A method and system for controlling operation risks of liquid-cooled energy storage system

Abstract

The present invention discloses an operation risk control method and system for a liquid-cooled energy storage system, including: defining the heat source and analyzing the flow direction and flow rate of the coolant for the target liquid-cooled energy storage system, constructing a simulation model to analyze the system response under different operating conditions, and constructing a first simulation data set; constructing a temperature prediction model, obtaining real-time operation monitoring information and inputting it into the temperature prediction model for analysis, identifying the hotspot area in the target liquid-cooled energy storage system, and obtaining hotspot area identification information; judging whether there is a risk of thermal runaway in the real-time operation of the target liquid-cooled energy storage system based on the hotspot area analysis information, and performing regulation and early warning; monitoring the temperature condition of the heat dissipation structure and the coolant condition in the pipeline when the target liquid-cooled energy storage system is running, obtaining the first monitoring information, performing abnormality detection according to the first monitoring information, and judging whether there is a leakage in the cooling pipeline of the target liquid-cooled energy storage system. Improve its safety, stability and operation efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of operation risk management and control, and in particular to an operation risk management and control method and system applied to a liquid-cooled energy storage system. Background Art

[0002] The operational risks of liquid-cooled energy storage systems mainly include coolant leakage, battery pack overheating, battery thermal runaway, and system electrical overload. Coolant leakage may lead to reduced cooling efficiency and even cause equipment short circuit or fire; battery overheating or thermal runaway may affect the battery's charging and discharging performance, and in severe cases may cause battery damage or explosion; and electrical overload may cause system power output instability, affect energy storage efficiency, and may cause equipment damage. If these risks are not warned and handled in a timely manner, they will not only affect the performance and life of the energy storage system, but may also cause system shutdown or even safety accidents, causing huge economic losses and safety hazards to operators.

[0003] At present, liquid-cooled energy storage systems often use basic temperature, pressure and current monitoring to determine the status of the equipment during operation, and use simple threshold settings to determine whether an abnormal situation occurs. However, this traditional monitoring method can only respond when a serious fault occurs, and it is impossible to accurately predict the potential risks of the system in real time. For this reason, there is an urgent need for an advanced method that can realize dynamic risk monitoring, analysis and early warning of liquid-cooled energy storage systems to improve their safety, stability and operating efficiency. Summary of the invention

[0004] The present invention overcomes the defects of the prior art and provides an operation risk management method and system for a liquid-cooled energy storage system, an important purpose of which is to improve the operation stability and safety of the liquid-cooled energy storage system.

[0005] To achieve the above objectives, the present invention provides, in a first aspect, an operation risk management method for a liquid-cooled energy storage system, comprising: Obtaining system construction information of a target liquid-cooled energy storage system, defining a heat source and analyzing a coolant flow direction and flow rate for the target liquid-cooled energy storage system, constructing a simulation model to analyze system responses under different operating conditions, and constructing a first simulation data set; Constructing a temperature prediction model, acquiring real-time operation monitoring information and inputting it into the temperature prediction model for analysis, identifying hot spots in the target liquid-cooled energy storage system, and obtaining hot spot identification information; Based on the hot spot area analysis information, determine whether there is a risk of thermal runaway during real-time operation of the target liquid-cooled energy storage system, and perform regulation and early warning; Monitor the temperature condition of the heat dissipation structure and the condition of the coolant in the pipeline when the target liquid-cooled energy storage system is running, obtain first monitoring information, perform abnormality detection based on the first monitoring information, and determine whether there is a leakage in the cooling pipeline of the target liquid-cooled energy storage system.

[0006] In this solution, the heat source of the target liquid-cooled energy storage system is defined, the flow direction and flow rate of the coolant are analyzed, a simulation model is constructed to analyze the system response under different operating conditions, and a first simulation data set is constructed, which specifically includes: Acquire system construction information of the target liquid-cooled energy storage system based on data retrieval, use 3D modeling technology to construct a geometric model of the target liquid-cooled energy storage system according to the system construction information, and define corresponding material properties; Extracting structural features of the target liquid-cooled energy storage system according to the system construction information, including component structural features, heat dissipation structural features, and pipeline features, to obtain system structural feature information; Obtaining the equipment specification and instruction manual of the target liquid-cooled energy storage system, defining the heat source and the heat source type in combination with the system structure characteristic information, and analyzing the flow direction and flow rate of the coolant in the target liquid-cooled energy storage system to obtain first analysis information; Constructing a liquid-cooled energy storage system simulation model by combining CFD software with a geometric model of the target liquid-cooled energy storage system, and defining the model heat source area and heat source flow direction using the first analysis information; Acquire the coolant property information of the target liquid-cooled energy storage system, and set the fluid boundary in combination with the system result characteristic information, including natural convection boundary conditions and forced convection boundary conditions; Several target liquid-cooled energy storage system operating conditions are preset, and the liquid-cooled energy storage system simulation model is used for simulation. The simulation results under different operating conditions are solved using a steady-state solver to form a first simulation data set.

[0007] In this solution, the temperature prediction model is constructed, real-time operation monitoring information is obtained and input into the temperature prediction model for analysis, hot spots in the target liquid-cooled energy storage system are identified, and hot spot identification information is obtained, specifically including: Acquire historical temperature monitoring data of the target liquid-cooled energy storage system during operation through historical data retrieval, including heat source temperature monitoring data and heat dissipation pipeline temperature monitoring data, mark abnormal temperatures and form a first data set; Obtain a first simulation data set, introduce a Markov algorithm, use the first simulation data set and the first data set to construct a temperature state transfer matrix under different operating conditions, and use a deep neural network to construct a temperature prediction model, perform deep learning and training on the temperature prediction model, and obtain a temperature prediction model that meets expectations; Monitor the target liquid-cooled energy storage system to obtain real-time operation monitoring information, perform data preprocessing on the real-time operation monitoring information, and input the data into the temperature prediction model for analysis; Based on the input real-time operation monitoring information, the operating condition characteristics of the target liquid-cooled energy storage system at the current moment are extracted, and the corresponding state transfer matrix is ​​obtained as the retrieval label. Based on the obtained state transfer matrix, the temperature prediction result at the next moment is generated to obtain the temperature prediction information; The temperature prediction information is input into a liquid-cooled energy storage system simulation model for simulation, and a spline function interpolation algorithm is introduced to generate a temperature distribution gradient diagram of the target liquid-cooled energy storage system at the next moment according to the simulation results; Based on the temperature distribution gradient map, the predicted temperature characteristics of each area of ​​the target liquid-cooled energy storage system are extracted, and judged against the preset threshold. The area greater than the preset threshold is defined as the hot spot area, and the hot spot area analysis information is obtained.

