Thermal management method, system and equipment for energy storage and storage medium

Abstract

The invention discloses a thermal management method, system and device for energy storage and a storage medium, and belongs to the technical field of energy storage thermal management, a battery cluster is divided into a plurality of battery cluster areas, and a thermal management strategy is determined according to temperature control constraints among different battery cluster areas and a layout route map of temperature control pipelines, so that the thermal management efficiency is improved. Effective heat management of the large integrated energy storage system is achieved, the ant colony algorithm is used for dynamically balancing the temperature control requirements of all the areas and the utilization efficiency of pipeline resources, invalid energy consumption is avoided, and cross-area cooperative control rules are established by analyzing heat transfer rules and potential conflicts between different temperature areas, so that the heat transfer efficiency of the large integrated energy storage system is improved. The problem of energy consumption waste or local overheating / supercooling possibly caused by traditional global regulation and control is avoided, under the temperature control constraint conditions, the optimal path combination, flow distribution and control mode are dynamically generated, and the temperature control precision is improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of energy storage thermal management, and particularly relates to an energy storage thermal management method, system, device and storage medium. BACKGROUND

[0002] With the rapid development of new energy technology, large-scale battery energy storage systems are widely used in power peak shaving, electric vehicle battery swap stations and other scenarios. However, heat accumulation is easy to occur in the charging and discharging process of the battery cluster, and local high temperature may cause thermal runaway, while low temperature environment will cause significant performance degradation of the battery.

[0003] In related technologies, for a battery cluster, a thermal management component is generally used to manage the heat of the battery, and the thermal management component issues the same thermal management strategy. However, the battery cluster contains a large number of battery monomers, and the conditions of each battery monomer are inconsistent. For a battery cluster with a large number, the unified thermal management mode issued by a single thermal management component may not meet the thermal management needs. SUMMARY

[0004] The purpose of the present application is to provide an energy storage thermal management method, system, device and storage medium, which aims to solve the technical problem that the existing battery cluster thermal management adopts a unified thermal management mode that cannot meet the thermal management needs.

[0005] To solve the above problems, the present application adopts the following technical solutions: An energy storage thermal management method, comprising the following steps: obtaining a thermal distribution map of a battery cluster and a layout route map of a plurality of temperature control pipes in the battery cluster; According to the thermal distribution map of the battery cluster, the battery cluster is divided into a plurality of battery cluster areas, the battery cluster areas in different temperature states are analyzed, and the temperature control constraints between different battery cluster areas are determined; Under the temperature control constraints, the thermal management strategy is determined according to the layout route map of the temperature control pipes; The thermal management strategy is obtained based on an ant colony algorithm.

[0006] Further, the thermal management strategy is obtained based on an ant colony algorithm, comprising: initializing ant colony parameters, and modeling the temperature control pipe network as a weighted graph structure, the nodes representing the positions of the intersection points between the temperature control pipes, and the edge weights including interference coefficients, energy consumption costs and conflict confrontation values, the interference coefficients being used to represent the heat transfer influence on other battery clusters, and the conflict confrontation values being determined according to the temperature control constraints; a plurality of ants start from a specified entrance, and each ant selects an initial path according to the edge weights between the nodes and a target probability formula; An initial flow distribution scheme is generated according to the initial path of each ant, and an opening value of a flow control device on the temperature control pipeline is calculated; According to the initial flow distribution scheme of each ant and the calculated opening value of the flow control device, the comprehensive score of each initial path is determined, the pheromone concentration is iteratively updated according to the comprehensive score, and the path pheromone of the path with the minimum temperature disturbance and the lowest energy consumption is preferentially enhanced; The initial path with the highest path pheromone concentration is taken as the optimal path, and the optimal initial flow, the opening of the corresponding flow control device, and the heat management mode are obtained according to the calculation results of the initial flow distribution scheme and the opening value corresponding to the determined optimal initial path.

[0007] Further, the priority and temperature control conflict of the battery cluster temperature control are determined according to the thermal distribution map of the battery cluster, and the opening and orientation of the flow control device in the temperature control pipeline are controlled.

[0008] Further, the determination of the temperature control constraint includes: Marking the battery cluster areas in different temperature states; Determining whether there is a temperature level difference conflict in the four positions of each marked battery cluster area in the battery cluster plan projection map, and marking the corresponding position as a conflict position when there is a conflict; Based on the marking of different temperature states, the marking of conflict positions, and the layout of the temperature control pipeline, a temperature constraint graph is constructed.

[0009] In a second aspect, a heat management system for energy storage is provided, including an acquisition module, a constraint division module, and a strategy determination module, wherein: The acquisition module is used to acquire a thermal distribution map of a battery cluster and a layout map of a plurality of temperature control pipelines in the battery cluster; The constraint division module is used to divide the battery cluster into a plurality of battery cluster areas according to the thermal distribution map of the battery cluster, analyze the battery cluster areas in different temperature states, and determine the temperature control constraints between different battery cluster areas; The strategy determination module is used to determine a heat management strategy according to the layout map of the temperature control pipeline under the temperature control constraint; The heat management strategy is obtained based on an ant colony algorithm.

[0010] Further, at least one flow control device is installed on each of the temperature control pipelines, and the flow control device is a four-way valve.

[0011] Further, it further includes an abnormality monitoring module for detecting the blockage of the temperature control pipeline or the failure of the flow control device installed on the temperature control pipeline.

[0012] Further, the abnormality processing module is further included for adding an abnormal temperature control pipeline into the forbidden selection list and re-performing the thermal management decision when the temperature control pipeline blockage or the failure of the flow control device installed on the temperature control pipeline is monitored.

[0013] In a third aspect, a terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the above method when executing the computer program.

[0014] In a fourth aspect, a computer readable storage medium stores a computer program, and the computer program implements the steps of the above method when executed by a processor.

