A power battery pack thermal management control system and method

Abstract

The application discloses a power battery pack thermal management control system and method, and belongs to the technical field of electric vehicles, and comprises the following modules: a multi-parameter acquisition module for acquiring battery pack parameter data in real time; a data preprocessing and fusion module for generating high-quality, unified format data sets; a dynamic prediction modeling module for realizing accurate temperature trend prediction; an intelligent decision-making module for generating an optimal thermal management strategy; a thermal management execution module for realizing accurate temperature regulation and thermal management; a system monitoring and diagnosis module for ensuring safe operation of the system; a man-machine interaction module for realizing man-machine collaborative intelligent thermal management. The application adopts the above-mentioned power battery pack thermal management control system and method, utilizes a particle swarm optimization algorithm, dynamically adjusts the power battery thermal management system of the thermal management strategy, realizes more accurate temperature prediction and control, optimizes energy consumption and prolongs the service life of the battery.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric vehicles, in particular to a power battery pack thermal management control system and method. BACKGROUND

[0002] With the rapid development of the new energy vehicle market, the performance and safety of the power battery pack, as the core energy storage device of the vehicle, directly affect the efficiency, range and service life of the vehicle. However, a large amount of heat is generated during the charging and discharging of the battery pack, especially when working under high-power charging and discharging and in harsh environments, the accumulation of heat may cause the temperature of the battery to rise rapidly, thereby causing thermal runaway, capacity decay or serious safety hazards. Therefore, the thermal management of the power battery pack has become one of the key technical problems in the design of new energy vehicles.

[0003] The current power battery thermal management system usually includes three ways of active cooling, passive heat dissipation and heating control, aiming to ensure that the battery pack remains within the safe temperature range under various working conditions.

[0004] However, the traditional thermal management system mainly has the following problems:

[0005] 1. The perception ability of the battery internal state is limited, it is difficult to achieve accurate temperature control; the control strategy is single, and lacks intelligent adjustment ability; when dealing with complex and variable working conditions, it is often difficult to achieve the best energy efficiency balance.

[0006] 2. The feedback of the real-time state of the battery and the thermal management effect is slow, which makes it difficult to adjust the strategy in time, affecting the overall efficiency of the system and the service life of the battery.

[0007] In summary, how to improve the operating efficiency and life of the battery pack, effectively prevent thermal runaway and other safety risks, and improve the overall reliability and safety of the power battery system has become a technical problem that needs to be solved. SUMMARY

[0008] The purpose of the present application is to provide a power battery pack thermal management control system and method, which uses a particle swarm optimization algorithm to dynamically adjust the thermal management strategy of the power battery thermal management system, realizes more accurate temperature prediction and control, optimizes energy consumption and prolongs the service life of the battery.

[0009] To achieve the above purpose, the present application provides a power battery pack thermal management control system, which comprises the following modules:

[0010] A multi-parameter acquisition module for real-time acquisition of battery pack parameter data;

[0011] A data preprocessing and fusion module for generating a high-quality, unified format data set;

[0012] Dynamic prediction modeling module: for realizing accurate temperature trend prediction;

[0013] Intelligent decision-making module: for generating optimal thermal management strategy;

[0014] Thermal management execution module: for realizing accurate temperature regulation and thermal management;

[0015] System monitoring and diagnosis module: for ensuring safe operation of the system;

[0016] Human-computer interaction module: for realizing human-computer collaborative intelligent thermal management.

[0017] Preferably, the multi-parameter acquisition module transmits data to the data preprocessing and fusion module, the data preprocessing and fusion module transmits data to the dynamic prediction modeling module, the dynamic prediction modeling module transmits data to the intelligent decision-making module, the intelligent decision-making module transmits data to the thermal management execution module, the thermal management execution module and the system monitoring and diagnosis module transmit data to each other, and the human-computer interaction module transmits data to each other with the multi-parameter acquisition module, the data preprocessing and fusion module, the dynamic prediction modeling module, the intelligent decision-making module, the thermal management execution module and the system monitoring and diagnosis module.

[0018] Preferably, the multi-parameter acquisition module includes a temperature sensor network, a current-voltage acquisition unit, a state-of-charge estimation unit, an environmental parameter sensor group, a data acquisition control unit and a communication interface unit;

[0019] The temperature sensor network: for real-time monitoring of battery monomer and module temperature distribution;

[0020] The current-voltage acquisition unit: for continuously measuring the charge and discharge current and terminal voltage of the battery pack, providing basic data for state-of-charge estimation and safety monitoring;

[0021] The state-of-charge estimation unit: for providing battery pack remaining capacity information;

[0022] The environmental parameter sensor group: for monitoring the environmental conditions around the battery pack, providing external reference data for thermal management strategy optimization;

[0023] The data acquisition control unit: for coordinating and managing the data acquisition frequency and timing of each sensor and performing preliminary data validity check;

[0024] The communication interface unit: for realizing high-speed and reliable data transmission with each module.

[0025] Preferably, the dynamic prediction modeling module comprises a model training unit, a model evaluation and selection unit, an online learning adaptation unit, a prediction execution unit, and a model version management unit;

[0026] The model training unit is configured to periodically train the temperature prediction model based on historical and real-time data, and continuously optimize the model parameters;

[0027] The model evaluation and selection unit is configured to automatically select the optimal model for actual prediction tasks;

[0028] The online learning adaptation unit is configured to adapt the model to changes in battery performance over time and new working conditions;

[0029] The prediction execution unit is configured to call the currently optimal model to predict future temperature trends, and output the prediction results for use by the intelligent decision module;

[0030] The model version management unit is configured to manage different versions of the temperature prediction model, record the model update history, and be able to roll back to previous stable versions.