[0008] In this solution, the hot spot area analysis information is used to determine whether the target liquid-cooled energy storage system has a risk of thermal runaway during real-time operation, and to perform regulation and early warning, specifically including: Acquire hot spot area analysis information, perform feature extraction on the hot spot area analysis information, extract location features, temperature features and corresponding area type features of the hot spot area, and obtain hot spot area feature information, wherein the area types are heating area and heat dissipation area; Perform thermal runaway analysis based on the characteristic information of the hot spot area. If there is only a heating area, obtain temperature change monitoring data of the heating area and calculate the temperature change rate in the heating area. Construct thermal runaway assessment rules, generate the temperature change sequence of the corresponding hot spot area per unit time based on the calculated temperature change rate, and use the constructed thermal runaway assessment rules to determine whether there is a thermal runaway risk. If there is a thermal runaway risk, obtain the corresponding control strategy for regulation; If there is only a heat dissipation area, the temperature tolerance of the heat dissipation area is obtained, and judged with the corresponding temperature characteristics to analyze whether the temperature of the target heat dissipation area exceeds the temperature tolerance; If the temperature tolerance of the regional components is within the limit, the corresponding hot spot area is a temperature controllable area. If the temperature tolerance of the regional components is exceeded, a thermal runaway analysis is performed on the target hot spot area, and the corresponding control strategy is obtained based on the analysis results for regulation. If the hot spot area contains heat dissipation areas and heat generation areas, thermal runaway judgments are performed separately, and the operating mode information of the current liquid-cooled energy storage system is obtained. According to the judgment results, early warnings are issued and control strategies are formulated for regulation.

[0009] In this solution, the temperature condition of the heat dissipation structure and the condition of the coolant in the pipeline of the target liquid-cooled energy storage system are monitored during operation to obtain first monitoring information, and abnormality detection is performed according to the first monitoring information, specifically including: A sensor array is set based on the heat dissipation structure characteristics of the target liquid-cooled energy storage system, and the set sensor positions are used as nodes to monitor the temperature condition of the heat dissipation structure and the condition of the coolant in the pipeline when the target liquid-cooled energy storage system is running, so as to obtain first monitoring information; Defining the sequence of sensors according to the coolant circulation direction characteristics in the pipeline of the target liquid-cooled energy storage system and generating a node sequence, and associating the monitoring data of the corresponding node with the node sequence in combination with the first monitoring information to obtain second analysis information; An anomaly detection model is constructed based on a generative adversarial network, and historical monitoring data in the pipeline under different operating modes when the target liquid-cooled energy storage system is operating normally is obtained to form a training data set for training the anomaly detection model; The second analysis information is input into the trained anomaly detection model, the second analysis information input into the model is subjected to feature extraction and an original sequence is generated, and the original sequence is input into the generator for sequence generation to obtain a generated sequence; The generated sequence is input into the discriminator for judgment, and the corresponding generated sequence is analyzed to determine whether it is accepted. If not, the next generated sequence is obtained for judgment until it meets the acceptance conditions and the final generated sequence is obtained; The reconstruction error between the final generated sequence and the original sequence is calculated, and anomaly detection is performed based on the calculated reconstruction error to obtain anomaly detection information.

[0010] In this solution, the step of determining whether there is leakage in the cooling pipe of the target liquid-cooled energy storage system specifically includes: Acquire historical flow monitoring data in the pipeline under different operation modes of the target liquid-cooled energy storage system, classify the operation modes into categories using a clustering algorithm, and obtain first category classification information; Based on the first category analysis information, each operating mode category is marked as normal operation and abnormal operation, and the flow monitoring characteristics of normal operation and abnormal operation under each operating mode category are extracted; Constructing a category portrait of each operating mode category through the extracted flow monitoring features, wherein the category portrait includes a normal operating category portrait and an abnormal operating category portrait, and constructing a first database based on the category portrait of each operating mode; Acquire anomaly detection information, perform similarity calculation on the anomaly detection information and the category portraits stored in the first database, judge the current operating status based on the similarity value, and acquire similar category portraits; If the category portrait similar to the current operating status is a normal operating portrait, it means that the target liquid-cooled energy storage system is in a normal operating state. If the category portrait similar to the current operating status is an abnormal operating portrait, it means that the target liquid-cooled energy storage system has an abnormal operating condition. If there is an abnormal operation, feature extraction is performed on the first monitoring information to obtain monitoring features of different monitoring nodes, including temperature features and flow features, to obtain second feature extraction information; Obtain an abnormal operation profile similar to the current operation status and perform feature extraction, perform difference calculation between the extracted features and the second feature extraction information, determine whether there is a leakage condition based on the calculated difference, and issue a risk warning.

