Ultra-fast charging control method and system for an electric vehicle

Abstract

The present invention discloses a supercharging control method and system for an electric vehicle, relating to the technical field of supercharging control. This method can accurately predict and evaluate the temperature change of the battery by collecting battery data in real time during the supercharging process and combining the normalized data set and the charging feature vector set. In particular, by constructing a heat and temperature algorithm model, the system can predict the change trend of the battery temperature during the supercharging process. When the predicted temperature value Tb exceeds the temperature threshold T, the system can immediately trigger the collaborative mechanism of the adaptive charging power and the cooling system, and automatically adjust the supercharging power Pcha and the cooling power Pcool. Through this mechanism, when the battery temperature is close to the safety upper limit, the overheating risk can be effectively avoided, and the safety of the charging process can be ensured. This measure significantly improves the accuracy of battery temperature management, reduces the risk of battery damage caused by abnormal temperature, and helps to extend the service life of the battery.

Description

Technical Field

[0001] The present invention relates to the technical field of supercharging control, and in particular to a supercharging control method and system for an electric vehicle. Background Art

[0002] As an important development direction in the global transportation field, electric vehicles (EVs) represent the trend of green travel in the future. With the rapid development of new energy vehicles, the charging technology and management system of electric vehicles are also constantly innovating and upgrading, especially in supercharging technology. Supercharging technology refers to a charging method that charges a large amount of electricity into the battery of an electric vehicle in a relatively short period of time. It is widely used in long-distance travel and emergency charging needs of electric vehicles. In order to improve the efficiency of supercharging and the service life of the battery, the battery management system BMS and the thermal management system play a vital role in the charging process of electric vehicles, ensuring that the temperature control and power regulation during the battery charging process are in the optimal state. Therefore, the innovation of supercharging control methods is particularly important, especially in the optimization of battery thermal management.

[0003] At present, in the existing supercharging technology, although the battery charging state is monitored by the intelligent battery management system, there are still a series of problems, especially in the temperature management and charging efficiency of the battery during the charging process. During the supercharging process, the battery generates a lot of heat due to the charging effect of the large current, which will cause the battery temperature to rise rapidly. Most of the existing thermal management systems rely on static temperature monitoring and cooling strategies, and fail to dynamically adapt to the needs under different charging conditions. Even if equipped with a cooling system, the real-time coordinated adjustment of charging power and temperature is often extensive and lacks accurate prediction and adjustment. Current technology cannot effectively avoid battery overheating or uneven temperature distribution, resulting in low charging efficiency, overcharging, and even loss of battery life. These problems have hindered the further development of supercharging technology, especially in the context of the popularization of fast charging piles and the increasing demand for ultra-long-range electric vehicles. How to ensure safe and efficient charging has become a key issue that needs to be solved urgently. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a supercharging control method and system for an electric vehicle, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented by the following technical scheme: comprising the following steps:

[0006] S1. After supercharging starts, the built-in sensor group is automatically turned on through the battery management system BMS of the electric vehicle to collect battery data in real time during the supercharging process, transmit it to the battery control system, and pre-process the battery data to obtain a normalized data set;

[0007] S2. Extract features from the normalized data set to obtain a charging feature vector set. At the same time, connect to the cloud server, build a cloud database in the cloud server, and transmit the charging feature vector set to the cloud database for storage;

[0008] S3. Build a heat and temperature algorithm model, extract the charging feature vector set and input it into the heat and temperature algorithm model, calculate and output the heat generation value Qgen and the predicted temperature value Tb, set the temperature threshold T, and perform temperature prediction evaluation on the temperature threshold T and the predicted temperature value Tb to analyze the temperature change of the battery of the electric vehicle during the supercharging process;

[0009] S4. When the battery temperature is abnormally predicted and evaluated, execute the adaptive charging power and cooling system cooperation mechanism, and calculate and output the supercharging power adjustment value Pcha and the cooling power adjustment value Pcool respectively;

[0010] S5. After the adaptive charging power and cooling system cooperation mechanism is executed, calculate and output the battery supercharging efficiency Eeff, set the efficiency threshold E, and then perform efficiency evaluation on the efficiency threshold E and the battery supercharging efficiency Eeff to judge the efficiency status and temperature adjustment situation during the supercharging process.