[0031] Preferably, the intelligent decision module comprises a decision input processing unit, a rule base management unit, a multi-objective optimization unit, a strategy generation unit, a decision evaluation and tuning unit, and a strategy output unit;

[0032] The decision input processing unit is configured to provide comprehensive data support for the decision-making process;

[0033] The rule base management unit is configured to maintain and update the preset decision rule base;

[0034] The multi-objective optimization unit is configured to find the best balance point among temperature control, energy management, and performance improvement;

[0035] The strategy generation unit is configured to formulate specific thermal management operation strategies;

[0036] The decision evaluation and tuning unit is configured to evaluate the effectiveness of the generated strategies and make fine adjustments through simulation prediction and historical data analysis;

[0037] The strategy output unit is configured to output the finally determined thermal management strategy to the thermal management execution module in a standardized format, while recording the decision-making process for subsequent analysis and improvement.

[0038] Preferably, the thermal management execution module comprises a strategy parsing unit, an active cooling control unit, a passive heat dissipation adjustment unit, a heating control unit, an execution coordination unit, and a feedback monitoring unit;

[0039] The strategy analysis unit is configured to receive and analyze the thermal management strategy from the intelligent decision module, and convert the thermal management strategy into specific execution parameters, wherein the thermal management strategy includes an active cooling control strategy, a passive heat dissipation control strategy, and a heating control strategy.

[0040] The active cooling control unit is configured to adjust the active cooling element according to the specific execution parameters.

[0041] The passive heat dissipation adjustment unit is configured to control the working state of the passive heat dissipation element, and optimize the heat distribution and buffering effect.

[0042] The heating control unit is configured to accurately adjust the power output of the battery heater.

[0043] The execution coordination unit is configured to realize the coordination of the cooling, heat dissipation, and heating processes, and avoid conflicts.

[0044] The feedback monitoring unit is configured to monitor the thermal management execution effect in real time, collect temperature change data, and provide timely feedback for strategy adjustment.

[0045] Preferably, the system monitoring and diagnosis module includes a system state acquisition unit, a performance evaluation unit, an abnormality detection unit, a fault diagnosis expert unit, a warning generation unit, and an automatic repair suggestion unit.

[0046] The system state acquisition unit is configured to provide real-time and comprehensive data basis for system monitoring and diagnosis.

[0047] The performance evaluation unit is configured to evaluate and analyze the overall operation efficiency, energy consumption, and temperature control accuracy of the system in real time.

[0048] The abnormality detection unit is configured to quickly identify abnormal conditions that deviate from the normal range.

[0049] The fault diagnosis expert unit is configured to perform in-depth analysis on the detected abnormalities, and determine the fault type, severity, and cause.

[0050] The warning generation unit is configured to generate warning information of different levels, and timely notify the operator through appropriate channels.

[0051] The automatic repair suggestion unit is configured to generate repair suggestions and automatically execute repair operations.

[0052] Preferably, the formula for calculating the charging and discharging current of the battery pack is as follows:

[0053]

[0054] wherein I primary is the actual current of the battery pack, i.e., the charging and discharging current; N primaryN represents the number of primary turns of the current transformer. secondary R is the number of secondary turns of the current transformer; load The load resistance through which the secondary current flows; V secondary The voltage generated by the secondary current passing through the load resistor;

[0055] The formula for calculating the terminal voltage of the battery pack is as follows:

[0056]

[0057] Among them, V battery V is the actual terminal voltage of the battery pack. measured R1 and R2 are the voltage divider output voltage; R1 and R2 are the resistance values ​​in the voltage divider.

[0058] The remaining capacity of the battery pack is:

[0059]

[0060] Where RC(t) is the remaining capacity of the battery pack at time t; C rated α is the rated capacity of the battery pack; α is a weighting factor used to adjust the contribution ratio of the current integral method and the open-circuit voltage method; SOC0 is the state of charge at the initial time t0; I(τ) is the battery current at time τ; F(V oc It is based on the open-circuit voltage V oc Estimated state of charge.

[0061] This invention also provides a method for operating a power battery pack thermal management control system, comprising the following steps:

[0062] S1. Use particle swarm optimization algorithm to find the best balance between temperature control, energy management and performance improvement;

[0063] S1.1. Taking into account factors such as temperature control, energy management, and performance improvement, a multi-objective function is constructed, and the optimization formula is as follows:

[0064] minimizef(T cell E consumption P perforrmance ) = W T ·(T cell -T optimal ) 2 +W E ·E consumption +W P ·P perforrmance ;

[0065] Among them, W T W E WP is a weight factor used to balance the relationship between temperature control, energy consumption management and performance improvement; T optimal is the optimal working temperature of the system; E consumption is the energy consumption; P performance is the system performance index; T cell is the temperature of the battery pack; minimize formula represents the optimization problem of the minimum objective function f(T cell , E consumption , P performance );

[0066] S1.2, randomly generate particles in the defined search space, each particle represents a set of solutions, and assign an initial position and velocity to each particle, wherein the position represents the parameter value of the solution, and the velocity represents the direction and amplitude of the parameter change;

[0067] S1.3, for each particle representing a solution, calculate its fitness value using the multi-objective optimization function;

[0068] S1.4, compare the fitness of the current position of each particle with the fitness of its historical best position, update the individual optimal position, and at the same time, select the position with the highest fitness among all particles as the global optimal position;