[0011] A second aspect of the present invention provides an operation risk management system applied to a liquid-cooled energy storage system, the system comprising: a memory, a processor, the memory containing an operation risk management method program applied to the liquid-cooled energy storage system, the operation risk management method program applied to the liquid-cooled energy storage system being executed by the processor to implement the following steps: Obtaining system construction information of a target liquid-cooled energy storage system, defining a heat source and analyzing a coolant flow direction and flow rate for the target liquid-cooled energy storage system, constructing a simulation model to analyze system responses under different operating conditions, and constructing a first simulation data set; Constructing a temperature prediction model, acquiring real-time operation monitoring information and inputting it into the temperature prediction model for analysis, identifying hot spots in the target liquid-cooled energy storage system, and obtaining hot spot identification information; Based on the hot spot area analysis information, determine whether there is a risk of thermal runaway during real-time operation of the target liquid-cooled energy storage system, and perform regulation and early warning; Monitor the temperature condition of the heat dissipation structure and the condition of the coolant in the pipeline when the target liquid-cooled energy storage system is running, obtain first monitoring information, perform abnormality detection based on the first monitoring information, and determine whether there is a leakage in the cooling pipeline of the target liquid-cooled energy storage system.

[0012] The present invention discloses an operation risk control method and system for a liquid-cooled energy storage system, including: defining the heat source and analyzing the flow direction and flow rate of the coolant for the target liquid-cooled energy storage system, constructing a simulation model to analyze the system response under different operating conditions, and constructing a first simulation data set; constructing a temperature prediction model, obtaining real-time operation monitoring information and inputting it into the temperature prediction model for analysis, identifying the hotspot area in the target liquid-cooled energy storage system, and obtaining hotspot area identification information; judging whether there is a risk of thermal runaway in the real-time operation of the target liquid-cooled energy storage system based on the hotspot area analysis information, and performing regulation and early warning; monitoring the temperature condition of the heat dissipation structure and the coolant condition in the pipeline when the target liquid-cooled energy storage system is running, obtaining the first monitoring information, performing abnormality detection according to the first monitoring information, and judging whether there is a leakage in the cooling pipeline of the target liquid-cooled energy storage system. Improve its safety, stability and operation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments or exemplary embodiments of the present invention, the drawings required for use in the embodiments or exemplary descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained according to the drawings without paying creative work.

[0014] Figure 1 A flow chart of an operation risk management method for a liquid-cooled energy storage system provided in one embodiment of the present invention; Figure 2 A flow chart of a method for analyzing liquid leakage in a liquid-cooled energy storage system provided by an embodiment of the present invention; Figure 3 A block diagram of an operation risk management system applied to a liquid-cooled energy storage system provided by one embodiment of the present invention; The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0015] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0016] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0017] Figure 1A flow chart of an operation risk management method for a liquid-cooled energy storage system provided in one embodiment of the present invention; like Figure 1 As shown, the present invention provides a flow chart of an operation risk management method for a liquid-cooled energy storage system, including: S102, obtaining system configuration information of a target liquid-cooled energy storage system, defining a heat source and analyzing a coolant flow direction and flow rate for the target liquid-cooled energy storage system, constructing a simulation model to analyze system responses under different operating conditions, and constructing a first simulation data set; S104, constructing a temperature prediction model, acquiring real-time operation monitoring information and inputting it into the temperature prediction model for analysis, identifying hot spots in the target liquid-cooled energy storage system, and obtaining hot spot identification information; S106, judging whether there is a risk of thermal runaway when the target liquid-cooled energy storage system is running in real time based on the hot spot area analysis information, and performing regulation and early warning; S108, monitoring the temperature of the heat dissipation structure and the coolant condition in the pipeline when the target liquid-cooled energy storage system is running, obtaining first monitoring information, performing abnormality detection based on the first monitoring information, and determining whether there is a leakage in the cooling pipeline of the target liquid-cooled energy storage system.

[0018] It should be noted that the present invention provides an operation risk control method and system for a liquid-cooled energy storage system, which obtains the system construction information of the target liquid-cooled energy storage system, defines the heat source and analyzes the flow direction and flow rate of the coolant of the target liquid-cooled energy storage system, builds a simulation model to analyze the system response under different operating conditions, and builds a first simulation data set; builds a temperature prediction model and uses the first simulation data set for model training, obtains real-time operation monitoring information and inputs it into the temperature prediction model for analysis, identifies the hot spot area in the target liquid-cooled energy storage system, obtains the hot spot area identification information, and thus identifies the existence of high-temperature areas when the liquid-cooled system is running; then, based on the hot spot area analysis information, determines whether there is a risk of thermal runaway when the target liquid-cooled energy storage system is running in real time, and performs regulation and early warning; further, monitors the temperature condition of the heat dissipation structure and the coolant condition in the pipeline when the target liquid-cooled energy storage system is running, obtains the first monitoring information, performs abnormal detection according to the first monitoring information, and determines whether there is a leakage in the cooling pipeline of the target liquid-cooled energy storage system. Thereby improving the safety and stability of system operation.

[0019] Furthermore, in a preferred embodiment of the present invention, the heat source definition and coolant flow direction and flow rate analysis of the target liquid-cooled energy storage system are performed, a simulation model is constructed to analyze the system response under different operating conditions, and a first simulation data set is constructed, which specifically includes: Acquire system construction information of the target liquid-cooled energy storage system based on data retrieval, use 3D modeling technology to construct a geometric model of the target liquid-cooled energy storage system according to the system construction information, and define corresponding material properties; Extracting structural features of the target liquid-cooled energy storage system according to the system construction information, including component structural features, heat dissipation structural features, and pipeline features, to obtain system structural feature information; Obtaining the equipment specification and instruction manual of the target liquid-cooled energy storage system, defining the heat source and the heat source type in combination with the system structure characteristic information, and analyzing the flow direction and flow rate of the coolant in the target liquid-cooled energy storage system to obtain first analysis information; Constructing a liquid-cooled energy storage system simulation model by combining CFD software with a geometric model of the target liquid-cooled energy storage system, and defining the model heat source area and heat source flow direction using the first analysis information; Acquire the coolant property information of the target liquid-cooled energy storage system, and set the fluid boundary in combination with the system result characteristic information, including natural convection boundary conditions and forced convection boundary conditions; Several target liquid-cooled energy storage system operating conditions are preset, and the liquid-cooled energy storage system simulation model is used for simulation. The simulation results under different operating conditions are solved using a steady-state solver to form a first simulation data set.

