and the thermal runaway knowledge graph is used for representing an association relationship between the state data of the energy storage power station and a thermal runaway process; and on the basis of the fault condition and the evolution path, determining a safety risk level of the energy storage power station. The present application can comprehensively and accurately evaluate the operation condition of the energy storage power station, and achieve long-time fault early-warning.

Description

A method and device for identifying energy storage power station faults based on knowledge graph Technical Field

[0001] The present application relates to the field of electric power, and in particular to a method and device for identifying energy storage power station faults based on a knowledge graph. Background Art

[0002] With the rapid development of renewable energy, energy storage power stations are becoming increasingly widely used. However, the risks of failure and safety in these stations are becoming increasingly prominent. In recent years, fires in energy storage power stations have become frequent. To ensure the safe and stable operation of energy storage power stations, real-time monitoring and analysis of their operation is necessary to promptly identify potential failure risks.

[0003] In existing technologies, energy storage power plants are primarily monitored through sensors and data acquisition systems. Fault conditions and safety risks are assessed through data analysis and processing. However, this approach often only considers limited health characteristic data such as cycle time and frequency, and electrical parameters such as real-time current and voltage. This makes it difficult to comprehensively and accurately assess the overall operational status and safety risks of the energy storage plant, resulting in limited lead time and an inability to provide long-term early warning.

[0004] Summary of the Invention

[0005] In order to comprehensively and accurately evaluate the operation status of energy storage power stations and achieve long-term fault warning, this application proposes a method and device for energy storage power station fault identification based on knowledge graph.

[0006] In a first aspect, the present application provides a method for identifying energy storage power station faults based on a knowledge graph, the method comprising:

[0007] Obtain status data of energy storage power stations;

[0008] The state data is fed into a pre-built energy storage power station fault identification model to predict the failure condition and evolution path of the energy storage power station. The energy storage power station fault identification model is constructed based on the thermal runaway knowledge graph, which is used to characterize the relationship between the state data of the energy storage power station and the thermal runaway process.

[0009] Determine the safety risk level of the energy storage power station based on the fault conditions and evolution path.

[0010] Through the above method, based on the real-time monitoring of the status data of the energy storage power station and the energy storage power station fault identification model, the fault situation and evolution path of the energy storage power station are predicted, and the thermal runaway process that may occur in the energy storage power station is comprehensively predicted. The safety risk level of the energy storage power station is further judged based on the fault situation and evolution path, providing protection for the safe and stable operation of the energy storage power station. Among them, the energy storage power station fault identification model is constructed based on the thermal runaway knowledge graph. The thermal runaway knowledge graph reflects the correlation between the status data and the thermal runaway process. The status data involved in the thermal runaway process is applied to the fault prediction and evolution path prediction of the energy storage power station. It comprehensively covers various data of the energy storage power station in the thermal runaway process and considers various factors that may be involved in the thermal runaway process, thereby achieving accurate prediction of the safety risks of the energy storage power station, timely discovering potential faults and safety risks, and realizing long-term fault warning. It provides reference and decision support for operation and maintenance personnel and avoids fire incidents in energy storage power stations.

[0011] In an optional embodiment, the step of constructing an energy storage power station fault identification model includes:

[0012] Obtain a thermal runaway knowledge graph for the energy storage power station. The thermal runaway knowledge graph includes the historical status data of the energy storage power station, the historical fault conditions corresponding to the historical status data, and the historical evolution paths.

[0013] The historical state data is used as the input of the initial energy storage power station fault identification model, and the historical fault conditions and historical evolution paths are used as the output of the initial energy storage power station fault identification model. The initial energy storage power station fault identification model is trained to obtain the energy storage power station fault identification model.

[0014] Through the above implementation, the thermal runaway knowledge graph contains the correlation between the energy storage power station status data and the thermal runaway process. The initial energy storage power station fault identification model is trained using historical status data, as well as the historical fault conditions and historical evolution paths corresponding to the historical status data, thereby obtaining an energy storage power station fault identification model. Based on the status data involved in the thermal runaway process of the energy storage power station, a variety of factors are comprehensively considered to improve the prediction accuracy of the energy storage power station fault identification model.