[0069] S1.5, according to the individual optimal position and the global optimal position, use the velocity and position update formula of the particle swarm optimization algorithm to calculate the new velocity and new position of each particle, and the velocity update formula is:

[0070]

[0071] wherein, is the velocity of particle i at time T; is the position of particle i at time T; pi is the individual optimal position of particle i; g is the global optimal position; ω is the inertia weight, which controls the inertia of the particle velocity; c1 is the individual learning factor; c2 is the social learning factor; r1 and r2 are random numbers in the range of [0, 1], which are used to introduce randomness; is the new velocity of particle i at time T+1;

[0072] The position update formula is:

[0073] wherein, is the new position of particle i at time T+1;

[0074] S1.6, repeat the process of particle fitness evaluation, optimal position update, and particle position and velocity adjustment until a preset number of iterations is reached, and finally output the global optimal position, which is the best balance point found between temperature control, energy management, and performance improvement;

[0075] S2, evaluate the effectiveness of the generated strategy through simulation prediction and historical data analysis, and fine-tune it;

[0076] S2.1, simulate the execution of the generated thermal management strategy under various operating conditions and quickly evaluate its potential effects;

[0077] S2.2, compare the simulation results with historical operating data to evaluate the improvement of the generated strategy over past strategies;

[0078] S2.3, based on preset key performance indicators, quantitatively evaluate the simulation results to identify the strengths and weaknesses of the generated strategy;

[0079] S2.4, determine the degree of influence of the parameters on performance by adjusting the strategy parameters and observing changes in system performance;

[0080] S2.5, based on the analysis results, make targeted adjustments to the generated strategy;

[0081] S2.6, repeat the above steps until the performance of the generated strategy meets the expected target.

[0082] Preferably, the thermal management strategy in S2.1 includes active cooling control strategy, passive heat dissipation control strategy, and heating control strategy;

[0083] The active cooling control strategy is mainly realized through an active cooling control unit to quickly reduce the temperature when the temperature T of the battery pack cell exceeds the preset high threshold T high , and the maximum temperature difference ΔT max inside the battery pack is greater than the allowed temperature difference threshold ΔT allow , active cooling is triggered; the cooling power P cool is adjusted according to the difference between the current temperature of the battery pack and the target temperature T target , as well as the efficiency parameter η cool of the active cooling control unit; the calculation formula of the cooling power is: P cool = η cool ·(T cell -T target ); through this formula, the cooling power will increase with the increase of the battery temperature, so as to reduce the temperature faster; when the temperature drops to T high and the temperature difference ΔT max is lower than the temperature difference threshold ΔT allowWhen this happens, active cooling stops;

[0084] The passive heat dissipation control strategy uses passive heat dissipation elements to slowly regulate the temperature; when the battery pack temperature approaches a threshold but does not reach the active cooling trigger condition, i.e., T... cell In T low <T cell <T high Within the range, and with the maximum temperature difference ΔT max Less than the allowable threshold ΔT allow In this case, a passive cooling control strategy is selected; the cooling power P of passive cooling is... passive Depends on the temperature difference ΔT between the battery pack and the environment env =T cell -T ambient The heat dissipation formula is expressed as: P passive =η passive ·ΔT env Among them, T ambient For ambient temperature, η passive This is the efficiency parameter for passive heat dissipation; when temperature T... cell Reduced to the low temperature threshold T low When the following conditions are met, passive cooling should be stopped;

[0085] The heating control strategy uses a battery heater for heating; in low-temperature environments, when the battery pack temperature T... cell Below the set low temperature threshold T low And the temperature difference ΔT max When the temperature exceeds the permissible range, a heating control strategy is activated to ensure the battery pack remains within a safe operating temperature range; heating power P heat The current battery pack temperature and the target temperature T target The difference is determined by the formula: P heat =η heat ·(T target -T cell ); where η heat The efficiency coefficient of the battery heater; when the temperature rises to T low Stop heating when the time is right;

[0086] Temperature difference control is a crucial step in ensuring temperature uniformity among individual cells within a battery pack; if the maximum temperature difference ΔT within the battery pack... max Exceeding the allowable temperature difference threshold ΔT allow That is: ΔT max =max(T) cell )-min(T cell )>ΔT allowThe system selects different control strategies according to the temperature difference; for small temperature difference, passive heat dissipation and adjustment of cooling power are preferentially selected; for large temperature difference, active cooling and heating are triggered to rapidly reduce the temperature difference.

[0087] Therefore, the power battery pack thermal management control system and method have the following beneficial effects:

[0088] 1) Through real-time multi-parameter acquisition, dynamic temperature prediction and intelligent decision-making, the thermal management strategy of the battery pack is integrated and optimized, and efficient temperature control and energy consumption balance are realized.

[0089] 2) Abnormal monitoring and self-diagnosis functions are provided to ensure the safety and reliability of the system.

[0090] The technical solutions of the present application will be further described in detail below with reference to the accompanying drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0091] Figure 1 is a structural schematic diagram of an embodiment of the power battery pack thermal management control system and method of the present application. DETAILED DESCRIPTION

[0092] The technical solutions of the present application will be further described in detail below with reference to the accompanying drawings and examples.

[0093] Unless otherwise defined, the technical terms or scientific terms used in the present application shall have the usual meanings understood by those skilled in the art to which the present application belongs. The "first", "second" and similar words used in the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Include" or "contain" and similar words mean that the elements or objects before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connected" or "connected" and similar words are not limited to physical or mechanical connection, but can include electrical connection, whether direct or indirect. "Up", "down", "left", "right" and the like only represent relative positional relationships, which may change accordingly when the absolute position of the described object changes.

