Temperature control method and system for new energy battery pack

Abstract

The invention relates to the technical field of battery temperature control, and discloses a temperature control method and system for a new energy battery pack, and the method comprises the steps: obtaining a real-time scene, an external environment and battery monitoring feature information through multi-dimensional data monitoring, setting a rigid temperature control condition according to the information, carrying out the predictive analysis to obtain a prediction constraint condition, and carrying out the calculation of the prediction constraint condition. According to the method, self-adaptive temperature control analysis is carried out based on hard temperature control conditions and prediction constraint conditions, temperature control target features are generated, a temperature control decision is generated through multi-target optimization analysis, and a temperature control system is driven to execute. The service life is prolonged, and the problem that a single temperature control mode cannot adapt to a specific working environment in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of battery temperature control, and in particular to a temperature control method and system for a new energy battery pack. Background Art

[0002] With the rapid development of new energy technologies, battery packs are playing an increasingly important role in various application scenarios, especially in electric vehicles (EVs), energy storage systems, and other renewable energy applications. The performance and safety of battery packs directly affect the operating efficiency and reliability of the overall system. Battery pack temperature management is one of the key factors in optimizing battery performance and extending its service life. Excessively high or low temperatures can lead to decreased battery performance and may even cause safety hazards such as battery overheating, thermal runaway, or shortened life. Therefore, ensuring that battery packs operate within an appropriate temperature range is of great technical value. To effectively control the temperature of battery packs, existing technologies mainly use a single temperature control method for temperature management. However, with the expansion of battery pack scale and the complexity of its application areas, a single temperature control method often cannot meet the changing environment and complex working conditions. Summary of the Invention

[0003] The purpose of the present invention is to provide a temperature control method and system for a new energy battery pack, aiming to solve the problem in the prior art that a single temperature control mode cannot adapt to a specific working environment.

[0004] The present invention is implemented as follows. In a first aspect, the present invention provides a temperature control method for a new energy battery pack, comprising: Perform multi-dimensional data monitoring on the battery pack to obtain real-time scene information, external environment information, and battery monitoring feature sequence of the battery pack; Setting hard temperature control conditions for the battery pack according to the real-time scene information and the external environment information; Acquire extended reference information of the battery pack according to the real-time scenario information, and perform predictive analysis in combination with the battery monitoring feature sequence to obtain prediction constraints; performing an adaptive temperature control analysis on the battery pack based on the hard temperature control condition and the prediction constraint condition to generate a temperature control target feature; According to the temperature control system information of the battery pack, a multi-objective optimization analysis of the overall temperature control system is performed on the temperature control target characteristics to obtain a temperature control decision and drive the temperature control system to execute the temperature control decision.

[0005] In a second aspect, the present invention provides a temperature control system for a new energy battery pack, which is used to implement the temperature control method for a new energy battery pack according to any one of the first aspects, comprising: A data monitoring module is used to perform multi-dimensional data monitoring on the battery pack to obtain real-time scene information, external environment information, and battery monitoring feature sequence of the battery pack; a temperature control limiting module, configured to set hard temperature control conditions for the battery pack based on the real-time scene information and the external environment information; A prediction constraint module, configured to obtain extended reference information of the battery pack based on the real-time scenario information, and perform predictive analysis in combination with the battery monitoring feature sequence to obtain prediction constraint conditions; a target analysis module, configured to perform adaptive temperature control analysis on the battery pack based on the hard temperature control conditions and the prediction constraints to generate a temperature control target feature; The temperature control decision module is used to perform a multi-objective optimization analysis of the overall temperature control system on the temperature control target characteristics according to the temperature control system information of the battery pack, obtain a temperature control decision and drive the temperature control system to execute the temperature control decision.

[0006] The present invention provides a temperature control method for a new energy battery pack, which has the following beneficial effects: The present invention obtains real-time scene, external environment and battery monitoring feature information through multi-dimensional data monitoring, sets hard temperature control conditions based on this information, and performs predictive analysis to obtain predictive constraints. Adaptive temperature control analysis is performed based on the hard temperature control conditions and predictive constraints to generate temperature control target features. Temperature control decisions are generated through multi-objective optimization analysis and driven to execute by the temperature control system. This method improves the intelligence and adaptability of the temperature control system, ensures the efficient and safe operation of the battery pack in different working environments, extends its service life, and solves the problem in the prior art that a single temperature control mode cannot adapt to a specific working environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 This is a schematic diagram of the steps of a temperature control method for a new energy battery pack provided by an embodiment of the present invention; Figure 2 It is a structural schematic diagram of a temperature control system of a new energy battery pack provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0008] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0009] The implementation of the present invention is described in detail below with reference to specific embodiments.

[0010] Reference Figure 1 、 Figure 2As shown, a preferred embodiment of the present invention is provided.

[0011] In a first aspect, the present invention provides a temperature control method for a new energy battery pack, comprising: S1: Perform multi-dimensional data monitoring on the battery pack to obtain real-time scene information, external environment information, and battery monitoring feature sequence of the battery pack; S2: Setting a hard temperature control condition for the battery pack according to the real-time scene information and the external environment information; S3: Acquire extended reference information of the battery pack according to the real-time scenario information, and perform predictive analysis in combination with the battery monitoring feature sequence to obtain prediction constraints; S4: performing adaptive temperature control analysis on the battery pack based on the hard temperature control condition and the prediction constraint condition to generate a temperature control target feature; S5: Based on the temperature control system information of the battery pack, perform a multi-objective optimization analysis of the overall temperature control system on the temperature control target characteristics, obtain a temperature control decision, and drive the temperature control system to execute the temperature control decision.

[0012] Specifically, in step S1 of the embodiment provided by the present invention, the real-time task and working status information of the battery pack is obtained through the intelligent control module or other intelligent control system of the battery pack. The working status of the battery pack, such as whether it is in charging, discharging or standby state, directly affects its temperature control requirements. By obtaining this information in real time, the temperature control strategy can be adjusted according to the current working task of the battery pack to ensure that the temperature of the battery pack is always within the optimal range under different working conditions. The real-time scene information helps to dynamically adjust the temperature control requirements of the battery pack, improve the response speed and flexibility of the temperature control system, and optimize the performance and safety of the battery pack.

[0013] More specifically, the temperature, humidity, air pressure and other information of the battery pack's environment are obtained through an environmental sensor group (such as temperature and humidity sensors, air pressure sensors, etc.). External environmental factors (such as temperature, humidity, etc.) have an important impact on the temperature control of the battery pack, especially under extreme weather conditions, such as high or low temperature environments. The temperature control requirements of the battery pack will change. By monitoring external environmental data, the impact of environmental changes on the battery pack can be evaluated in real time. External environmental information can provide the necessary compensation factors for the battery pack's temperature control system, making the temperature control strategy more accurate, avoiding temperature control instability caused by environmental factors, and extending the service life of the battery pack.

[0014] More specifically, the sensor group collects data such as the battery pack's internal temperature, voltage, current, remaining capacity, and charge and discharge status to generate a battery monitoring feature sequence. The internal state of the battery pack (such as voltage, current, remaining capacity, etc.) has a direct impact on its temperature change. By monitoring these characteristic data, possible faults or abnormalities in the battery pack can be discovered in a timely manner, and temperature control adjustments can be made. Through real-time collection and analysis of the battery monitoring feature sequence, abnormal conditions and potential risks of the battery pack can be discovered, fault prediction and early warning capabilities can be improved, and efficient operation of the battery pack can be ensured.

[0015] More specifically, real-time scene information, external environment information and battery monitoring feature sequence data are integrated to perform time domain, frequency domain and correlation feature analysis to generate comprehensive monitoring data. Single monitoring data (such as relying solely on temperature data or battery power data) is difficult to fully reflect the operating status of the battery pack. Through multi-dimensional data fusion, the status of the battery pack can be comprehensively evaluated from different angles, providing a more accurate basis for temperature control decision-making. Multi-dimensional data fusion and comprehensive analysis can improve the accuracy and intelligence level of the monitoring system, ensuring that the temperature control system can dynamically and accurately respond to different battery pack operating conditions.

[0016] More specifically, based on multi-dimensional data, combined with machine learning or deep learning algorithms, deep feature mining and pattern recognition are performed on the data to generate a deep monitoring model for the battery pack. Through advanced data mining algorithms (such as neural networks, support vector machines, etc.), potential rules and patterns can be identified from complex data, further improving the early warning and decision-making capabilities of the monitoring system. Deep feature mining and pattern recognition can improve the intelligence level of the temperature control system, automatically adjust temperature control measures, and ensure that the battery pack can maintain the optimal state under various operating conditions.

[0017] More specifically, real-time monitoring data is transmitted via wireless or wired networks to a central control system for centralized management and analysis. A feedback mechanism is then used to adjust the battery pack's temperature control measures. To achieve efficient remote monitoring and temperature control adjustments, it is essential to ensure that data is transmitted to the central control system in real time and stably. This data feedback allows for timely temperature adjustments to the battery pack to prevent abnormal temperatures or overheating. The data transmission and feedback mechanism ensures the real-time and flexibility of the temperature control system, enabling timely responses to changes in battery pack status and reducing safety risks associated with abnormal temperatures.