[0015] In an optional embodiment, obtaining a thermal runaway knowledge graph of an energy storage power station includes:

[0016] Determine the state data type of the energy storage power station based on the battery thermal runaway evolution mechanism;

[0017] Obtain historical status data of the energy storage power station based on the status data type;

[0018] According to the historical status data, the historical fault conditions and historical evolution paths corresponding to the historical status data are obtained.

[0019] In an optional embodiment, determining the state data type of the energy storage power station based on the battery thermal runaway evolution mechanism includes:

[0020] Determine the thermal runaway process of energy storage power stations based on the evolution mechanism of battery thermal runaway;

[0021] According to the thermal runaway process, the state data type is determined.

[0022] Through the above implementation, the status data type of the energy storage power station is determined based on the battery thermal runaway evolution mechanism. Based on the battery thermal runaway evolution mechanism, it is helpful to better analyze the evolution process of battery thermal runaway. The relevant data in the battery thermal runaway evolution process is determined as status data, thereby more accurately monitoring and predicting the fault conditions and evolution paths of the energy storage power station.

[0023] In an optional embodiment, the thermal runaway process includes an external process, a battery internal change process, and a thermal runaway occurrence process. According to the thermal runaway process, determining the state data type includes:

[0024] Determine the external parameters of the energy storage power station based on the external process;

[0025] Determine the internal parameters of the battery in the energy storage power station based on the internal changes of the battery;

[0026] Determine the thermal propagation parameters of the energy storage power station based on the thermal runaway process;

[0027] The state data type is determined based on external parameters, battery internal parameters and heat propagation parameters.

[0028] Through the above implementation, the thermal runaway process is comprehensively analyzed and divided into an external process, an internal battery change process, and a thermal runaway occurrence process. External parameters are determined based on the external process, internal battery parameters are determined based on the internal battery change process, and heat propagation parameters are determined based on the thermal runaway occurrence process. By determining corresponding parameters for different thermal runaway processes, we can fully understand the operation and fault conditions of the energy storage power station, which helps to improve the accuracy of the prediction of the energy storage power station fault identification model.

[0029] In an optional embodiment, the method further includes:

[0030] According to the safety risk level, prevention and control warning information is sent to the energy storage power station.

[0031] Through the above implementation, prevention and control warning information can be sent to the energy storage power station in a timely manner according to the safety risk level, reminding operation and maintenance personnel to pay attention to potential safety risks and take corresponding prevention and control measures, thereby improving operation and maintenance efficiency, helping to avoid accidents and reduce losses caused by fires in energy storage power stations.

[0032] In a second aspect, the present application also provides a knowledge graph-based energy storage power station fault identification device, which includes:

[0033] An acquisition module is used to obtain status data of the energy storage power station;

[0034] The prediction module is used to input the status data into a pre-built energy storage power station fault identification model to predict the fault condition and evolution path of the energy storage power station. The energy storage power station fault identification model is constructed based on the thermal runaway knowledge graph, which is used to characterize the relationship between the energy storage power station status data and the thermal runaway process;

[0035] The determination module is used to determine the safety risk level of the energy storage power station based on the fault conditions and evolution path.

[0036] Through the above-mentioned device, based on the real-time monitoring of the status data of the energy storage power station and the energy storage power station fault identification model, the fault situation and evolution path of the energy storage power station are predicted, and the thermal runaway process that may occur in the energy storage power station is comprehensively predicted. The safety risk level of the energy storage power station is further judged based on the fault situation and evolution path, providing protection for the safe and stable operation of the energy storage power station. Among them, the energy storage power station fault identification model is constructed based on the thermal runaway knowledge graph. The thermal runaway knowledge graph reflects the correlation between the status data and the thermal runaway process. The status data involved in the thermal runaway process is applied to the fault prediction and evolution path prediction of the energy storage power station. It comprehensively covers various data of the energy storage power station in the thermal runaway process and considers various factors that may be involved in the thermal runaway process, thereby achieving accurate prediction of the safety risks of the energy storage power station, timely discovering potential faults and safety risks, and realizing long-term fault warning. It provides reference and decision support for operation and maintenance personnel and avoids fire incidents in energy storage power stations.