[0015] Compared with the prior art, the present application has the following beneficial technical effects: The present application provides a thermal management method for energy storage, which divides a battery cluster into multiple battery cluster areas, determines a thermal management strategy according to temperature control constraints between different battery cluster areas and a layout route map of temperature control pipelines, realizes effective thermal management of a large integrated energy storage system, quickly searches for an optimal pipeline combination, flow distribution scheme and control logic that can meet the temperature control constraints of each area in the temperature control pipeline network through an ant colony algorithm, and compared with a traditional fixed strategy or a simple greedy algorithm, the ant colony algorithm can dynamically balance the temperature control requirements of each area and the utilization efficiency of pipeline resources, avoid invalid energy consumption, and thus significantly reduce the overall energy consumption of the thermal management system under the premise of meeting the temperature control target. The strategy generation process based on the ant colony algorithm has iterative optimization characteristics, can quickly re-search for an optimal strategy according to dynamic changes in temperature distribution and adjustments of temperature control constraints, and can adapt to working condition changes without manual intervention. It can flexibly cope with complex and variable operating scenarios.

[0016] By analyzing the heat transfer law and potential conflicts between different temperature regions, a cross-region cooperative control rule is established, which avoids the energy waste or local overheating / overcooling problems that may be caused by traditional global regulation, dynamically generates an optimal path combination, flow distribution and control mode under these temperature control constraints, and improves the temperature control accuracy.

[0017] The application provides a thermal management system for energy storage, which is used for thermal management of different temperature control pipelines by arranging multiple independent thermal management modules, and different thermal management modules can be combined for use for a large energy storage integrated system, so that effective thermal management of the large integrated energy storage system is realized, and a flow control device is arranged at a target position of each temperature control pipeline, so that the opening degree can be dynamically adjusted according to real-time temperature requirements, the actual flow is matched with the requirements, unnecessary pump power consumption and energy loss are reduced, meanwhile, multiple thermal management modules work in parallel, and other modules can share the load when a single module fails, so that system paralysis is avoided. For example, when a temperature control pipeline is blocked, the control module can add the pipeline to a prohibited selection list and re-plan a path through an abnormality monitoring module.

[0018] The system takes the pipeline intersection as a path planning node, comprehensively considers the interference coefficient, energy consumption cost and conflict confrontation value under the temperature control constraint through a weighted graph model, so that the ants can both avoid the regions with high heat transfer interference and high energy consumption and follow the cross-region temperature control constraint rules in the path selection process. The initial path combination generated by the ants is directly related to the opening degree of the flow control device, fine regulation and control are realized through the proportional relationship between the opening degree value and the actual flow, and the local overcooling / overheating problem caused by the global unified flow is avoided. The pheromone updating mechanism takes temperature interference and energy consumption as priorities, dynamically strengthens the selection probability of the optimal path, ensures that the system continuously optimizes the strategy in the real-time temperature change, realizes the balance between the temperature control accuracy, energy consumption efficiency and system reliability through the intelligent path search, multi-objective constraint optimization and dynamic feedback mechanism, and provides an efficient and stable thermal control solution for the high-power-density energy storage system.

[0019] Preferably, the abnormality processing module can timely process the blocking or failure abnormality through effective monitoring of the abnormality monitoring module, and when the blocking or failure is monitored, the abnormal pipeline is added to the prohibited selection list, and thermal management decision is re-performed, so that the execution error of the thermal management can be effectively avoided. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 A flow chart of a thermal management method for energy storage in the embodiment of the application; Figure 2 A structural diagram of a thermal management system for energy storage in the embodiment of the application; Figure 3 A flow chart of a thermal management strategy generation method in the thermal management method for energy storage in the embodiment of the application. DETAILED DESCRIPTION

[0021] Clearly, the embodiments described are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0022] In the description of the present application, it should be understood that the terms "comprising" and "including" indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not exclude one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0023] It should also be understood that the terms used in the specification of the present application are only for the purpose of describing the specific embodiments and are not intended to limit the present application. As used in the specification and the appended claims of the present application, the singular forms "a", "an" and "the" are intended to include the plural forms, unless the context clearly indicates otherwise.

[0024] It should be further understood that the term "and / or" used in the specification and the appended claims of the present application means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations, for example, A and / or B can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in the present application generally represents an "or" relationship between the front and rear associated objects.

[0025] It should be understood that although the terms first, second, third, etc. may be used in the embodiments of the present application to describe the preset ranges, etc., these preset ranges should not be limited to these terms. These terms are only used to distinguish the preset ranges from each other. For example, the first preset range can also be referred to as the second preset range, and similarly, the second preset range can also be referred to as the first preset range, without departing from the scope of the embodiments of the present application.

[0026] Depending on the context, the word "if" as used herein can be interpreted as meaning "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detecting (a stated condition or event)" can be interpreted as meaning "when determined" or "in response to determining" or "when detecting (a stated condition or event)" or "in response to detecting (a stated condition or event)".

[0027] Various structural diagrams according to the disclosed embodiments of the present application are shown in the drawings. These diagrams are not drawn to scale, in which certain details are exaggerated for clarity of presentation and may be omitted, for example. The shapes and relative sizes of the various regions, layers, and the relative positions of these in the drawings are merely examples and may deviate in actuality due to manufacturing tolerances or technical limitations, and regions / layers with different shapes, sizes, and relative positions can be additionally designed according to actual needs by those skilled in the art.

[0028] A thermal management method for energy storage, as shown in Figure 1 comprises the following steps: Step one, obtaining a thermal distribution map of a battery cluster and a layout route map of multiple temperature control pipelines in the battery cluster; The battery cluster is composed of various battery clusters, and each battery cluster is composed of multiple battery monomers. The temperature monitoring device adopts an infrared thermal imager, a thermocouple sensor, or a fiber distributed sensor. In this embodiment, the temperature monitoring module is taken as an example for illustration of the fiber distributed sensor, which measures temperature through fiber backscattering Raman scattering. The fiber distributed sensor is laid between the battery clusters of the battery cluster to monitor the temperature between the battery clusters and obtain the thermal distribution map of the battery cluster.