[0094] Example 1

[0095] As shown in Figure 1 , the present application provides a power battery pack thermal management system, which comprises the following modules:

[0096] Multi-parameter acquisition module, for real-time acquisition of battery pack internal temperature, current, voltage, state of charge and environmental parameter data. The multi-parameter acquisition module is the basic module of the system, responsible for real-time acquisition of key parameters inside the battery pack, including temperature, current, voltage, state of charge (SOC) and external environmental parameters. The real-time and accuracy of these data are the prerequisite for all subsequent operations. Through the sensor network distributed inside and outside the battery pack, the multi-parameter acquisition module can capture the detailed thermodynamic state and operating environment of the battery pack. These data not only provide direct basis for temperature management, but also provide basic support for the safety and efficiency of the entire system. With the development of sensor technology, the accuracy and resolution of collected data are getting higher and higher, which lays a solid foundation for subsequent data processing and decision-making.

[0097] The multi-parameter acquisition module includes the following components:

[0098] Temperature sensor network: Deploy sensor arrays at key positions in the battery pack to monitor battery cell and module temperature distribution in real time. Current and voltage acquisition unit: Use high-precision current transformers and voltage dividers to continuously measure the charge and discharge current and terminal voltage of the battery pack, providing basic data for state of charge estimation and safety monitoring.

[0099] The formula for calculating the charge and discharge current of the battery pack is:

[0100]

[0101] Where I primary is the actual current of the battery pack, i.e. the charge and discharge current; N primary is the primary number of turns of the current transformer; N secondary is the secondary number of turns of the current transformer; R load is the load resistance through which the secondary current passes; V secondary is the voltage generated by the secondary current passing through the load resistance;

[0102] The formula for calculating the terminal voltage of the battery pack is:

[0103]

[0104] Where V battery is the actual terminal voltage of the battery pack; V measured is the voltage output by the voltage divider; R1 and R2 are the resistance values in the voltage divider.

[0105] State of charge estimation unit: Based on the current integration method and open circuit voltage method, the state of charge of the battery pack is calculated in real time, providing information on the remaining capacity of the battery pack.

[0106] The remaining capacity of the battery pack is:

[0107]

[0108] wherein RC(t) is the remaining capacity of the battery pack at time t; C rated is the rated capacity of the battery pack; a is a weighting factor to adjust the contribution proportion of the current integration method and the open-circuit voltage method; SOC0 is the state of charge at the initial time t0; I(τ) is the battery current at time τ; f(V oc ) is the estimated state of charge according to the open-circuit voltage V oc .

[0109] Environmental parameter sensor group: monitors the environmental conditions around the battery pack, providing external reference data for thermal management strategy optimization. Data acquisition control unit: coordinates the data acquisition frequency and timing of each sensor, ensures the synchronization and integrity of the data, and performs preliminary data validity check. Communication interface unit: uses CAN bus or other suitable communication protocol for vehicle environment, realizes high-speed and reliable data transmission with other modules.

[0110] Data preprocessing and fusion module, used for filtering, standardizing and fusing the data collected by the multi-parameter acquisition module, generating high-quality and unified format data set. The data preprocessing and fusion module plays a core role in data processing in the whole system. Since the original data often has noise, outliers and inconsistent formats, it needs to be preprocessed through filtering, standardization and other techniques to improve the quality of the data. In addition, different types of data collected by multiple sensors need to be fused to form a unified and coherent data set for subsequent analysis and decision-making. The effectiveness of the data preprocessing and fusion module directly affects the overall performance of the system: high-quality data not only improves the accuracy of prediction, but also reduces the response time of the system, so as to realize more accurate thermal management.

[0111] Dynamic prediction modeling module, based on real-time and historical data to build and iteratively update temperature change prediction model, to realize accurate temperature trend prediction. The core of the dynamic prediction modeling module is to accurately predict the temperature change trend of the battery pack based on real-time and historical data. This prediction not only considers the current state, but also combines the patterns and trends of historical data, through continuous iteration and model updating to ensure the accuracy of prediction. The accuracy of the dynamic prediction modeling module directly affects the decision-making effect of the intelligent decision-making module, and its forward-looking in time dimension makes the whole system can deal with potential temperature abnormal situation in advance, to prevent temperature too high or too low damage to the battery pack.

[0112] The dynamic prediction modeling module includes the following components:

[0113] Model training unit: Utilize deep learning algorithms to periodically train temperature prediction models based on historical and real-time data, continuously optimizing model parameters. Model evaluation and selection unit: Evaluate the prediction performance of different models through cross-validation and automatically select the optimal model for actual prediction tasks. Online learning adaptation unit: Continuously receive new data and perform incremental learning to adapt the model to changes in battery performance over time and new working conditions.

[0114] Prediction execution unit: Receive real-time state data, invoke the current optimal model to predict future temperature trends, and output prediction results for the intelligent decision-making module. Model version management unit: Manage different versions of temperature prediction models, record model update history, and roll back to previous stable versions if necessary to ensure system reliability.

[0115] Intelligent decision-making module: Based on prediction results and preset rules, apply multi-objective optimization algorithms to generate optimal thermal management strategies. The intelligent decision-making module not only balances the cooling and heating needs of the battery but also considers energy efficiency, system lifespan, and operational safety. By weighing these factors, the intelligent decision-making module can output control strategies that align with the overall interests of the system, thereby optimizing the thermal management of the battery pack. The level of intelligence in this process directly affects the performance and lifespan of the battery system and is the core of the system's "intelligent" management.