[0018] It is understandable that through multi-dimensional data monitoring, the real-time scene information, external environment information and battery monitoring feature sequence of the battery pack can be fully and accurately obtained. The combination of these data provides a comprehensive temperature control decision-making basis for the battery pack, allowing the temperature control system to be adaptively adjusted according to actual conditions. Ultimately, the entire system not only improves the temperature control efficiency, but also optimizes the operating performance and safety of the battery pack and extends the battery life.

[0019] Specifically, in step S2 of the embodiment provided by the present invention, the basic temperature control range of the battery pack is first defined, including a safe temperature range, an optimal operating temperature range, an overheating alarm temperature, etc. The temperature control conditions should be set based on the rated temperature requirements of the battery pack, the manufacturer's recommended range, and safety standards. Different types of battery packs have different temperature requirements. Exceeding this range may affect battery performance and life and even cause safety problems. By setting these basic temperature control conditions, a clear direction can be provided for the temperature control strategy of the battery pack, ensuring that the temperature control strategy has a clear safety boundary, effectively avoiding performance degradation or damage of the battery pack due to overheating or overcooling, and improving battery service life and safety.

[0020] More specifically, dynamic temperature control conditions are set based on the current working scenario information of the battery pack (for example, charging, discharging, standby, charging and discharging power, etc.). For example, during charging, due to the heat accumulation of the electrochemical reaction inside the battery, the temperature control conditions need to be stricter than in the discharging state. The battery pack will generate different amounts of heat in different working scenarios. Therefore, the temperature control conditions should be adjusted according to the working mode to cope with the actual workload. By dynamically adjusting the temperature control conditions according to the real-time scenario, the battery can be prevented from overheating when the load is too large. By dynamically adjusting the temperature control conditions, it can adapt to the heat changes in different working scenarios, ensuring that the battery pack can still maintain safe operation under high load, and avoiding accidents or performance degradation caused by insufficient temperature control.

[0021] More specifically, adaptive temperature control conditions are set for the battery pack based on external environmental information (such as ambient temperature, humidity, air pressure, etc.). For example, when the ambient temperature is high, the cooling effort needs to be increased; when the ambient temperature is low, the heating system needs to be enabled to ensure the normal operation of the battery. Changes in ambient temperature and humidity will directly affect the heat dissipation efficiency of the battery pack and the chemical reaction rate of the battery. Therefore, external environmental information plays a vital role in the setting of temperature control conditions. By adjusting the temperature control requirements according to environmental changes, the battery pack can be prevented from malfunctioning under extreme climatic conditions, ensuring that the battery pack can operate normally under various environmental conditions and maintain the optimal temperature range. Through adaptive temperature control, the negative impact of environmental changes can be reduced and the stability and reliability of the battery pack can be improved.

[0022] More specifically, specific temperature control thresholds are set according to the defined temperature control conditions. For example, the cooling system is started when the battery pack temperature exceeds 45°C, and the heating system is started when it is below -10°C. An alarm mechanism is also set. When the battery temperature exceeds the preset threshold, the system can trigger an alarm and automatically adjust the temperature control measures. The setting of the temperature control threshold helps to respond to changes in the battery pack temperature in a timely manner to prevent it from exceeding the safe range. The alarm mechanism ensures that it can respond quickly when the battery pack temperature is abnormal to prevent equipment damage or safety hazards. By setting specific thresholds and alarm mechanisms, remedial measures can be taken in time when the temperature is abnormal, effectively improving the safety and intelligent response capabilities of the battery pack, and preventing overheating or overcooling from causing permanent damage to the battery pack.

[0023] More specifically, the temperature control conditions are reviewed and optimized regularly, and the temperature control strategy is adjusted based on the battery pack's operating data, real-time scenario information, external environmental changes, and historical temperature control data. Through machine learning or data analysis methods, the response time, efficiency, and accuracy of the temperature control system are optimized. The performance of the battery pack is closely related to environmental factors, working conditions, etc. Therefore, the temperature control conditions need to be adjusted as the battery pack's usage time increases and the environment changes. Continuous optimization of the temperature control strategy can better adapt to the actual needs of the battery pack. By dynamically optimizing the temperature control strategy, the system can maintain the best operating state throughout the different life cycles of the battery pack, extending the service life of the battery pack, while improving the adaptability and stability of the battery pack in complex environments.

[0024] More specifically, based on the aforementioned temperature control conditions, a temperature control plan is implemented and battery pack temperature changes are monitored in real time. Sensors collect real-time temperature data from the battery pack and compare it with pre-set hard temperature control conditions, automatically executing temperature control measures (such as activating cooling or heating systems). Implementing the temperature control plan is a key step in ensuring the battery pack remains within a safe temperature range during real-time operation. The real-time monitoring and feedback mechanism enables rapid identification and response to temperature anomalies, ensuring the timeliness and effectiveness of temperature control measures. This real-time monitoring and feedback mechanism ensures the efficient execution of the temperature control system, keeping the battery pack within the optimal temperature range and ensuring battery safety, stability, and efficiency.

[0025] It is understandable that through the above steps, reasonable hard temperature control conditions can be set for the battery pack to ensure that the battery pack can maintain a safe temperature range under different working scenarios and environmental conditions. Each step dynamically adjusts the temperature control requirements through real-time scene and environmental information feedback to ensure that the battery pack can still maintain efficient and safe operation under high load, extreme temperature and other conditions, thereby extending the battery life and improving safety.

[0026] Specifically, in step S3 of the embodiment provided by the present invention, the intelligent control system or sensor network of the battery pack is used to collect real-time scene information of the battery pack, such as charging / discharging status, load power, battery temperature, remaining power, etc. The real-time scene information provides basic data support for the current working status of the battery pack. This information is the key to analyzing the future working status and performance changes of the battery pack. By acquiring real-time scene information, the current working mode of the battery pack can be determined, providing an important basis for subsequent predictive analysis. The real-time scene information can accurately reflect the real-time working conditions of the battery pack, so that subsequent analysis can be closely fitted with the current status of the battery, ensuring the accuracy and practicality of the predictive analysis.

[0027] More specifically, based on the real-time scenario information of the battery pack, further relevant extended reference information is collected, such as the external temperature, humidity, air pressure, wind speed, etc. of the battery pack's environment, or the battery pack's historical operating data, maintenance records, equipment characteristics, etc. The extended reference information can provide additional background data to help identify potential influencing factors and trends. For example, ambient temperature and humidity will affect the temperature management of the battery, and historical operating data can reveal the aging status or potential failure modes of the battery pack. Through the extended reference information, a more comprehensive understanding of the working environment and potential risks of the battery pack can be achieved. The extended reference information can provide broader background support, provide more dimensional basis for predictive analysis, increase the comprehensiveness and accuracy of the prediction, and improve the reliability of the prediction results.

[0028] More specifically, the real-time monitoring data of the battery pack (such as voltage, current, temperature, and remaining charge) is combined with real-time scenario information and extended reference information to form a multi-dimensional data set. Time series analysis is then performed on the battery pack's monitoring feature sequence to identify possible trends, periodicity, and abnormal patterns. The battery monitoring feature sequence provides detailed historical data on the battery pack during operation. Combined with this data, the battery pack's behavior under different operating conditions can be analyzed to identify potential failures, performance degradation trends, or abnormal operating patterns. By combining multi-dimensional data, a more comprehensive understanding of the battery pack's health status can be achieved. Analysis of the battery monitoring feature sequence can reveal the operating patterns of the battery pack, identify potential risks, and help predict the battery pack's possible future state, thereby effectively preventing failures and improving the safety and reliability of the battery pack.

[0029] More specifically, statistical methods, machine learning, or deep learning algorithms are used to analyze acquired data (including real-time scenario information, extended reference information, and battery monitoring feature sequences) to construct predictive models. These models can be regression models, classification models, neural network models, etc. The goal is to predict future performance changes, health status, and possible failures of battery packs. Through predictive analysis, potential battery pack failures and performance degradation can be identified in advance, allowing preventive maintenance to avoid sudden failures. Predictive models can simulate the behavior of battery packs in different operating scenarios and environmental conditions to predict their future state. Predictive analysis can accurately predict the future performance of battery packs and provide advance reports on the battery pack's health status, thereby facilitating timely action, such as adjusting workloads, optimizing charging strategies, and performing maintenance, to maximize the battery pack's service life and improve operational efficiency.

[0030] More specifically, based on the output results of the prediction model, combined with the working scenario and environmental information of the battery pack, prediction constraints are generated. For example, based on the predicted temperature changes, a temperature limit range needs to be set; if performance degradation is predicted, a time window needs to be set for early battery replacement. Prediction constraints help provide clear operating boundaries for the operation of the battery pack and ensure that the battery pack operates within the preset constraints. For example, temperature limits and power limits are all intended to prevent the battery pack from exceeding the safety range or efficiency range during operation. Prediction constraints ensure that the battery pack can operate within a controllable range in the future, avoiding overheating, over-discharge or other potential problems, ensuring the efficient and safe operation of the system, and providing a basis for battery pack maintenance.