[0029] Each temperature control pipeline is laid around each battery cluster according to a preset layout route. The preset layout routes of the various temperature control pipelines are all different, and there is intersection or overlap between the multiple temperature control pipelines. Each temperature control pipeline is provided with a flow control device at at least one target position.

[0030] Step two, dividing the battery cluster into multiple battery cluster regions according to the thermal distribution map of the battery cluster, analyzing the battery cluster regions in different temperature states, and determining the temperature control constraints between different battery cluster regions; The collected original data of the thermal distribution map of the battery cluster is subjected to moving average filtering to eliminate noise. Then, the DBSCAN clustering algorithm is adopted to divide the battery cluster into a high-temperature zone (>45℃), a medium-temperature zone (25℃-45℃), and a temperature loss zone (0℃ or below). Based on the clustering results, the Alpha Shape algorithm is used to generate the polygon region boundary, and the centroid coordinates of each region are calculated.

[0031] The determination of the temperature control constraints includes: Labeling the battery cluster regions in different temperature states; Determining whether there is a temperature level difference conflict in the four positions of each labeled battery cluster region in the battery cluster planar projection map. When there is a conflict, the corresponding position is marked as a conflict position; Based on the labels of different temperature states, the labels of conflict positions, and the layout of temperature control pipelines, a temperature constraint map is constructed.

[0032] According to the pre-laid temperature control pipe route and temperature region mark, it is determined whether the temperature control pipe flowing around the certain temperature region will cause temperature influence on the battery cluster along the route when the temperature control process is performed on the certain temperature region, and whether the temperature influence can cause thermal runaway or battery failure. When the temperature control route and the temperature region mark will cause influence and can cause thermal runaway or battery failure, the temperature control route and the temperature region mark are marked as conflict. Therefore, on this basis, for each temperature region, a temperature control constraint graph can be established respectively, and in each temperature control constraint graph, the temperature level difference conflict existing around the current temperature region and the conflict between the current temperature region and the temperature control route are marked.

[0033] Step three, under the temperature control constraint, according to the layout route map of the temperature control pipe, the thermal management strategy is determined.

[0034] According to the temperature control constraint, the temperature control pipe layout route map, and the position of each flow control device of each temperature control pipe, the target thermal management module and the thermal management strategy are determined, the thermal management strategy including a thermal management mode, an initial flow, and the opening degree and direction of each flow control device on the corresponding temperature control pipe, and the thermal management mode including a refrigeration mode or a heating mode.

[0035] For the high-temperature region, the refrigeration mode is started, and the refrigeration equipment (such as a refrigeration compressor, a cooling fan, etc.) is started to circulate the cooling liquid to the battery cluster around the high-temperature region through the temperature control pipe to take away the heat. For the temperature loss region, the heating mode is adopted, and the heating equipment (such as an electric heating wire, a PTC heater, etc.) is started to make the heating medium (such as hot water, hot air) circulate in the temperature control pipe to provide heat for the battery cluster in the temperature loss region.

[0036] For the refrigeration mode, according to the heat generation rate of the battery cluster in the high-temperature region, the target cooling speed, and the specific heat capacity of the cooling liquid, the required initial flow of the cooling liquid is calculated. For the heating mode, according to the heat loss rate of the battery cluster in the temperature loss region, the target heating speed, and the specific heat capacity of the heating medium, the initial flow of the heating medium is calculated, which can be calculated by the following formula:

[0037] Wherein, Q is the heat load, m is the mass flow of the liquid, represents the specific heat capacity of the liquid, represents the temperature difference between the inlet and outlet of the liquid.

[0038] Specifically, with reference to the temperature control constraint graph, the temperature regions with temperature level difference conflicts in the surrounding positions preferentially adopt a time-sharing control mode, for example, a certain time period takes the refrigeration mode as the priority control mode, and the remaining time period takes the heating mode as the priority control mode. In addition, the temperature regions with temperature level difference conflicts in the surrounding positions can also determine the priority of control according to the urgency, for example, a certain temperature region represents a high-temperature region of the battery cluster, and the temperature of the high-temperature region is far higher than 45°C, for example, 65°C, and the adjacent conflicting temperature region is a low-temperature region, and the temperature of the low-temperature region is not much different from 0°C, for example, -1°C, then the high-temperature region is preferentially processed, and the refrigeration control mode is preferentially executed. In the process of executing the refrigeration control mode, the positions of the high-temperature region and the temperature control pipeline layout map are used to determine a plurality of temperature control pipelines, to determine whether they can be connected to other second regions that need to be cooled and have a lower priority than the current high-temperature region. When they exist, the initial flow of each temperature control pipeline is determined by the above formula according to the actual temperature and the expected temperature of the high-temperature region and the actual temperature and the expected temperature of the second region. At the same time, the opening degree and the direction of each flow control device are determined through the temperature control constraint graph, so that a certain amount of refrigeration fluid can be sent to the region. The amount of refrigeration fluid is determined by the actual temperature and the expected temperature of the second region. Then, the flow control can be realized by controlling the opening degree of the flow control device.

[0039] At the same time, the pipelines that may cause serious temperature control conflicts are excluded by referring to the temperature control constraint graph. For such pipelines, the initial flow of the corresponding temperature control pipeline can be controlled to be 0, and the flow control device at the intersection of the pipeline is adjusted to adjust the flow direction and the opening degree, so that the pipeline does not flow into any liquid. If the pipeline that may cause conflicts must be used, it is further evaluated whether the conflicts can be solved by adjusting the flow and time-sharing control. The further evaluation can be a pre-visualization in the pre-constructed digital twin model to determine whether the corresponding scheme causes adverse effects and the degree of adverse effects. When the adverse effects do not cause thermal failure or battery failure, the corresponding flow control mode or time-sharing control mode can be used for temperature control. The flow control mode is determined by controlling the opening degree of the flow control device.

