Vehicle power distribution control management system and method

Abstract

The invention discloses a vehicle power supply distribution control management system and method, and relates to the technical field of vehicle power supplies, and the method comprises the steps: collecting the historical driving data of a vehicle and the driving behavior data of a driver, analyzing the driving habit of the driver, and monitoring the driving state of the vehicle in real time through combining with a vehicle-mounted sensor; comprehensively judging whether the vehicle enters a high-load state or not; when the vehicle enters a high-load state, the charging and discharging power of each battery module is dynamically adjusted according to the temperature distribution and load requirements of each battery module in the battery pack; evaluating the power supply condition of each battery module according to a power adjustment result, sending an early warning prompt to a driver if the power supply is insufficient, and continuously monitoring and analyzing the temperature difference between the battery modules in the battery pack and predicting the temperature change of each battery module if the power supply is sufficient, and the cooling strategy of the vehicle system is intelligently adjusted, and temperature balance of all battery modules of the vehicle in the high-load state is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle power supply, and in particular to a vehicle power supply distribution control management system and method. Background Art

[0002] In the rapid development of electric vehicle technology, the thermal management of battery systems has always been a key bottleneck restricting its performance improvement and cost optimization, especially under high-load operating conditions. At present, electric vehicles widely use battery management systems (BMS) to monitor key parameters such as temperature, current, and voltage of battery packs, and implement thermal management strategies based on these parameters to ensure that the battery operates within a safe and efficient temperature range.

[0003] Existing technologies mainly rely on preset temperature thresholds and fixed heat dissipation strategies to manage battery temperature. When the battery temperature reaches or exceeds a preset threshold, the heat dissipation system will start, such as increasing the fan speed or strengthening the coolant circulation, to reduce the battery temperature. However, this heat dissipation control strategy based on fixed rules has obvious limitations: first, it cannot predict the thermal load changes of the battery under high-load conditions in advance, resulting in the start-up of the heat dissipation system often lagging behind the sharp rise in battery temperature, and cannot effectively curb the occurrence of temperature peaks; second, the existing technology lacks an in-depth understanding of the thermal characteristics of the battery under different working conditions, and cannot dynamically adjust the heat dissipation strategy according to the real-time working conditions, resulting in significant differences in the heat dissipation effect under different working conditions, making it difficult to achieve the optimal; finally, due to the lack of fine control of battery temperature changes, the existing technology often leads to large fluctuations in battery temperature, which not only aggravates the thermal stress inside the battery, but also accelerates the battery aging process and shortens the battery life. Summary of the invention

[0004] The object of the present invention is to provide a vehicle power distribution control management system and method to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solution: a vehicle power distribution control management method, characterized in that: the method comprises:

[0006] Step S100: Collect the historical driving data of the vehicle and the driving behavior data of the driver, analyze the driving habits of the driver, and monitor the driving status of the vehicle in real time in combination with the vehicle-mounted sensors to comprehensively determine whether the vehicle enters a high-load state;

[0007] Step S200: When the vehicle enters a high load state, dynamically adjusting the charge and discharge power of each battery module according to the temperature distribution and load requirements of each battery module in the battery pack;

[0008] Step S300: Evaluate the power supply of each battery module according to the power adjustment result, and issue a warning to the driver if there is insufficient power supply; if the power supply is sufficient, continuously monitor the temperature of each battery module;

[0009] Step S400: Analyze the temperature difference between the battery modules in the battery pack, predict the temperature change of each battery module, and intelligently adjust the cooling system of the vehicle to achieve temperature balance of each battery module under high load conditions.

[0010] Further, the step S100 includes: step S101: the historical driving data of the vehicle refers to the relevant information of the driving condition of the vehicle in the past period of time obtained from the driving record system of the vehicle, and the driving behavior data of the driver refers to the behavior data of the driver in the driving process captured and recorded in real time by the vehicle-mounted sensor;

[0011] Step S102: extracting features from the two types of data collected, including extracting the vehicle's mileage, driving time, speed and related data from the historical driving data, and extracting the frequency of use of the accelerator pedal, the braking force, the steering wheel rotation angle and speed from the driver's driving behavior data; performing cluster analysis on the extracted feature data using the K-means clustering algorithm, and finally dividing the driver's driving habits into K different driving behavior patterns according to the analysis results, represented as {C1, C2, ..., C k}, where C k represents the kth driving behavior mode, and based on the usage specifications of vehicle components and the statistical analysis of historical data, sets the conditions for vehicles in different driving behavior modes to enter a high-load state, wherein the conditions for entering a high-load state include engine load, motor load, vehicle acceleration, fuel consumption exceeding a set threshold, and battery voltage being lower than a set threshold, and the setting of the threshold is based on the usage specifications of vehicle components and the statistical analysis of historical data;

[0012] Step S103: Obtain the current driving data of the vehicle and the driving behavior data of the driver in real time through the vehicle-mounted sensor and compare them with the classification results {C1, C2, ..., C k} to match and determine the driving behavior mode of the current driver. According to the preset threshold conditions, when any one of the conditions is met, it is determined that the vehicle enters a high-load state.

[0013] In the above technical solution, the objective driving conditions of the vehicle and the subjective driving behavior of the driver are taken into consideration, making the judgment result more accurate and comprehensive. Through the dual verification of historical data and real-time data, the performance of the vehicle under high load conditions can be more effectively predicted, providing strong support for subsequent power distribution management.