[0037] In an optional embodiment, the prediction module includes:

[0038] The acquisition submodule is used to obtain the thermal runaway knowledge graph of the energy storage power station. The thermal runaway knowledge graph includes the historical status data of the energy storage power station, the historical fault conditions corresponding to the historical status data, and the historical evolution path;

[0039] The training submodule is used to use the historical status data as the input of the initial energy storage power station fault identification model, and the historical fault conditions and historical evolution paths as the output of the initial energy storage power station fault identification model, to train the initial energy storage power station fault identification model and obtain the energy storage power station fault identification model.

[0040] In a third aspect, the present application also provides a computer device comprising a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to thereby execute the steps of the energy storage power station fault identification method based on the knowledge graph of the first aspect or any embodiment of the first aspect.

[0041] In a fourth aspect, the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the energy storage power station fault identification method based on the knowledge graph of the first aspect or any embodiment of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the specific implementation methods or the description of the prior art. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0043] FIG1 is a flow chart of a method for identifying energy storage power station faults based on a knowledge graph according to an exemplary embodiment;

[0044] FIG2 is a schematic diagram of the structure of a knowledge graph-based energy storage power station fault identification device according to an exemplary embodiment;

[0045] FIG3 is a schematic diagram of a hardware structure of a computer device according to an exemplary embodiment. DETAILED DESCRIPTION

[0046] The following will clearly and completely describe the technical solution of this application in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.

[0047] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0048] In order to comprehensively and accurately evaluate the operation status of energy storage power stations and achieve long-term fault warning, this application proposes a method and device for energy storage power station fault identification based on knowledge graph.

[0049] Figure 1 is a flow chart of a method for identifying energy storage power station faults based on a knowledge graph according to an exemplary embodiment. As shown in Figure 1 , the method for identifying energy storage power station faults based on a knowledge graph includes the following steps S101 to S103 .

[0050] Step S101: Acquire status data of the energy storage power station.

[0051] In an optional embodiment, an energy storage station is a device system that stores, converts, and releases cyclical electrical energy through electrochemical cells or electromagnetic energy storage media. It can effectively address power system issues such as peak-load shifting, output stabilization, improved power quality, and peak-load shifting, and is crucial for balancing load fluctuations. Furthermore, energy storage stations offer economies of scale, stabilizing voltage during peak load periods, smoothing grid fluctuations, and ensuring power supply quality. Furthermore, energy storage stations can charge and discharge energy through the energy storage system, storing energy during off-peak periods and releasing it during peak periods, thereby reducing electricity costs and improving energy efficiency.

[0052] In an optional embodiment, the energy storage station includes a battery pack, an energy storage converter, an isolation transformer, and other equipment. The battery pack, as the core component of the energy storage station, is used to store electrical energy. The battery pack typically consists of multiple battery cells, which can be lithium-ion batteries, lead-acid batteries, sodium-sulfur batteries, and other types. The energy storage converter is used to perform energy conversion between the battery pack and the power grid, including charging and discharging. The isolation transformer isolates the energy storage station from the power grid, ensuring its independent operation and safety.

[0053] In an optional embodiment, based on relevant factors in the thermal runaway process of the energy storage power station, the status data of the energy storage power station may include external parameters, internal parameters of the battery, heat propagation parameters, etc.

[0054] Step S102: Input the status data into a pre-built energy storage power station fault identification model to predict the fault condition and evolution path of the energy storage power station. The energy storage power station fault identification model is constructed based on the thermal runaway knowledge graph, which is used to characterize the relationship between the status data of the energy storage power station and the thermal runaway process.

[0055] In an optional embodiment, the energy storage power station fault identification model can be constructed by algorithms such as machine learning, which is not specifically limited here.

[0056] In an optional embodiment, the fault condition predicted by the energy storage power station fault identification model may be a fault condition of each device in the energy storage power station, a fault condition of a battery, or a fault condition of other equipment in the energy storage power station, without specific limitation herein.

[0057] In an optional embodiment, the evolution path predicted by the energy storage power station fault identification model is the evolution path of each device in the energy storage power station under the state data.

[0058] Step S103: Determine the safety risk level of the energy storage power station based on the fault condition and evolution path.

[0059] In an optional embodiment, the safety risk level of the energy storage power station is determined based on the degree of loss caused by the fault condition and the evolution path. Different fault conditions and different evolution paths correspond to different safety risk levels.