[0040] The opening degree of each flow control device (such as a valve) has a certain functional relationship with the flow through the device, and the opening-flow curve can be obtained through experiments or data provided by the manufacturer. According to the initial flow calculated, the opening degree of each flow control device on each temperature control pipeline is determined in combination with the temperature of the temperature region passed through and the opening-flow curve. For example, when passing through the temperature region with the highest priority, the temperature difference between the other temperature regions passed through and the temperature region with the highest priority is determined, and the opening degree of the flow control device is adjusted according to the temperature difference. When the temperature difference is higher, the opening degree of the flow control device is smaller, so as to prevent greater influence on other temperature regions. In actual operation, the opening degree of the flow control device is dynamically adjusted according to the real-time temperature feedback of the battery cluster to realize accurate temperature control. Specifically, a PID control algorithm can be used to calculate the opening adjustment amount corresponding to the temperature error (the difference between the set temperature and the actual temperature) and the rate of change thereof.

[0041] The heat management strategy is obtained based on an ant colony algorithm, and includes The application further provides a heat management system for energy storage, comprising: The collection module is configured to collect data about the wind turbine nacelle and the wind turbine impeller, wherein the wind turbine nacelle data at least includes vibration, inclination angle, bolt pretightening force, rotor speed and electromagnetic data, and the wind turbine impeller data at least includes vibration, temperature and aerodynamic load data. The processing module is configured to perform rotating noise processing on the collected wind turbine impeller data. The diagnosis module is configured to input the collected wind turbine nacelle data and the processed wind turbine impeller data into a trained multi-physical field coupling diagnosis model to perform fault diagnosis on the operation state of the wind turbine.

[0042] As a preferred embodiment of the application, the application provides a heat management system for energy storage, as shown in Figure 2 The heat management system comprises: A battery cluster composed of a plurality of battery clusters; A plurality of temperature monitoring modules configured to monitor the temperature distribution of the plurality of battery clusters; A plurality of heat management modules, each of which comprises a temperature control pipeline, each temperature control pipeline is laid around each battery cluster according to a preset layout route, the preset layout routes of the temperature control pipelines are different from each other, and the temperature control pipelines intersect and / or overlap with each other, and each temperature control pipeline is provided with a flow control device at at least one target position; A control module connected with the plurality of temperature monitoring modules and the plurality of heat management modules, configured to determine a target heat management module and a heat management strategy according to the layout route of each temperature control pipeline, the target position of the flow control device and the temperature distribution, and send the heat management strategy to the target heat management module.

[0043] Exemplarily, the battery cluster is composed of battery clusters, and each battery cluster is composed of multiple battery monomers. In order to perform thermal management on the battery cluster, multiple temperature monitoring modules are provided. The temperature monitoring device can be an infrared thermal imager, a thermocouple sensor, or a fiber distributed sensor. The embodiment takes the fiber distributed sensor as an example for description. The fiber distributed sensor measures temperature through fiber backscattering Raman scattering. The fiber distributed sensor is laid between the battery clusters of the battery cluster, and can monitor the temperature between the battery clusters.

[0044] The thermal management module includes a temperature control pipeline and a fluid circulation system. The fluid circulation system includes a medium conveying pump, such as a compressor, a heat exchanger, and the like. The embodiment does not elaborate on the fluid circulation system, which is a prior art. The temperature control pipeline is connected with the fluid circulation system, and is used to convey heat exchange medium fluid to cool or heat the battery cluster, so as to prevent the battery cluster from being overheated to cause thermal runaway or being too cold to affect the battery performance. In the embodiment, multiple thermal management modules are provided, each of which controls the starting position of fluid conveying of one temperature control pipeline. Multiple temperature control pipelines are laid according to a pre-set layout route. The temperature control pipelines intersect and / or overlap with each other. At least one flow control device is further provided on the temperature control pipelines. The flow control device can control the flow of heating fluid or cooling fluid and the flow direction of the fluid. The flow control device can be provided at the intersection point between the temperature control pipelines. The flow control device can be a four-way valve. The flow control device can control the flow in each direction by controlling the opening degree of the four-way valve in each direction, so as to adjust the opening degree of the flow control device according to different battery cluster temperature levels, to realize targeted cooling or heating of different battery cluster temperatures, and to avoid that the fluid temperature is not suitable for the current temperature of the battery cluster through which the fluid flows, for example, that the high-temperature fluid flowing through the battery cluster adversely affects the battery cluster with normal temperature.

[0045] The way to obtain the temperature control pipeline layout route and the flow control device position of each temperature control pipeline in the multiple thermal management modules can be to import CAD drawings and the temperature control pipeline layout route, and to mark the unique ID and coordinate information of each pipeline. The determination of the flow control device position of each temperature control pipeline can be to mark the position of each flow control device by using an RFID tag or a two-dimensional code, and to collect the position data in real time by using a handheld scanning device or a fixed reader / writer.

[0046] The control module can be any device with computing capability, which is communicatively connected with the temperature monitoring module and the thermal management module respectively. The control module determines the target thermal management module and the thermal management strategy according to the layout route of each temperature control pipeline, the target position of the flow control device and the temperature distribution, according to the pre-embedded algorithm. The target thermal management module refers to the thermal management module to be started, and the thermal management strategy includes the flow of the temperature control pipeline corresponding to the thermal management module, the opening, orientation and thermal management mode of each flow control device of the temperature control pipeline, and the thermal management mode includes heating or refrigeration.

[0047] Specifically, the priority of battery cluster temperature control can be determined according to the temperature distribution, and the temperature control conflict can be determined according to the temperature distribution. Then, according to the temperature priority and the temperature control conflict, multiple thermal management modules are started for rapid temperature control processing. For example, the battery cluster with the highest priority is processed first. Assuming that the battery cluster with the highest priority needs to be cooled, in order to perform rapid temperature control, all temperature control pipelines flowing through the battery cluster are determined. Then, it is determined whether there is a temperature control conflict in the flow path of the temperature control pipeline. If a battery cluster with the same priority exists in the flow path of a temperature control pipeline and no flow control device exists before the battery cluster, the battery cluster needs to be heated, then the temperature control pipeline is cancelled (when there is no conflict with other temperature control pipelines) or marked as time-sharing use (when all exist conflicts), and then the opening and orientation of the flow control device in the temperature control pipeline are determined according to the position of the battery cluster and the temperature of the battery cluster, so as to control the actual flow, that is, the flow of the refrigerant or the heating liquid, thereby achieving effective control of different battery cluster positions and different battery cluster temperatures. Time-sharing use refers to alternating different temperature control strategies in different time periods, including whether the temperature control pipeline is heating or refrigerating, the flow of the temperature control pipeline and the opening of each flow control device.