[0014] Further, the step S200 includes: step S201: obtaining the charging state of each battery module and the acceleration data of the vehicle in real time through the vehicle-mounted sensor, and building a neural network prediction in combination with the current driving habit classification result, taking the acceleration of the vehicle, the average charging state of the battery pack and the current driving behavior pattern as feature inputs, and predicting the total load demand P at time t through the training and learning of the neural network. total (t); The total load is distributed to each battery module by considering the charge state of each battery module, according to the formula:

[0015]

[0016] Where P total,i (t) represents the load demand of each battery module at time t, and N represents the number of battery modules in the battery pack;

[0017] Step S202: Obtain the temperature parameter T of each battery module through the temperature sensor i , where T i represents the temperature of the i-th battery module, monitors the temperature of each battery module in real time, and builds a temperature scheduling model to balance the temperature and load requirements of different battery modules; for each battery module, a temperature safety interval [T min , T max ], where T min and T max Indicates the lower and upper limits of the safe temperature range. If the battery temperature T i If it exceeds the safety range, the charging and discharging power of the corresponding battery module will be adjusted;

[0018] For each battery module, according to the temperature T of the corresponding battery module i Adjust its charging and discharging power according to the formula:

[0019]

[0020] Where P i (t) represents the charge and discharge power of the i-th battery module at time t, P represents the rated power of the battery module, T represents the normal operating temperature of the battery module, and T i (t) represents the temperature of the ith battery module at time t; when the temperature of the battery module T i (t) is in the temperature safety range [T min , T max ], indicating that the battery module can work normally and provide maximum power; when T i (t) is lower than T min and T i (t) exceeds T max hour, The value of will increase, making P i As the value of (t) decreases, the charging power of the battery module will decrease;

[0021] Step S203: setting an objective function for adjusting the charge and discharge power among the multiple battery modules, thereby balancing the power demand and temperature safety, according to the formula:

[0022]

[0023] Where Y represents the objective function, and λ represents the weight factor of temperature deviation on power allocation. The gradient descent algorithm is used to optimize the objective function Y through continuous iteration, and finally the charging and discharging power of each battery module at time t is obtained.

[0024] In the above technical solution, when the vehicle enters a high-load state, the charging and discharging power of each battery module can be dynamically adjusted according to the temperature distribution and load demand of each battery module in the battery pack, which not only ensures the efficient utilization of the battery pack, but also avoids overheating or damage caused by overload of a single battery module. The total load demand is predicted by a neural network, and the load is distributed according to the charging state of the battery module, and the power is adjusted in combination with the temperature scheduling model. This multi-level optimization strategy enables the performance of the battery pack to be fully utilized, while also extending the battery life.

[0025] Further, step S300 includes: step S301: after adjusting the charge and discharge power of each battery module, evaluating the power supply of each battery module to determine whether the existing power can meet the adjusted load demand, for each battery module i, comparing the actual power output P at time t i (t) and load demand P total,i (t), if P i (t)>=P total,i (t), the battery module is considered to have sufficient power supply; if P i (t) <P total,i (t), it is considered that the battery module has insufficient power supply;

[0026] Step S302: If any battery module has insufficient power supply, a warning prompt is issued to the driver through the vehicle display screen, which includes the number of the battery module with insufficient power supply and the difference between the current load demand and the power output; if all battery modules have sufficient power supply, the temperature of each battery module is continuously monitored.

[0027] In the above technical solution, after adjusting the charging and discharging power, the power supply of each battery module will be evaluated to ensure that the power supply can meet the adjusted load demand; once insufficient power supply is detected, an early warning prompt will be immediately issued to the driver through the vehicle display screen, so that the driver can understand the power status of the battery module in time and take corresponding countermeasures; this early warning mechanism not only improves driving safety, but also avoids vehicle failures or accidents caused by insufficient power.

[0028] Further, the step S400 includes: step S401: constructing an LSTM model, collecting temperature data of each battery module in real time through a temperature sensor, comparing and calculating the temperature difference between each battery module to form a temperature difference data set, and taking the historical temperature data, current load demand, ambient temperature and battery charge and discharge strategy as inputs of the model, training the model, and using the trained model to predict the temperature change of each battery module in the future;

[0029] Step S402: According to the temperature prediction result and the preset temperature safety range, the working mode of the vehicle cooling system is intelligently adjusted. If it is predicted that the temperature of a battery module will exceed T in the future, max , the cooling system is started in advance to reduce the temperature of the battery module; if it is predicted that the temperature of a battery module will be lower than T in the future min , the working part of the cooling system can be reduced.

[0030] In the above technical solution, an LSTM model is constructed to predict the temperature changes of each battery module in the future, and the working mode of the vehicle cooling system is intelligently adjusted according to the prediction results. This can not only effectively prevent the battery module from being damaged due to overheating, but also reduce the working part of the cooling system when necessary, thereby improving the energy efficiency of the vehicle.

[0031] A vehicle power distribution control and management system, the system comprising a data collection and analysis module, a power adjustment module, a power supply evaluation module, and a temperature prediction and adjustment module;

[0032] The data collection and analysis module is used to collect the historical driving data of the vehicle and the driving behavior data of the driver, analyze the driving habits of the driver, and monitor the driving status of the vehicle in real time in combination with the on-board sensors to comprehensively judge whether the vehicle has entered a high-load state;

[0033] The power adjustment module is used to dynamically adjust the charge and discharge power of each battery module according to the temperature distribution and load requirements of each battery module in the battery pack when the vehicle enters a high load state;

[0034] The power supply evaluation module is used to evaluate the power supply of each battery module according to the power adjustment result, and issue a warning to the driver if there is insufficient power supply, and continuously monitor the temperature of each battery module if the power supply is sufficient;

[0035] The temperature prediction and adjustment module is used to analyze the temperature difference between the battery modules in the battery pack, predict the temperature change of each battery module, and intelligently adjust the vehicle's cooling system to achieve temperature balance of each battery module under high load conditions.

