ATS cooling system control method based on vehicle VCU control

Abstract

The invention discloses an ATS cooling system control method based on whole vehicle VCU control, and aims to achieve intelligent scheduling of a cooling system by optimizing cooperative control of an engine, a battery and a transmission so as to meet the requirements of modern vehicles on the aspects of high efficiency, high reliability and low energy consumption, and achieve intelligent scheduling of the cooling system according to the temperature control requirement difference of different parts. A multi-objective optimization scheduling strategy is provided, the flow of cooling liquid, the rotating speed of a fan and the pump speed can be adjusted in real time, and the working temperature of an engine, a battery and a transmission is accurately controlled. Through a self-adaptive control algorithm and a real-time feedback mechanism, the cooling system can be dynamically adjusted according to the real-time working condition of the vehicle and the environment change, the response speed of the system is increased, the energy consumption is reduced, and overcooling is avoided. And a fault early warning and predictive maintenance method is adopted, so that the reliability and the safety of the system are effectively improved. By optimizing cooperative work of the cooling system, the energy efficiency of the vehicle can be improved, the service life of parts is prolonged, and energy loss is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile cooling system control, and in particular to an ATS cooling system control method based on whole vehicle VCU control. Background Art

[0002] The engine is prone to generate too much heat under high load, long-term operation, rapid acceleration and other conditions, resulting in excessive engine temperature. Overheating may cause engine damage, performance degradation and even shutdown. Traditional cooling systems often rely on preset working modes, which may cause excessive operation of coolant flow, fan speed, etc., resulting in unnecessary energy consumption. When the cooling system overworks unnecessarily, especially under low load conditions, the cooling system will waste a lot of energy, thereby increasing the overall energy consumption of the vehicle. The engine, battery and transmission have different temperature requirements during operation. For example, the engine requires strong cooling under high load, while the battery requires a certain temperature range to maintain optimal performance, and the transmission also needs to avoid overheating. Since the cooling requirements of different components are independent and variable, how to balance these requirements becomes a challenge. Difficulty in cooling system coordination: The cooling system of the vehicle is usually designed and operated independently, which may make it difficult to coordinate the work of different cooling systems under complex working conditions, increasing the complexity of system control. Summary of the invention