[0048] The embodiment of the present application provides a thermal management system for energy storage. Multiple independent thermal management modules are arranged to perform thermal management on different temperature control pipelines. For a large energy storage integrated system, different thermal management modules can be combined for use to achieve effective thermal management of the large integrated energy storage system. The target position of each temperature control pipeline is provided with a flow control device, which can be dynamically adjusted in opening according to real-time temperature requirements, so as to match the actual flow with the requirements, reduce unnecessary pump power consumption and energy loss, and meanwhile, multiple thermal management modules work in parallel, and other modules can share the load when a single module fails, thereby avoiding system paralysis. For example, when a temperature control pipeline is blocked, the control module can add it to the prohibited selection list through the abnormality monitoring module and re-plan the path.

[0049] In detail, the generation process of the thermal management strategy in the control module is as shown in Figure 3 ​The ant colony parameters are initialized, and the pipe network is modeled as a weighted graph structure. The nodes represent the positions of the intersections between the temperature control pipes, and the edge weights include the interference coefficient, the energy consumption cost, and the conflict confrontation value. The interference coefficient is used to represent the influence on the heat transfer of other battery clusters, and the conflict confrontation value is determined according to the temperature control constraint. A plurality of ants start from a specified entrance. Each ant selects an initial path according to the edge weight between nodes and a target probability formula. In the target probability formula, the conflict confrontation value is taken as a reward term. An initial flow allocation scheme is generated according to the initial path of each ant, and the opening value of the flow control device is calculated. The opening value is proportional to the ratio of the actual flow to the maximum capacity of the pipe. The comprehensive score of different initial path combinations is determined according to the initial flow allocation scheme and the opening of each ant. The pheromone concentration is iteratively updated according to the comprehensive score, and the path information of the minimum temperature interference and the lowest energy consumption is preferentially enhanced. According to the path information, the optimal thermal management combination module, the initial flow, the opening of the corresponding flow control device, and the thermal management mode are obtained. The thermal management mode includes heating or refrigeration.

[0050] For example, the number of ants N is set to 50 for path exploration in the search space. The iteration number G is set to 200 to control the convergence process of the algorithm. The pheromone evaporation coefficient is set to 0.2 to simulate the evaporation of pheromone over time. The heuristic factor and the expected heuristic factor are set to 1 and 2, respectively, to balance the role of pheromone and heuristic information in path selection.

[0051] The positions of the intersections between the temperature control pipes are defined as the nodes of the graph. Each node can be represented by its coordinates in the battery cluster planar projection graph. For each edge in the graph, its weight is composed of the interference coefficient, the energy consumption cost, and the conflict confrontation value. The edge weight can be calculated by a weighting formula as follows: ; wherein, are the weight coefficients, respectively represent interference coefficient, energy consumption cost and conflict confrontation value, the interference coefficient is calculated by a heat transfer model, for example, using Fourier's law, considering the influence of factors such as fluid temperature, flow rate, pipe material and the like in the pipe on the temperature of the surrounding battery cluster, the surrounding battery cluster can be understood as the battery cluster adjacent to the four sides of the battery cluster; the energy consumption cost is calculated according to factors such as pipe length, pipe diameter, fluid resistance and the like, for example, using the Darcy-Weisbach formula to calculate the resistance loss along the pipe, and then obtaining the energy consumption cost. The conflict confrontation value is determined according to the temperature control constraint, if the node connected by the edge crosses the region of different temperature levels, or passes through the conflict position, the value is large, otherwise the value is small, the determination of the conflict confrontation value can be a static determination mode, for example, a mapping relationship between crossing temperature level regions and confrontation values is established, for example, crossing two temperature level regions, the confrontation value is set to 1.5, or when passing through the conflict marker position, the confrontation value is set to 1.5, when not passing through the conflict position and not crossing the region of different temperature levels, the confrontation value is 1.

[0052] A plurality of ants start from the specified entry node, each ant selects the next node according to the edge weight between the nodes and the target probability formula, thereby forming an initial path. The target probability formula is: ; wherein, represents the probability of the ant transferring from the current node i to the next node j, represents the pheromone concentration on the path between node i and node j, represents the reciprocal of the weight of the edge between node i and node j, represents the conflict confrontation reward term introduced between node i and node j, , represents the conflict confrontation value between the current node i and node j, A represents the set of next nodes that the ant can select at the current node i, represents the pheromone concentration on the path between node i and node k, represents the reciprocal of the weight of the edge between node i and node k, represents the conflict confrontation reward term introduced between node i and node k, respectively represent the pheromone importance factor, the heuristic information importance factor and the confrontation reward importance factor, respectively can take values 1, 2, 2, which are not limited in the embodiment, and can be determined by the person skilled in the art as needed.

[0053] According to the initial path of each ant, the combination of temperature control pipes on the path is determined, and for each pipe combination, an initial flow distribution scheme is generated according to the heat load demand of the high-temperature area or temperature loss area covered by the pipe, and the opening value of each flow control device is proportional to the ratio of the actual flow and the highest capacity of the pipe. According to the initial flow distribution scheme of each ant and the opening, the comprehensive score of different initial path combinations is determined, and the pheromone concentration is iteratively updated according to the comprehensive score, wherein the comprehensive score can be calculated by first calculating the scores of the initial path combinations on the temperature interference index, the energy consumption index and the conflict resolution index, and then using the weighted average method to obtain the comprehensive score.