[0036] The data collection and analysis module includes a data collection unit, a driving habit analysis unit, and a high load state judgment unit;

[0037] The data collection unit collects the historical driving data of the vehicle and the driving behavior data of the driver; the driving habit analysis unit extracts features from the two collected data, performs cluster analysis on the extracted feature data through the K-means clustering algorithm, and finally divides the driver's driving habits into K different driving behavior modes according to the analysis results, which are represented as {C1, C2, ..., C k}, where C k represents the kth driving behavior mode; based on the usage specifications of vehicle components and statistical analysis of historical data, the conditions for vehicles under different driving behavior modes to enter a high load state are set;

[0038] The high load state judgment unit obtains the current driving data of the vehicle and the driving behavior data of the driver in real time through the vehicle-mounted sensor and the classification result {C1, C2, ..., C k} to match and determine the driving behavior mode of the current driver. According to the preset threshold conditions, when any one of the conditions is met, it is determined that the vehicle enters a high-load state.

[0039] The power adjustment module includes a load demand prediction and allocation unit, a temperature monitoring and power adjustment unit, and a power balance optimization unit;

[0040] The load demand prediction and allocation unit obtains the charging status of each battery module and the acceleration data of the vehicle in real time through the on-board sensor, and builds a neural network prediction based on the current driving habit classification results. The vehicle acceleration, the average charging status of the battery pack and the current driving behavior pattern are used as feature inputs. Through the training and learning of the neural network, the total load demand P at time t is predicted. total (t); The total load is distributed to each battery module by considering the charge state of each battery module, according to the formula:

[0041]

[0042] Where P total,i (t) represents the load demand of each battery module at time t, and N represents the number of battery modules in the battery pack;

[0043] The temperature monitoring and power adjustment unit obtains the temperature parameter T of each battery module through the temperature sensor. i , where T i represents the temperature of the i-th battery module, monitors the temperature of each battery module in real time, and builds a temperature scheduling model to balance the temperature and load requirements of different battery modules; for each battery module, a temperature safety interval [T min , T max ], where T min and T max Indicates the lower and upper limits of the safe temperature range. If the battery temperature T i If the temperature exceeds the safe range, the charge and discharge power of the corresponding battery module is adjusted; for each battery module, according to the temperature T i Adjust its charging and discharging power according to the formula:

[0044]

[0045] Where P i (t) represents the charge and discharge power of the i-th battery module at time t, P represents the rated power of the battery module, T represents the normal operating temperature of the battery module, and T i (t) represents the temperature of the i-th battery module at time t;

[0046] The power balance optimization unit sets an objective function for adjusting the charge and discharge power between multiple battery modules to balance power demand and temperature safety, according to the formula:

[0047]

[0048] Where Y represents the objective function, and λ represents the weight factor of temperature deviation on power allocation. The gradient descent algorithm is used to optimize the objective function Y through continuous iteration, and finally the charging and discharging power of each battery module at time t is obtained.

[0049] The power supply assessment module includes a power supply assessment unit and an early warning prompt unit;

[0050] The power supply evaluation unit is used to evaluate the power supply of each battery module after adjusting the charge and discharge power of each battery module, to determine whether the existing power can meet the adjusted load demand, and for each battery module i, to compare the actual power output P at time t. i (t) and load demand P total,i (t), if Pi (t)>=P total,i (t), the battery module is considered to have sufficient power supply; if P i (t) <P total,i (t), it is considered that the battery module has insufficient power supply;

[0051] The early warning prompt unit is used to issue a early warning prompt to the driver through the vehicle display screen when any battery module has insufficient power supply. The prompt content includes the number of the battery module with insufficient power supply and the difference between the current load demand and the power output; if the power supply of all battery modules is sufficient, the temperature of each battery module is continuously monitored.

[0052] The temperature prediction and adjustment module includes a temperature prediction unit and a cooling system adjustment unit;

[0053] The temperature prediction unit is used to build an LSTM model, collect the temperature data of each battery module in real time through the temperature sensor, compare and calculate the temperature difference between each battery module to form a temperature difference data set, and use the historical temperature data, current load demand, ambient temperature and battery charging and discharging strategy as the input of the model to train the model, and use the trained model to predict the temperature change of each battery module in the future;

[0054] The cooling system adjustment unit intelligently adjusts the working mode of the vehicle cooling system according to the temperature prediction result and the preset temperature safety range. If it is predicted that the temperature of a battery module will exceed Tmax in the future, the cooling system is started in advance to reduce the temperature of the battery module; if it is predicted that the temperature of a battery module will be lower than Tmin in the future, the working part of the cooling system can be reduced.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] The present invention collects the vehicle's historical driving data and the driver's driving behavior data, and combines the on-board sensors to monitor the vehicle's driving status in real time, so as to more accurately determine whether the vehicle has entered a high-load state. This comprehensive judgment method is more comprehensive and reliable than relying solely on vehicle driving data or driver behavior data, and helps to prevent in advance possible performance degradation or failure of the vehicle under high load. When the vehicle enters a high-load state, the present invention can dynamically adjust the charge and discharge power of each battery module according to the temperature distribution and load requirements of each battery module in the battery pack. This dynamic adjustment strategy can ensure that the battery pack can still maintain stable performance under high load, avoid overloading or overheating of a single battery module, thereby extending the service life of the battery.