[0020] It should be noted that the system construction information of the target liquid-cooled energy storage system is first obtained through data retrieval technology, including the design details and layout of each component. Using three-dimensional modeling technology, the geometric model of the target liquid-cooled energy storage system is constructed based on this construction information, and the corresponding material properties are defined for each component. Then, based on the system construction information, the structural characteristics of the target liquid-cooled energy storage system are extracted, which includes the specific structure of the components, the heat dissipation structure, and the pipeline characteristics, and then the structural characteristic information of the system is obtained. After obtaining the system structural characteristic information, the equipment specification and instruction manual of the target liquid-cooled energy storage system are further obtained. By combining the structural characteristic information, the heat source and heat source type of the system are defined, and the flow direction and flow rate of the coolant in the system are analyzed to obtain the first analysis information. These analysis results will provide key parameters for subsequent fluid simulation and thermal management optimization. Next, CFD (computational fluid dynamics) software is used to construct a simulation model of the liquid-cooled energy storage system in combination with the geometric model of the target liquid-cooled energy storage system, and the heat source area and heat source flow direction in the model are defined according to the first analysis information to ensure that the simulation model can accurately reflect the heat distribution and cooling process in the actual system. Subsequently, the coolant property information of the target liquid-cooled energy storage system is obtained, and the fluid boundary conditions are set in combination with the structural characteristic information of the system, including the definition of boundary conditions such as natural convection and forced convection. In this way, different fluid movement conditions can be simulated, and the performance of the system under different working conditions can be better predicted. Finally, several operating conditions of the target liquid-cooled energy storage system are preset, and multiple simulation analyses are performed using the constructed simulation model. The steady-state solver is used to solve the simulation results under different working conditions, and then the first simulation data set is obtained.

[0021] Furthermore, in a preferred embodiment of the present invention, the temperature prediction model is constructed, real-time operation monitoring information is obtained and input into the temperature prediction model for analysis, hot spot areas in the target liquid-cooled energy storage system are identified, and hot spot area identification information is obtained, specifically including: Acquire historical temperature monitoring data of the target liquid-cooled energy storage system during operation through historical data retrieval, including heat source temperature monitoring data and heat dissipation pipeline temperature monitoring data, mark abnormal temperatures and form a first data set; Obtain a first simulation data set, introduce a Markov algorithm, use the first simulation data set and the first data set to construct a temperature state transfer matrix under different operating conditions, and use a deep neural network to construct a temperature prediction model, perform deep learning and training on the temperature prediction model, and obtain a temperature prediction model that meets expectations; Monitor the target liquid-cooled energy storage system to obtain real-time operation monitoring information, perform data preprocessing on the real-time operation monitoring information, and input the data into the temperature prediction model for analysis; Based on the input real-time operation monitoring information, the operating condition characteristics of the target liquid-cooled energy storage system at the current moment are extracted, and the corresponding state transfer matrix is ​​obtained as the retrieval label. Based on the obtained state transfer matrix, the temperature prediction result at the next moment is generated to obtain the temperature prediction information; The temperature prediction information is input into a liquid-cooled energy storage system simulation model for simulation, and a spline function interpolation algorithm is introduced to generate a temperature distribution gradient diagram of the target liquid-cooled energy storage system at the next moment according to the simulation results; Based on the temperature distribution gradient map, the predicted temperature characteristics of each area of ​​the target liquid-cooled energy storage system are extracted, and judged against the preset threshold. The area greater than the preset threshold is defined as the hot spot area, and the hot spot area analysis information is obtained.

[0022] It should be noted that, first, the temperature monitoring data of the target liquid-cooled energy storage system during operation is obtained through historical data retrieval technology, including important monitoring data such as heat source temperature and heat dissipation pipe temperature. By analyzing these historical temperature data, abnormal temperature values ​​are marked to construct a first data set. Next, the first simulation data set is obtained, and the Markov algorithm is introduced. Using this algorithm, the temperature state transfer matrix under different operating conditions is constructed in combination with the first data set and the first simulation data set. By combining a deep neural network, a temperature prediction model is further constructed, and the model is deeply learned and trained to obtain a temperature prediction model that meets the expected effect. After completing the construction and training of the temperature prediction model, the current operation monitoring information of the system is obtained and input into the trained temperature prediction model for analysis. Based on the operation monitoring information at the current moment, the operating condition characteristics of the target liquid-cooled energy storage system are extracted, and these characteristics are used as retrieval tags to obtain the corresponding state transfer matrix. Based on the state transfer matrix, the temperature prediction result at the next moment can be generated, thereby obtaining the temperature prediction information for a period of time in the future. Next, this temperature prediction information is input into the simulation model of the liquid-cooled energy storage system for further simulation analysis. By introducing the spline function interpolation algorithm, the temperature distribution gradient map of the target liquid-cooled energy storage system at the next moment is generated according to the simulation results. This gradient map can show the temperature change trend of each area of ​​the system in detail. Based on this temperature distribution gradient map, the predicted temperature characteristics of each area of ​​the system are extracted and compared with the preset temperature threshold. For areas greater than the preset threshold, they are defined as hot spots, so as to obtain analytical information about the hot spots. This process provides a more accurate temperature control basis for real-time monitoring and management of liquid-cooled energy storage systems, which helps system fault warning and safety assurance.