[0031] More specifically, during the operation of the battery pack, the working status of the battery and changes in the external environment are monitored in real time, and the prediction constraints are adjusted in time through a dynamic feedback mechanism. When the battery pack status deviates or the environmental conditions change, the feedback mechanism will automatically adjust the prediction constraints. The implementation of prediction analysis and constraints is a dynamic process. As the battery pack operates and the external environment changes, real-time monitoring and feedback adjustment can ensure that the battery pack operates in the optimal state. If the constraints fail to effectively respond to new changes, timely adjustment can avoid failures. Through real-time monitoring and feedback adjustment, the flexibility and adaptability of the prediction constraints can be ensured, and timely responses can be made to emergencies or deviations during operation, thereby improving the safety and stability of the battery pack operation.

[0032] It is understandable that by acquiring real-time scene information, collecting extended reference information, combining monitoring feature sequences, and implementing predictive analysis, predictive constraints can be generated for the battery pack. These conditions not only provide clear boundaries for the operation of the battery pack, but can also be dynamically adjusted to cope with changes in the external environment and anomalies that occur during operation. Ultimately, this process can effectively improve the operating efficiency of the battery pack, reduce the occurrence of failures, extend its service life, and ensure its safe and stable operation.

[0033] Specifically, in step S4 of the embodiment provided by the present invention, the hard temperature control conditions and predictive constraints of the battery pack are determined by acquiring real-time scene information, extended reference information and predictive analysis results. For example, the hard temperature control conditions include the maximum safe temperature of the battery, the operating temperature range, etc., while the predictive constraints are generated based on future ambient temperature, load changes or changes in the health status of the battery pack. The hard temperature control conditions are to ensure that the battery pack operates within a safe range, while the predictive constraints help adjust the temperature control strategy according to future changes to avoid adverse conditions such as overheating or low temperature of the battery pack during operation. This step ensures that the basic data source of the temperature control system is accurate and timely, provides a solid foundation for subsequent adaptive temperature control, and makes the temperature control strategy more targeted and timely.

[0034] More specifically, the battery pack's operating mode (such as charging, discharging, and standby) and current state are combined to analyze the battery's temperature requirements under different operating conditions. This includes analyzing the temperature trends of the battery pack under different load conditions, charging speeds, and environmental conditions. The battery pack's temperature requirements vary with different operating states. For example, during the charging process, the battery generates a certain amount of heat. If the temperature is not effectively controlled, it will affect the battery's performance and lifespan. Therefore, the temperature control strategy must be adjusted in real time according to different operating modes. By analyzing the battery's operating mode and temperature requirements, a more precise temperature control strategy can be formulated to ensure that the battery temperature remains within the optimal range under different operating conditions, avoiding the impact of excessively high or low temperatures and improving battery safety and performance.

[0035] More specifically, based on the hard temperature control conditions and predicted constraints, combined with the temperature demand analysis of the battery pack, an adaptive temperature control strategy is formulated. This includes adjusting the operating rate of the heat dissipation system (such as a fan or water cooling system), changing the charging rate, adjusting the power output or taking other measures. The core of the adaptive temperature control strategy is to dynamically adjust the operating mode of the temperature control system according to the real-time battery status and predicted environmental changes. For example, when the external ambient temperature is predicted to rise, the system needs to increase the cooling capacity, or reduce the energy consumption of the temperature control equipment when the load is reduced. Through the adaptive temperature control strategy, we can effectively respond to environmental changes and battery load fluctuations, keep the battery operating within the optimal temperature range, and avoid the negative impact of temperature fluctuations on battery performance.

[0036] More specifically, while implementing the temperature control strategy, a dynamic adjustment and feedback mechanism is established to monitor the temperature changes of the battery pack in real time, and dynamically adjust the temperature control system based on real-time temperature feedback. For example, if the battery pack temperature exceeds the preset range, the cooling capacity is automatically increased, or the charging power is reduced to lower the temperature. Real-time monitoring and dynamic adjustment can ensure that the temperature control strategy can respond to changes in the battery pack in a timely manner. For example, when the battery pack temperature is too high under high load, measures must be taken immediately to cool it down; if the temperature is too low, the working mode needs to be adjusted to ensure battery energy output. The dynamic adjustment and feedback mechanism can promptly correct any deviations in the temperature control strategy to ensure that the battery pack is always within a safe temperature range, thereby improving the operating safety and life of the battery.

[0037] More specifically, based on the above analysis, the temperature control target characteristics of the battery pack are generated. These characteristics include the expected temperature range, temperature adjustment speed, response time for the execution of the temperature control strategy, etc. The temperature control target characteristics provide a quantitative target for the actual temperature control operation, ensuring that the adjustment target of the temperature control system is clear and can be effectively controlled under complex working conditions. By generating temperature control target characteristics, a clear target can be provided for the optimization of the temperature control system, which helps to ensure that the battery pack always remains in a safe and stable temperature range under different operating conditions, thereby improving the overall operating performance and efficiency of the battery.

[0038] More specifically, after implementing the temperature control target feature, the temperature changes of the battery pack are monitored in real time, and the effectiveness of the temperature control strategy is verified based on the actual operating conditions. If it is found that the temperature control effect does not meet expectations, the temperature control strategy will continue to be optimized, including adjusting the target temperature range, adjusting the cooling efficiency, etc. The temperature control strategy needs to be verified in actual operation to ensure that it can operate effectively in different working environments. The optimization process ensures that the strategy can adapt to changing working conditions and environmental changes to avoid temperature control failure. Through verification and optimization, the temperature control strategy can be continuously improved to make it more adapted to the actual needs of the battery pack and improve the stability and performance of battery operation.

[0039] It is understandable that by combining hard temperature control conditions with predictive constraints, as well as a detailed analysis of the battery pack's temperature requirements, an adaptive temperature control strategy can be developed. This strategy, combined with real-time monitoring and feedback mechanisms, ensures that the battery pack can maintain the optimal temperature state under different operating modes, thereby extending the battery's service life and improving its operating efficiency. By generating temperature control target characteristics and verifying and optimizing them, precise temperature control of the battery pack can be achieved, avoiding the risks brought by temperature anomalies.

[0040] Specifically, in step S5 of the embodiment provided by the present invention, all relevant information about the battery pack temperature control system is collected, including hard temperature control conditions (such as maximum and minimum temperature limits), forecast constraints (such as ambient temperature and load variations), the current battery pack temperature state, and cooling system capabilities. To ensure that all relevant data is timely, accurate, and comprehensive, the temperature control system's decisions must be based on a comprehensive understanding of the system's current state. Only by accurately collecting system information can the accuracy of subsequent analysis and decision-making be ensured, laying the data foundation for subsequent temperature control target feature analysis and optimization. This ensures that the system has a comprehensive and dynamic understanding of battery status and environmental conditions, preventing temperature control strategy failures due to incomplete information.

[0041] More specifically, based on the collected temperature control system information, the temperature control target characteristics are defined and quantified. These characteristics usually include the desired temperature range, temperature change rate, system response time, system stability requirements, etc. Clarifying and quantifying the temperature control target characteristics is the basis for temperature control decision-making, ensuring that the temperature control system can achieve specific optimization goals in complex environments. The definition of temperature control target characteristics helps to carry out targeted optimization of the temperature control system, so that the system can adjust the operating strategy according to actual needs, maintain optimal temperature conditions, and improve battery efficiency and life.

[0042] More specifically, a multi-objective optimization model is constructed based on the temperature control target characteristics as well as the hard temperature control conditions and prediction constraints. The model needs to consider multiple objectives at the same time, such as temperature control accuracy, energy consumption, cooling system load, cost, etc. Common optimization algorithms include genetic algorithms, particle swarm optimization (PSO), simulated annealing, etc. In actual operation, the temperature control system faces multiple objectives that need to be balanced, such as precise temperature control and reduced energy consumption. The multi-objective optimization model can comprehensively consider these objectives to ensure that the optimal compromise is found among multiple objectives. Through multi-objective optimization, the system's energy consumption can be minimized, costs can be reduced, and system stability can be improved while meeting temperature control accuracy, ensuring the efficiency and sustainability of the temperature control system.

[0043] More specifically, by solving the multi-objective optimization model, a series of possible temperature control decisions are obtained. Then, based on the calculation results of the model, post-processing is performed to select the most appropriate temperature control strategy. This strategy should ensure that all objectives are optimally balanced and meet the actual needs of the battery pack. The decision of the temperature control system needs to be based on the results calculated by the multi-objective optimization model to ensure that the selected solution best meets the needs of the system. The post-processing steps help filter out solutions that do not meet the constraints and select the optimal decision. Through optimization calculations, the temperature control decision can balance the system's energy consumption and operating costs while ensuring the safety of the battery pack and improving efficiency, so that the temperature control system can operate effectively in different environments.

[0044] More specifically, the temperature control decisions obtained from the optimization analysis are converted into specific operating instructions to drive the execution of the temperature control system. For example, these can adjust the operating status of the cooling system, adjust the battery charging rate, or adjust the power output. The temperature control decisions obtained from the optimization analysis must be converted into specific execution instructions to ensure that the system can adjust according to the optimization decisions during actual operation. By accurately executing temperature control decisions, the temperature control system can respond to changes in the environment and battery pack in real time, always keeping the battery pack within the optimal operating temperature range, effectively extending the battery life, and improving the stability and safety of the system.