[0003] A method for controlling an ATS cooling system based on a vehicle VCU control comprises the following steps: S1. Data collection and sensor monitoring: Collect data from various sensors, including engine, electronic control unit, battery, and coolant temperature, obtain the vehicle's temperature status in real time, monitor external ambient temperature and driving condition information, provide auxiliary data through the vehicle's environmental perception system, and collect battery temperature, charging status, and discharge load data to provide real-time cooling demand information for the battery management system; S2. Temperature control and regulation strategy: Combine multiple sensor data and calculate the optimal working state required by the cooling system through algorithm fusion analysis. Based on real-time data, the VCU runs an adaptive control algorithm to adjust the working mode of the cooling system, including coolant flow, electric fan speed, and pump speed, to achieve the required temperature control target. Fuzzy control algorithms are used to handle complex control requirements, especially when the system has multiple variables and strong nonlinear characteristics, to achieve precise temperature regulation; S3. Dynamic scheduling of cooling system: decide whether to switch cooling mode according to real-time temperature and load. For example, use air cooling system under low load and enable water cooling system under high load to provide more efficient cooling effect. Adjust fan speed and working state according to cooling demand. When driving at high speed, fan speed can be appropriately reduced to reduce energy consumption. When heat load is high, fan speed is increased to accelerate heat dissipation. Adjust water pump flow rate according to coolant temperature change to ensure that the flow rate of coolant in important components such as engine and transmission matches demand. S4. Energy efficiency optimization: Determine whether to turn on the energy-saving mode based on the current working conditions. For example, in low-load and low-temperature environments, reduce unnecessary energy consumption by reducing the cooling intensity. In an efficient thermal management system, optimize the heat exchange process between coolant and other heat sources, improve energy efficiency, reduce energy loss, and recover the heat generated during the cooling process (such as for heating in the car). Temperature prediction and pre-adjustment, use prediction algorithms to predict future cooling needs based on historical data and real-time parameters, and integrate them to obtain ,in, Indicates in the future Cooling needs at all times, k Indicates the adjustment coefficient of the cooling system, which is determined by the performance of the vehicle cooling system. From the current moment t The number of time steps to look back, represents the number of time steps in the historical data used to predict future cooling demand, represents the weight parameter, obtained by model training, Indicates the past Cooling needs at all times, Indicates the current engine temperature. Represents noise and prediction errors, predicts future cooling needs through formulas, and adjusts the cooling system in advance to avoid excessive temperature fluctuations and ensure maximum energy efficiency; S5. Fault detection and handling: Real-time monitoring of the operating status of each component of the cooling system (such as water pumps, electric fans, temperature sensors, etc.), diagnosis of potential faults, triggering warnings if a fault or abnormality occurs, and taking emergency control measures. Cooling system abnormality protection: When the temperature exceeds the preset safety threshold, the protection mode is automatically activated to limit engine power, reduce vehicle speed, or activate the backup cooling system to ensure that the vehicle operates within a safe temperature range. Automatic recovery mechanism: When a cooling system fails, the automatic recovery mechanism is activated to switch to the backup cooling mode or adjust other systems to reduce the temperature, and the driver is notified for further inspection; S6. Intelligent control and optimization: Through machine learning algorithms, a large amount of historical data and real-time working conditions are analyzed to optimize the control strategy of the cooling system. As the vehicle is used for a longer time, the VCU can make intelligent adjustments based on the driver's habits and road conditions. Vehicle coordination and network control: If the vehicle is equipped with vehicle-to-everything (V2X), the VCU can exchange data with other vehicles or infrastructure to further optimize the control of the cooling system based on factors such as traffic conditions and ambient temperature. S7. Multi-objective collaborative control: Coordinated control of the engine, battery, and transmission. Based on the vehicle's multi-objective requirements: the temperature requirements of different components of the engine, transmission, and battery, the various cooling systems are optimized to avoid overcooling or overheating of a certain component. The vehicle's driving mode is coordinated with thermal management: In different driving modes (such as sports mode, economic mode, hybrid mode, etc.), the VCU adjusts the cooling strategy to match driving requirements to ensure a balance between vehicle performance and efficiency.

[0004] Furthermore, a control method of the ATS cooling system based on the vehicle VCU control is provided. In step S2, multiple sensor data are combined and analyzed by algorithm fusion to calculate the optimal working state required by the cooling system. Based on real-time data, an adaptive control algorithm is run to adjust the working mode of the cooling system, including coolant flow, electric fan speed, and pump speed. The specific steps are as follows; S21. Multi-sensor data fusion: Remove noise and smooth sensor data through filters (such as Kalman filters), handle missing data or outliers, use the data fusion algorithm Kalman filter to combine data from different sensors, calculate the comprehensive thermal load status of each system component, consider sensor errors, data uncertainty and environmental factors, improve the accuracy of temperature estimation through weighted processing, and evaluate the power output and cooling intensity required by the cooling system to ensure that the temperature of the engine, battery and other key components is within the safe operating range; S22. Optimization algorithm and model construction: Define the optimization objectives of the cooling system, set the objectives as: minimize temperature difference, minimize energy consumption, and achieve the optimal operating temperature range of the equipment. Based on physical principles and sensor data, establish a mathematical model of the cooling system, and use the simulated annealing optimization algorithm to calculate the optimal working state of the cooling system (coolant flow, electric fan speed, pump speed, etc.); S23. Adaptive control algorithm design: Design an adaptive control algorithm model predictive control that adapts to changes in system demand. According to real-time data and optimization models, set control objectives: keep the coolant temperature within the set range, control the pump speed and wind speed to maintain a suitable cooling effect, and find the best balance between energy saving and high efficiency; S24. Real-time feedback and adjustment: Based on the real-time monitored sensor data (such as temperature, pressure, etc.), the operating status of the cooling system is adjusted in real time through the adaptive control algorithm. According to the current and predicted system status, the coolant flow, electric fan speed, and pump speed control parameters are adjusted. According to the optimization results and the output of the control algorithm, the working mode of the cooling system is adjusted: S25. System monitoring and adjustment: monitor the working status of the system in real time, compare it with the optimization target, evaluate the current control effect, and dynamically adjust the control strategy based on the monitoring results; S26. Performance evaluation and improvement: Key indicators such as the operating efficiency, energy consumption, and temperature control accuracy of the cooling system ensure that the system optimization goals are achieved. Based on the performance evaluation results, the optimization algorithm and control strategy are continuously adjusted to improve the operating efficiency of the cooling system.