[0011] Preferably, S1 includes S11 and S12;

[0012] S11. Directly connect to the electric vehicle through the supercharging cable, access the battery management system BMS of the electric vehicle, automatically turn on the built-in sensor group of the electric vehicle, and collect the battery data of the electric vehicle in real time during the supercharging process;

[0013] The built-in sensor group includes a voltage sensor, a current sensor, a temperature sensor, and a thermal sensor;

[0014] The battery data includes the voltage Vbat, the charging current Icha, the battery temperature T, the battery heat transfer Q, the ambient temperature Tenv, and the coolant temperature Tcoo;

[0015] S12. Then transmit the battery data to the battery control system of the electric vehicle, and preprocess the battery data in the battery control system to obtain a normalized data set. The preprocessing includes denoising, outlier detection, timestamp marking, missing value filling, and normalization;

[0016] The denoising is performed by using the moving average method to denoise the battery data;

[0017] The outlier detection is performed by using the Z-score standard deviation method to identify the outliers in the battery data and eliminate the outliers;

[0018] The timestamp marking marks the battery data with timestamps based on the acquisition time of the built-in sensor group;

[0019] The missing value filling is performed by using data at adjacent moments;

[0020] The normalization standardizes by using the Min-Max normalization method to map the value of each parameter in the battery data to a fixed interval, eliminating the differences in different dimensions of each parameter in the battery data;

[0021] The normalized data set includes the battery voltage Vbat(t) at time t, the charging current Icha(t) at time t, the battery temperature T(t) at time t, the heat transfer quantity Q(t) of the battery at time t, the ambient temperature Tenv(t) at time t, and the coolant temperature Tcoo(t) at time t.

[0022] Preferably, the S2 includes S21 and S22;

[0023] S21, based on the normalized data set, performs feature extraction to obtain a charging feature vector set;

[0024] The charging feature vector set includes the battery internal resistance Rbat(t) at time t, the battery temperature gradient △Tbat(t) at time t, the battery heat capacity Cbat(t) at time t, the ambient temperature Tenv(t) at time t, the coolant cooling efficiency Ncoo(t) at time t, and the charging current Icha(t) at time t;

[0025] The battery internal resistance Rbat(t) at time t is extracted by combining the voltage Vbat(t) at time t and the charging current Icha(t) at time t. The specific feature extraction algorithm formula is: ; where, Vopen represents the open-circuit voltage of the battery;

[0026] The battery temperature gradient △Tbat(t) at time t is extracted by calculating the temperature difference of the battery temperature T at different positions of the battery. The specific feature extraction algorithm formula is: ; where, Tbat max represents the upper temperature limit point inside the battery, and Tbat min represents the lower temperature limit point inside the battery;

[0027] The battery heat capacity Cbat(t) at time t is extracted by using the heat balance equation and combining the battery temperature T(t) at time t and the heat transfer quantity Q(t) of the battery at time t. The specific feature extraction algorithm formula is: ; where d represents a small variable, dQ(t) represents the small change in the heat transferred by the battery at time t, and dT(t) represents the small change in the battery temperature at time t;

[0028] The coolant cooling efficiency Ncoo(t) at time t is calculated and extracted by monitoring the temperature change of the cooling system. The specific feature extraction algorithm formula is: , where △Tcoo(t) represents the coolant temperature change at time t, and Tx max represents the upper limit of the designed temperature difference of the cooling system;

[0029] S22. Connect the cloud server and the battery control system through a communication network, construct a cloud database in the cloud server, upload the charging feature vector set to the cloud database through the communication network, and perform cloud storage on the charging feature vector set.

[0030] Preferably, S3 includes S31, S32, and S33;

[0031] S31. Construct the heat and temperature algorithm model in the cloud server. The heat and temperature algorithm model includes a heat algorithm model and a temperature algorithm model, and extract the charging feature vector set and input it into the heat algorithm model for calculation to output the heat generation value Qgen, and predict the heat generated by the battery of the electric vehicle during the supercharging process;

[0032] The heat generation value Qgen is calculated and output through the following heat algorithm model;

[0033] ;

[0034] In the formula, Qgen(t) represents the heat generation value at time t.