[0116] Intelligent decision-making module includes the following components:

[0117] Decision input processing unit: Responsible for receiving and integrating temperature prediction results from the dynamic prediction modeling module and current system state information, providing comprehensive data support for the decision-making process. Rule base management unit: Used to maintain and update the preset decision rule base. Multi-objective optimization unit: Utilizes particle swarm optimization algorithms to find the best balance between temperature control, energy management, and performance improvement.

[0118] Strategy generation unit: Based on optimization results, formulate specific thermal management operation strategies, including cooling / heating intensity, duration, and execution sequence parameters. Decision evaluation and tuning unit: Evaluate the effectiveness of generated strategies through simulation prediction and historical data analysis and make fine-tuning adjustments. Strategy output unit: Output the final determined thermal management strategy to the thermal management execution module in a standardized format, while recording the decision-making process for subsequent analysis and improvement.

[0119] The thermal management execution module coordinates the control of active cooling, passive heat dissipation, or heating operations based on the output of the intelligent decision-making module, achieving precise temperature regulation and thermal management. The thermal management execution module is the execution unit of the system, responsible for converting the strategies generated by the intelligent decision-making module into specific operational actions. This module controls active cooling systems (such as fans, cooling liquid pumps) and passive heat dissipation devices (such as heat sinks), and enables heating devices when necessary to maintain the battery pack within the optimal operating temperature range. The flexibility and response speed of the thermal management execution module are critical to ensuring the stable operation of the system, as it needs to accurately control the intensity and method of temperature regulation based on real-time thermal management strategies, avoiding battery overheating or overcooling, and ensuring the efficient and safe operation of the battery pack.

[0120] The thermal management execution module includes the following components:

[0121] Strategy analysis unit: receives and analyzes the thermal management strategies from the intelligent decision-making module and converts them into specific execution instructions and parameters. Active cooling control unit: adjusts active cooling elements based on specific execution instructions and parameters to achieve precise active cooling. Passive heat dissipation adjustment unit: used to control the working state of passive heat dissipation elements, optimizing heat distribution and buffering effect.

[0122] Heating control unit: used to accurately adjust the power output of the battery heater to ensure that the battery pack maintains an optimal operating temperature range. Execution coordination unit: used to coordinate cooling, heat dissipation, and heating processes to avoid conflicts. Feedback monitoring unit: used to monitor the thermal management execution effect in real time, collecting temperature change data to provide timely feedback for strategy adjustment.

[0123] System monitoring and diagnosis module: continuously evaluates system performance, monitors abnormal conditions in real time, performs fault diagnosis and early warning, and ensures safe and reliable operation of the system. The system monitoring and diagnosis module continuously evaluates the running state of the system, discovers abnormalities in time and performs fault diagnosis by monitoring the working condition of each module. The system monitoring and diagnosis module can also warn of potential failures or dangerous situations, alerting users or automatically triggering appropriate safety protection measures. Through continuous evaluation of system performance, the monitoring and diagnosis module can ensure the long-term stability and reliability of the system, preventing safety accidents caused by improper temperature management.

[0124] The system monitoring and diagnosis module includes the following components:

[0125] System state acquisition unit: continuously collects running data and state information from each module to provide real-time and comprehensive data basis for system monitoring and diagnosis. Performance evaluation unit: based on pre-set performance indicators and historical data, the overall running efficiency, energy consumption, and temperature control accuracy of the system are evaluated and analyzed in real time. Abnormality detection unit, used to quickly identify abnormal conditions that deviate from the normal range;

[0126] Fault diagnosis expert unit: in-depth analysis of detected anomalies, determine the fault type, severity and possible causes. Early warning generation unit: according to the fault diagnosis results, generate different levels of early warning information, and timely inform the operator through appropriate channels. Automatic repair suggestion unit: for some automatically handled abnormal conditions, generate repair suggestions or automatically execute repair operations to improve the self-repairing ability of the system.

[0127] Human-computer interaction module, for providing intuitive system state display, operation control and remote monitoring interface, realizing human-computer collaborative intelligent thermal management. The human-computer interaction module not only displays the current state and historical data of the system, but also allows users to set and control through a friendly interface. In addition, through the remote monitoring function, users can monitor the state of the battery pack at any time and place, adjust the operation strategy, realize remote fault diagnosis and maintenance. The design of the human-computer interaction module directly affects the user experience, which improves the operability and maintenance convenience of the system, making the complex thermal management process intuitive and easy to understand.

[0128] The multi-parameter acquisition module transmits data to the data preprocessing and fusion module, the data preprocessing and fusion module transmits data to the dynamic prediction modeling module, the dynamic prediction modeling module transmits data to the intelligent decision module, the intelligent decision module transmits data to the thermal management execution module, the thermal management execution module and the system monitoring and diagnosis module transmit data to each other, and the human-computer interaction module and the multi-parameter acquisition module, data preprocessing and fusion module, dynamic prediction modeling module, intelligent decision module, thermal management execution module and system monitoring and diagnosis module transmit data to each other.

[0129] The application provides a running method of a power battery pack thermal management control system, comprising the following steps:

[0130] S1, using a particle swarm optimization algorithm to find the best balance point between temperature control, energy consumption management and performance improvement;

[0131] S1.1, comprehensively considering the temperature control, energy consumption management and performance improvement factors, constructing the target of the multi-objective function, and the optimization formula is:

[0132] minimizef(T cell ,E consumption ,P performance )=W T ·(T cell -T optimal ) 2 +W E ·E consumption +W P ·P performance ;

[0133] Wherein, WT , W E、 W P is a weight factor for balancing the relationship between temperature control, energy consumption management and performance improvement; T optimal is the optimal working temperature of the system; E consumption is the energy consumption; P performance is the system performance index; T cell is the temperature of the battery pack; minimize formula represents the optimization problem of the minimum objective function F(T cell , E consumption , P performance ).