[0023] Further, in a preferred embodiment of the present invention, the determination of whether there is a risk of thermal runaway in the real-time operation of the target liquid-cooled energy storage system based on the hot spot area analysis information, and the regulation and early warning are specifically included: Acquire hot spot area analysis information, perform feature extraction on the hot spot area analysis information, extract location features, temperature features and corresponding area type features of the hot spot area, and obtain hot spot area feature information, wherein the area types are heating area and heat dissipation area; Perform thermal runaway analysis based on the characteristic information of the hot spot area. If there is only a heating area, obtain temperature change monitoring data of the heating area and calculate the temperature change rate in the heating area. Construct thermal runaway assessment rules, generate the temperature change sequence of the corresponding hot spot area per unit time based on the calculated temperature change rate, and use the constructed thermal runaway assessment rules to determine whether there is a thermal runaway risk. If there is a thermal runaway risk, obtain the corresponding control strategy for regulation; If there is only a heat dissipation area, the temperature tolerance of the heat dissipation area is obtained, and judged with the corresponding temperature characteristics to analyze whether the temperature of the target heat dissipation area exceeds the temperature tolerance; If the temperature tolerance of the regional components is within the limit, the corresponding hot spot area is a temperature controllable area. If the temperature tolerance of the regional components is exceeded, a thermal runaway analysis is performed on the target hot spot area, and the corresponding control strategy is obtained based on the analysis results for regulation. If the hot spot area contains heat dissipation areas and heat generation areas, thermal runaway judgments are performed separately, and the operating mode information of the current liquid-cooled energy storage system is obtained. According to the judgment results, early warnings are issued and control strategies are formulated for regulation.

[0024] It should be noted that the hot spot area analysis information is first obtained and feature extraction is performed to extract the location features, temperature features and area type features of the hot spot area, thereby forming the feature information of the hot spot area. The area types here can be divided into heating areas and heat dissipation areas. Through the extraction of these features, the operating status of different areas in the system can be fully understood, providing necessary data support for subsequent thermal runaway analysis. When conducting thermal runaway analysis, the situation where only the heating area exists is first considered. In this case, it is necessary to obtain the temperature change monitoring data of the heating area and calculate the temperature change rate of the area. This rate reflects the speed of temperature change in the area and is an important indicator for judging whether there is a risk of thermal runaway. Subsequently, based on the calculated temperature change rate, a thermal runaway evaluation rule is constructed. Through this rule, a temperature change sequence of the heating area per unit time can be generated, and the sequence can be used to evaluate whether there is a risk of thermal runaway. If the risk of thermal runaway is detected, the corresponding control strategy will be further obtained for regulation to ensure stable operation of the system. If the analysis results only show that there is a heat dissipation area, it is necessary to further obtain the temperature tolerance of the area and compare it with the actual temperature characteristics of the heat dissipation area. If the temperature of the heat dissipation area does not exceed its tolerance, it means that the temperature of the area is within the controllable range and belongs to the temperature controllable area; if the temperature exceeds the tolerance, the hot spot area needs to be analyzed for thermal runaway. According to the analysis results, appropriate control strategies are adopted to adjust to avoid further temperature increase and cause system failure or safety hazards. In some cases, the hot spot area may contain both the heat dissipation area and the heating area. In this case, it is necessary to judge the thermal runaway of the heating area and the heat dissipation area separately, and conduct a comprehensive analysis in combination with the operating mode information of the current liquid-cooled energy storage system. If the judgment result shows that there is a risk of thermal runaway, an early warning should be issued immediately, and a control strategy should be formulated to regulate the system, for example, adjusting the operating mode of the heating area or changing the working mode of the heat dissipation operation. By accurately analyzing the temperature changes and thermal runaway risks of each area, the safety and stability of the liquid-cooled energy storage system during operation can be effectively ensured.

[0025] Further, in a preferred embodiment of the present invention, the temperature condition of the heat dissipation structure and the condition of the coolant in the pipeline when the target liquid-cooled energy storage system is running are monitored to obtain first monitoring information, and abnormality detection is performed according to the first monitoring information, specifically including: A sensor array is set based on the heat dissipation structure characteristics of the target liquid-cooled energy storage system, and the set sensor positions are used as nodes to monitor the temperature condition of the heat dissipation structure and the condition of the coolant in the pipeline when the target liquid-cooled energy storage system is running, so as to obtain first monitoring information; Defining the sequence of sensors according to the coolant circulation direction characteristics in the pipeline of the target liquid-cooled energy storage system and generating a node sequence, and associating the monitoring data of the corresponding node with the node sequence in combination with the first monitoring information to obtain second analysis information; An anomaly detection model is constructed based on a generative adversarial network, and historical monitoring data in the pipeline under different operating modes when the target liquid-cooled energy storage system is operating normally is obtained to form a training data set for training the anomaly detection model; The second analysis information is input into the trained anomaly detection model, the second analysis information input into the model is subjected to feature extraction and an original sequence is generated, and the original sequence is input into the generator for sequence generation to obtain a generated sequence; The generated sequence is input into the discriminator for judgment, and the corresponding generated sequence is analyzed to determine whether it is accepted. If not, the next generated sequence is obtained for judgment until it meets the acceptance conditions and the final generated sequence is obtained; The reconstruction error between the final generated sequence and the original sequence is calculated, and anomaly detection is performed based on the calculated reconstruction error to obtain anomaly detection information.

[0026] It should be noted that, first, the sensor array is set according to the heat dissipation structure characteristics of the target liquid-cooled energy storage system, the sensors are arranged at the key positions of the heat dissipation structure, and these positions are monitored as nodes. The role of the sensor is to monitor the temperature condition of the heat dissipation structure and the flow condition of the coolant in the pipeline in real time when the system is running, and finally obtain the first monitoring information. Next, based on the circulation direction characteristics of the coolant in the pipeline of the target liquid-cooled energy storage system, the sequence is defined for each sensor and a node sequence is generated. These node sequences are associated with the data in the first monitoring information to generate the second analysis information. Generative adversarial network (GAN) is introduced to build an anomaly detection model. The historical monitoring data in the pipeline of the target liquid-cooled energy storage system under normal operating conditions and different operating modes are obtained, and these data are used to form a training data set for training the anomaly detection model. These training data can help the model learn the temperature change pattern and flow characteristics of the coolant in the pipeline during normal operation, thereby providing a basis for subsequent anomaly detection. The second analysis information is input into the anomaly detection model for processing. After being input into the model, the model first extracts features from the second analysis information and generates an original sequence. These feature data are then fed into the generator for sequence generation. The generator generates new temperature and flow rate sequences based on the rules learned during the training process. Next, the generated sequence is input into the discriminator for judgment. The discriminator analyzes whether the generated sequence conforms to the normal operating mode. If the generated sequence is not accepted, the model will generate the next round of sequences for judgment until the generated sequence meets the acceptance conditions, thereby obtaining the final generated sequence. Finally, by calculating the reconstruction error between the generated sequence and the original sequence, the anomaly detection model identifies abnormal fluctuations or data deviations, and then determines whether the target liquid-cooled energy storage system is currently in an abnormal state.