[0057] After adjusting the charge and discharge power of the battery module, the present invention will evaluate the power supply of each battery module to ensure that the power supply can meet the adjusted load demand, and build an LSTM model to predict the temperature change of each battery module in the future, and intelligently adjust the working mode of the vehicle cooling system according to the prediction results. This intelligent adjustment strategy can prevent the performance degradation or damage caused by overheating or too low temperature of the battery module in advance, and ensure that the battery pack can still maintain the best working state under high load; at the same time, the intelligent adjustment of the working mode of the cooling system can also reduce unnecessary energy consumption and improve the energy efficiency of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 A method flow chart of a vehicle power distribution control management method of the present invention; DETAILED DESCRIPTION

[0059] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0060] Example: Figure 1 The present invention provides a technical solution, a vehicle power distribution control management method, characterized in that: the method comprises:

[0061] Step S100: Collect the historical driving data of the vehicle and the driving behavior data of the driver, analyze the driving habits of the driver, and monitor the driving status of the vehicle in real time in combination with the vehicle-mounted sensors to comprehensively determine whether the vehicle enters a high-load state;

[0062] Step S200: When the vehicle enters a high load state, dynamically adjusting the charge and discharge power of each battery module according to the temperature distribution and load requirements of each battery module in the battery pack;

[0063] Step S300: Evaluate the power supply of each battery module according to the power adjustment result, and issue a warning to the driver if there is insufficient power supply; if the power supply is sufficient, continuously monitor the temperature of each battery module;

[0064] Step S400: Analyze the temperature difference between the battery modules in the battery pack, predict the temperature change of each battery module, and intelligently adjust the cooling system of the vehicle to achieve temperature balance of each battery module under high load conditions.

[0065] The step S100 comprises: step S101: the historical driving data of the vehicle refers to the relevant information of the driving condition of the vehicle in the past period of time obtained from the driving record system of the vehicle, and the driving behavior data of the driver refers to the behavior data of the driver in the driving process captured and recorded in real time by the vehicle-mounted sensor;

[0066] Step S102: extracting features from the two types of data collected, including extracting the vehicle's mileage, driving time, speed and related data from the historical driving data, and extracting the frequency of use of the accelerator pedal, the braking force, the steering wheel rotation angle and speed from the driver's driving behavior data; performing cluster analysis on the extracted feature data using the K-means clustering algorithm, and finally dividing the driver's driving habits into K different driving behavior patterns according to the analysis results, represented as {C1, C2, ..., C k}, where C k represents the kth driving behavior mode, and based on the usage specifications of vehicle components and the statistical analysis of historical data, sets the conditions for vehicles in different driving behavior modes to enter a high-load state, wherein the conditions for entering a high-load state include engine load, motor load, vehicle acceleration, fuel consumption exceeding a set threshold, and battery voltage being lower than a set threshold, and the setting of the threshold is based on the usage specifications of vehicle components and the statistical analysis of historical data;

[0067] Step S103: Obtain the current driving data of the vehicle and the driving behavior data of the driver in real time through the vehicle-mounted sensor and compare them with the classification results {C1, C2, ..., C k} to match and determine the driving behavior mode of the current driver. According to the preset threshold conditions, when any one of the conditions is met, it is determined that the vehicle enters a high-load state.

[0068] In the above technical solution, the objective driving conditions of the vehicle and the subjective driving behavior of the driver are taken into consideration, making the judgment result more accurate and comprehensive. Through the dual verification of historical data and real-time data, the performance of the vehicle under high load conditions can be more effectively predicted, providing strong support for subsequent power distribution management.

[0069] The step S200 includes: step S201: obtaining the charging state of each battery module and the acceleration data of the vehicle in real time through the vehicle-mounted sensor, and building a neural network prediction in combination with the current driving habit classification result, taking the acceleration of the vehicle, the average charging state of the battery pack and the current driving behavior pattern as feature inputs, and predicting the total load demand P at time t through the training and learning of the neural network. total (t); The total load is distributed to each battery module by considering the charge state of each battery module, according to the formula:

[0070]

[0071] Where P total,i (t) represents the load demand of each battery module at time t, and N represents the number of battery modules in the battery pack;

[0072] Step S202: Obtain the temperature parameter T of each battery module through the temperature sensor i , where T i represents the temperature of the i-th battery module, monitors the temperature of each battery module in real time, and builds a temperature scheduling model to balance the temperature and load requirements of different battery modules; for each battery module, a temperature safety interval [T min , T max ], where T min and T max Indicates the lower and upper limits of the safe temperature range. If the battery temperature T i If it exceeds the safety range, the charging and discharging power of the corresponding battery module will be adjusted;

[0073] For each battery module, according to the temperature T of the corresponding battery module i Adjust its charging and discharging power according to the formula:

[0074]

[0075] Where P i (t) represents the charge and discharge power of the i-th battery module at time t, P represents the rated power of the battery module, T represents the normal operating temperature of the battery module, and T i (t) represents the temperature of the ith battery module at time t; when the temperature of the battery module T i (t) is in the temperature safety range [T min , T max ], indicating that the battery module can work normally and provide maximum power; when T i (t) is lower than T min and T i (t) is lower than T max hour, The value of will increase, making P i As the value of (t) decreases, the charging power of the battery module will decrease;

[0076] Step S203: setting an objective function for adjusting the charge and discharge power among the multiple battery modules, thereby balancing the power demand and temperature safety, according to the formula:

[0077]

[0078] Where Y represents the objective function, and λ represents the weight factor of temperature deviation on power allocation. The gradient descent algorithm is used to optimize the objective function Y through continuous iteration, and finally the charging and discharging power of each battery module at time t is obtained.

[0079] In the above technical solution, when the vehicle enters a high-load state, the charging and discharging power of each battery module can be dynamically adjusted according to the temperature distribution and load demand of each battery module in the battery pack, which not only ensures the efficient utilization of the battery pack, but also avoids overheating or damage caused by overload of a single battery module. The total load demand is predicted by a neural network, and the load is distributed according to the charging state of the battery module, and the power is adjusted in combination with the temperature scheduling model. This multi-level optimization strategy enables the performance of the battery pack to be fully utilized, while also extending the battery life.