[0045] More specifically, during the execution of temperature control decisions, the temperature changes of the battery pack and the system operating status are monitored in real time, and the temperature control system is adjusted based on the real-time data. For example, if the system temperature does not change as expected, the cooling intensity needs to be adjusted or the charging rate needs to be modified. The temperature control system needs to be dynamically adjusted during execution to cope with changes in the external environment or fluctuations in the system's own status. The real-time feedback mechanism ensures that the temperature control system can respond quickly according to actual conditions. Through real-time monitoring and feedback adjustment, the temperature control system can be continuously optimized during actual operation, so that the battery pack is always in a safe and efficient working state, thereby improving the response speed and stability of the overall system.

[0046] More specifically, after the temperature control decision is executed, the actual operating effect of the temperature control system is evaluated and optimized based on the evaluation results. For example, the execution effect of the temperature control decision is analyzed to determine whether the temperature control target is met and whether the energy consumption is in line with expectations. Evaluating the execution effect of the temperature control system is a necessary step to ensure continuous optimization of the system. If problems or deficiencies are found, further optimization and adjustment of the decision must be made to improve the execution effect of the system. Evaluation and optimization ensure that the temperature control system can be continuously improved, improve temperature control accuracy, reduce energy consumption, and increase the safety and life of the battery pack. Through continuous optimization, the system can adapt to future changes and challenges.

[0047] It is understandable that by collecting battery pack temperature control system information, defining temperature control target characteristics, building a multi-objective optimization model, and executing decisions, an efficient and accurate temperature control system can be achieved. The system can balance and optimize under multiple objectives, not only keeping the battery pack at the optimal operating temperature, but also controlling energy consumption and system costs, improving the safety and operating efficiency of the battery pack. Through real-time monitoring and feedback mechanisms, the temperature control system can be continuously improved to cope with various dynamic environmental changes.

[0048] The present invention provides a temperature control method for a new energy battery pack, which has the following beneficial effects: The present invention obtains real-time scene, external environment and battery monitoring feature information through multi-dimensional data monitoring, sets hard temperature control conditions based on this information, and performs predictive analysis to obtain predictive constraints. Adaptive temperature control analysis is performed based on the hard temperature control conditions and predictive constraints to generate temperature control target features. Temperature control decisions are generated through multi-objective optimization analysis and driven to execute by the temperature control system. This method improves the intelligence and adaptability of the temperature control system, ensures the efficient and safe operation of the battery pack in different working environments, extends its service life, and solves the problem in the prior art that a single temperature control mode cannot adapt to a specific working environment.

[0049] Preferably, the step of performing multi-dimensional data monitoring on the battery pack to obtain real-time scene information, external environment information, and battery monitoring feature sequence of the battery pack includes: S11: continuously collecting temperature and voltage data of the battery pack through a sensor group pre-deployed on the battery pack, and arranging the temperature data and voltage data at each moment in chronological order to generate a temperature monitoring sequence and a voltage monitoring sequence; S12: performing multi-dimensional analysis of time domain features, frequency domain features, and correlation features on the temperature monitoring sequence and the voltage monitoring sequence, respectively, to generate a basic feature monitoring sequence for the battery pack; S13: Sending a query command to the intelligent control module that controls the battery pack to query and obtain task information of the intelligent control module driving the battery pack, and performing semantic parsing and feature encoding on the task information to obtain real-time scenario information describing the current working scenario of the battery pack; wherein the working scenario includes a fast charging scenario, a normal charging scenario, an energy-saving power supply scenario, and a normal power supply scenario; S14: Continuously collecting various environmental data of the working environment of the battery pack through a pre-deployed environmental sensor group, performing vectorization expression and cluster analysis on the collected environmental data to obtain a number of environmental directional information, and substituting the environmental directional information into a pre-built external environment analysis model to obtain external environmental information of the battery pack; S15: According to the real-time scene information and the external environment information, the corresponding battery pack deep monitoring mode is retrieved from a pre-built database to perform deep feature mining on the basic feature monitoring sequence to generate a battery monitoring feature sequence that needs to be monitored under the current real-time scene information and external environment information.

[0050] Specifically, temperature and voltage data are collected through a sensor group deployed in the battery pack to continuously collect temperature and voltage data from the battery pack. The data is arranged in chronological order to generate temperature and voltage monitoring sequences. Real-time temperature and voltage data collection is the basis for monitoring the health of the battery pack. Recording this data in an orderly manner through time series provides a reliable data source for subsequent feature analysis. Continuous monitoring of temperature and voltage data allows for real-time capture of changes in the battery pack's operating status, early identification of abnormal fluctuations, and prevention of problems such as battery overheating or excessive discharge, ensuring the safe operation of the battery pack.

[0051] More specifically, a multi-dimensional analysis is performed on the temperature and voltage monitoring sequences, and a multi-dimensional analysis of the time domain features, frequency domain features and correlation features is performed on the temperature monitoring sequences and the voltage monitoring sequences respectively. These analysis methods may include mean, variance, spectrum analysis, etc. The time domain features and frequency domain features can reveal the periodicity and trend changes of the data, and the correlation features help to understand the mutual influence between temperature and voltage. Through comprehensive analysis, potential failures or performance degradation of the battery pack can be identified. Multi-dimensional analysis can not only fully understand the behavior patterns of the battery pack, but also efficiently extract important features to help the system judge the changing trend of the battery status, identify anomalies and take corresponding measures to ensure the efficient and safe operation of the battery.

[0052] More specifically, by controlling the intelligent control module of the battery pack to send an inquiry instruction, the current task information of the battery pack is queried, and the obtained task information is semantically parsed and feature-encoded to obtain the current working scenario status of the battery pack. The working status of the battery pack is closely related to the task of its control module. The working characteristics of the battery under different tasks (such as charging, discharging, standby, etc.) will be significantly different. Therefore, obtaining the battery's task information and parsing its semantics will help to determine the battery's working scenario. Through task information analysis, the battery's current working scenario (such as fast charging, normal charging, energy-saving power supply, etc.) can be accurately identified, thereby providing valuable context information for subsequent monitoring and optimization.

[0053] More specifically, a pre-deployed set of environmental sensors continuously collects various data about the battery pack's environment, such as temperature, humidity, air pressure, and light. This collected data is vectorized and subjected to cluster analysis. Environmental factors significantly impact battery performance, and environmental changes can lead to performance fluctuations or overheating. Therefore, real-time collection of environmental data and cluster analysis can help understand the impact of external factors on the battery. By monitoring environmental data in real time, dynamic information about external conditions can be obtained, providing more comprehensive context for battery monitoring. This information is crucial for subsequently optimizing temperature control strategies and extending battery life.

[0054] More specifically, the environmental data collected by the environmental sensor group is substituted into a pre-built external environment analysis model to analyze the impact of the external environment on the performance of the battery pack and obtain the external environmental information of the battery pack. Environmental factors directly affect the temperature, charge and discharge efficiency and other performance indicators of the battery pack. The environmental model helps to adjust the operating strategy of the battery pack in real time according to external data to ensure that the battery operates under optimal environmental conditions. Through external environmental analysis, the battery pack can dynamically adjust the working mode according to environmental changes to avoid performance degradation or safety problems caused by harsh environmental conditions, and further improve the adaptability and durability of the battery pack.

[0055] More specifically, based on real-time scene information and external environmental information, the corresponding battery pack deep monitoring mode is retrieved from a pre-built database, and deep feature mining is performed on the basic feature monitoring sequence to generate the battery monitoring feature sequence required for current monitoring. The performance of the battery pack is different in each working scenario and environmental conditions. Therefore, it is necessary to retrieve the appropriate deep monitoring mode according to the specific scenario for precise monitoring. This process helps to identify the current operating status of the battery and its potential problems. Deep feature mining can more accurately capture subtle changes in the battery pack in different scenarios, avoid missing potential signs of failure, and make timely adjustments when abnormalities are found to ensure the efficiency, stability and safety of the battery pack.

[0056] More specifically, based on real-time scene information, external environment information and the results of deep feature mining, the currently required battery monitoring feature sequences are generated. These feature sequences will serve as the basic data for subsequent monitoring and provide the system with real-time battery pack health information. The battery monitoring feature sequence is the key data for battery status monitoring. By generating and optimizing the monitoring feature sequence, the battery health status can be tracked in real time and anomalies can be discovered in time. By accurately generating the battery monitoring feature sequence, real-time feedback information can be provided to the temperature control system and battery management system (BMS), helping the system to respond quickly and adjust strategies to ensure the long-term, stable and safe operation of the battery.

[0057] It is understandable that through the continuous implementation of multiple steps, the battery pack can obtain multi-dimensional real-time monitoring information, including the battery pack's temperature and voltage data, working scene information, external environment information, etc. Each step is designed to comprehensively monitor the battery's operating status and make timely adjustments based on real-time data, thereby optimizing the battery pack's performance and extending its service life. This comprehensive data monitoring system can not only identify anomalies in a timely manner, but also effectively respond to environmental and task changes, providing strong support for the battery management system.