[0054] The temperature interference index can be calculated by the root mean square error (RMSE) or the mean absolute error (MAE) of the temperature deviation. Specifically, temperature sensors are arranged reasonably in the battery cluster to obtain real-time temperature data of each battery cluster and the surrounding environment. By using heat transfer models such as Fourier heat conduction law, convective heat transfer equation, etc., and combining the temperature, flow rate, flow, etc. of the fluid in the pipe, the temperature change of each battery cluster under the current path combination is simulated. According to the simulated temperature distribution, the deviation between the actual temperature and the expected temperature of each battery cluster is calculated. The expected temperature can be pre-set according to the working characteristics and safety requirements of the battery. The energy consumption index can be obtained by adding the pipe transportation energy consumption and the flow control device energy consumption. The pipe transportation energy consumption can be calculated by using fluid mechanics formula according to the length, diameter, material of the pipe and the flow rate, density, viscosity, etc. of the fluid. The energy consumption of the flow control device is related to the type, specification, opening and running time of the device. The power-opening curve of the device can be obtained by referring to the technical manual of the device, and the energy consumption can be calculated according to the actual opening. According to the temperature distribution of the battery cluster and the temperature control constraint, the conflict resolution index determines the areas with temperature level difference conflicts. These areas may be adjacent high-temperature areas and temperature loss areas, or areas where heat transfer is disturbed due to pipe intersection. Temperature sensors are arranged in the conflict areas to monitor temperature changes in real time, and the temperature values of the conflict areas before and after the implementation of the heat management strategy are recorded. The conflict resolution degree can be evaluated by calculating the temperature difference change of the conflict area. The smaller the temperature difference, the better the conflict resolution effect.

[0055] Then, the pheromone concentration is iteratively updated according to the comprehensive score, and the path information of the path combination with the highest pheromone concentration is preferentially enhanced. According to the path information, the path combination with the highest pheromone concentration is selected as the optimal heat management combination module. At the same time, the optimal initial flow and the opening of the corresponding flow control device are obtained according to the calculation results of the initial flow distribution scheme and the opening corresponding to the path combination.

[0056] The application embodiment provides a thermal management system for energy storage, which takes a pipeline intersection point as a path planning node, comprehensively considers interference coefficients, energy consumption costs and conflict confrontation values under temperature control constraints through a weighted graph model, so that the ants can avoid areas with high heat transfer interference and high energy consumption and follow cross-region temperature control constraint rules in the path selection process. The initial path combination generated by the ants is directly related to the opening degree of the flow control device, and fine regulation and control is realized through the proportional relationship between the opening degree value and the actual flow, so as to avoid the local overcooling / overheating problem caused by global unified flow. The pheromone updating mechanism prioritizes temperature interference and energy consumption, dynamically strengthens the selection probability of the optimal path, and ensures that the system continuously optimizes the strategy in real-time temperature changes. Through intelligent path search, multi-objective constraint optimization and dynamic feedback mechanism, the embodiment realizes the balance between temperature control accuracy, energy consumption efficiency and system reliability, and provides an efficient and stable thermal control solution for high-power-density energy storage systems.

[0057] As an optional implementation, a thermal management system for energy storage is provided, further comprising: An abnormality monitoring module is configured to detect pipeline blockage or flow control device failure; An abnormality processing module is configured to add an abnormal pipeline to a prohibited selection list and re-perform thermal management decision-making when blockage or failure is detected.

[0058] By way of example, the abnormality monitoring module can be an electromagnetic flowmeter installed at the inlet / outlet of each temperature control pipeline. During testing, the orientations and opening degrees of all flow control devices are controlled so that they can only flow along one pipeline. Then, the actual flow is monitored through the electromagnetic flowmeter. When the actual flow is lower than the target flow, it is considered that blockage occurs. The target flow can be a theoretical flow. The abnormality monitoring module can also be configured to read the actual opening degree of the valve through the Modbus RTU protocol, and then compare the difference between the actual opening degree and the instruction opening degree. When the difference exceeds 15%, it is considered that the flow control device fails. When blockage or failure is detected, the abnormal pipeline is added to the prohibited selection list, and thermal management decision-making is re-performed according to the ant colony algorithm.

[0059] The application embodiment provides a thermal management system for energy storage, which can timely handle blockage or failure abnormalities through effective monitoring of the abnormality monitoring module, re-perform thermal management decision-making, and effectively avoid executing incorrect thermal management.

[0060] As an optional implementation, the abnormality monitoring module comprises: A plurality of infrared sensors are arranged above the battery cluster, cover the battery cluster and the temperature control pipeline, and are configured to acquire thermal images of the battery cluster and the temperature control pipeline. an image stitching module configured to stitch the plurality of infrared sensor images to obtain an overall thermal image; a temperature-controlled pipeline thermal image extraction module configured to extract a temperature-controlled pipeline thermal image from the overall thermal image according to a temperature-controlled pipeline layout map; an anomaly judgment module configured to determine a temperature-controlled pipeline blockage or a flow control device failure according to the temperature-controlled pipeline thermal image.

[0061] Exemplarily, the plurality of infrared sensors are arranged above the battery cluster in a grid or matrix manner to ensure that their fields of view completely cover the battery cluster and all the temperature-controlled pipelines. The monitoring areas of the sensors are connected to each other and have no obvious blind area. Each infrared sensor scans the battery cluster and the temperature-controlled pipelines below at a set time interval (e.g., once per second) to obtain corresponding thermal image data. For each image obtained by the infrared sensor, a feature extraction algorithm such as SIFT or SURF is used to extract feature points in the image. These feature points have scale, rotation, and illumination invariance and can be accurately matched in different images. For example, in the SIFT algorithm, a Gaussian difference pyramid is first constructed for the image, then extreme points are searched on different scales of the pyramid, the position and scale of the feature points are accurately determined by fitting a three-dimensional quadratic function, and finally the principal direction and descriptor of the feature points are calculated.