[0027] Furthermore, in a preferred embodiment of the present invention, the step of determining whether there is a liquid leakage in the cooling pipe of the target liquid-cooled energy storage system specifically includes: Acquire historical flow monitoring data in the pipeline under different operation modes of the target liquid-cooled energy storage system, classify the operation modes into categories using a clustering algorithm, and obtain first category classification information; Based on the first category analysis information, each operating mode category is marked as normal operation and abnormal operation, and the flow monitoring characteristics of normal operation and abnormal operation under each operating mode category are extracted; Constructing a category portrait of each operating mode category through the extracted flow monitoring features, wherein the category portrait includes a normal operating category portrait and an abnormal operating category portrait, and constructing a first database based on the category portrait of each operating mode; Acquire anomaly detection information, perform similarity calculation on the anomaly detection information and the category portraits stored in the first database, determine the current operating status based on the similarity value, and acquire similar category portraits; If the category portrait similar to the current operating status is a normal operating portrait, it means that the target liquid-cooled energy storage system is in a normal operating state. If the category portrait similar to the current operating status is an abnormal operating portrait, it means that the target liquid-cooled energy storage system has an abnormal operating condition. If there is an abnormal operation, feature extraction is performed on the first monitoring information to obtain monitoring features of different monitoring nodes, including temperature features and flow features, to obtain second feature extraction information; Obtain an abnormal operation profile similar to the current operation status and perform feature extraction, perform difference calculation between the extracted features and the second feature extraction information, determine whether there is a leakage condition based on the calculated difference, and issue a risk warning.

[0028] It should be noted that by obtaining the historical flow monitoring data in the pipeline of the target liquid-cooled energy storage system under different operating modes, and using the operating mode as a category, the clustering algorithm is used to classify these data, thereby obtaining the first category division information. Then, based on the first category division information, each operating mode category is further analyzed to mark which ones belong to the normal operating state and which ones belong to the abnormal operating state. At the same time, the flow monitoring features of normal operation and abnormal operation under each category are extracted to distinguish and diagnose the state of the system. Through the extracted flow monitoring features, a corresponding category portrait is constructed for each operating mode category. The category portrait includes not only the portrait during normal operation, but also the portrait during abnormal operation. These portraits help form the standard mode of the system under various working conditions by recording the key flow characteristics under different operating states. A first database is constructed based on these category portraits, and the flow characteristics during normal operation and abnormal operation are stored therein, providing a basis for subsequent abnormal detection and operation state judgment. Subsequently, the abnormal detection information is obtained and the similarity is calculated with the category portraits stored in the first database. By calculating the similarity between the current monitoring information and each category portrait, the current operating status of the system can be judged. If the current monitoring information is similar to a certain category portrait, and the category portrait corresponds to a normal operating state, it means that the target liquid-cooled energy storage system is in a normal operating state. If the category portrait with a higher degree of similarity corresponds to an abnormal operating state, it indicates that the system may be abnormal. Once it is determined that the target liquid-cooled energy storage system has an abnormal operating condition, further feature extraction will be performed on the first monitoring information, especially temperature features and flow features, and these features will be combined into the second feature extraction information. Then, by obtaining an abnormal operating portrait similar to the current operating condition, the feature information in the portrait is extracted, and the difference is calculated with the second feature extraction information. By calculating the difference, the system can determine whether there is a leakage and further evaluate the impact of the leakage on the operation of the system. If the difference exceeds the normal range, the risk warning mechanism is triggered to promptly warn of potential leakage risks and ensure that the system can take effective measures to troubleshoot and repair.

[0029] Figure 2 A flow chart of a method for analyzing liquid leakage in a liquid-cooled energy storage system provided by an embodiment of the present invention; like Figure 2 As shown, the present invention provides a flow chart of a method for analyzing liquid leakage in a liquid-cooled energy storage system, comprising: S202, obtaining anomaly detection information, performing similarity calculation on the anomaly detection information and the category portrait stored in the first database, judging the current operating status based on the similarity value, and obtaining a similar category portrait; S204, if the category portrait similar to the current operating status is a normal operating portrait, it means that the target liquid-cooled energy storage system is in a normal operating state; if the category portrait similar to the current operating status is an abnormal operating portrait, it means that the target liquid-cooled energy storage system has an abnormal operating condition; S206, if there is an abnormal operation, extracting features from the first monitoring information, obtaining monitoring features of different monitoring nodes, including temperature features and flow features, and obtaining second feature extraction information; S208, obtaining an abnormal operation profile similar to the current operation status and performing feature extraction, performing difference calculation between the extracted features and the second feature extraction information, judging whether there is a leakage condition based on the calculated difference, and performing a risk warning.

[0030] It should be noted that under normal operation of the liquid-cooled energy storage system, whether for the heating part or the heat dissipation structure, the corresponding operating characteristics under different operating modes are always maintained within a stable range. Similarly, for the heat dissipation structure, the heat dissipation structure absorbs the heat from the heating part, and circulates the coolant after absorbing the heat through the pipeline, so that the coolant heat is dissipated and the heat is repeatedly circulated. Therefore, for the coolant, its corresponding temperature characteristics during operation are in a stable range. If the heat is not dissipated in time and then absorbed again, it may cause excessive heat accumulation. At the same time, the leakage of the coolant brings not only changes in flow rate, but also changes in temperature. The reduction of coolant may cause the heat to be unable to be discharged or the coolant to accumulate too much heat, thereby causing operational risks. Therefore, using the monitoring data under normal operation to form a category portrait under each operating mode, it can greatly understand the normal circulation heat dissipation under the operation of this mode. When there is a difference, it means that there is an abnormal situation and regulatory intervention is required to avoid operational risks.