[0080] Step S300 includes: Step S301: After adjusting the charge and discharge power of each battery module, evaluate the power supply of each battery module to determine whether the existing power can meet the adjusted load demand. For each battery module i, compare the actual power output P at time t. i (t) and load demand P total,i (t), if P i (t)>=P total,i (t), the battery module is considered to have sufficient power supply; if P i (t) <P total,i (t), it is considered that the battery module has insufficient power supply;

[0081] Step S302: If any battery module has insufficient power supply, a warning prompt is issued to the driver through the vehicle display screen, which includes the number of the battery module with insufficient power supply and the difference between the current load demand and the power output; if all battery modules have sufficient power supply, the temperature of each battery module is continuously monitored.

[0082] In the above technical solution, after adjusting the charging and discharging power, the power supply of each battery module will be evaluated to ensure that the power supply can meet the adjusted load demand; once insufficient power supply is detected, an early warning prompt will be immediately issued to the driver through the vehicle display screen, so that the driver can understand the power status of the battery module in time and take corresponding countermeasures; this early warning mechanism not only improves driving safety, but also avoids vehicle failures or accidents caused by insufficient power.

[0083] The step S400 includes: step S401: constructing an LSTM model, collecting temperature data of each battery module in real time through a temperature sensor, comparing and calculating the temperature difference between each battery module to form a temperature difference data set, and taking the historical temperature data, current load demand, ambient temperature and battery charge and discharge strategy as the input of the model, training the model, and using the trained model to predict the temperature change of each battery module in the future;

[0084] Step S402: According to the temperature prediction result and the preset temperature safety range, the working mode of the vehicle cooling system is intelligently adjusted. If it is predicted that the temperature of a battery module will exceed T in the future, max , the cooling system is started in advance to reduce the temperature of the battery module; if it is predicted that the temperature of a battery module will be lower than T in the future min , the working part of the cooling system can be reduced.

[0085] In the above technical solution, an LSTM model is constructed to predict the temperature changes of each battery module in the future, and the working mode of the vehicle cooling system is intelligently adjusted according to the prediction results. This can not only effectively prevent the battery module from being damaged due to overheating, but also reduce the working part of the cooling system when necessary, thereby improving the energy efficiency of the vehicle.

[0086] A vehicle power distribution control and management system, the system comprising a data collection and analysis module, a power adjustment module, a power supply evaluation module, and a temperature prediction and adjustment module;

[0087] The data collection and analysis module is used to collect the historical driving data of the vehicle and the driving behavior data of the driver, analyze the driving habits of the driver, and monitor the driving status of the vehicle in real time in combination with the on-board sensors to comprehensively judge whether the vehicle has entered a high-load state;

[0088] The power adjustment module is used to dynamically adjust the charge and discharge power of each battery module according to the temperature distribution and load requirements of each battery module in the battery pack when the vehicle enters a high load state;

[0089] The power supply evaluation module is used to evaluate the power supply of each battery module according to the power adjustment result, and issue a warning to the driver if there is insufficient power supply, and continuously monitor the temperature of each battery module if the power supply is sufficient;

[0090] The temperature prediction and adjustment module is used to analyze the temperature difference between the battery modules in the battery pack, predict the temperature change of each battery module, and intelligently adjust the vehicle's cooling system to achieve temperature balance of each battery module under high load conditions.

[0091] The data collection and analysis module includes a data collection unit, a driving habit analysis unit, and a high load state judgment unit;

[0092] The data collection unit collects the historical driving data of the vehicle and the driving behavior data of the driver; the driving habit analysis unit extracts features from the two collected data, performs cluster analysis on the extracted feature data through the K-means clustering algorithm, and finally divides the driver's driving habits into K different driving behavior modes according to the analysis results, which are represented as {C1, C2, ..., C k}, where C k represents the kth driving behavior mode; based on the usage specifications of vehicle components and statistical analysis of historical data, the conditions for vehicles under different driving behavior modes to enter a high load state are set;

[0093] The high load state judgment unit obtains the current driving data of the vehicle and the driving behavior data of the driver in real time through the vehicle-mounted sensor and the classification result {C1, C2, ..., C k} to match and determine the driving behavior mode of the current driver. According to the preset threshold conditions, when any one of the conditions is met, it is determined that the vehicle enters a high-load state.

[0094] The power adjustment module includes a load demand prediction and allocation unit, a temperature monitoring and power adjustment unit, and a power balance optimization unit;

[0095] The load demand prediction and allocation unit obtains the charging status of each battery module and the acceleration data of the vehicle in real time through the on-board sensor, and builds a neural network prediction based on the current driving habit classification results. The vehicle acceleration, the average charging status of the battery pack and the current driving behavior pattern are used as feature inputs. Through the training and learning of the neural network, the total load demand P at time t is predicted. total (t); The total load is distributed to each battery module by considering the charge state of each battery module, according to the formula:

[0096]

[0097] Where P total,i (t) represents the load demand of each battery module at time t, and N represents the number of battery modules in the battery pack;

[0098] The temperature monitoring and power adjustment unit obtains the temperature parameter T of each battery module through the temperature sensor. i , where T irepresents the temperature of the i-th battery module, monitors the temperature of each battery module in real time, and builds a temperature scheduling model to balance the temperature and load requirements of different battery modules; for each battery module, a temperature safety interval [T min , T max ], where T min and T max Indicates the lower and upper limits of the safe temperature range. If the battery temperature T i If the temperature exceeds the safe range, the charge and discharge power of the corresponding battery module is adjusted; for each battery module, according to the temperature T i Adjust its charging and discharging power according to the formula:

[0099]

[0100] Where P i (t) represents the charge and discharge power of the i-th battery module at time t, P represents the rated power of the battery module, T represents the normal operating temperature of the battery module, and T i (t) represents the temperature of the i-th battery module at time t;

[0101] The power balance optimization unit sets an objective function for adjusting the charge and discharge power between multiple battery modules to balance power demand and temperature safety, according to the formula:

[0102]

[0103] Where Y represents the objective function, and λ represents the weight factor of temperature deviation on power allocation. The gradient descent algorithm is used to optimize the objective function Y through continuous iteration, and finally the charging and discharging power of each battery module at time t is obtained.