[0062] Using the extracted feature points, feature matching is performed between adjacent images. A nearest neighbor matching algorithm can be used to calculate the Euclidean distance between the feature point descriptors in different images, and feature point pairs with a distance less than a certain threshold are regarded as matching points. To improve the accuracy of matching, the RANSAC algorithm can be used to filter the matching points and remove the mis-matching points. According to the matching feature points, a transformation matrix between adjacent images is calculated. The least squares method can be used to solve the parameters of the transformation matrix, and the calculated transformation matrix is used to perform geometric transformation on the adjacent images to align them in space. Then, an image fusion algorithm is used to fuse the aligned images to obtain an overall thermal image. According to the temperature-controlled pipeline layout map, the approximate position of the temperature-controlled pipeline in the overall thermal image is determined. The layout map and the thermal image can be mapped to coordinates to obtain the pixel coordinate range of the pipeline in the thermal image. According to the determined pixel coordinate range, the thermal image part of the temperature-controlled pipeline is cropped from the overall thermal image. To improve the accuracy of extraction, an image segmentation algorithm (such as threshold-based segmentation, region-based segmentation, or edge-based segmentation) can be used to further refine the pipeline region.

[0063] When the system is running normally, collect the thermal imaging data of the temperature-controlled pipeline for a period of time, analyze the temperature distribution characteristics of the pipeline under different working conditions, and establish a temperature distribution model under the normal state. Specifically, statistical methods (such as mean and standard deviation) or machine learning algorithms can be used to describe the temperature distribution under the normal state. When new thermal imaging of the temperature-controlled pipeline is obtained, it is compared with the normal state model. If the temperature of a certain section of the pipeline is significantly lower than other parts, and the temperature gradient is abnormally increased, it may indicate that the pipeline has been blocked. The threshold of temperature difference and temperature gradient can be used to determine the blocking condition. For example, when the temperature of a certain section of the pipeline is more than 10℃ different from the temperature of the adjacent section, and the temperature gradient is more than 5℃ / cm, it is determined as blocked. The failure of the flow control device may manifest as abnormal changes in the temperature distribution of the pipeline. If the flow control device fails to cause excessive flow, the temperature of the pipeline may decrease as a whole; if the flow is too small, the temperature of the pipeline may increase as a whole. The change trend of the pipeline temperature and the uniformity of the temperature distribution can be monitored to determine whether the flow control device is malfunctioning. For example, when the temperature of the pipeline changes by more than 5℃ in a short period of time (such as 10 minutes), and the temperature distribution uniformity increases (such as the standard deviation increases), it is determined that the flow control device may be malfunctioning.

[0064] The embodiment of the present application provides a thermal management system for energy storage, which can effectively determine the abnormal position according to the temperature condition through an infrared sensor, has a simple scheme, is strong in realizability, and has low cost compared with installing monitoring devices at each position.

[0065] As an optional implementation, the anomaly judgment module comprises: The thermal imaging sample collection module is configured to collect thermal imaging of the temperature-controlled pipeline under normal conditions and thermal imaging of the temperature-controlled pipeline under abnormal conditions, and mark the normal condition and the abnormal condition. The marking content includes normal, abnormal, abnormal reason, and abnormal position. The anomaly diagnosis model training module is configured to train the target neural network according to the output of the thermal imaging sample collection module to obtain the anomaly diagnosis module. The anomaly judgment sub-module is configured to input the thermal imaging of the temperature-controlled pipeline into the pre-trained anomaly diagnosis model to obtain the blocking condition of the temperature-controlled pipeline or the failure condition of the flow control device.

[0066] Exemplarily, a high-precision and high-resolution infrared thermal imager is selected to ensure that it can clearly capture the temperature distribution of the temperature-controlled pipeline surface. Multiple thermal imagers are installed at appropriate positions to cover all temperature-controlled pipelines and ensure that complete thermal imaging data is collected. During data collection, the battery cluster operating environment is kept as stable as possible to reduce external factors (such as light, ventilation, etc.) that interfere with thermal imaging. At the same time, environmental temperature, humidity, and other parameters are recorded for subsequent analysis. Typical working conditions are determined in which the battery cluster and temperature-controlled pipeline are in normal operation, such as stable load, normal flow, and temperature setting. Under these typical working conditions, thermal imaging of the temperature-controlled pipeline is collected at certain time intervals (such as every 5 minutes), and a sufficient number of samples (such as no less than 1000) are collected to cover different time periods and different working conditions. The collected thermal images are labeled as "normal".

[0067] By simulating abnormal conditions such as pipeline blockage and flow control device failure, corresponding thermal images are collected. Specifically, for pipeline blockage, the pipeline can be partially or completely blocked; for flow control device failure, the opening of the device can be adjusted or a fault can be simulated. When an anomaly occurs, thermal images are collected in a timely manner, and the time of the anomaly, the cause of the anomaly (such as pipeline blockage, valve failure, etc.), and the location of the anomaly (such as the specific pipeline number and position coordinates) are recorded. A sufficient number of abnormal samples (no less than 500 for each type of anomaly) are also collected, and the collected abnormal thermal images are labeled as "abnormal" and the cause of the anomaly and the location of the anomaly are recorded in detail.

[0068] The collected thermal images are subjected to histogram equalization, filtering, and other operations to enhance the contrast and clarity of the images. The collected sample data is divided into certain proportions (such as 70% training set, 15% validation set, and 15% test set). Then, a target neural network architecture is selected, which can be a convolutional neural network (CNN) such as ResNet, VGG, etc. A cross-entropy loss function is used, which is suitable for multi-classification problems and can measure the difference between the model's predicted results and the true labels. The Adam optimizer is selected, which can adaptively adjust the learning rate of each parameter.

[0069] Next, the weights and biases of the neural network are randomly initialized. The training set data is input into the neural network, the model's predicted results are calculated through forward propagation, and then the loss between the predicted results and the true labels is calculated according to the loss function. Then, the optimizer is used for backpropagation to update the model's parameters. After each training cycle, the validation set data is used to evaluate the model's performance. If the model exhibits overfitting or underfitting, the model's hyperparameters (such as learning rate, batch size, network depth, etc.) can be adjusted.

[0070] Finally, the temperature control pipeline thermal imaging is input into the pre-trained abnormal diagnosis model to obtain the temperature control pipeline blockage or the flow control device failure.