[0031] Figure 3 An operation risk control system 3 applied to a liquid-cooled energy storage system is provided in one embodiment of the present invention. The system includes: a memory 31 and a processor 32. The memory 31 contains an operation risk control method program applied to the liquid-cooled energy storage system. When the operation risk control method program applied to the liquid-cooled energy storage system is executed by the processor 32, the following steps are implemented: Obtaining system construction information of a target liquid-cooled energy storage system, defining a heat source and analyzing a coolant flow direction and flow rate for the target liquid-cooled energy storage system, constructing a simulation model to analyze system responses under different operating conditions, and constructing a first simulation data set; Constructing a temperature prediction model, acquiring real-time operation monitoring information and inputting it into the temperature prediction model for analysis, identifying hot spots in the target liquid-cooled energy storage system, and obtaining hot spot identification information; Based on the hot spot area analysis information, determine whether there is a risk of thermal runaway during real-time operation of the target liquid-cooled energy storage system, and perform regulation and early warning; Monitor the temperature condition of the heat dissipation structure and the condition of the coolant in the pipeline when the target liquid-cooled energy storage system is running, obtain first monitoring information, perform abnormality detection based on the first monitoring information, and determine whether there is a leakage in the cooling pipeline of the target liquid-cooled energy storage system.

[0032] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0033] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0034] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0035] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0036] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0037] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for controlling operational risks of a liquid-cooled energy storage system, characterized in that: include: Obtaining system construction information of a target liquid-cooled energy storage system, defining a heat source and analyzing a coolant flow direction and flow rate for the target liquid-cooled energy storage system, constructing a simulation model to analyze system responses under different operating conditions, and constructing a first simulation data set; Constructing a temperature prediction model, acquiring real-time operation monitoring information and inputting it into the temperature prediction model for analysis, identifying hot spots in the target liquid-cooled energy storage system, and obtaining hot spot identification information; Based on the hot spot area analysis information, determine whether there is a risk of thermal runaway during real-time operation of the target liquid-cooled energy storage system, and perform regulation and early warning; Monitor the temperature condition of the heat dissipation structure and the condition of the coolant in the pipeline when the target liquid-cooled energy storage system is running, obtain first monitoring information, perform abnormality detection based on the first monitoring information, and determine whether there is a leakage in the cooling pipeline of the target liquid-cooled energy storage system.

2. The operation risk management method for a liquid-cooled energy storage system according to claim 1, characterized in that: The heat source definition and coolant flow direction and flow rate analysis of the target liquid-cooled energy storage system, the construction of a simulation model to analyze the system response under different operating conditions, and the construction of a first simulation data set specifically include: Acquire system construction information of the target liquid-cooled energy storage system based on data retrieval, use 3D modeling technology to construct a geometric model of the target liquid-cooled energy storage system according to the system construction information, and define corresponding material properties; Extracting structural features of the target liquid-cooled energy storage system according to the system construction information, including component structural features, heat dissipation structural features, and pipeline features, to obtain system structural feature information; Obtaining the equipment specification and instruction manual of the target liquid-cooled energy storage system, defining the heat source and the heat source type in combination with the system structure characteristic information, and analyzing the flow direction and flow rate of the coolant in the target liquid-cooled energy storage system to obtain first analysis information; Constructing a liquid-cooled energy storage system simulation model by combining CFD software with a geometric model of the target liquid-cooled energy storage system, and defining the model heat source area and heat source flow direction using the first analysis information; Acquire the coolant property information of the target liquid-cooled energy storage system, and set the fluid boundary in combination with the system result characteristic information, including natural convection boundary conditions and forced convection boundary conditions; Several target liquid-cooled energy storage system operating conditions are preset, and the liquid-cooled energy storage system simulation model is used for simulation. The simulation results under different operating conditions are solved using a steady-state solver to form a first simulation data set.

3. The operation risk management method for a liquid-cooled energy storage system according to claim 1, characterized in that: The step of constructing a temperature prediction model, acquiring real-time operation monitoring information and inputting the information into the temperature prediction model for analysis, identifying hot spots in the target liquid-cooled energy storage system, and obtaining hot spot identification information specifically includes: Acquire historical temperature monitoring data of the target liquid-cooled energy storage system during operation through historical data retrieval, including heat source temperature monitoring data and heat dissipation pipeline temperature monitoring data, mark abnormal temperatures and form a first data set; Obtain a first simulation data set, introduce a Markov algorithm, use the first simulation data set and the first data set to construct a temperature state transfer matrix under different operating conditions, and use a deep neural network to construct a temperature prediction model, perform deep learning and training on the temperature prediction model, and obtain a temperature prediction model that meets expectations; Monitor the target liquid-cooled energy storage system to obtain real-time operation monitoring information, perform data preprocessing on the real-time operation monitoring information, and input the data into the temperature prediction model for analysis; Based on the input real-time operation monitoring information, the operating condition characteristics of the target liquid-cooled energy storage system at the current moment are extracted, and the corresponding state transfer matrix is ​​obtained as the retrieval label. Based on the obtained state transfer matrix, the temperature prediction result at the next moment is generated to obtain the temperature prediction information; The temperature prediction information is input into a liquid-cooled energy storage system simulation model for simulation, and a spline function interpolation algorithm is introduced to generate a temperature distribution gradient diagram of the target liquid-cooled energy storage system at the next moment according to the simulation results; Based on the temperature distribution gradient map, the predicted temperature characteristics of each area of ​​the target liquid-cooled energy storage system are extracted, and judged against the preset threshold. The area greater than the preset threshold is defined as the hot spot area, and the hot spot area analysis information is obtained.