[0134] S1.2, randomly generate particles in the defined search space, each particle represents a set of solutions, and assign an initial position and velocity to each particle, wherein the position represents the parameter value of the solution, and the velocity represents the direction and amplitude of the parameter change;

[0135] S1.3, for each solution represented by a particle, calculate its fitness value using a multi-objective optimization function;

[0136] S1.4, compare the fitness of the current position of each particle with the fitness of its historical best position, update the individual optimal position, and at the same time, select the position with the highest fitness among all particles as the global optimal position;

[0137] S1.5, according to the individual optimal position and the global optimal position, use the velocity and position update formula of the particle swarm optimization algorithm to calculate the new velocity and new position of each particle, and the velocity update formula is:

[0138]

[0139] wherein, is the velocity of particle i at time T; is the position of particle i at time T; pi is the individual optimal position of particle i; g is the global optimal position; ω is the inertia weight, which controls the inertia of the particle velocity; c1 is the individual learning factor; c2 is the social learning factor; r1 and r2 are random numbers in the range of [0, 1], which are used to introduce randomness; is the new velocity of particle i at time T+1;

[0140] The position update formula is:

[0141] wherein, is the new position of particle i at time T+1;

[0142] S1.6, repeat the process of particle fitness evaluation, optimal position update, and particle position and velocity adjustment until a preset number of iterations is reached, and finally output the global optimal position, which is the best balance point found between temperature control, energy management, and performance improvement;

[0143] S2, evaluate the effectiveness of the generated strategy through simulation prediction and historical data analysis, and fine-tune it;

[0144] S2.1, simulate the execution of the generated thermal management strategy under various working conditions to quickly evaluate its potential effects;

[0145] The thermal management strategy includes active cooling control strategy, passive heat dissipation control strategy, and heating control strategy.

[0146] The active cooling control strategy mainly realizes rapid temperature drop through the active cooling control unit. When the temperature T cell of the battery pack exceeds the preset high temperature threshold T high , and the maximum temperature difference ΔT max inside the battery pack is greater than the allowed temperature difference threshold ΔT allow , active cooling is triggered. The cooling power P cool is adjusted according to the difference between the current temperature of the battery pack and the target temperature T target , as well as the efficiency parameter η cool of the active cooling control unit. The calculation formula of the cooling power is as follows: P cool = η cool ·(T cell -T target ). Through this formula, the cooling power will increase with the increase of the battery temperature, so as to reduce the temperature faster. When the temperature drops below T high , and the temperature difference ΔT max is lower than the temperature difference threshold ΔT allow , the active cooling stops.

[0147] The passive heat dissipation control strategy slowly adjusts the temperature through passive heat dissipation elements. When the temperature of the battery pack approaches the high temperature threshold, but does not reach the triggering condition of active cooling (i.e. T cell is in the interval T low <T cell <T high , and the temperature difference ΔT max is less than the allowed threshold ΔT allow , the passive heat dissipation control strategy is selected. The heat dissipation power P passive of passive heat dissipation depends on the temperature difference ΔT env between the battery pack and the environment T cell -T ambient ; the specific heat dissipation formula can be expressed as: P passive = ηpassive • ΔT env ; where T ambient is the ambient temperature, η passive is the efficiency parameter of passive cooling; when the temperature T cell drops below the low temperature threshold T low , passive cooling is stopped.

[0148] The heating control strategy is to heat up by the battery heater. In low temperature environment, when the battery pack temperature T cell is lower than the set low temperature threshold T low , and the maximum temperature difference ΔT max exceeds the allowed range, the heating control strategy is started to ensure the battery pack is maintained within the safe operating temperature range. The heating power P heat is determined by the difference between the current battery pack temperature and the target temperature T target , formula: P heat = η heat ·(T target -T cell ); where η heat is the efficiency coefficient of the battery heater. When the temperature rises to T low , heating is stopped.

[0149] Temperature difference control is an important step to ensure the uniformity of the temperature between each single battery cell inside the battery pack. If the maximum temperature difference ΔT max inside the battery pack exceeds the allowed temperature difference threshold ΔT allow , i.e.: ΔT max = max(T cell )-min(T cell )> ΔT allow , the system will choose different control strategies according to the temperature difference. For smaller temperature difference, passive cooling or adjusting cooling power is preferred; for larger temperature difference, active cooling or heating is triggered to ensure the temperature difference is quickly reduced.

[0150] S2.2, compare the simulation results with historical operation data to evaluate the improvement of the generated strategy compared to the past strategies;

[0151] S2.3, based on the pre-set key performance indicators, quantitatively evaluate the simulation results to identify the strengths and weaknesses of the generated strategy;

[0152] S2.4, by adjusting the strategy parameters and observing the changes in system performance, determine the degree of influence of the parameters on performance;

[0153] S2.5, according to the analysis results, make targeted adjustments to the generated strategy;

[0154] S2.6, repeat the above steps until the performance of the generated policy reaches the expected target.

[0155] Therefore, the application adopts the above-mentioned power battery pack thermal management control system and method, through real-time multi-parameter acquisition, dynamic temperature prediction and intelligent decision, integrates and optimizes the thermal management strategy of the battery pack, realizes efficient temperature control and energy consumption balance; has abnormal monitoring and self-diagnosis function, ensures the safety and reliability of the system.