[0058] Preferably, the step of setting a hard temperature control condition for the battery pack according to the real-time scene information and the external environment information includes: S21: Retrieving a preset temperature limit of the battery pack, and performing a gradient dynamic safety threshold adjustment on the preset temperature limit according to the real-time scenario information to generate a plurality of dynamic adjustment gradients and corresponding safety weights; S22: performing environmental compensation analysis on the dynamic adjustment gradients at each level according to the external environmental information to generate environmental compensation factors corresponding to the dynamic adjustment gradients at each level, and adaptively correcting the dynamic adjustment gradients at each level and corresponding safety weights according to the environmental compensation factors to generate a plurality of dynamic adaptation limits of the battery pack and corresponding limit safety weights; S23: configuring extreme operating conditions for the battery pack according to the real-time scenario information and the external environment information, performing simulated stress tests on each of the dynamic adaptation limits based on the extreme operating conditions, and revising the limit safety weight of each of the dynamic adaptation limits according to the results; S24: performing weighted fusion of the dynamic adaptive limits based on the revised limit safety weights, and configuring a safety margin to generate a hard temperature control condition for the battery pack.

[0059] Specifically, the preset temperature limit of the battery pack is first retrieved, and the preset temperature limit is dynamically adjusted in a gradient manner according to the real-time scene information to generate a number of dynamic adjustment gradients and corresponding safety weights. The temperature limit of the battery pack is usually pre-set, but different working scenarios require different temperature control standards. By dynamically adjusting the temperature limit according to the real-time scene information, it can be ensured that the battery is within a safe operating temperature range under various operating conditions. This gradient adjustment can flexibly adjust the temperature limit according to the real-time status of the battery, enhance the adaptability of the battery pack under different working conditions, and avoid performance problems or safety risks caused by over-reliance on fixed temperature limits.

[0060] More specifically, based on external environmental information, an environmental compensation analysis is performed on each dynamic adjustment gradient. Environmental compensation factors corresponding to each level of dynamic adjustment gradient are generated. Then, based on the environmental compensation factors, adaptive corrections are made to the dynamic adjustment gradients and the corresponding safety weights, generating dynamic adaptive limits and corresponding limit safety weights. The external environment (such as temperature and humidity) directly affects the battery's operating efficiency and temperature variations. Therefore, environmental compensation is key to ensuring the stable operation of battery packs in different environments. Environmental compensation analysis can reduce the adverse effects of the external environment on battery performance, ensuring that the battery pack can operate stably under a wider range of environmental conditions while maintaining the safety and reliability of the temperature control system.

[0061] More specifically, based on real-time scenario information and external environmental information, extreme operating conditions are configured for the battery pack. Based on these extreme operating conditions, stress tests are performed to simulate the working performance of the battery pack under extreme conditions. The limit safety weights of each dynamic adaptation limit are corrected based on the test results. In actual operation, the battery pack may face extreme operating conditions (such as high temperature, high load, etc.), which may cause battery overheating, failure or even damage. Therefore, it is very important to simulate extreme operating conditions and test the battery's coping capabilities. Stress testing can help foresee problems that may arise in the battery under extreme conditions and adjust the temperature control limits according to the test results to ensure that the battery can operate safely and stably under the worst operating conditions, thereby reducing the risk of battery failure.

[0062] More specifically, based on the revised limit safety weight, each dynamic adaptive limit is weightedly integrated. At the same time, in order to ensure that the battery pack can cope with uncertain factors, a certain safety margin is configured. This process can generate the rigid temperature control conditions of the battery pack. A single temperature limit may not fully guarantee the safety of the battery pack. Therefore, it is necessary to weightedly integrate each dynamic adaptive limit according to its importance and safety. In addition, in order to cope with emergencies, adding a safety margin can further reduce the risk of the temperature control system. The weighted integrated temperature control limit can better balance the safety and performance of the battery under different working conditions. By configuring the safety margin, the system has higher fault tolerance in actual operation, avoiding potential risks caused by overly strict or loose temperature control.

[0063] More specifically, through the above steps, hard temperature control conditions suitable for the battery pack are finally generated. These conditions include dynamically adjusted temperature limits, corrected safety weights, weighted limit fusion results, and safety margins, forming a comprehensive temperature control strategy for the battery pack. Hard temperature control conditions are the basis for safe and stable operation of the battery pack. They ensure that the battery can remain within a safe temperature range in various working environments and scenarios. Only through systematic and scientific temperature control strategies can the battery pack maximize its service life and ensure safety. Hard temperature control conditions provide a detailed and precise temperature control strategy that can effectively control temperature under different working conditions and environmental conditions, thereby improving the safety, stability and life of the battery. This strategy helps prevent dangers such as overcharging and discharging, overheating, and ensure the efficient operation of the battery pack in various working scenarios.

[0064] It is understandable that through the above steps, by comprehensively considering real-time scene information, external environmental information and extreme working conditions, it is possible to formulate highly adaptable and scientifically reasonable battery pack hard temperature control conditions. This process effectively combines dynamic adjustment, environmental compensation, extreme working condition simulation and safety margin configuration to ensure that the battery pack can operate stably and safely under different conditions and maximize the battery life.

[0065] Preferably, the step of acquiring the extended reference information of the battery pack according to the real-time scene information and performing predictive analysis in combination with the battery monitoring feature sequence to obtain prediction constraints includes: S301: When the real-time scene information is a power supply scene, obtaining remaining power data, running trajectory data, and target location data of the new energy vehicle equipped with the battery pack as extended reference information; S302: Analyzing theoretical power consumption of the battery pack based on the extended reference information to obtain theoretical remaining power of the battery pack after the new energy vehicle reaches a target location; S303: Performing feature analysis of power loss influencing factors on the battery monitoring feature sequence to obtain power loss influencing features fed back in the battery monitoring feature sequence; S304: Acquiring temperature control system information configured for the battery pack, simulating various levels of temperature control measures for the battery pack based on the temperature control system information, and generating temperature change effect characteristics and temperature control power consumption characteristics of the battery pack corresponding to the various levels of temperature control measures; S305: Adaptively correcting the power loss impact characteristic based on the temperature change effect characteristic of the temperature control measure to adapt to the temperature change, and combining the characteristic with the temperature control power consumption characteristic to perform a predictive analysis on the theoretical remaining power corresponding to the temperature control measure to obtain an estimated remaining power of the battery pack corresponding to the temperature control measure. S306: Based on the temperature control measures at each level and the corresponding estimated remaining power, the battery pack is analyzed for power loss conditions of the temperature control measures to generate expected power loss characteristics of the battery pack for each level of temperature control measures, and based on the expected power loss characteristics of the battery pack for each level of temperature control measures, expected execution weights of the battery pack for each level of temperature control measures when the remaining power data is each value are generated, which are used together as prediction constraints.

[0066] Specifically, when the real-time scene information is a power supply scene, the remaining power data, operating trajectory data, and target location data of the new energy vehicle equipped with the battery pack are obtained as extended reference information. In the power supply scene, the remaining power, operating trajectory and target location of the battery are important factors affecting battery performance and consumption. By obtaining this information, we can fully understand the actual working status of the battery in a specific scene and provide basic data for subsequent predictive analysis. This step provides the necessary external data for the battery pack's power consumption prediction, making the analysis process more accurate. Through these extended reference information, we can estimate the battery's power consumption and remaining power in the future to ensure that the battery pack can complete the task as expected.

[0067] More specifically, based on the expanded reference information, a theoretical power consumption analysis of the battery pack is performed to obtain the theoretical remaining power of the battery pack after the new energy vehicle reaches the target location. The theoretical consumption analysis of the battery pack can help understand the energy consumption of the battery pack before the target location is reached. By analyzing the remaining power and the target location, it can be predicted whether the battery is sufficient to support the vehicle to complete the task. This step helps to accurately predict the changes in battery power during driving through consumption analysis, ensure reasonable energy management of the battery pack throughout the journey, and avoid the battery from failing to reach the target location due to insufficient power.

[0068] More specifically, the characteristics of the factors affecting power loss are analyzed in the battery monitoring feature sequence to obtain the power loss influencing characteristics fed back in the battery monitoring feature sequence. The battery monitoring feature sequence can reflect the health status and power loss of the battery in actual operation. By analyzing these characteristics, the key factors of power loss can be identified, providing a basis for the subsequent power prediction and temperature control measures. By analyzing the battery monitoring characteristics, the patterns and factors of battery loss can be more accurately grasped, which helps to optimize the battery management strategy, improve battery utilization efficiency, and extend the battery life.

[0069] More specifically, the temperature control system information configured for the battery pack is obtained, and temperature control measures of various levels are simulated for the battery pack based on the temperature control system information to generate temperature change effect characteristics and temperature control power consumption characteristics for the battery pack corresponding to the temperature control measures of various levels. The temperature control measures of the battery directly affect the operating temperature of the battery, and the temperature in turn affects the power consumption and performance of the battery. Therefore, different temperature control measures need to be simulated to evaluate their impact on battery performance and power consumption. The simulation of temperature control measures can provide temperature change and power consumption information of the battery under different temperature control strategies, helping to optimize the battery's temperature control strategy to improve the battery's energy efficiency and extend its service life.