[0035] Preferably, S32. Based on the heat generation value Qgen, combined with the charging feature vector set, input it into the temperature algorithm model, calculate and output the predicted temperature value Tb, and predict and analyze the temperature of the battery of the electric vehicle during the supercharging process;

[0036] The predicted temperature value Tb is calculated and output through the following temperature algorithm model;

[0037] ;

[0038] In the formula, Tb(t) represents the predicted temperature value at time t;

[0039] S33. Initially set the temperature threshold T based on the battery temperature standard of the electric vehicle, then perform temperature prediction evaluation on the predicted temperature value Tb(t) at the moment t and the temperature threshold T, analyze the abnormal change of the battery temperature during the supercharging process, and generate the trigger condition for the collaborative mechanism of the adaptive charging power and the cooling system based on the evaluation result. The specific evaluation content is as follows;

[0040] When the predicted temperature value Tb(t) at the moment t > the temperature threshold T, it indicates that the temperature change of the battery is abnormal during the supercharging process. At this time, trigger the execution of the collaborative mechanism of the adaptive charging power and the cooling system;

[0041] When the predicted temperature value Tb(t) at the moment t ≤ the temperature threshold T, it indicates that the temperature change of the battery is normal during the supercharging process, and there is no need for intervention and continuous monitoring.

[0042] Preferably, the S4 includes S41 and S42;

[0043] S41. When the temperature change is evaluated as abnormal through temperature prediction, execute the collaborative mechanism of the adaptive charging power and the cooling system. The collaborative mechanism of the adaptive charging power and the cooling system includes an adaptive charging power adjustment mechanism and a cooling system adjustment mechanism;

[0044] The adaptive charging power adjustment mechanism calculates and outputs the supercharging power adjustment value Pcha according to the predicted temperature value Tb(t) of the battery at the moment t during the supercharging process. When the battery temperature is approaching the upper limit, the supercharging power adjustment value Pcha is sent to the battery control system through the cloud server, and the supercharging power is controlled through the battery control system;

[0045] The supercharging power adjustment value Pcha is calculated and output through the following algorithm formula;

[0046] ;

[0047] In the formula, Pcha(t) represents the supercharging power adjustment value at the moment t, Pmax represents the upper limit value of the supercharging power, and Tmax represents the upper limit value of the battery safety temperature.

[0048] Preferably, S42. The cooling system adjustment mechanism calculates and outputs the cooling power adjustment value Pcool through the battery temperature gradient △Tbat(t) at the moment t, the battery heat capacity Cbat(t) at the moment t, the ambient temperature Tenv(t) at the moment t, and the coolant cooling efficiency Ncoo(t) at the moment t, and combines with the predicted temperature value Tb(t) at the moment t to be predicted, and dynamically adjusts the power of the battery cooling system;

[0049] The cooling power adjustment value Pcool is calculated and output through the following algorithm formula;

[0050] ;

[0051] In the formula, Pcool(t) represents the cooling power adjustment value at time t.

[0052] Preferably, S5 includes S51 and S52;

[0053] After the collaborative mechanism of the re - adaptive charging power and the cooling system is executed, the battery over - charging efficiency Eeff of the electric vehicle is comprehensively calculated to quantify the heat management and over - charging power conditions of the electric vehicle during over - charging;

[0054] The battery over - charging efficiency Eeff is calculated and output through the following algorithm formula;

[0055] .

[0056] Preferably, in S52, based on the standard of the battery charging temperature of the electric vehicle, an efficiency threshold E is set, and then the battery over - charging efficiency Eeff is evaluated with the efficiency threshold E to analyze the heat management and charging power during over - charging. The specific evaluation content is as follows;

[0057] When the battery over - charging efficiency Eeff ≥ the efficiency threshold E, the battery temperature is in a normal state under the current adjusted over - charging efficiency, and at this time, no intervention is required and continuous monitoring is carried out;

[0058] When the battery over - charging efficiency Eeff < the efficiency threshold E, the battery temperature is in an abnormal state under the current adjusted over - charging efficiency. At this time, the cooling system efficiency is automatically increased to 100%, and S5 is executed again to re - analyze the heat management and charging power during over - charging. If an abnormal state is detected in the secondary analysis, the over - charging is automatically stopped. If the secondary analysis shows a normal state, continuous monitoring is continued.