[0060] Through the above method, based on the real-time monitoring of the status data of the energy storage power station and the energy storage power station fault identification model, the fault situation and evolution path of the energy storage power station are predicted, and the thermal runaway process that may occur in the energy storage power station is comprehensively predicted. The safety risk level of the energy storage power station is further judged based on the fault situation and evolution path, providing protection for the safe and stable operation of the energy storage power station. Among them, the energy storage power station fault identification model is constructed based on the thermal runaway knowledge graph. The thermal runaway knowledge graph reflects the correlation between the status data and the thermal runaway process. The status data involved in the thermal runaway process is applied to the fault prediction and evolution path prediction of the energy storage power station. It comprehensively covers various data of the energy storage power station in the thermal runaway process and considers various factors that may be involved in the thermal runaway process, thereby achieving accurate prediction of the safety risks of the energy storage power station, timely discovering potential faults and safety risks, and realizing long-term fault warning. It provides reference and decision support for operation and maintenance personnel and avoids fire incidents in energy storage power stations.

[0061] In one example, in step S102 above, an energy storage power station fault identification model is constructed through the following steps:

[0062] Step a1: Obtain a thermal runaway knowledge graph of the energy storage power station. The thermal runaway knowledge graph includes historical status data of the energy storage power station, historical fault conditions corresponding to the historical status data, and historical evolution paths.

[0063] Step a2: Use the historical status data as the input of the initial energy storage power station fault identification model, and the historical fault conditions and historical evolution paths as the output of the initial energy storage power station fault identification model. Train the initial energy storage power station fault identification model to obtain the energy storage power station fault identification model.

[0064] In an embodiment of the present application, the thermal runaway knowledge graph includes the correlation between the state data of the energy storage power station and the thermal runaway process. An initial energy storage power station fault identification model is trained using historical state data, as well as historical fault conditions and historical evolution paths corresponding to the historical state data, thereby obtaining an energy storage power station fault identification model. Based on the state data involved in the thermal runaway process of the energy storage power station, a variety of factors are comprehensively considered to improve the prediction accuracy of the energy storage power station fault identification model.

[0065] In one example, in step a1 above, the thermal runaway knowledge graph of the energy storage power station is obtained through the following steps:

[0066] Step b1: Based on the battery thermal runaway evolution mechanism, determine the state data type of the energy storage power station.

[0067] In an optional embodiment, the battery thermal runaway evolution mechanism includes the triggering factors of battery thermal runaway, the chemical reactions of battery thermal runaway, heat transfer and heat accumulation, the physical manifestations of thermal runaway, and the chain reaction of thermal runaway. When determining the thermal runaway process of an energy storage power station, it is necessary to comprehensively consider these factors and analyze them in conjunction with the actual operation of the energy storage station. By gaining a deeper understanding of the evolution mechanism of battery thermal runaway, thermal runaway events in energy storage power stations can be more accurately predicted and prevented, thereby improving the safety and stability of energy storage stations.

[0068] In an optional embodiment, battery thermal runaway may be triggered by a variety of factors, such as overcharging, over-discharging, high temperature, short circuit, etc. These factors may accelerate the chemical reaction inside the battery and generate a large amount of heat.

[0069] In an optional embodiment, the chemical reactions that cause battery thermal runaway generally include redox reactions between positive and negative electrode materials, decomposition of the electrolyte, etc. These reactions generate a large amount of heat and gas, causing the temperature and pressure inside the battery to rise.

[0070] In an alternative embodiment, heat transfer refers to the transfer of heat from the battery housing to the external environment as the internal temperature of the battery rises. If heat is not properly controlled, the battery temperature will continue to rise, resulting in heat accumulation.

[0071] In an optional embodiment, as the battery temperature rises, the physical properties of the battery may also change, such as casing expansion, electrolyte leakage, etc. These physical manifestations can serve as an important basis for determining whether the battery has thermal runaway.

[0072] In an optional embodiment, the chain reaction of thermal runaway refers to the chain reaction that may be triggered once a battery experiences thermal runaway, such as temperature rise of adjacent batteries, electrolyte leakage, etc. These chain reactions may affect the safety of the entire energy storage power station.

[0073] Step b2: Obtain historical status data of the energy storage power station according to the status data type.