[0005] Furthermore, a control method of the ATS cooling system based on the vehicle VCU control is provided. In step S4, a prediction algorithm is used to predict future cooling demand based on historical data and real-time parameters. The specific steps are as follows; S41. Data collection: collect historical data including vehicle internal and external temperature, humidity, vehicle running time, cooling system start time, load changes, and real-time parameters including current vehicle speed, engine load, ambient temperature, current cooling system status: coolant temperature, fan speed; S42. Data preprocessing: Integrate historical data with real-time data, process data by standardization and normalization, ensure that different parameters have the same weight, construct time series features, capture the dynamic changes of cooling demand, and construct data sets; S43. Prediction model training: Divide the data into training set and test set to ensure the generalization ability of the model. Use the training set to train the time series model and adjust the model's hyperparameters. Use the test set to evaluate the model's performance and integrate the obtained ,in, Indicates in the future Cooling needs at all times, k Indicates the adjustment coefficient of the cooling system, which is determined by the performance of the vehicle cooling system. From the current moment t The number of time steps to look back, represents the number of time steps in the historical data used to predict future cooling demand, represents the weight parameter, obtained by model training, Indicates the past Cooling needs at all times, Indicates the current engine temperature. represents noise, prediction error; S44. Predicting cooling demand: The model uses historical and real-time parameters to predict cooling demand in future time periods, and the output result is the cooling power demand at a certain moment in the future; S45. Adjust the cooling system in advance: Based on the prediction results, proactively adjust the cooling system before the cooling demand increases: increase the cooling fan speed and reduce the coolant temperature.

[0006] Furthermore, a control method of the ATS cooling system based on the vehicle VCU control is provided. In step S7, the engine, battery, and transmission are coordinated and controlled to optimize and schedule each cooling system according to the vehicle's multi-objective requirements: the temperature requirements of different components of the engine, transmission, and battery. The specific steps are as follows: S71. Define temperature control targets: Set temperature thresholds to set the ideal operating temperature range for each component (engine, battery, transmission). The temperature requirement range for the engine is 90°C to 110°C; the temperature control range for the battery is 20°C to 45°C; the operating temperature range for the transmission is 70°C to 90°C. For each component, set a safe temperature upper and lower limit. Exceeding this range will cause damage to the system. S72. Cooling demand analysis: Calculate the cooling demand of different components based on the vehicle operating conditions (such as load, speed, ambient temperature, etc.). When the engine load increases, the temperature rises and more coolant flow is required. The battery generates more heat during high-power discharge and needs to be cooled more. The transmission generates more heat at high speed and load, so the flow of coolant and oil should be adjusted appropriately. S73. Multi-objective optimization scheduling strategy: Comprehensively consider the factors of minimizing energy consumption, temperature balance, and cooling system efficiency, use a multi-objective optimization algorithm to design the objective optimization function, and set the objective weights: the temperature control of the battery is set as the optimal objective, and the temperature control of the engine and transmission is set as the suboptimal objective; S74. Fault detection and early warning: Monitor the health status of the cooling system: Monitor the working status of the cooling system in real time and detect abnormal conditions. When the system detects a cooling system failure, it immediately triggers an alarm and automatically switches to the backup cooling mode for maintenance to avoid temperature control failure due to failure.