[0059] An over - charging control system for an electric vehicle includes an over - charging data acquisition module, a feature extraction module, a heat and temperature analysis module, an adaptive adjustment module, and an over - charging efficiency and temperature analysis module;

[0060] The over - charging data acquisition module automatically activates the built - in sensor group through the battery management system BMS of the electric vehicle after the start of over - charging, collects the battery data during over - charging in real - time, transmits it to the battery control system, and pre - processes the battery data to obtain a normalized data set;

[0061] The feature extraction module extracts charging feature vectors from the normalized dataset, and at the same time connects to the cloud server, constructs a cloud database in the cloud server, and transmits the charging feature vector set to the cloud database for storage;

[0062] The heat and temperature analysis module constructs a heat and temperature algorithm model, extracts the charging feature vector set and inputs it into the heat and temperature algorithm model, calculates and outputs the heat generation value Qgen and the predicted temperature value Tb, sets the temperature threshold T, and performs temperature prediction evaluation on the temperature threshold T and the predicted temperature value Tb to analyze the temperature change of the battery of the electric vehicle during the supercharging process;

[0063] When the adaptive adjustment module predicts that the battery temperature is abnormal through temperature prediction evaluation, it executes the collaborative mechanism of the adaptive charging power and the cooling system, and calculates and outputs the supercharging power adjustment value Pcha and the cooling power adjustment value Pcool respectively;

[0064] After the collaborative mechanism of the adaptive charging power and the cooling system is executed, the supercharging efficiency and temperature analysis module calculates and outputs the battery supercharging efficiency Eeff, sets the efficiency threshold E, and then performs efficiency evaluation on the efficiency threshold E and the battery supercharging efficiency Eeff to judge the efficiency status and temperature adjustment situation during the supercharging process.

[0065] The present invention provides a supercharging control method and system for an electric vehicle. It has the following beneficial effects:

[0066] (1) By collecting battery data in real time during the supercharging process and combining the normalized dataset and the charging feature vector set, this method can accurately predict and evaluate the temperature change of the battery. Especially by constructing a heat and temperature algorithm model, the system can predict the change trend of the battery temperature during the supercharging process. When the predicted temperature value Tb exceeds the temperature threshold T, the system can immediately trigger the collaborative mechanism of the adaptive charging power and the cooling system, and automatically adjust the supercharging power Pcha and the cooling power Pcool. Through this mechanism, when the battery temperature is close to the safety upper limit, the overheating risk can be effectively avoided, ensuring the safety of the charging process. This measure significantly improves the accuracy of battery temperature management, reduces the risk of battery damage caused by abnormal temperature, and helps to extend the service life of the battery.

[0067] (2) By comprehensively calculating the supercharging efficiency Eeff of the battery and setting an efficiency threshold E for evaluation, the system can effectively optimize the thermal management and power adjustment during charging. In the present invention, when the charging efficiency of the battery during supercharging is lower than the predetermined efficiency threshold E, the system will automatically activate the cooling system adjustment mechanism, increase the cooling system efficiency to 100%, and re-evaluate the thermal management and charging power of the battery. This process ensures that even if there is an efficiency anomaly during supercharging, the system can restore to the normal state through intelligent adaptive adjustment. In addition, the system can dynamically adjust the charging power and cooling power according to the real-time temperature and thermal management of the battery, so as to maintain the best charging efficiency of the battery throughout the charging process. This technology not only improves the efficiency of the battery charging process, but also effectively reduces the energy loss and excessive heat accumulation during charging.

[0068] (3) This method adopts a method for storing and calculating the charging feature vector set supported by a cloud server. By uploading the real-time data of the battery to the cloud database, the system can uniformly store and analyze the large-scale electric vehicle charging data and optimize the algorithm. The construction of the cloud database and the cloud learning function enable the battery control system to self-optimize in terms of charging characteristics, temperature control, and power adjustment based on the continuously accumulated battery data. This intelligent system based on data analysis can further improve the charging efficiency and safety of the battery according to the calculation results of the cloud server. At the same time, the support of cloud data also enables the sharing of experiences between vehicles, thus providing a more accurate and efficient supercharging control strategy. Brief Description of the Drawings

[0069] Figure 1 is a schematic flow chart of a supercharging control method for an electric vehicle according to the present invention;

[0070] Figure 2 is a schematic diagram of the steps of a supercharging control system for an electric vehicle according to the present invention. Detailed Embodiments

[0071] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0072] Embodiment 1

[0073] Please refer to Figure 1 , the present invention provides a supercharging control method for an electric vehicle. To achieve the above objectives, the present invention is realized through the following technical solutions: including the following steps:

[0074] S1. After the start of ultra-fast charging, automatically activate the built-in sensor group through the battery management system (BMS) of the electric vehicle, collect battery data in real time during the ultra-fast charging process, transmit it to the battery control system, and preprocess the battery data to obtain a normalized data set;