[0074] Step b3: According to the historical status data, obtain the historical fault conditions and historical evolution paths corresponding to the historical status data.

[0075] In one example, in step b1 above, the state data type of the energy storage power station is determined in the following manner:

[0076] First, based on the battery thermal runaway evolution mechanism, the thermal runaway process of the energy storage power station is determined. For example, the thermal runaway process includes external processes (such as external usage), internal changes in the battery (including but not limited to SEI film decomposition, dendrite growth, positive electrode oxygen release, negative electrode lithium deposition, internal short circuit, leakage, etc.), and the thermal runaway process.

[0077] Then, according to the thermal runaway process, the state data type is determined.

[0078] In an embodiment of the present application, the status data type of the energy storage power station is determined based on the battery thermal runaway evolution mechanism. Based on the battery thermal runaway evolution mechanism, it is helpful to better analyze the evolution process of battery thermal runaway, and determine the relevant data in the evolution process of battery thermal runaway as status data, so as to more comprehensively and accurately monitor and predict the fault conditions and evolution paths of the energy storage power station.

[0079] In one example, the thermal runaway process includes an external process, a battery internal change process, and a thermal runaway occurrence process.

[0080] The external process refers to the external use process. For example, the external process includes the process of mechanically triggering battery thermal runaway (such as the deformation of the lithium battery pack due to impact, internal short circuit of the battery pack, and other behaviors that damage the battery pack, which may cause thermal runaway of the battery).

[0081] The internal battery process refers to the electrochemical reactions involved in thermal runaway, such as the decomposition of the positive and negative electrodes, interactions between them, and internal short circuits. Furthermore, when the temperature reaches 120-130°C, the protective SEI membrane is destroyed, the negative electrode reacts with the solvent and binder, and the temperature rises, causing the separator to melt and close. When the temperature continues to rise above 150°C, the internal electrolyte begins to decompose, releasing further heat and further heating the battery.

[0082] Thermal runaway occurs when the battery temperature reaches above 200°C, causing the cathode material to decompose, releasing large amounts of heat and gas, and continuing to rise in temperature. At 250-350°C, the lithium-intercalated anode begins to react with the electrolyte. Ultimately, during this reaction, the electrolyte reacts violently with the oxygen produced by the cathode reaction, further causing the battery to enter thermal runaway.

[0083] In the embodiment of the present application, the state data type is determined by the following content:

[0084] First, external parameters of the energy storage power station are determined based on the external process. In the embodiment of the present application, the external parameters include external usage parameters and external environment parameters.

[0085] In an optional embodiment, external usage parameters include mechanical abuse data (such as needle puncture and impact), thermal abuse data (such as high and low temperatures), electrical abuse data (such as overcharging and short circuiting), and battery quality data. External environmental parameters include, but are not limited to, temperature, humidity, wind speed, and light intensity. These external environmental parameters reflect the environmental conditions of the energy storage power station and affect the operating status and lifespan of the battery. Battery charge and discharge performance and lifespan are closely related to temperature. Excessively high temperatures can lead to dangerous conditions such as internal battery short circuits and thermal runaway. Therefore, monitoring the temperature of the energy storage power station can promptly identify potential safety risks and enable appropriate measures. Excessive humidity can cause internal battery short circuits and corrosion. Therefore, monitoring the humidity of the energy storage power station can ensure the normal operation and lifespan of the battery. Wind speed has a significant impact on the heat dissipation and cooling performance of the energy storage power station. In hot weather, slow wind speeds can cause battery temperatures to overheat, triggering thermal runaway. Therefore, monitoring the wind speed of the energy storage power station can enable timely adjustment of the cooling system to ensure normal battery operation. For solar energy storage power stations, light intensity is a key factor affecting battery power generation. Excessive sunlight can cause batteries to overheat and reduce their lifespan. Therefore, monitoring the light intensity of the energy storage station can help adjust the battery's operating status in a timely manner to ensure its normal operation and longevity.

[0086] Secondly, according to the internal changes of the battery, the internal parameters of the battery of the energy storage power station are determined.

[0087] In an optional embodiment, the internal parameters of the battery of the energy storage power station include voltage, current, temperature, state of charge, etc.