[0156] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, but not to limit them, although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that: it can still modify or equivalently replace the technical solutions of the present application, and these modifications or equivalent replacements also cannot make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present application.

Claims

1. A power battery pack thermal management control system, characterized in that: The system comprises the following modules: Multi-parameter acquisition module: for real-time acquisition of battery pack parameter data; The multi-parameter acquisition module includes a temperature sensor network, a current-voltage acquisition unit, a state of charge estimation unit, an environmental parameter sensor group, a data acquisition control unit, and a communication interface unit; The temperature sensor network: for real-time monitoring of battery cell and module temperature distribution; The current-voltage acquisition unit: for continuous measurement of the charge and discharge current and terminal voltage of the battery pack, providing basic data for state of charge estimation and safety monitoring; The state of charge estimation unit: for providing battery pack remaining capacity information; The environmental parameter sensor group: for monitoring the environmental conditions around the battery pack, providing external reference data for thermal management strategy optimization; The data acquisition control unit: for coordinating the data acquisition frequency and timing of each sensor and performing preliminary data validity checks; The communication interface unit: for realizing high-speed and reliable data transmission with each module; Data preprocessing and fusion module: for generating high-quality, unified format data sets; Dynamic prediction modeling module: for realizing accurate temperature trend prediction; Intelligent decision-making module: for generating optimal thermal management strategies; The intelligent decision-making module includes a decision input processing unit, a rule base management unit, a multi-objective optimization unit, a strategy generation unit, a decision evaluation and tuning unit, and a strategy output unit; The decision input processing unit: for providing comprehensive data support for the decision-making process; The rule base management unit: for maintaining and updating the preset decision rule base; The multi-objective optimization unit: for finding the best balance point between temperature control, energy consumption management, and performance improvement; The strategy generation unit: for formulating specific thermal management operation strategies; The decision evaluation and tuning unit: for evaluating the effectiveness of the generated strategies through simulation prediction and historical data analysis and making fine adjustments; The strategy output unit: for outputting the finally determined thermal management strategies to the thermal management execution module in a standardized format, while recording the decision-making process for subsequent analysis and improvement; Thermal management execution module: for realizing accurate temperature regulation and thermal management; The thermal management execution module includes a strategy parsing unit, an active cooling control unit, a passive heat dissipation adjustment unit, a heating control unit, an execution coordination unit, and a feedback monitoring unit; The strategy parsing unit: for receiving and parsing the thermal management strategies from the intelligent decision-making module, and converting them into specific execution parameters, including active cooling control strategies, passive heat dissipation control strategies, and heating control strategies; The active cooling control unit: for adjusting the active cooling elements according to the specific execution parameters; The passive heat dissipation adjustment unit: for controlling the working state of the passive heat dissipation elements, optimizing heat distribution and buffering effect; The heating control unit: for accurately adjusting the power output of the battery heater; The execution coordination unit: for realizing the coordination of cooling, heat dissipation, and heating processes to avoid conflicts; The feedback monitoring unit: for real-time monitoring of the thermal management execution effect, collecting temperature change data, and providing timely feedback for strategy adjustment; System monitoring and diagnosis module: for ensuring the safe operation of the system; Human-computer interaction module; Intelligent thermal management for human-computer collaboration; The operation method of the power battery pack thermal management control system comprises the following steps: S1, using particle swarm optimization algorithm to find the best balance point between temperature control, energy management and performance improvement; S1.1, considering temperature control, energy management and performance improvement factors, constructing a multi-objective function target, the optimization formula is: ； wherein, , , is a weight factor balancing the relationship between temperature control, energy consumption management and performance improvement; is the optimal operating temperature of the system; is the energy consumption; is the system performance indicator; is the temperature of the battery pack; formula represents the optimization problem of the minimum objective function . S1.2, randomly generate particles in the defined search space, each particle represents a set of solutions, and assign an initial position and velocity to each particle, where the position represents the parameter value of the solution, and the velocity represents the direction and amplitude of the parameter change; S1.3, for each particle representing a solution, use the multi-objective optimization function to calculate its fitness value; S1.4, compare the fitness of the current position of each particle with the fitness of its historical best position, update the individual optimal position, and select the position with the highest fitness among all particles as the global optimal position; S1.5, according to the individual optimal position and the global optimal position, use the velocity and position update formula of the particle swarm optimization algorithm to calculate the new velocity and position of each particle, the velocity update formula is: ； where is the particle at time ; is the particle at time ; is the individual optimal position of the particle ; is the global optimal position; is the inertia weight, controlling the inertia of the particle velocity; is the individual learning factor; is the social learning factor; and is a random number in the range [0, 1] used to introduce randomness; is the new velocity of the particle at time ; The position update formula is: ; wherein is a particle at time new position; S1.6, repeatedly execute the particle fitness evaluation, optimal position update and particle position and velocity adjustment process until the preset number of iterations is reached, and finally output the global optimal position, which is the best balance point found between temperature control, energy management and performance improvement; S2, evaluate the effectiveness of the generated strategy through simulation prediction and historical data analysis and fine-tune it; S2.1, simulate the execution of the generated thermal management strategy under various working conditions to quickly evaluate its potential effect; S2.2, compare the simulation results with historical operation data to evaluate the improvement degree of the generated strategy compared with the past strategy; S2.3, based on the preset key performance indicators, quantitatively evaluate the simulation results to identify the advantages and disadvantages of the generated strategy; S2.4, determine the degree of influence of the parameters on the performance by adjusting the strategy parameters and observing the changes in system performance; S2.5, according to the analysis results, adjust the generated strategy; S2.6, repeat the above steps until the performance of the generated strategy reaches the expected target.