[0075] S2. Extract features from the normalized data set to obtain a charging feature vector set. At the same time, connect to the cloud server, build a cloud database in the cloud server, and transmit the charging feature vector set to the cloud database for storage;

[0076] S3. Build a heat and temperature algorithm model, extract the charging feature vector set and input it into the heat and temperature algorithm model, calculate and output the heat generation value Qgen and the predicted temperature value Tb, set the temperature threshold T, and perform temperature prediction evaluation on the temperature threshold T and the predicted temperature value Tb to analyze the temperature change of the battery of the electric vehicle during ultra-fast charging;

[0077] S4. When the battery temperature is abnormally predicted and evaluated, execute the collaborative mechanism of the adaptive charging power and the cooling system, and calculate and output the ultra-fast charging power adjustment value Pcha and the cooling power adjustment value Pcool respectively;

[0078] S5. After the collaborative mechanism of the adaptive charging power and the cooling system is executed, calculate and output the ultra-fast charging efficiency Eeff of the battery, set the efficiency threshold E, and then perform efficiency evaluation on the efficiency threshold E and the ultra-fast charging efficiency Eeff of the battery to judge the efficiency status and temperature adjustment situation during ultra-fast charging.

[0079] In this embodiment, the method automatically activates the built-in sensor group through the battery management system (BMS) of the electric vehicle to collect battery data in real time during the ultra-fast charging process. The collected battery data is preprocessed to obtain a normalized data set, ensuring the dimensional consistency between different data types. Then, feature extraction is performed on the normalized data to generate a charging feature vector set, which is uploaded to the database in the cloud server for storage, providing a basis for subsequent data analysis and model optimization. On the cloud server, based on the extracted charging feature vector set, a heat and temperature algorithm model is constructed. By calculation, the heat generation value Qgen and the predicted temperature value Tb are output, and a temperature threshold T is set for real-time evaluation of the battery temperature change. If the prediction result shows that the battery temperature is abnormal, the system will execute the collaborative mechanism of the adaptive charging power and the cooling system, adjusting the ultra-fast charging power Pcha and the cooling power Pcool to effectively manage the battery temperature, prevent overheating and optimize the charging efficiency. Finally, based on the temperature management and power adjustment during the ultra-fast charging process, the ultra-fast charging efficiency Eeff of the battery is calculated and compared with the efficiency threshold E to further evaluate the thermal management effect and the optimization level of the charging power during the battery charging process. Through this method, the present invention can accurately manage the battery temperature during the ultra-fast charging process, avoid risks such as overheating, and ensure the safety and health of the battery. At the same time, by dynamically adjusting the charging power and the cooling power, not only the charging efficiency of the battery is optimized, but also the energy waste and excessive heat accumulation are reduced, improving the overall efficiency of the charging process. In addition, based on cloud data analysis and feature extraction, the system can achieve intelligent adaptive adjustment, improving the automation and intelligence level of the electric vehicle charging system and ensuring the efficient and safe operation of the ultra-fast charging process.

[0080] Embodiment 2

[0081] This embodiment is an explanatory description based on Embodiment 1. Please refer to Figure 1 , specifically: S1 includes S11 and S12;

[0082] S11. Directly connect to the electric vehicle through the ultra-fast charging cable and access the battery management system (BMS) of the electric vehicle to automatically activate the built-in sensor group of the electric vehicle and collect the battery data of the electric vehicle in real time during the ultra-fast charging process;

[0083] The built-in sensor group includes a voltage sensor, a current sensor, a temperature sensor, and a thermosensitive sensor;

[0084] The battery data includes the battery voltage Vbat, the charging current Icha, the battery temperature T, the battery heat transfer Q, the ambient temperature Tenv, and the coolant temperature Tcoo;

[0085] The battery temperature T, the ambient temperature Tenv, and the coolant temperature Tcoo are collected by temperature sensors installed at different positions of the battery;

[0086] The voltage Vbat, the charging current Icha, and the heat transfer Q of the battery are respectively acquired through a voltage sensor, a current sensor, and a thermal sensor.

[0087] S12. Then, the battery data is transmitted to the battery control system of the electric vehicle, and the battery data is preprocessed in the battery control system to obtain a normalized data set. The preprocessing includes denoising, outlier detection, timestamp marking, missing value filling, and normalization.

[0088] Denoising is performed on the battery data by using a moving average method.