[0088] Battery voltage is an important parameter that reflects the state of the electrochemical reaction within the battery. By monitoring the battery voltage, we can determine the battery's charge and discharge status and whether there are any abnormal conditions, such as internal short circuits.

[0089] Battery current is a parameter that reflects the battery's charge and discharge capabilities. By monitoring the battery current, you can determine the battery's charge and discharge rate and efficiency, as well as whether it is overcharged or over-discharged.

[0090] Battery temperature is a key parameter that reflects the internal thermal balance of the battery. By monitoring the battery temperature, we can determine the heat dissipation and safety of the battery, as well as whether there is a risk of thermal runaway.

[0091] The state of charge (SOC) is a parameter that reflects the remaining capacity of the battery. By monitoring the SOC, you can determine the remaining charge of the battery and whether it is undercharged or overcharged.

[0092] Again, according to the thermal runaway process, the thermal propagation parameters of the energy storage power station are determined.

[0093] In an optional embodiment, heat spread parameters include, but are not limited to, the thermal resistance between the battery cell and the side panel, the thermal resistance between the battery cells, the thickness of the insulation pad outside the side panel, and the thermal resistance between the battery cell and the water cooling plate. Furthermore, heat spread parameters may also include trigger conditions, spread speed, and spread range. Trigger conditions include a steep voltage drop, a temperature rise rate ≥1°C / s, or a temperature exceeding the battery's upper limit.

[0094] Finally, the state data type is determined based on the external parameters, the battery internal parameters, and the heat propagation parameters. For example, the external parameters, the battery internal parameters, and the heat propagation parameters can be used as the state data type, so that the state data corresponding to the energy storage power station can be collected based on the state data type.

[0095] In the embodiments of the present application, a comprehensive analysis of the thermal runaway process is performed, dividing the thermal runaway process into an external process, a battery internal change process, and a thermal runaway occurrence process. External parameters are determined based on the external process, internal battery parameters are determined based on the battery internal change process, and heat propagation parameters are determined based on the thermal runaway occurrence process. By determining corresponding parameters for different thermal runaway processes, a comprehensive understanding of the operation and fault conditions of the energy storage power station is achieved, which helps to improve the accuracy of the prediction of the energy storage power station fault identification model.

[0096] In one example, the method provided in the embodiment of the present application further includes:

[0097] According to the safety risk level, prevention and control warning information is sent to the energy storage power station.

[0098] In the embodiment of the present application, prevention and control warning information can be sent to the energy storage power station in a timely manner according to the safety risk level, reminding operation and maintenance personnel to pay attention to potential safety risks and take corresponding prevention and control measures to improve operation and maintenance efficiency, help avoid accidents, and reduce losses caused by fires in energy storage power stations.

[0099] Based on the same inventive concept, an embodiment of the present application further provides a knowledge graph-based energy storage power station fault identification device, as shown in FIG2 , which includes:

[0100] The acquisition module 201 is used to acquire the status data of the energy storage power station; for details, please refer to the description of step S101 in the above embodiment, which will not be repeated here.

[0101] Prediction module 202 is used to input the status data into a pre-built energy storage power station fault identification model to predict the fault condition and evolution path of the energy storage power station. The energy storage power station fault identification model is constructed based on the thermal runaway knowledge graph, which is used to characterize the relationship between the status data of the energy storage power station and the thermal runaway process. For details, please refer to the description of step S102 in the above embodiment and will not be repeated here.

[0102] The determination module 203 is used to determine the safety risk level of the energy storage power station according to the fault condition and the evolution path. For details, please refer to the description of step S103 in the above embodiment, which will not be repeated here.

[0103] Through the above-mentioned device, based on the real-time monitoring of the status data of the energy storage power station and the energy storage power station fault identification model, the fault situation and evolution path of the energy storage power station are predicted, and the thermal runaway process that may occur in the energy storage power station is comprehensively predicted. The safety risk level of the energy storage power station is further judged based on the fault situation and evolution path, providing protection for the safe and stable operation of the energy storage power station. Among them, the energy storage power station fault identification model is constructed based on the thermal runaway knowledge graph. The thermal runaway knowledge graph reflects the correlation between the status data and the thermal runaway process. The status data involved in the thermal runaway process is applied to the fault prediction and evolution path prediction of the energy storage power station. It comprehensively covers various data of the energy storage power station in the thermal runaway process and considers various factors that may be involved in the thermal runaway process, thereby achieving accurate prediction of the safety risks of the energy storage power station, timely discovering potential faults and safety risks, and realizing long-term fault warning. It provides reference and decision support for operation and maintenance personnel and avoids fire incidents in energy storage power stations.