[0104] The power supply assessment module includes a power supply assessment unit and an early warning prompt unit;

[0105] The power supply evaluation unit is used to evaluate the power supply of each battery module after adjusting the charge and discharge power of each battery module, to determine whether the existing power can meet the adjusted load demand, and for each battery module i, to compare the actual power output P at time t. i (t) and load demand P total,i (t), if P i (t)>=P total,i (t), the battery module is considered to have sufficient power supply; if P i (t) <P total,i (t), it is considered that the battery module has insufficient power supply;

[0106] The early warning prompt unit is used to issue an early warning prompt to the driver through the vehicle display screen when any battery module has insufficient power supply. The prompt content includes the number of the battery module with insufficient power supply and the difference between the current load demand and the power output; if the power supply of all battery modules is sufficient, the temperature of each battery module is continuously monitored.

[0107] The temperature prediction and adjustment module includes a temperature prediction unit and a cooling system adjustment unit;

[0108] The temperature prediction unit is used to build an LSTM model, collect the temperature data of each battery module in real time through the temperature sensor, compare and calculate the temperature difference between each battery module to form a temperature difference data set, and use the historical temperature data, current load demand, ambient temperature and battery charging and discharging strategy as the input of the model to train the model, and use the trained model to predict the temperature change of each battery module in the future;

[0109] The cooling system adjustment unit intelligently adjusts the working mode of the vehicle cooling system according to the temperature prediction result and the preset temperature safety range. If it is predicted that the temperature of a battery module will exceed Tmax in the future, the cooling system is started in advance to reduce the temperature of the battery module; if it is predicted that the temperature of a battery module will be lower than Tmin in the future, the working part of the cooling system can be reduced.

[0110] Embodiment: The vehicle's mileage, driving time, average speed and other data in the past month are obtained from the vehicle's driving record system, and the driver's accelerator pedal usage frequency, brake pedal stepping force, steering wheel rotation angle and speed and other data are captured and recorded in real time through the vehicle-mounted sensor during driving, and the collected data are feature extracted to obtain a feature data set; the feature data set is clustered and analyzed using the K-means clustering algorithm (setting K=3), and the driver's driving habits are divided into three modes: C1 (aggressive driving), C2 (normal driving), and C3 (gentle driving); based on the usage specifications of vehicle components and statistical analysis of historical data, conditions for vehicles in different driving behavior modes to enter a high-load state are set; for example, for the C1 mode, the engine load exceeds 80%, the motor load exceeds 70%, the vehicle acceleration is greater than 0.5g, the fuel consumption exceeds 15L / 100km, or the battery voltage is lower than 12V as conditions for entering a high-load state;

[0111] The vehicle's current driving data and the driver's driving behavior data are obtained in real time through on-board sensors, and the real-time data is matched with the classification results {C1, C2, C3} to determine that the current driver's driving behavior mode is C1; according to the preset threshold conditions, when the current engine load reaches 85% and the motor load reaches 75%, it is determined that the vehicle enters a high-load state.

[0112] The charging status of each battery module and the acceleration data of the vehicle are obtained in real time through the on-board sensors; a neural network prediction model is constructed, and the total load demand P at t = 10s is predicted through neural network training and learning. total (10s) = 200kW;

[0113] Assume that there are 5 battery modules in the battery pack, and the charging states of the battery modules are {60%, 55%, 50%, 45%, 40%} respectively.

[0114] Calculate the load demand of each battery module at t=10s according to the formula:

[0115] P total,1 (10s)=(60%) / (60%+55%+50%+45%+40%)×200=48kW;

[0116] P total,2 (10s)=(55%) / (60%+55%+50%+45%+40%)×200=44kW;

[0117] P total,3 (10s)=(50%) / (60%+55%+50%+45%+40%)×200=40kW;

[0118] P total,4 (10s)=(45%) / (60%+55%+50%+45%+40%)×200=36kW;

[0119] P total,5 (10s)=(40%) / (60%+55%+50%+45%+40%)×200=32kW;

[0120] The normal operating temperature of each battery module is set to 25°C, and the safe temperature range is [20°C, 30°C]. The temperature parameters of each battery module are obtained through the temperature sensor, which are {24°C, 26°C, 27°C, 23°C, 22°C} respectively.

[0121] Adjust the charge and discharge power of each battery module according to the formula: For the first battery module: P1(10s)=200×(1-(|24-25|) / (30-20))=180kW; Calculate the charge and discharge power of other battery modules and get:

[0122] P2(10s)=198kW,P3(10s)=195kW,P4(10s)=192kW,P5(10s)=187.5kW;

[0123] The objective function Y is determined and optimized using the gradient descent algorithm. After multiple iterations, the final charge and discharge power of each battery module at t = 10s is {185kW, 197kW, 196kW, 191kW, 186kW}.

[0124] By comparing the actual power output of each battery module at t=10s with the load demand, it is found that the actual power output of all battery modules is greater than or equal to the load demand, so it is considered that the power supply is sufficient; an LSTM model is constructed, and historical temperature data, current load demand, ambient temperature and battery charging and discharging strategy are used as input for training, and the trained model is used to predict the temperature change of each battery module in the next minute; assuming that it is predicted that the temperature of the first battery module will exceed 30°C in the next minute, the cooling system is started in advance to reduce its temperature; for other battery modules, since their temperatures are predicted to remain in a safe range, there is no need to adjust the working mode of the cooling system.