4. The operation risk management method for a liquid-cooled energy storage system according to claim 1, characterized in that: The step of determining whether there is a risk of thermal runaway in the real-time operation of the target liquid-cooled energy storage system based on the hot spot area analysis information, and performing regulation and early warning specifically includes: Acquire hot spot area analysis information, perform feature extraction on the hot spot area analysis information, extract location features, temperature features and corresponding area type features of the hot spot area, and obtain hot spot area feature information, wherein the area types are heating area and heat dissipation area; Perform thermal runaway analysis based on the characteristic information of the hot spot area. If there is only a heating area, obtain temperature change monitoring data of the heating area and calculate the temperature change rate in the heating area. Construct thermal runaway assessment rules, generate the temperature change sequence of the corresponding hot spot area per unit time based on the calculated temperature change rate, and use the constructed thermal runaway assessment rules to determine whether there is a thermal runaway risk. If there is a thermal runaway risk, obtain the corresponding control strategy for regulation; If there is only a heat dissipation area, the temperature tolerance of the heat dissipation area is obtained, and judged with the corresponding temperature characteristics to analyze whether the temperature of the target heat dissipation area exceeds the temperature tolerance; If the temperature tolerance of the regional components is within the limit, the corresponding hot spot area is a temperature controllable area. If the temperature tolerance of the regional components is exceeded, a thermal runaway analysis is performed on the target hot spot area, and the corresponding control strategy is obtained based on the analysis results for regulation. If the hot spot area includes the heat dissipation area and the heat generation area, thermal runaway judgment is performed separately, and the operation mode information of the current liquid-cooled energy storage system is obtained. According to the judgment results, early warning is issued and a control strategy is formulated for regulation.

5. The operation risk management method for a liquid-cooled energy storage system according to claim 1, characterized in that: The monitoring target liquid-cooled energy storage system is operated with respect to the temperature condition of the heat dissipation structure and the condition of the coolant in the pipeline to obtain first monitoring information, and performing abnormality detection according to the first monitoring information specifically includes: A sensor array is set based on the heat dissipation structure characteristics of the target liquid-cooled energy storage system, and the set sensor positions are used as nodes to monitor the temperature condition of the heat dissipation structure and the condition of the coolant in the pipeline when the target liquid-cooled energy storage system is running, so as to obtain first monitoring information; Defining the sequence of sensors according to the coolant circulation direction characteristics in the pipeline of the target liquid-cooled energy storage system and generating a node sequence, and associating the monitoring data of the corresponding node with the node sequence in combination with the first monitoring information to obtain second analysis information; An anomaly detection model is constructed based on a generative adversarial network, and historical monitoring data in the pipeline under different operating modes when the target liquid-cooled energy storage system is operating normally is obtained to form a training data set for training the anomaly detection model; The second analysis information is input into the trained anomaly detection model, the second analysis information input into the model is subjected to feature extraction and an original sequence is generated, and the original sequence is input into the generator for sequence generation to obtain a generated sequence; The generated sequence is input into the discriminator for judgment, and the corresponding generated sequence is analyzed to determine whether it is accepted. If not, the next generated sequence is obtained for judgment until it meets the acceptance conditions and the final generated sequence is obtained; The reconstruction error between the final generated sequence and the original sequence is calculated, and anomaly detection is performed based on the calculated reconstruction error to obtain anomaly detection information.

6. The operation risk management method for a liquid-cooled energy storage system according to claim 1, characterized in that: The determining whether there is a liquid leakage in the cooling pipeline of the target liquid-cooled energy storage system specifically includes: Acquire historical flow monitoring data in the pipeline under different operation modes of the target liquid-cooled energy storage system, classify the operation modes into categories using a clustering algorithm, and obtain first category classification information; Based on the first category analysis information, each operating mode category is marked as normal operation and abnormal operation, and the flow monitoring characteristics of normal operation and abnormal operation under each operating mode category are extracted; Constructing a category portrait of each operating mode category through the extracted flow monitoring features, wherein the category portrait includes a normal operating category portrait and an abnormal operating category portrait, and constructing a first database based on the category portrait of each operating mode; Acquire anomaly detection information, perform similarity calculation on the anomaly detection information and the category portraits stored in the first database, determine the current operating status based on the similarity value, and acquire similar category portraits; If the category portrait similar to the current operating status is a normal operating portrait, it means that the target liquid-cooled energy storage system is in a normal operating state. If the category portrait similar to the current operating status is an abnormal operating portrait, it means that the target liquid-cooled energy storage system has an abnormal operating condition. If there is an abnormal operation, feature extraction is performed on the first monitoring information to obtain monitoring features of different monitoring nodes, including temperature features and flow features, to obtain second feature extraction information; Obtain an abnormal operation profile similar to the current operation status and perform feature extraction, perform difference calculation between the extracted features and the second feature extraction information, determine whether there is a leakage condition based on the calculated difference, and issue a risk warning.

7. An operation risk management and control system applied to a liquid-cooled energy storage system, characterized in that: The system includes: a memory and a processor, wherein the memory contains an operation risk control method program applied to a liquid-cooled energy storage system, and when the operation risk control method program applied to a liquid-cooled energy storage system is executed by the processor, the following steps are implemented: Obtaining system construction information of a target liquid-cooled energy storage system, defining a heat source and analyzing a coolant flow direction and flow rate for the target liquid-cooled energy storage system, constructing a simulation model to analyze system responses under different operating conditions, and constructing a first simulation data set; Constructing a temperature prediction model, acquiring real-time operation monitoring information and inputting it into the temperature prediction model for analysis, identifying hot spots in the target liquid-cooled energy storage system, and obtaining hot spot identification information; Based on the hot spot area analysis information, determine whether there is a risk of thermal runaway during real-time operation of the target liquid-cooled energy storage system, and perform regulation and early warning; Monitor the temperature condition of the heat dissipation structure and the condition of the coolant in the pipeline when the target liquid-cooled energy storage system is running, obtain first monitoring information, perform abnormality detection based on the first monitoring information, and determine whether there is a leakage in the cooling pipeline of the target liquid-cooled energy storage system.

Images