[0007] Beneficial effects of the present invention: By accurately adjusting the working status of each cooling system (such as coolant flow, pump speed and fan speed), it is ensured that the cooling power is started or increased only when necessary, thereby reducing unnecessary energy consumption. By accurately controlling the temperature of the engine, battery and transmission, damage to any component due to excessive temperature is avoided, thereby extending the service life of each component. Under different working conditions, through precise cooling control, it can ensure that the engine, battery and transmission operate within the optimal operating temperature range, avoiding power loss or unstable performance due to overheating. Improve the vehicle's dynamic performance such as acceleration and load capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 It is a flow chart of an ATS cooling system control method based on vehicle VCU control; DETAILED DESCRIPTION

[0009] A control method for an ATS cooling system based on vehicle VCU control, the process is as follows: Figure 1 As shown, the following steps are included; S1. Data collection and sensor monitoring: Collect data from various sensors, including engine, electronic control unit, battery, and coolant temperature, obtain the vehicle's temperature status in real time, monitor external ambient temperature and driving condition information, provide auxiliary data through the vehicle's environmental perception system, and collect battery temperature, charging status, and discharge load data to provide real-time cooling demand information for the battery management system; S2. Temperature control and regulation strategy: Combine multiple sensor data and calculate the optimal working state required by the cooling system through algorithm fusion analysis. Based on real-time data, the VCU runs an adaptive control algorithm to adjust the working mode of the cooling system, including coolant flow, electric fan speed, and pump speed, to achieve the required temperature control target. Fuzzy control algorithms are used to handle complex control requirements, especially when the system has multiple variables and strong nonlinear characteristics, to achieve precise temperature regulation; S3. Dynamic scheduling of cooling system: decide whether to switch cooling mode according to real-time temperature and load. For example, use air cooling system under low load and enable water cooling system under high load to provide more efficient cooling effect. Adjust fan speed and working state according to cooling demand. When driving at high speed, fan speed can be appropriately reduced to reduce energy consumption. When heat load is high, fan speed is increased to accelerate heat dissipation. Adjust water pump flow rate according to coolant temperature change to ensure that the flow rate of coolant in important components such as engine and transmission matches demand. S4. Energy efficiency optimization: Determine whether to turn on the energy-saving mode based on the current working conditions. For example, in low-load and low-temperature environments, reduce unnecessary energy consumption by reducing the cooling intensity. In an efficient thermal management system, optimize the heat exchange process between coolant and other heat sources, improve energy efficiency, reduce energy loss, and recover the heat generated during the cooling process (such as for heating in the car). Temperature prediction and pre-adjustment, use prediction algorithms to predict future cooling needs based on historical data and real-time parameters, and integrate them to obtain ,in, Indicates in the future Cooling needs at all times, k Indicates the adjustment coefficient of the cooling system, which is determined by the performance of the vehicle cooling system. From the current moment t The number of time steps to look back, represents the number of time steps in the historical data used to predict future cooling demand, represents the weight parameter, obtained by model training, Indicates the past Cooling needs at all times, Indicates the current engine temperature. Represents noise and prediction errors, predicts future cooling needs through formulas, and adjusts the cooling system in advance to avoid excessive temperature fluctuations and ensure maximum energy efficiency; S5. Fault detection and handling: Real-time monitoring of the operating status of each component of the cooling system (such as water pumps, electric fans, temperature sensors, etc.), diagnosis of potential faults, triggering warnings if a fault or abnormality occurs, and taking emergency control measures. Cooling system abnormality protection: When the temperature exceeds the preset safety threshold, the protection mode is automatically activated to limit engine power, reduce vehicle speed, or activate the backup cooling system to ensure that the vehicle operates within a safe temperature range. Automatic recovery mechanism: When a cooling system fails, the automatic recovery mechanism is activated to switch to the backup cooling mode or adjust other systems to reduce the temperature, and the driver is notified for further inspection; S6. Intelligent control and optimization: Through machine learning algorithms, a large amount of historical data and real-time working conditions are analyzed to optimize the control strategy of the cooling system. As the vehicle is used for a longer time, the VCU can make intelligent adjustments based on the driver's habits and road conditions. Vehicle coordination and network control: If the vehicle is equipped with vehicle-to-everything (V2X), the VCU can exchange data with other vehicles or infrastructure to further optimize the control of the cooling system based on factors such as traffic conditions and ambient temperature. S7. Multi-objective collaborative control: Coordinated control of the engine, battery, and transmission. Based on the vehicle's multi-objective requirements: the temperature requirements of different components of the engine, transmission, and battery, the various cooling systems are optimized to avoid overcooling or overheating of a certain component. The vehicle's driving mode is coordinated with thermal management: In different driving modes (such as sports mode, economic mode, hybrid mode, etc.), the VCU adjusts the cooling strategy to match driving requirements to ensure a balance between vehicle performance and efficiency.