2. A power battery pack thermal management control system according to claim 1, characterized in that: The multi-parameter acquisition module transmits data to the data preprocessing and fusion module, the data preprocessing and fusion module transmits data to the dynamic prediction modeling module, the dynamic prediction modeling module transmits data to the intelligent decision module, the intelligent decision module transmits data to the thermal management execution module, the thermal management execution module and the system monitoring and diagnosis module transmit data to each other, and the human-computer interaction module transmits data to each other with the multi-parameter acquisition module, the data preprocessing and fusion module, the dynamic prediction modeling module, the intelligent decision module, the thermal management execution module and the system monitoring and diagnosis module.

3. A power battery pack thermal management control system according to claim 2, wherein: The dynamic prediction modeling module includes a model training unit, a model evaluation and selection unit, an online learning adaptation unit, a prediction execution unit and a model version management unit; The model training unit is configured to periodically train the temperature prediction model based on historical and real-time data, and constantly optimize the model parameters; The model evaluation and selection unit is configured to automatically select the optimal model for actual prediction tasks; The online learning adaptation unit is configured to adapt the model to changes in battery performance over time and new working conditions; The prediction execution unit is configured to invoke the currently optimal model to perform future temperature trend prediction, and output the prediction results for use by the intelligent decision module; The model version management unit is configured to manage different versions of the temperature prediction model, record the model update history, and be able to roll back to a previous stable version.

4. The power battery pack thermal management control system of claim 2, wherein: The system monitoring and diagnosis module includes a system state acquisition unit, a performance evaluation unit, an anomaly detection unit, a fault diagnosis expert unit, a warning generation unit, and an automatic repair suggestion unit; The system state acquisition unit is configured to provide a real-time and comprehensive data basis for system monitoring and diagnosis; The performance evaluation unit is configured to evaluate and analyze the overall operation efficiency, energy consumption, and temperature control accuracy of the system in real time; The anomaly detection unit is configured to quickly identify abnormal conditions that deviate from the normal range; The fault diagnosis expert unit is configured to conduct in-depth analysis of detected anomalies, determine the fault type, severity, and cause; The warning generation unit is configured to generate warning information of different levels and timely notify the operator through appropriate channels; The automatic repair suggestion unit is configured to generate repair suggestions and automatically execute repair operations.

5. The power battery pack thermal management control system of claim 1, wherein: The calculation formula of the battery pack's charging and discharging current is represented as: ； wherein, is the actual current of the battery, i.e. the charge or discharge current; is the primary number of turns of the current transformer; is the secondary number of turns of the current transformer; is the load resistance through which the secondary current passes; is the voltage generated by the secondary current passing through the load resistance; The calculation formula of the battery pack's terminal voltage is represented as: ； wherein, is the actual terminal voltage of the battery pack; is the voltage divider output voltage; and is the resistance value in the voltage divider; The remaining capacity of the battery pack is: ； wherein, is the remaining capacity of the battery pack at time ; is the rated capacity of the battery pack; is a weighting factor to adjust the proportion of the contribution of the current integration method and the open circuit voltage method; is the state of charge at the initial time ; is the battery current at time ; is the state of charge estimated from the open circuit voltage .

6. A power battery pack thermal management control system according to claim 5, wherein: The thermal management strategy in S2.1 includes active cooling control strategy, passive heat dissipation control strategy, and heating control strategy; The active cooling control strategy mainly realizes fast temperature drop through an active cooling control unit, when the temperature of the battery pack exceeds a preset high temperature threshold , and the maximum temperature difference inside the battery pack is greater than an allowed temperature difference threshold , active cooling is triggered; the cooling power is adjusted according to the difference between the current temperature of the battery pack and the target temperature and the efficiency parameter of the active cooling control unit ; the calculation formula of the cooling power is: Through this formula, the cooling power will increase with the increase of the battery temperature, so as to reduce the temperature faster; when the temperature drops to below, and the temperature difference is lower than the temperature difference threshold , active cooling stops; The passive cooling control strategy slowly regulates the temperature by passive cooling elements; when the temperature of the battery pack is close to the threshold, but does not reach the triggering condition of active cooling, i.e. is in the interval , and the maximum temperature difference is less than the allowed threshold , the passive cooling control strategy is selected; the cooling power of passive cooling depends on the temperature difference between the battery pack and the environment ; The heat dissipation formula is expressed as: ; wherein, Tambient is the ambient temperature, Ttarget is the target temperature, Tlow is a low temperature threshold, and wherein passive heat dissipation is stopped when the temperature Ttarget decreases below the low temperature threshold Tlow. The heating control strategy is performed by a battery heater; in a low temperature environment, when the battery pack temperature is lower than a set low temperature threshold , and the temperature difference exceeds the allowed range, the heating control strategy is started to ensure that the battery pack is maintained within a safe working temperature range; the heating power is determined by the difference between the current battery pack temperature and the target temperature , and the formula is: ; wherein, is the efficiency coefficient of the battery heater; when the temperature rises to , the heating is stopped; Temperature difference control is an important step to ensure the uniformity of the temperature among the individual cells inside the battery pack; if the maximum temperature difference inside the battery pack exceeds the allowed temperature difference threshold , i.e. : ; the system will choose different control strategies according to the temperature difference; for small temperature difference, passive heat dissipation and adjustment of cooling power are preferred; for large temperature difference, active cooling and heating are triggered to quickly reduce the temperature difference.

Images