[0070] More specifically, based on the temperature change effect characteristics of the temperature control measures, the power loss impact characteristics are adaptively corrected for temperature changes. At the same time, combined with the temperature control power consumption characteristics, a predictive analysis of the theoretical remaining power is performed to obtain the estimated remaining power of the battery pack under temperature control measures. Temperature changes will directly affect the power consumption of the battery. Therefore, it is necessary to adaptively correct the power loss according to the impact of the temperature control measures to ensure that the prediction results are more accurate. Through adaptive correction, the temperature control effect and battery loss characteristics can be combined to more accurately predict the remaining power of the battery, providing reliable data support for actual operations and avoiding excessive battery loss due to temperature changes.

[0071] More specifically, based on the temperature control measures at each level and the corresponding estimated remaining power, the battery pack's power loss status of the temperature control measures is analyzed to generate the expected power loss characteristics of the battery pack for each level of temperature control measures. Each temperature control measure has a different impact on the battery's power loss. Therefore, it is necessary to analyze the power loss characteristics under different temperature control measures to optimize the battery pack's temperature control strategy and reduce unnecessary power consumption. Through the power loss status analysis, specific temperature control strategies can be provided for different working scenarios to ensure optimal energy utilization of the battery pack in different environments and reduce the risk of excessive consumption.

[0072] More specifically, based on the expected power loss characteristics of the battery pack corresponding to each level of temperature control measures, the expected execution weights of the battery pack corresponding to each level of temperature control measures when the remaining power data is each numerical value are generated as prediction constraints. By combining the expected power loss characteristics and the execution weights, a reasonable operating range can be set for the battery pack to ensure that the battery pack can operate efficiently and safely under different remaining power and temperature control conditions. The prediction constraints provide a clear decision-making basis for the battery management system, and can dynamically adjust the temperature control strategy according to the real-time status of the battery to avoid insufficient power or excessive consumption due to insufficient prediction, thereby improving the utilization efficiency and safety of the battery pack.

[0073] It is understandable that the above steps achieve accurate prediction of the remaining power of the battery pack through comprehensive analysis of real-time scene information and battery monitoring data. Through adaptive correction of temperature control measures, characteristic analysis of power loss, and environmental adaptability analysis, it ensures that the battery pack can be optimized and managed under different conditions, improving battery performance and service life. The generated prediction constraints provide strong decision-making support for the battery management system, helping the system maintain optimal state during operation.

[0074] Preferably, the step of acquiring the extended reference information of the battery pack according to the real-time scene information and performing predictive analysis in combination with the battery monitoring feature sequence to obtain prediction constraints includes: S3001: When the real-time scene information is a charging scene, obtaining current power data and charging efficiency data of the new energy vehicle equipped with the battery pack as extended reference information; S3002: Performing a predictive analysis of an expected charging time of the battery pack based on the extended reference information to obtain an expected charging time of the battery pack; S3003: Performing feature analysis of power increase influencing factors on the battery monitoring feature sequence to obtain power increase influencing features fed back in the battery monitoring feature sequence, and correcting the expected charging time based on the power increase influencing features to generate a corrected charging time. S3004: Obtain the temperature control system information configured for the battery pack, simulate the temperature control measures of each level for the battery pack according to the temperature control system information, perform corresponding variation simulation on the corrected charging time, and generate the expected execution weights of the temperature control measures of each level corresponding to the current power data of the battery pack for each value based on the variation simulation results, which are used together as prediction constraints.

[0075] Specifically, when the real-time scene information is a charging scene, the current power data and charging efficiency data of the new energy vehicle equipped with the battery pack are obtained as extended reference information. In the charging scene, the current power and charging efficiency of the battery are key factors affecting the charging time. By obtaining these two data, accurate initial data can be provided for subsequent charging time prediction and optimization. By collecting the current power and charging efficiency data, accurate initial information can be provided for the time estimation of the charging process, ensuring that the analysis results are consistent with the actual charging situation and avoiding unnecessary errors.

[0076] More specifically, based on the expanded reference information, a predictive analysis of the expected charging time of the battery pack is performed to obtain the expected charging time of the battery pack. The charging time of the battery pack directly depends on the current power level and the charging efficiency. Through a comprehensive analysis of these two factors, the time required for charging can be predicted and the charging process can be effectively planned. This step quantifies the charging process of the battery pack and can predict the battery charging time in advance, helping users to reasonably arrange the charging time and avoid overcharging or insufficient charging.

[0077] More specifically, the battery monitoring feature sequence is analyzed for characteristics of factors affecting power increase to obtain the power increase influencing characteristics fed back in the battery monitoring feature sequence. During the charging process, the battery's charging efficiency is not only affected by the current power level, but is also closely related to factors such as battery health and temperature. By analyzing the battery monitoring feature sequence, these factors affecting charging efficiency can be identified. This step can deeply explore the factors affecting battery health and charging status, improve the accuracy of charging time prediction, and by understanding the impact of battery health and other external factors, more accurate corrections can be made to the charging time.

[0078] More specifically, the expected charging time is corrected according to the characteristics affecting the increase in battery power to generate a corrected charging time. The battery health status and other factors affecting charging efficiency will affect the rate of increase in battery power during the charging process. Therefore, the original charging time must be corrected according to the characteristics affecting the increase in battery power to obtain a more accurate charging time estimate. This step corrects the charging time deviation caused by battery health and other factors, making the charging time prediction more in line with actual conditions, which helps users and the system make more reasonable time arrangements during the charging process.

[0079] More specifically, the temperature control system information configured for the battery pack is obtained, and the temperature control measures of various levels are simulated for the battery pack based on the temperature control system information to perform corresponding variation simulations on the corrected charging time. The temperature control system will affect the temperature of the battery during the charging process, and the temperature directly affects the charging efficiency. By simulating different temperature control measures, their impact on the charging time can be evaluated, and then variation simulations can be performed. By simulating the impact of different temperature control measures on the charging time, the charging performance of the battery under different temperature control conditions can be accurately predicted. In this way, the charging time can be adjusted according to the actual temperature of the battery and the management strategy to ensure the efficiency and safety of the charging process.

[0080] More specifically, based on the results of the change simulation, the expected execution weights of the temperature control measures at each level corresponding to the current power data of the battery pack are generated when the current power data is various numerical values, which are used together as prediction constraints. By simulating the changes in charging time caused by temperature control measures, a weight can be assigned to each temperature control measure to indicate the degree of its impact on the charging process. Combined with the remaining power of the battery pack, the expected execution weights under different temperature control conditions can be generated. The generated execution weights provide the battery management system with accurate prediction constraints, which helps to dynamically adjust the temperature control strategy during the charging process to improve charging efficiency and ensure charging safety and battery health.

[0081] It can be understood that, by combining the above steps, the impact of charging time and temperature control measures is comprehensively predicted, and finally an operational prediction constraint condition is generated. During the charging process, the interaction of multiple factors such as temperature control, charging efficiency, and battery health status needs to be comprehensively analyzed to determine the optimization plan of the charging process. By predicting the constraints, the charging strategy can be dynamically adjusted to improve the efficiency and safety of the charging process. This step ensures the efficient management of the charging process and the protection of battery health. Through reasonable temperature control measures and charging time adjustments, the charging process is optimized, the battery life is extended, and energy waste is reduced. Through multi-dimensional analysis of charging scenarios, including real-time scenario information, extended reference information, analysis of the impact characteristics of increased power, and simulation of temperature control measures, the charging time can be accurately predicted and an effective temperature control strategy can be formulated. The prediction constraints finally generated provide reliable decision support for the battery management system, ensuring the efficiency, accuracy and safety of the battery charging process.

[0082] Preferably, the step of performing adaptive temperature control analysis on the battery pack based on the hard temperature control condition and the prediction constraint condition to generate a temperature control target feature includes: S41: collecting real-time temperature data and real-time power data of the battery pack, and performing a threshold analysis on the real-time temperature data based on the hard temperature control condition to generate a threshold breach risk index of the real-time temperature data relative to the hard temperature control condition; S42: configuring first execution weights for each level of temperature control measures corresponding to the battery pack based on a risk index of the real-time temperature data exceeding a threshold of the hard temperature control condition, and performing expected execution weight analysis of each level of temperature control measures on the real-time power data according to the prediction constraint condition to configure second execution weights for each level of temperature control measures corresponding to the battery pack; S43: Performing feature conversion and concatenation processing on the first execution weights and the second execution weights corresponding to the temperature control measures at each level to generate a first priority curve and a second priority curve, and performing superposition analysis on the first priority curve and the second priority curve to generate a comprehensive priority curve; S44: Extracting the characteristics of the curve change trend based on the comprehensive priority curve to prioritize the temperature control measures, and simulating the temperature control effect of the battery pack for each temperature control measure according to the priority ranking, so as to use the most prioritized simulation effect as the temperature control target feature.