[0089] Outlier detection is used to identify outliers in the battery data by using the Z-score standard deviation method, and the outliers are removed.

[0090] Timestamp marking is performed on the battery data based on the acquisition time of the built-in sensor group.

[0091] Missing value filling is performed by using data at adjacent times.

[0092] Normalization is performed by using the Min-Max normalization method to map the value of each parameter in the battery data to a fixed interval, eliminating the different dimensional differences of each parameter in the battery data.

[0093] The normalized data set includes the voltage Vbat(t) at time t, the charging current Icha(t) at time t, the battery temperature T(t) at time t, the heat transfer Q(t) of the battery at time t, the ambient temperature Tenv(t) at time t, and the coolant temperature Tcoo(t) at time t.

[0094] In this embodiment, the method is as follows: when ultra-fast charging starts, the electric vehicle is directly connected to the battery management system BMS through a charging cable, and the built-in sensor group is automatically started to collect battery data in real time. Subsequently, the collected battery data is transmitted to the battery control system, and a series of preprocessing steps are performed in the control system to ensure the quality and accuracy of the data. These preprocessing steps include denoising, removing invalid data through outlier detection, aligning the data time using timestamp marking, filling missing values with data at adjacent times, and converting the data to a unified standard interval through the Min-Max normalization method to eliminate the dimensional differences between different parameters. After preprocessing, a normalized data set is formed. This series of processing steps first ensures the accuracy and consistency of the data, thereby improving the reliability of subsequent analysis.

[0095] Embodiment 3

[0096] This embodiment is an explanatory description based on Embodiment 2. Please refer toFigure 1 , specifically: S2 includes S21 and S22;

[0097] S21, based on the normalized dataset, performs feature extraction to obtain a charging feature vector set;

[0098] The charging feature vector set includes the battery internal resistance Rbat(t) at time t, the battery temperature gradient △Tbat(t) at time t, the battery heat capacity Cbat(t) at time t, the ambient temperature Tenv(t) at time t, the coolant cooling efficiency Ncoo(t) at time t, and the charging current Icha(t) at time t;

[0099] The battery internal resistance Rbat(t) at time t is extracted by combining the voltage Vbat(t) at time t and the charging current Icha(t) at time t. The specific feature extraction algorithm formula is: ; where Vopen represents the open-circuit voltage of the battery, i.e., the voltage without load;

[0100] The battery temperature gradient △Tbat(t) at time t is extracted by calculating the temperature difference of the battery temperature T at different positions of the battery. The specific feature extraction algorithm formula is: ; where Tbat max represents the upper limit point of the temperature inside the battery, and Tbat min represents the lower limit point of the temperature inside the battery;

[0101] The battery heat capacity Cbat(t) at time t is extracted by using the heat balance equation and combining the battery temperature T(t) at time t and the heat transfer Q(t) of the battery at time t. The specific feature extraction algorithm formula is: ; where d represents a small variable, dQ(t) represents the small change in the heat transfer of the battery at time t, and dT(t) represents the small change in the battery temperature at time t;

[0102] The coolant cooling efficiency Ncoo(t) at time t is extracted by monitoring the temperature change of the cooling system. The specific feature extraction algorithm formula is: , where △Tcoo(t) represents the temperature change of the coolant at time t, and Tx max represents the upper limit of the design temperature difference of the cooling system;

[0103] S22, connects the cloud server and the battery control system through a communication network, constructs a cloud database in the cloud server, uploads the charging feature vector set to the cloud database through the communication network, and performs cloud storage on the charging feature vector set.

[0104] In this embodiment, the method extracts features from battery data based on a normalized data set to form a charging feature vector set. These parameters are calculated and extracted through different algorithm formulas, reflecting the dynamic changes of the battery during the supercharging process. Subsequently, the charging feature vector set is uploaded to the cloud database for cloud storage, combining the computing power of the cloud server and the advantages of remote storage to ensure the efficient management and processing of data. This approach not only makes data storage more secure and flexible but also supports more complex analysis and optimization calculations. Through the above implementation method, the present invention can obtain various operating states and change data of the battery in real time and accurately, and through the extraction of feature vectors, help the battery management system to identify abnormal situations of the battery in a timely manner, thereby optimizing the power control and thermal management strategies during the charging process.