[0071] The embodiment of the present application provides a thermal management system for energy storage, a thermal imaging sample collection module collects thermal radiation data in normal and abnormal states through dynamic collection, and a multi-dimensional sample library containing abnormal types, positions and causes is constructed in combination with artificial labeling, so that high-quality data support is provided for model training. An abnormal diagnosis model training module constructs an end-to-end learning framework based on a deep neural network, can automatically extract temperature distribution features and pipeline structure information hidden in a thermal imaging image, breaks through the limitations of traditional threshold detection, and effectively identifies complex fault modes such as local blockage and flow device failure. An abnormal judgment submodule deploys the trained model on an edge end, realizes online inference of real-time thermal imaging data, quickly locates a fault position and discriminates a failure type through feature mapping, and provides millisecond-level response fault early warning for the thermal management system. Through the intelligent diagnosis mechanism driven by data, the embodiment realizes non-contact monitoring of the temperature control pipeline without affecting the operation of the battery, and significantly improves the reliability and operation and maintenance efficiency of the battery cluster thermal management.

[0072] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media (including but not limited to magnetic disk storage, CD ROM, optical storage, etc.) containing computer usable program codes.

[0073] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be realized by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one flow or multiple flows and / or blocks Figure 1 The functions specified in one flow or multiple flows and / or blocks

[0074] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flow Figure 1 of the flow or flows and / or blocks Figure 1 of the block or blocks specified in the flow.

[0075] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 of the flow or flows and / or blocks Figure 1 of the block or blocks specified in the flow.

[0076] Finally, it should be noted that the above-mentioned embodiments are merely used to illustrate the technical solutions of the present application, but are not intended to limit the protection scope of the present application. Although the present application has been described in detail with reference to the above-mentioned embodiments, it should be understood by those skilled in the art that, after reading the present application, various modifications, replacements or equivalent replacements can be made to the specific embodiments of the present application, but these modifications, replacements or equivalent replacements are all within the protection scope of the claims of the present application.

Claims

1. A thermal management method for energy storage, characterized in that, Includes the following steps: Obtain the thermal distribution map of the battery cluster and the layout route map of multiple temperature control pipes in the battery cluster; Based on the thermal distribution map of the battery cluster, the battery cluster is divided into multiple battery cluster regions. The battery cluster regions at different temperature states are analyzed to determine the temperature control constraints between different battery cluster regions. Under temperature control constraints, a thermal management strategy is determined based on the layout route of the temperature control pipeline; The thermal management strategy is derived based on the ant colony algorithm.

2. The thermal management method for energy storage according to claim 1, characterized in that, The thermal management strategy is derived based on the ant colony algorithm and includes: Initialize the ant colony parameters and model the temperature-controlled pipeline network as a weighted graph structure. Nodes represent the locations of the intersections between temperature-controlled pipelines. Edge weights include interference coefficients, energy consumption costs, and conflict resistance values. The interference coefficients are used to characterize the heat transfer impact on other battery clusters, and the conflict resistance values ​​are determined based on temperature control constraints. Multiple ants start from a designated entry point, and each ant selects an initial path based on the edge weights between nodes and the target probability formula; An initial flow distribution scheme is generated based on the initial path of each ant, and the opening value of the flow control device on the temperature-controlled pipeline is calculated. Based on the initial flow allocation scheme for each ant and the calculated opening value of the flow control device, the comprehensive score of each initial path is determined. The pheromone concentration is iteratively updated based on the comprehensive score, and the pheromone of the path with the least temperature interference and the lowest energy consumption is given priority. The initial path with the highest path pheromone concentration is taken as the optimal path. At the same time, based on the initial flow distribution scheme and opening value corresponding to the determined optimal initial path, the optimal initial flow, the opening degree of the corresponding flow control device, and the thermal management mode are calculated.

3. The thermal management method for energy storage according to claim 1, characterized in that, The priority and conflict of temperature control of the battery cluster are determined based on the thermal distribution diagram of the battery cluster, and then the opening and orientation of the flow control device in the temperature control pipeline are controlled.

4. The thermal management method for energy storage according to claim 1, characterized in that, The determination of the temperature control constraint includes: Mark the battery cluster regions at different temperature states; Determine whether there are temperature level differences or conflicts in the surrounding positions of each marked battery cluster area within the battery cluster planar projection map. If a conflict exists, mark the corresponding position as the conflict position. A temperature constraint diagram is constructed based on the markings of different temperature states, the markings of conflict locations, and the layout of temperature-controlled pipelines.

5. A thermal management system for energy storage, characterized in that, It includes an acquisition module, a constraint partitioning module, and a strategy determination module, wherein: Acquisition module: used to acquire the thermal distribution map of the battery cluster and the layout route map of multiple temperature control pipes in the battery cluster; The constraint partitioning module is used to divide the battery cluster into multiple battery cluster regions based on the thermal distribution map of the battery cluster, analyze the battery cluster regions at different temperature states, and determine the temperature control constraints between different battery cluster regions. Strategy determination module: Used to determine the thermal management strategy based on the layout route of the temperature control pipeline under temperature control constraints; The thermal management strategy is derived based on the ant colony algorithm.

6. A thermal management system for energy storage according to claim 5, characterized in that, Each of the temperature-controlled pipelines is equipped with at least one flow control device, which is a four-way valve.

7. A thermal management system for energy storage according to claim 5, characterized in that, It also includes an anomaly monitoring module, used to detect blockages in temperature-controlled pipelines or malfunctions in flow control devices installed on temperature-controlled pipelines.

8. A thermal management system for energy storage according to claim 7, characterized in that, It also includes an anomaly handling module, which adds the abnormal temperature control pipe to the prohibited selection list and re-makes thermal management decisions when a blockage is detected in the temperature control pipe or a flow control device installed on the temperature control pipe fails.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements as claimed in claim 1.

4. The steps of any of the methods described.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements as described in claim 1.

4. The steps of any of the methods described.

Images