[0125] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A vehicle power distribution control management method, characterized in that: The method comprises: Step S100: Collect the historical driving data of the vehicle and the driving behavior data of the driver, analyze the driving habits of the driver, and monitor the driving status of the vehicle in real time in combination with the vehicle-mounted sensors to comprehensively determine whether the vehicle enters a high-load state; Step S200: When the vehicle enters a high load state, dynamically adjusting the charge and discharge power of each battery module according to the temperature distribution and load requirements of each battery module in the battery pack; Step S300: Evaluate the power supply of each battery module according to the power adjustment result, and issue a warning to the driver if there is insufficient power supply; if the power supply is sufficient, continuously monitor the temperature of each battery module; Step S400: Analyze the temperature difference between the battery modules in the battery pack, predict the temperature change of each battery module, and intelligently adjust the cooling system of the vehicle to achieve temperature balance of each battery module under high load conditions.

2. A vehicle power distribution control management method according to claim 1, characterized in that: The step S100 includes: Step S101: the historical driving data of the vehicle refers to the relevant information of the driving condition of the vehicle in the past period of time obtained from the driving record system of the vehicle, and the driving behavior data of the driver refers to the behavior data of the driver during driving captured and recorded in real time by the vehicle-mounted sensor; Step S102: extracting features from the two types of data collected, including extracting the vehicle's mileage, driving time, speed and related data from the historical driving data, and extracting the frequency of use of the accelerator pedal, the braking force, the steering wheel rotation angle and speed from the driver's driving behavior data; performing cluster analysis on the extracted feature data using the K-means clustering algorithm, and finally dividing the driver's driving habits into K different driving behavior patterns according to the analysis results, represented as {C1, C2, ..., C k }, where C k represents the kth driving behavior mode, and based on the usage specifications of vehicle components and the statistical analysis of historical data, sets the conditions for vehicles in different driving behavior modes to enter a high-load state, wherein the conditions for entering a high-load state include engine load, motor load, vehicle acceleration, fuel consumption exceeding a set threshold, and battery voltage being lower than a set threshold, and the setting of the threshold is based on the usage specifications of vehicle components and the statistical analysis of historical data; Step S103: Obtain the current driving data of the vehicle and the driving behavior data of the driver in real time through the vehicle-mounted sensor and compare them with the classification results {C1, C2, ..., C k } to match and determine the driving behavior mode of the current driver. According to the preset threshold conditions, when any one of the conditions is met, it is determined that the vehicle enters a high-load state.

3. A vehicle power distribution control management method according to claim 1, characterized in that: The step S200 includes: Step S201: The charging state of each battery module and the acceleration data of the vehicle are obtained in real time through the on-board sensors, and a neural network prediction is constructed in combination with the current driving habit classification results. The vehicle acceleration, the average charging state of the battery pack and the current driving behavior pattern are used as feature inputs. Through the training and learning of the neural network, the total load demand P at time t is predicted. total (t); The total load is distributed to each battery module by considering the charge state of each battery module, according to the formula: Where P total,i (t) represents the load demand of each battery module at time t, and N represents the number of battery modules in the battery pack; Step S202: Obtain the temperature parameter T of each battery module through the temperature sensor i , where T i represents the temperature of the i-th battery module, monitors the temperature of each battery module in real time, and builds a temperature scheduling model to balance the temperature and load requirements of different battery modules; for each battery module, a temperature safety interval [T min , T max ], where T min and T max Indicates the lower and upper limits of the safe temperature range. If the battery temperature T i If the temperature exceeds the safe range, the charge and discharge power of the corresponding battery module is adjusted; for each battery module, according to the temperature T i Adjust its charging and discharging power according to the formula: Where P i (t) represents the charge and discharge power of the i-th battery module at time t, P represents the rated power of the battery module, T represents the normal operating temperature of the battery module, and T i (t) represents the temperature of the i-th battery module at time t; Step S203: setting an objective function for adjusting the charge and discharge power among multiple battery modules to balance power demand and temperature safety, according to the formula: Where Y represents the objective function, and λ represents the weight factor of temperature deviation on power allocation. The gradient descent algorithm is used to optimize the objective function Y through continuous iteration, and finally the charging and discharging power of each battery module at time t is obtained.

4. A vehicle power distribution control management method according to claim 1, characterized in that: Step S300 includes: Step S301: After adjusting the charge and discharge power of each battery module, evaluate the power supply of each battery module to determine whether the existing power can meet the adjusted load demand. For each battery module i, compare the actual power output P at time t. i (t) and load demand P total,i (t), if P i (t)>=P total,i (t), the battery module is considered to have sufficient power supply; if P i (t) <P total,i (t), it is considered that the battery module has insufficient power supply; Step S302: If any battery module has insufficient power supply, a warning prompt is issued to the driver through the vehicle display screen, which includes the number of the battery module with insufficient power supply and the difference between the current load demand and the power output; if all battery modules have sufficient power supply, the temperature of each battery module is continuously monitored.

5. A vehicle power distribution control management method according to claim 1, characterized in that: The step S400 includes: Step S401: construct an LSTM model, collect the temperature data of each battery module in real time through the temperature sensor, compare and calculate the temperature difference between each battery module to form a temperature difference data set, and use the historical temperature data, current load demand, ambient temperature and battery charging and discharging strategy as the input of the model, train the model, and use the trained model to predict the temperature change of each battery module in the future; Step S402: According to the temperature prediction result and the preset temperature safety range, the working mode of the vehicle cooling system is intelligently adjusted. If it is predicted that the temperature of a battery module will exceed T in the future, max , the cooling system is started in advance to reduce the temperature of the battery module; if it is predicted that the temperature of a battery module will be lower than T in the future min , the working part of the cooling system can be reduced.