[0010] Furthermore, a control method of the ATS cooling system based on the vehicle VCU control is provided. In step S2, multiple sensor data are combined and analyzed by algorithm fusion to calculate the optimal working state required by the cooling system. Based on real-time data, an adaptive control algorithm is run to adjust the working mode of the cooling system, including coolant flow, electric fan speed, and pump speed. The specific steps are as follows; S21. Multi-sensor data fusion: Remove noise and smooth sensor data through filters (such as Kalman filters), handle missing data or outliers, use the data fusion algorithm Kalman filter to combine data from different sensors, calculate the comprehensive thermal load status of each system component, consider sensor errors, data uncertainty and environmental factors, improve the accuracy of temperature estimation through weighted processing, and evaluate the power output and cooling intensity required by the cooling system to ensure that the temperature of the engine, battery and other key components is within the safe operating range; S22. Optimization algorithm and model construction: Define the optimization objectives of the cooling system, set the objectives as: minimize temperature difference, minimize energy consumption, and achieve the optimal operating temperature range of the equipment. Based on physical principles and sensor data, establish a mathematical model of the cooling system, and use the simulated annealing optimization algorithm to calculate the optimal working state of the cooling system (coolant flow, electric fan speed, pump speed, etc.); S23. Adaptive control algorithm design: Design an adaptive control algorithm model predictive control that adapts to changes in system demand. According to real-time data and optimization models, set control objectives: keep the coolant temperature within the set range, control the pump speed and wind speed to maintain a suitable cooling effect, and find the best balance between energy saving and high efficiency; S24. Real-time feedback and adjustment: Based on the real-time monitored sensor data (such as temperature, pressure, etc.), the operating status of the cooling system is adjusted in real time through the adaptive control algorithm. According to the current and predicted system status, the coolant flow, electric fan speed, and pump speed control parameters are adjusted. According to the optimization results and the output of the control algorithm, the working mode of the cooling system is adjusted: S25. System monitoring and adjustment: monitor the working status of the system in real time, compare it with the optimization target, evaluate the current control effect, and dynamically adjust the control strategy based on the monitoring results; S26. Performance evaluation and improvement: Key indicators such as the operating efficiency, energy consumption, and temperature control accuracy of the cooling system ensure that the system optimization goals are achieved. Based on the performance evaluation results, the optimization algorithm and control strategy are continuously adjusted to improve the operating efficiency of the cooling system.