[0104] In one example, the prediction module 202 includes:

[0105] The acquisition submodule is used to obtain the thermal runaway knowledge graph of the energy storage power station. The thermal runaway knowledge graph includes the historical status data of the energy storage power station, the historical fault conditions and historical evolution paths corresponding to the historical status data; for details, please refer to the description in the above embodiment and will not be repeated here.

[0106] The training submodule is used to train the initial energy storage power station fault identification model using historical state data as input and historical fault conditions and historical evolution paths as output. This model is then trained to obtain an energy storage power station fault identification model. For details, refer to the description in the above embodiment and will not be repeated here.

[0107] In one example, obtaining the submodule includes:

[0108] The determination unit is used to determine the state data type of the energy storage power station based on the battery thermal runaway evolution mechanism; the details are described in the above embodiment and will not be repeated here.

[0109] The first acquisition unit is used to acquire historical status data of the energy storage power station according to the status data type; for details, please refer to the description in the above embodiment and will not be repeated here.

[0110] The second acquisition unit is used to acquire the historical fault conditions and historical evolution paths corresponding to the historical status data according to the historical status data. For details, please refer to the description in the above embodiment and will not be repeated here.

[0111] In one example, the determining unit includes:

[0112] The first determination subunit is used to determine the thermal runaway process of the energy storage power station based on the battery thermal runaway evolution mechanism; the details are described in the above embodiment and will not be repeated here.

[0113] The second determining subunit is used to determine the state data type according to the thermal runaway process. For details, please refer to the description in the above embodiment and will not be repeated here.

[0114] In one example, the thermal runaway process includes an external process, an internal battery change process, and a thermal runaway occurrence process. The second determination subunit is configured to determine external parameters of the energy storage power station based on the external process; determine internal battery parameters of the energy storage power station based on the internal battery change process; determine heat propagation parameters of the energy storage power station based on the thermal runaway occurrence process; and determine the state data type based on the external parameters, internal battery parameters, and heat propagation parameters. For details, please refer to the description in the above embodiment and will not be repeated here.

[0115] In one example, the apparatus further includes:

[0116] The early warning module is used to send prevention and control early warning information to the energy storage power station according to the safety risk level. The details are described in the above embodiment and will not be repeated here.

[0117] The specific limitations and beneficial effects of the above-mentioned device can be found in the above-mentioned limitations on the knowledge graph-based energy storage power station fault identification method, and will not be repeated here. Each of the above-mentioned modules can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each of the above modules.

[0118] Figure 3 is a schematic diagram of the hardware structure of a computer device according to an exemplary embodiment. As shown in Figure 3 , the device includes one or more processors 310 and memory 320. Memory 320 includes persistent memory, volatile memory, and a hard disk. Figure 3 uses one processor 310 as an example. The device may also include an input device 330 and an output device 340.

[0119] The processor 310 , the memory 320 , the input device 330 and the output device 340 may be connected via a bus or other means. FIG3 takes the bus connection as an example.

[0120] The processor 310 may be a central processing unit (CPU). The processor 310 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips. The general-purpose processor may be a microprocessor or any conventional processor.

[0121] Memory 320, as a non-transitory computer-readable storage medium, includes persistent memory, volatile memory, and a hard disk, and can be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as the program instructions / modules corresponding to the knowledge graph-based energy storage power station fault identification method in the embodiments of the present application. Processor 310 executes the non-transitory software programs, instructions, and modules stored in memory 320 to execute various server functional applications and data processing, thereby implementing any of the aforementioned knowledge graph-based energy storage power station fault identification methods.

[0122] The memory 320 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data used as needed, etc. In addition, the memory 320 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 320 may optionally include a memory remotely located relative to the processor 310, and these remote memories may be connected to the data processing device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0123] The input device 330 can receive input digital or character information and generate signal input related to user settings and function control. The output device 340 can include a display device such as a display screen.