[0083] Specifically, the real-time temperature data and real-time power data of the battery pack are collected, and a threshold analysis is performed on the temperature data based on the hard temperature control conditions to generate a risk index for the temperature data to break through the threshold of the hard conditions. Hard temperature control conditions (such as the upper / lower limit of the safety temperature) are usually set by the manufacturer or standard and must be strictly followed. The risk index assessment can quantify the urgency of the battery breaking through the safe temperature zone, form an early warning indicator for temperature control response, support the dynamic switching strategy of the temperature control system to avoid risks, and provide a quantitative basis for the subsequent temperature control weight calculation. More specifically, based on the above-mentioned threshold breakthrough risk index, a first execution weight is assigned to each level of temperature control measures corresponding to the battery pack (various cooling modes and corresponding cooling intensities). The higher the weight, the more urgent and the higher the priority. The temperature control response should prioritize meeting safety requirements. When the risk is high, more intense measures must be quickly activated. The first weight reflects the risk-oriented temperature control priority.

[0084] More specifically, based on the prediction constraints, the real-time power data is analyzed, and the second execution weight of each level of temperature control measures is calculated based on the temperature control simulation weight distribution under different power ranges. The battery has different tolerances to temperature changes under different SOC (State of Charge), for example, it is more sensitive at high power, and temperature control can be relatively loose at low power. This step reflects the power-driven temperature control adjustment mechanism, avoids redundant consumption of temperature control resources, optimizes energy efficiency, achieves a balance between economy and safety, and supports precise temperature control strategy execution on demand. More specifically, the first execution weight and the second execution weight of each level of temperature control measures are normalized, smoothed or nonlinearly mapped, and other feature conversion processes are performed to generate: the first priority curve (risk-driven) and the second priority curve (power-driven). The two are then connected and compared. Direct comparison of weights has dimensional or curve trend differences. Through feature conversion, the two types of weights are made comparable and fused in a unified space, achieving a unified expression of the two strategies and providing a temperature control response trend in the form of a curve, which is convenient for dynamic analysis of the system. More specifically, the two priority curves mentioned above are superimposed and analyzed (such as weighted fusion, dynamic adjustment factors, etc.) to generate a comprehensive priority curve that comprehensively reflects the comprehensive priority of each temperature control measure under the current state, integrates the priorities of the two dimensions of safety and performance, provides a dynamic sorting basis for the optimal temperature control measure sequence, embodies the multi-objective decision-making optimization idea, and provides accurate input for downstream control strategies.

[0085] More specifically, the dynamic change trend features of the comprehensive priority curve (such as slope, inflection point, stable interval, etc.) are extracted, and the priority of each temperature control measure is sorted based on the time series features. The change trend reveals which temperature control measures should be activated immediately and which can be delayed or suspended, reflecting time sensitivity and strategy rationality, realizing dynamic scheduling and sorting of temperature control strategies, supporting progressive control switching between multiple strategies, and improving the real-time intelligent response capability of the temperature control system. More specifically, based on priority, the battery pack temperature control effect of each temperature control measure is simulated (such as thermal management model, energy consumption simulation, etc.), the overall effect of each combination of measures is evaluated, and the result with the best effect is output as the temperature control target feature. The simulation ensures that the selected temperature control measure not only has theoretical priority, but also can achieve the best temperature control benefit in practice. The output can be used for the execution layer's control target, thereby improving the matching ability of the vehicle's thermal management system to the battery.

[0086] Preferably, the step of performing a multi-objective optimization analysis of the overall temperature control system on the temperature control target characteristics based on the temperature control system information of the battery pack to obtain a temperature control decision includes: S51: parsing a specific execution mode of the temperature control target feature according to information of the temperature control system in which the battery pack is located, so as to obtain a preparatory execution mode for the battery pack to execute the temperature control target feature; S52: collecting real-time temperature information and temperature requirement information of other key locations of the overall system where the battery pack is deployed through the temperature control system where the battery pack is located, simulating temperature changes of the real-time temperature information of each key location according to the preparatory execution mode, and evaluating the value of the overall temperature control system based on the preparatory execution mode in combination with the temperature requirement information; S53: Using the result of the value assessment as a supervision condition, adjusting specific execution parameters of the preparatory execution mode to obtain a temperature control decision.

[0087] Specifically, based on the temperature control system information of the battery pack, the specific execution method of the temperature control target characteristics is analyzed. The goal of this step is to define the preliminary execution mode of the temperature control target characteristics (such as temperature control strategy, adjustment method, etc.) according to the working conditions, hard temperature control conditions and prediction constraints of the battery pack. The execution method of the temperature control target characteristics needs to be refined in combination with the real-time working status and environmental conditions of the battery pack. This step determines the temperature control strategy of the battery pack under different environmental and load conditions by analyzing the temperature control target characteristics, ensures optimized execution, provides a preliminary execution mode of the temperature control strategy, avoids unnecessary repeated calculations and redundant decisions, makes the parameter adjustment and optimization in subsequent decision-making steps clearer, and improves the responsiveness of the system.

[0088] More specifically, the temperature control system where the battery pack is located is used to collect real-time temperature information and temperature demand information from other key locations in the overall system where the battery pack is deployed. Based on the preparatory execution mode, the temperature change simulation is performed on the real-time temperature information of each key location. Combined with the temperature demand information of the location, the preparatory execution mode is adjusted and optimized. The temperature management of the battery pack not only depends on a single area, but also needs to consider the synergy of the overall temperature control system. The temperature and demand information of key locations (such as radiators, charging modules, etc.) provides a background for the dynamic changes of the system, which helps to optimize the global temperature control. By simulating the temperature changes at different key locations, the temperature control balance of the entire system is ensured. Combined with the temperature demand information, the performance requirements of the system under different working conditions are accurately reflected, providing a real basis for decision-making.

[0089] More specifically, based on the results of the temperature change simulation and combined with the temperature demand information, the value of the overall temperature control system of the preparatory execution mode is evaluated. The evaluation criteria may include the effectiveness of the temperature control effect, system energy efficiency, response speed and other relevant factors. In the battery pack temperature control system, different execution methods will bring different effects and benefits. Through comprehensive evaluation, the advantages and disadvantages of different execution modes can be quantitatively analyzed to ensure that the final temperature control decision can find the best balance between efficiency and safety. Through value evaluation, clear quantitative standards are provided for temperature control decisions to avoid over-reliance on a certain execution mode, thereby achieving multi-objective optimization, providing a comprehensive system evaluation result, and supporting the selection and optimization of different modes.

[0090] More specifically, the specific execution parameters of the preparatory execution mode are adjusted based on the value assessment results of the temperature control system as supervision conditions. The goal of the adjustment is to make the preparatory execution mode more compatible with the temperature control target characteristics to optimize the performance of the overall temperature control system. Adjusting the execution parameters can flexibly adjust the temperature control strategy according to actual needs, so that the system is always in the optimal temperature control state. By adjusting the execution parameters under the guidance of value assessment, the temperature and energy efficiency can be controlled more accurately, the execution parameters of the temperature control system can be dynamically adjusted, the flexibility of the temperature control response can be improved, and it can be ensured that the temperature control strategy can adapt to different working conditions and needs, thereby improving the accuracy and adaptability of the temperature control effect.

[0091] More specifically, after adjusting the execution parameters, the final temperature control decision is generated. This decision will serve as the control input of the battery pack temperature control system to guide the execution of temperature control measures during actual operation. The temperature control decision is the final product of the entire optimization and analysis process and is the core of ensuring the safe and efficient operation of the battery pack. The final decision needs to ensure that the temperature control measures can respond to the needs of the battery pack and the overall system, generate the optimal temperature control decision, ensure that the system operates in a safe and efficient state, support precise temperature control management of the entire system, and improve the service life and performance of the battery pack.

[0092] Reference Figure 2 As shown, in a second aspect, the present invention provides a temperature control system for a new energy battery pack, which is used to implement a temperature control method for a new energy battery pack according to any one of the first aspects, comprising: A data monitoring module is used to perform multi-dimensional data monitoring on the battery pack to obtain real-time scene information, external environment information, and battery monitoring feature sequence of the battery pack; a temperature control limiting module, configured to set hard temperature control conditions for the battery pack based on the real-time scene information and the external environment information; A prediction constraint module, configured to obtain extended reference information of the battery pack based on the real-time scenario information, and perform predictive analysis in combination with the battery monitoring feature sequence to obtain prediction constraint conditions; a target analysis module, configured to perform adaptive temperature control analysis on the battery pack based on the hard temperature control conditions and the prediction constraints to generate a temperature control target feature; The temperature control decision module is used to perform a multi-objective optimization analysis of the overall temperature control system on the temperature control target characteristics according to the temperature control system information of the battery pack, obtain a temperature control decision and drive the temperature control system to execute the temperature control decision.

[0093] In this embodiment, for the specific implementation of each module in the above system embodiment, please refer to the above method embodiment, which will not be repeated here.