[0011] Furthermore, a control method of the ATS cooling system based on the vehicle VCU control is provided. In step S4, a prediction algorithm is used to predict future cooling demand based on historical data and real-time parameters. The specific steps are as follows; S41. Data collection: collect historical data including vehicle internal and external temperature, humidity, vehicle running time, cooling system start time, load changes, and real-time parameters including current vehicle speed, engine load, ambient temperature, current cooling system status: coolant temperature, fan speed; S42. Data preprocessing: Integrate historical data with real-time data, process data by standardization and normalization, ensure that different parameters have the same weight, construct time series features, capture the dynamic changes of cooling demand, and construct data sets; S43. Prediction model training: Divide the data into training set and test set to ensure the generalization ability of the model. Use the training set to train the time series model and adjust the model's hyperparameters. Use the test set to evaluate the model's performance and integrate the obtained ,in, Indicates in the future Cooling needs at all times, k Indicates the adjustment coefficient of the cooling system, which is determined by the performance of the vehicle cooling system. From the current moment t The number of time steps to look back, represents the number of time steps in the historical data used to predict future cooling demand, represents the weight parameter, obtained by model training, Indicates the past Cooling needs at all times, Indicates the current engine temperature. represents noise, prediction error; S44. Predicting cooling demand: The model uses historical and real-time parameters to predict cooling demand in future time periods, and the output result is the cooling power demand at a certain moment in the future; S45. Adjust the cooling system in advance: Based on the prediction results, proactively adjust the cooling system before the cooling demand increases: increase the cooling fan speed and reduce the coolant temperature.

[0012] Furthermore, a control method of the ATS cooling system based on the vehicle VCU control is provided. In step S7, the engine, battery, and transmission are coordinated and controlled to optimize and schedule each cooling system according to the vehicle's multi-objective requirements: the temperature requirements of different components of the engine, transmission, and battery. The specific steps are as follows: S71. Define temperature control targets: Set temperature thresholds to set the ideal operating temperature range for each component (engine, battery, transmission). The temperature requirement range for the engine is 90°C to 110°C; the temperature control range for the battery is 20°C to 45°C; the operating temperature range for the transmission is 70°C to 90°C. For each component, set a safe temperature upper and lower limit. Exceeding this range will cause damage to the system. S72. Cooling demand analysis: Calculate the cooling demand of different components based on the vehicle operating conditions (such as load, speed, ambient temperature, etc.). When the engine load increases, the temperature rises and more coolant flow is required. The battery generates more heat during high-power discharge and needs to be cooled more. The transmission generates more heat at high speed and load, so the flow of coolant and oil should be adjusted appropriately. S73. Multi-objective optimization scheduling strategy: Comprehensively consider the factors of minimizing energy consumption, temperature balance, and cooling system efficiency, use a multi-objective optimization algorithm to design the objective optimization function, and set the objective weights: the temperature control of the battery is set as the optimal objective, and the temperature control of the engine and transmission is set as the suboptimal objective; S74. Fault detection and early warning: Monitor the health status of the cooling system: Monitor the working status of the cooling system in real time and detect abnormal conditions. When the system detects a cooling system failure, it immediately triggers an alarm and automatically switches to the backup cooling mode for maintenance to avoid temperature control failure due to failure.