6. A vehicle power distribution control management system, characterized in that: The system includes a data collection and analysis module, a power adjustment module, a power supply assessment module, and a temperature prediction and regulation module; The data collection and analysis module is used to collect the historical driving data of the vehicle and the driving behavior data of the driver, analyze the driving habits of the driver, and monitor the driving status of the vehicle in real time in combination with the on-board sensors to comprehensively judge whether the vehicle has entered a high-load state; The power adjustment module is used to dynamically adjust the charge and discharge power of each battery module according to the temperature distribution and load requirements of each battery module in the battery pack when the vehicle enters a high load state; The power supply evaluation module is used to evaluate the power supply of each battery module according to the power adjustment result, and issue a warning to the driver if there is insufficient power supply, and continuously monitor the temperature of each battery module if the power supply is sufficient; The temperature prediction and adjustment module is used to analyze the temperature difference between the battery modules in the battery pack, predict the temperature change of each battery module, and intelligently adjust the vehicle's cooling system to achieve temperature balance of each battery module under high load conditions.

7. A vehicle power distribution control management system according to claim 6, characterized in that: The data collection and analysis module includes a data collection unit, a driving habit analysis unit, and a high load state judgment unit; The data collection unit collects the historical driving data of the vehicle and the driving behavior data of the driver; the driving habit analysis unit extracts features from the two collected data, performs cluster analysis on the extracted feature data through the K-means clustering algorithm, and finally divides the driver's driving habits into K different driving behavior modes according to the analysis results, which are represented as {C1, C2, ..., C k }, where C k represents the kth driving behavior mode; based on the usage specifications of vehicle components and statistical analysis of historical data, the conditions for vehicles under different driving behavior modes to enter a high load state are set; The high load state judgment unit obtains the current driving data of the vehicle and the driving behavior data of the driver in real time through the vehicle-mounted sensor and the classification result {C1, C2, ..., C k } to match and determine the driving behavior mode of the current driver. According to the preset threshold conditions, when any one of the conditions is met, it is determined that the vehicle enters a high-load state.

8. A vehicle power distribution control management system according to claim 6, characterized in that: The power adjustment module includes a load demand prediction and allocation unit, a temperature monitoring and power adjustment unit, and a power balance optimization unit; The load demand prediction and allocation unit obtains the charging status of each battery module and the acceleration data of the vehicle in real time through the on-board sensor, and builds a neural network prediction based on the current driving habit classification results. The vehicle acceleration, the average charging status of the battery pack and the current driving behavior pattern are used as feature inputs. Through the training and learning of the neural network, the total load demand P at time t is predicted. total (t); The total load is distributed to each battery module by considering the charge state of each battery module, according to the formula: Where P total,i (t) represents the load demand of each battery module at time t, and N represents the number of battery modules in the battery pack; The temperature monitoring and power adjustment unit obtains the temperature parameter T of each battery module through the temperature sensor. i , where T i represents the temperature of the i-th battery module, monitors the temperature of each battery module in real time, and builds a temperature scheduling model to balance the temperature and load requirements of different battery modules; for each battery module, a temperature safety interval [T min , T max ], where T min and T max Indicates the lower and upper limits of the safe temperature range. If the battery temperature T i If the temperature exceeds the safe range, the charge and discharge power of the corresponding battery module is adjusted; for each battery module, according to the temperature T i Adjust its charging and discharging power according to the formula: Where P i (t) represents the charge and discharge power of the i-th battery module at time t, P represents the rated power of the battery module, T represents the normal operating temperature of the battery module, and T i (t) represents the temperature of the i-th battery module at time t; The power balance optimization unit sets an objective function for adjusting the charge and discharge power between multiple battery modules to balance power demand and temperature safety, according to the formula: Where Y represents the objective function, and λ represents the weight factor of temperature deviation on power allocation. The gradient descent algorithm is used to optimize the objective function Y through continuous iteration, and finally the charging and discharging power of each battery module at time t is obtained.

9. A vehicle power distribution control management system according to claim 6, characterized in that: The power supply assessment module includes a power supply assessment unit and an early warning prompt unit; The power supply evaluation unit is used to evaluate the power supply of each battery module after adjusting the charge and discharge power of each battery module, to determine whether the existing power can meet the adjusted load demand, and for each battery module i, to compare the actual power output P at time t. i (t) and load demand P total,i (t), if P i (t)>=P total,i (t), the battery module is considered to have sufficient power supply; if P i (t) <P total,i (t), it is considered that the battery module has insufficient power supply; The early warning prompt unit is used to issue an early warning prompt to the driver through the vehicle display screen when any battery module has insufficient power supply. The prompt content includes the number of the battery module with insufficient power supply and the difference between the current load demand and the power output; if the power supply of all battery modules is sufficient, the temperature of each battery module is continuously monitored.

10. A vehicle power distribution control management system according to claim 6, characterized in that: The temperature prediction and adjustment module includes a temperature prediction unit and a cooling system adjustment unit; The temperature prediction unit is used to build an LSTM model, collect the temperature data of each battery module in real time through the temperature sensor, compare and calculate the temperature difference between each battery module to form a temperature difference data set, and use the historical temperature data, current load demand, ambient temperature and battery charging and discharging strategy as the input of the model to train the model, and use the trained model to predict the temperature change of each battery module in the future; The cooling system adjustment unit intelligently adjusts the working mode of the vehicle cooling system according to the temperature prediction result and the preset temperature safety range. If it is predicted that the temperature of a battery module will exceed Tmax in the future, the cooling system is started in advance to reduce the temperature of the battery module; if it is predicted that the temperature of a battery module will be lower than Tmin in the future, the working part of the cooling system can be reduced.

Images