[0124] One or more modules are stored in the memory 320 , and when executed by one or more processors 310 , the method shown in FIG. 1 is performed.

[0125] The above-mentioned product can execute the method provided in the embodiment of this application, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the relevant description in the embodiment shown in Figure 1.

[0126] The present application also provides a non-transitory computer storage medium, which stores computer-executable instructions that can execute the method in any of the above method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD); the storage medium can also include a combination of the above types of memory.

[0127] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device that includes the element.

[0128] The above are merely specific embodiments of the present application to enable those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but rather is intended to conform to the widest scope consistent with the principles and novel features of the present application.

Claims

1. A method for fault identification of an energy storage power station based on a knowledge graph, characterized in that, The method includes: Obtaining the status data of the energy storage power station; Inputting the status data into a pre-constructed energy storage power station fault identification model to predict the fault conditions and evolution paths of the energy storage power station. The energy storage power station fault identification model is constructed based on a thermal runaway knowledge graph, and the thermal runaway knowledge graph is used to characterize the correlation between the status data of the energy storage power station and the thermal runaway process; Determining the safety risk level of the energy storage power station according to the fault conditions and the evolution paths.

2. The method according to claim 1, wherein The steps of constructing the energy storage power station fault identification model include: Obtaining the thermal runaway knowledge graph of the energy storage power station, where the thermal runaway knowledge graph includes the historical status data of the energy storage power station, the corresponding historical fault conditions and historical evolution paths of the historical status data; Using the historical status data as the input of the initial energy storage power station fault identification model, and the historical fault conditions and the historical evolution paths as the output of the initial energy storage power station fault identification model, training the initial energy storage power station fault identification model to obtain the energy storage power station fault identification model.

3. The method according to claim 2, wherein Obtaining the thermal runaway knowledge graph of the energy storage power station includes: Based on the battery thermal runaway evolution mechanism, determining the type of status data of the energy storage power station; According to the type of status data, obtaining the historical status data of the energy storage power station; According to the historical status data, obtaining the corresponding historical fault conditions and historical evolution paths of the historical status data.

4. The method according to claim 3, wherein Based on the battery thermal runaway evolution mechanism, determining the type of status data of the energy storage power station includes: Based on the battery thermal runaway evolution mechanism, determining the thermal runaway process of the energy storage power station; According to the thermal runaway process, determining the type of status data.

5. The method according to claim 4, wherein The thermal runaway process includes an external process, a battery internal change process, and a thermal runaway occurrence process. According to the thermal runaway process, determining the type of status data includes: According to the external process, determining the external parameters of the energy storage power station; According to the battery internal change process, determining the battery internal parameters of the energy storage power station; According to the thermal runaway occurrence process, determining the thermal spread parameters of the energy storage power station; According to the external parameters, the battery internal parameters, and the thermal spread parameters, determining the type of status data.

6. The method according to claim 1, wherein The method further includes: Sending a prevention and control warning message to the energy storage power station according to the safety risk level.

7. An energy storage power station fault recognition device based on a knowledge graph, characterized in that, The device includes: An acquisition module for obtaining the status data of the energy storage power station; A prediction module for inputting the status data into a pre-constructed energy storage power station fault identification model to predict the fault conditions and evolution paths of the energy storage power station. The energy storage power station fault identification model is constructed based on a thermal runaway knowledge graph, and the thermal runaway knowledge graph is used to characterize the correlation between the status data of the energy storage power station and the thermal runaway process; A determination module for determining the safety risk level of the energy storage power station according to the fault conditions and the evolution paths.

8. The device according to claim 7, characterized in that, The prediction module includes: An acquisition sub-module, configured to acquire a thermal runaway knowledge graph of the energy storage power station, where the thermal runaway knowledge graph includes historical state data of the energy storage power station, historical fault conditions corresponding to the historical state data, and historical evolution paths; A training sub-module, configured to use the historical state data as the input of an initial energy storage power station fault identification model, and the historical fault conditions and the historical evolution paths as the output of the initial energy storage power station fault identification model, and train the initial energy storage power station fault identification model to obtain the energy storage power station fault identification model.

9. A computer device, characterized in that, It includes a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the steps of the knowledge graph-based energy storage power station fault identification method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the knowledge graph-based energy storage power station fault identification method according to any one of claims 1-7.

Images