Claims

1. A method for controlling an ATS cooling system based on vehicle VCU control, characterized in that: The steps include: S1. Data collection and sensor monitoring: Collect data from various sensors, including engine, electronic control unit, battery, coolant temperature, monitor external ambient temperature, driving condition information, provide auxiliary data through the vehicle's environmental perception system, and collect battery temperature, charging status, and discharge load data; S2. Temperature control and regulation strategy: Combine multiple sensor data, calculate the optimal working state required by the cooling system through algorithm fusion analysis, run adaptive control algorithm based on real-time data, adjust the working mode of the cooling system, including coolant flow, electric fan speed, and pump speed, to achieve the required temperature control target, use fuzzy control algorithm to handle complex control requirements, and achieve precise temperature regulation when the system has multiple variables and strong nonlinear characteristics; S3. Dynamic scheduling of cooling system: based on real-time temperature and load, decide whether to switch cooling mode. Use air cooling system under low load, and enable water cooling system under high load to provide more efficient cooling effect. Adjust fan speed and working state according to cooling demand. When driving at high speed, fan speed is reduced to reduce energy consumption, and when heat load is high, fan speed is increased to accelerate heat dissipation. Adjust water pump flow rate according to coolant temperature change, so that the flow rate of coolant in engine and transmission components matches demand. S4. Energy efficiency optimization: Determine whether to turn on the energy-saving mode based on the current working conditions. In the efficient thermal management system, optimize the heat exchange process between the coolant and other heat sources, improve energy efficiency, reduce energy loss, and recover the heat generated during the cooling process. Use the prediction algorithm to predict future cooling needs based on historical data and real-time parameters, and integrate them to obtain ,in, Indicates in the future Cooling needs at all times, k Indicates the adjustment coefficient of the cooling system, which is determined by the performance of the vehicle cooling system. From the current moment t The number of time steps to look back, represents the number of time steps in the historical data used to predict future cooling demand, represents the weight parameter, obtained by model training, Indicates the past Cooling needs at all times, Indicates the current engine temperature. Represents noise and prediction errors, predicts future cooling needs through formulas, and adjusts the cooling system in advance to avoid excessive temperature fluctuations and ensure maximum energy efficiency; S5. Fault detection and handling: Real-time monitoring of cooling system components: water pump, electric fan, temperature sensor operating status, diagnose potential faults, trigger warnings, and take emergency control measures. Cooling system abnormal protection: When the temperature exceeds the preset safety threshold, the protection mode is automatically activated, the engine power is limited, the vehicle speed is reduced, and the backup cooling system is activated. When the cooling system fails, the automatic recovery mechanism is activated, switching to the backup cooling mode or adjusting other systems to reduce the temperature, and the driver is notified for further inspection; S6. Intelligent control and optimization: By analyzing a large amount of historical data and real-time working conditions, the control strategy of the cooling system is optimized. As the vehicle is used for a longer time, intelligent adjustments are made based on the driver's habits and road conditions. The vehicle is equipped with a car network to exchange data with other vehicles and infrastructure, and the control of the cooling system is further optimized based on traffic conditions and ambient temperature factors. S7. Multi-objective collaborative control: The engine, battery, and transmission are collaboratively controlled. Based on the vehicle's multi-objective requirements: the temperature requirements of different components of the engine, transmission, and battery, each cooling system is optimized and scheduled to avoid overcooling or overheating of a component. The vehicle's driving mode is coordinated with thermal management: In different driving modes: sports mode, economy mode, and hybrid mode, the cooling strategy is adjusted to match driving requirements to ensure a balance between vehicle performance and efficiency.

2. The ATS cooling system control method based on vehicle VCU control as claimed in claim 1, characterized in that: In step S2, multiple sensor data are combined and analyzed by algorithm fusion to calculate the optimal working state required by the cooling system. Based on real-time data, an adaptive control algorithm is run to adjust the working mode of the cooling system, including coolant flow, electric fan speed, and pump speed. The specific steps are as follows; S21. Multi-sensor data fusion: Remove noise and smooth sensor data through Kalman filter, handle missing data and outliers, use data fusion algorithm to combine data from different sensors, calculate the comprehensive thermal load status of each system component, consider sensor errors, data uncertainty and environmental factors, improve the accuracy of temperature estimation through weighted processing, and evaluate the power output and cooling intensity required by the cooling system; S22. Optimization algorithm and model construction: Define the optimization objectives of the cooling system, set the objectives as: minimize temperature difference, minimize energy consumption, and achieve the optimal operating temperature range of the equipment. Based on physical principles and sensor data, establish a mathematical model of the cooling system, and use the simulated annealing optimization algorithm to calculate the optimal working state of the cooling system: coolant flow, electric fan speed, and pump speed; S23. Adaptive control algorithm design: Design an adaptive control algorithm model predictive control that adapts to changes in system demand. According to real-time data and optimization models, set control objectives: keep the coolant temperature within the set range, control the pump speed and wind speed to maintain a suitable cooling effect, and find the best balance between energy saving and high efficiency; S24. Real-time feedback and adjustment: Based on the real-time monitored sensor data: temperature, pressure, the operating status of the cooling system is adjusted in real time through the adaptive control algorithm. According to the current and predicted system status, the coolant flow, electric fan speed, and pump speed control parameters are adjusted. According to the optimization results and the output of the control algorithm, the working mode of the cooling system is adjusted: S25. System monitoring and adjustment: monitor the working status of the system in real time, compare it with the optimization target, evaluate the current control effect, and dynamically adjust the control strategy based on the monitoring results; S26. Performance evaluation and improvement: The key indicators of the cooling system’s operating efficiency, energy consumption, and temperature control accuracy ensure that the system’s optimization goals are achieved. Based on the performance evaluation results, the optimization algorithm and control strategy are continuously adjusted to improve the cooling system’s operating efficiency.