[0094] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A temperature control method for a new energy battery pack, characterized in that: include: Perform multi-dimensional data monitoring on the battery pack to obtain real-time scene information, external environment information, and battery monitoring feature sequence of the battery pack; Setting hard temperature control conditions for the battery pack according to the real-time scene information and the external environment information; Acquire extended reference information of the battery pack according to the real-time scenario information, and perform predictive analysis in combination with the battery monitoring feature sequence to obtain prediction constraints; performing an adaptive temperature control analysis on the battery pack based on the hard temperature control condition and the prediction constraint condition to generate a temperature control target feature; According to the temperature control system information of the battery pack, a multi-objective optimization analysis of the overall temperature control system is performed on the temperature control target characteristics to obtain a temperature control decision and drive the temperature control system to execute the temperature control decision.

2. The temperature control method of the new energy battery pack according to claim 1, characterized in that: The steps of performing multi-dimensional data monitoring on a battery pack to obtain real-time scene information, external environment information, and a battery monitoring feature sequence of the battery pack include: The sensor group pre-deployed on the battery pack continuously collects temperature and voltage data of the battery pack, and arranges the temperature data and voltage data at each moment in chronological order to generate a temperature monitoring sequence and a voltage monitoring sequence; Performing multi-dimensional analysis of time domain features, frequency domain features, and correlation features on the temperature monitoring sequence and the voltage monitoring sequence, respectively, to generate a basic feature monitoring sequence for the battery pack; Sending a query command to the intelligent control module that controls the battery pack to query and obtain task information of the intelligent control module driving the battery pack, and performing semantic parsing and feature encoding on the task information to obtain real-time scenario information describing the current working scenario of the battery pack; wherein the working scenario includes a fast charging scenario, a normal charging scenario, an energy-saving power supply scenario, and a normal power supply scenario; Using a pre-deployed environmental sensor group, various environmental data of the working environment of the battery pack are continuously collected, and the collected environmental data are vectorized and clustered to obtain a number of environmental directional information. By substituting the environmental directional information into a pre-built external environment analysis model, the external environment information of the battery pack is obtained; According to the real-time scene information and the external environment information, the corresponding battery pack deep monitoring mode is retrieved from a pre-built database to perform deep feature mining on the basic feature monitoring sequence to generate the battery monitoring feature sequence that needs to be monitored under the current real-time scene information and external environment information.

3. The temperature control method of the new energy battery pack according to claim 1, characterized in that: The step of setting a hard temperature control condition for the battery pack according to the real-time scene information and the external environment information includes: Retrieving a preset temperature limit of the battery pack, and performing a gradient dynamic safety threshold adjustment on the preset temperature limit according to the real-time scenario information to generate a plurality of dynamic adjustment gradients and corresponding safety weights; performing an environmental compensation analysis on the dynamic adjustment gradients at each level according to the external environmental information to generate environmental compensation factors corresponding to the dynamic adjustment gradients at each level, and adaptively correcting the dynamic adjustment gradients at each level and corresponding safety weights according to the environmental compensation factors to generate a plurality of dynamic adaptation limits of the battery pack and corresponding limit safety weights; configuring extreme operating conditions for the battery pack according to the real-time scenario information and the external environment information, performing simulated stress tests on each of the dynamic adaptation limits based on the extreme operating conditions, and revising the limit safety weight of each of the dynamic adaptation limits according to the results; The dynamic adaptive limits are weightedly integrated based on the revised limit safety weights, and a safety margin is configured to generate a hard temperature control condition for the battery pack.

4. The temperature control method of the new energy battery pack according to claim 1, characterized in that: The steps of acquiring extended reference information of the battery pack according to the real-time scenario information and performing predictive analysis in combination with the battery monitoring feature sequence to obtain prediction constraints include: When the real-time scene information is a power supply scene, the remaining power data, the running trajectory data, and the target location data of the new energy vehicle equipped with the battery pack are obtained as the expanded reference information; Analyzing the theoretical power consumption of the battery pack based on the extended reference information to obtain a theoretical remaining power of the battery pack after the new energy vehicle reaches a target location; Performing feature analysis of power loss influencing factors on the battery monitoring feature sequence to obtain power loss influencing features fed back in the battery monitoring feature sequence; Acquiring temperature control system information configured for the battery pack, simulating various levels of temperature control measures for the battery pack based on the temperature control system information, and generating temperature change effect characteristics and temperature control power consumption characteristics of the battery pack corresponding to the various levels of temperature control measures; Adaptively correcting the power loss impact characteristics based on the temperature change effect characteristics of the temperature control measures to account for temperature changes, and combining the characteristics with the temperature control power consumption characteristics to perform a predictive analysis of the theoretical remaining power corresponding to the temperature control measures to obtain an estimated remaining power of the battery pack corresponding to the temperature control measures; Based on the temperature control measures at each level and the corresponding inferred remaining power, the power loss status of the temperature control measures of the battery pack is analyzed to generate the expected power loss characteristics of the battery pack for each level of temperature control measures, and based on the expected power loss characteristics of the battery pack corresponding to the temperature control measures at each level, the expected execution weights of the battery pack corresponding to each level of temperature control measures when the remaining power data is each numerical value are generated, which are collectively used as prediction constraints.

5. The temperature control method of the new energy battery pack according to claim 1, characterized in that: The steps of acquiring extended reference information of the battery pack according to the real-time scenario information and performing predictive analysis in combination with the battery monitoring feature sequence to obtain prediction constraints include: When the real-time scene information is a charging scene, obtaining current power data and charging efficiency data of the new energy vehicle equipped with the battery pack as expanded reference information; performing a predictive analysis of an expected charging time of the battery pack based on the extended reference information to obtain the expected charging time of the battery pack; performing feature analysis of power increase influencing factors on the battery monitoring feature sequence to obtain power increase influencing features fed back in the battery monitoring feature sequence, and correcting the expected charging time based on the power increase influencing features to generate a corrected charging time; Obtain information about the temperature control system configured for the battery pack, simulate various levels of temperature control measures for the battery pack based on the temperature control system information, perform corresponding variation simulation on the corrected charging time, and generate expected execution weights of the temperature control measures at various levels corresponding to the battery pack when the current power data is various numerical values ​​based on the variation simulation results, which are used together as prediction constraints.

6. The temperature control method of the new energy battery pack according to any one of claims 4 or 5, characterized in that: The step of performing adaptive temperature control analysis on the battery pack based on the hard temperature control condition and the prediction constraint condition to generate a temperature control target feature includes: collecting real-time temperature data and real-time power data of the battery pack, and performing a threshold analysis on the real-time temperature data based on the hard temperature control condition to generate a threshold breach risk index of the real-time temperature data relative to the hard temperature control condition; Based on a threshold breach risk index of the real-time temperature data from the hard temperature control condition, a first execution weight is configured for each level of temperature control measures corresponding to the battery pack; and according to the prediction constraint condition, the expected execution weights of each level of temperature control measures are analyzed for the real-time power data to configure a second execution weight for each level of temperature control measures corresponding to the battery pack; Performing feature conversion and concatenation on the first execution weights and second execution weights corresponding to each level of temperature control measures to generate a first priority curve and a second priority curve, and superimposing and analyzing the first priority curve and the second priority curve to generate a comprehensive priority curve; Based on the comprehensive priority curve, the curve change trend feature extraction is performed to prioritize the temperature control measures, and the battery pack temperature control effect of each temperature control measure is simulated according to the priority ranking, so that the most prioritized simulation effect is used as the temperature control target feature.

7. The temperature control method of the new energy battery pack according to claim 1, characterized in that: The steps of performing a multi-objective optimization analysis of the overall temperature control system on the temperature control target characteristics according to the temperature control system information of the battery pack to obtain a temperature control decision include: parsing a specific execution mode of the temperature control target feature according to information of the temperature control system in which the battery pack is located, so as to obtain a preliminary execution mode for the battery pack to execute the temperature control target feature; The temperature control system where the battery pack is located collects real-time temperature information and temperature demand information of other key locations of the overall system where the battery pack is deployed, and simulates temperature changes of the real-time temperature information of each key location according to the preparatory execution mode, so as to evaluate the value of the overall temperature control system of the preparatory execution mode in combination with the temperature demand information; The result of the value assessment is used as a supervision condition to adjust specific execution parameters of the preparatory execution mode to obtain a temperature control decision.

8. A temperature control system for a new energy battery pack, characterized in that: A temperature control method for a new energy battery pack according to any one of claims 1 to 7, comprising: A data monitoring module is used to perform multi-dimensional data monitoring on the battery pack to obtain real-time scene information, external environment information, and battery monitoring feature sequence of the battery pack; a temperature control limiting module, configured to set hard temperature control conditions for the battery pack based on the real-time scene information and the external environment information; A prediction constraint module, configured to obtain extended reference information of the battery pack based on the real-time scenario information, and perform predictive analysis in combination with the battery monitoring feature sequence to obtain prediction constraint conditions; a target analysis module, configured to perform adaptive temperature control analysis on the battery pack based on the hard temperature control conditions and the prediction constraints to generate a temperature control target feature; The temperature control decision module is used to perform a multi-objective optimization analysis of the overall temperature control system on the temperature control target characteristics according to the temperature control system information of the battery pack, obtain a temperature control decision and drive the temperature control system to execute the temperature control decision.

Images