3. The ATS cooling system control method based on vehicle VCU control as claimed in claim 1, characterized in that: In step S4, a prediction algorithm is used to predict future cooling demand based on historical data and real-time parameters. The specific steps are as follows; S41. Data collection: collect historical data including vehicle internal and external temperature, humidity, vehicle running time, cooling system start time, load changes, and real-time parameters including current vehicle speed, engine load, ambient temperature, current cooling system status: coolant temperature, fan speed; S42. Data preprocessing: Integrate historical data with real-time data, process data by standardization and normalization, ensure that different parameters have the same weight, construct time series features, capture the dynamic changes of cooling demand, and construct data sets; S43. Prediction model training: Divide the data into training set and test set to ensure the generalization ability of the model. Use the training set to train the time series model and adjust the model's hyperparameters. Use the test set to evaluate the performance of the model and integrate the obtained ,in, Indicates in the future Cooling needs at all times, k Indicates the adjustment coefficient of the cooling system, which is determined by the performance of the vehicle cooling system. From the current moment t The number of time steps to look back, represents the number of time steps in the historical data used to predict future cooling demand, represents the weight parameter, obtained by model training, Indicates the past Cooling needs at all times, Indicates the current engine temperature. represents noise, prediction error; S44. Predicting cooling demand: The model uses historical and real-time parameters to predict cooling demand in future time periods, and the output result is the cooling power demand at a certain moment in the future; S45. Adjust the cooling system in advance: Based on the prediction results, proactively adjust the cooling system before the cooling demand increases: increase the cooling fan speed and reduce the coolant temperature.

4. The ATS cooling system control method based on vehicle VCU control as claimed in claim 1, characterized in that: In step S7, the engine, battery, and transmission are coordinated and controlled to optimize and schedule each cooling system according to the vehicle's multi-objective requirements: the temperature requirements of different components of the engine, transmission, and battery. The specific steps are as follows: S71. Define temperature control targets: Set temperature thresholds for each component: Set ideal operating temperature ranges for the engine, battery, and transmission. The temperature requirement range for the engine is 90°C to 110°C; the temperature control range for the battery is 20°C to 45°C; the operating temperature range for the transmission is 70°C to 90°C. For each component, set a safe temperature upper and lower limit. Exceeding this range will cause damage to the system. S72. Cooling demand analysis: Calculate the cooling demand of different components based on the vehicle operating conditions: load, speed, and ambient temperature. When the engine load increases, the temperature rises, requiring more coolant flow. The battery generates more heat during high-power discharge, requiring enhanced cooling. The transmission generates more heat at high speed and load, so the flow of coolant and oil should be appropriately adjusted. S73. Multi-objective optimization scheduling strategy: Comprehensively consider the factors of minimizing energy consumption, temperature balance, and cooling system efficiency, use a multi-objective optimization algorithm to design the objective optimization function, and set the objective weights: the temperature control of the battery is set as the optimal objective, and the temperature control of the engine and transmission is set as the suboptimal objective; S74. Fault detection and early warning: Monitor the health status of the cooling system: Monitor the working status of the cooling system in real time and detect abnormal conditions. When the system detects a cooling system failure, it immediately triggers an alarm and automatically switches to the backup cooling mode for maintenance to avoid temperature control failure due to failure.

Images