[0105] Embodiment 4

[0106] This embodiment is an explanatory description carried out in Embodiment 3. Please refer to Figure 1 , specifically: S3 includes S31, S32, and S33;

[0107] S31. Construct a heat and temperature algorithm model in the cloud server. The heat and temperature algorithm model includes a heat algorithm model and a temperature algorithm model, and extract the charging feature vector set and input it into the heat algorithm model for calculation to output the heat generation value Qgen, and predict the heat generated by the battery of the electric vehicle during the supercharging process;

[0108] The heat generation value Qgen is calculated and output through the following heat algorithm model;

[0109] ;

[0110] In the formula, Qgen(t) represents the heat generation value at time t.

[0111] S32. Based on the heat generation value Qgen, combined with the charging feature vector set, input it into the temperature algorithm model, calculate and output the predicted temperature value Tb, and predict and analyze the temperature of the battery of the electric vehicle during the supercharging process;

[0112] The predicted temperature value Tb is calculated and output through the following temperature algorithm model;

[0113] ;

[0114] In the formula, Tb(t) represents the predicted temperature value at time t;

[0115] S33. Initially set the temperature threshold T based on the battery temperature standard of the electric vehicle, then perform temperature prediction evaluation on the predicted temperature value Tb(t) at time t and the temperature threshold T, analyze the abnormal change of the battery temperature during the supercharging process, and generate the trigger condition for the collaborative mechanism of the adaptive charging power and the cooling system based on the evaluation result. The specific evaluation content is as follows;

[0116] When the predicted temperature value Tb(t) at time t > the temperature threshold T, it indicates that the predicted temperature change of the battery is abnormal during the supercharging process. At this time, trigger the execution of the collaborative mechanism of the adaptive charging power and the cooling system;

[0117] When the predicted temperature value Tb(t) at time t ≤ the temperature threshold T, it indicates that the predicted temperature change of the battery is normal during the supercharging process, and there is no need to intervene and continue monitoring.

[0118] In this embodiment, this method constructs a heat and temperature algorithm model in the cloud server, combines the charging feature vector set, and calculates the heat generation value Qgen generated by the battery. This value reflects the heat generated by the battery during the supercharging process, which is crucial for monitoring the battery temperature change. Through the following heat algorithm model, the heat generation value Qgen(t) at time t can be accurately calculated, which helps to predict the heat change of the battery during the supercharging process, thereby providing data support for the subsequent temperature control strategy. Next, based on the calculated heat generation value Qgen(t), combined with the charging feature vector, the data is further input into the temperature algorithm model to predict and output the temperature value Tb of the battery. This temperature prediction value reflects the temperature that the battery may reach during the supercharging process, and can predict the occurrence of abnormal temperature in advance, thereby providing a basis for the intervention of the temperature control system. The calculation accuracy and real-time performance of this temperature algorithm model ensure the accurate prediction of the battery temperature and lay a foundation for the optimization of the battery temperature control. Finally, combined with the temperature standard of the electric vehicle battery, set the initial temperature threshold T. Compare and evaluate the predicted battery temperature value Tb with this threshold. When the predicted temperature value Tb at time t is greater than the temperature threshold T, the system identifies that the battery temperature is abnormal during the supercharging process and triggers the collaborative mechanism of the adaptive charging power and the cooling system to adjust the working states of the charging power and the cooling system to ensure that the battery temperature is within the safe range. When the predicted temperature value Tb is less than or equal to the temperature threshold T, the battery temperature change is normal, and the system continues to monitor without intervention.

[0119] Embodiment 5

[0120] This embodiment is an explanatory description based on Embodiment 3. Please refer to Figure 1 , specifically: S4 includes S41 and S42;

[0121] S41. When it is evaluated through temperature prediction that the temperature change is abnormal, execute the collaborative mechanism of the adaptive charging power and the cooling system. The collaborative mechanism of the adaptive charging power and the cooling system includes an adaptive charging power adjustment mechanism and a cooling system adjustment mechanism;

[0122] The adaptive charging power adjustment mechanism calculates and outputs the overcharge power adjustment value Pcha according to the predicted temperature value Tb(t) of the battery at time t during the overcharge process, and adaptively adjusts the overcharge power adjustment value Pcha to be sent to the battery control system through the cloud server when the battery temperature is approaching the upper limit, and controls the overcharge power through the battery control system;

[0123] The overcharge power adjustment value Pcha is calculated and output through the following algorithm formula;

[0124] ;

[0125] In the formula, Pcha(t) represents the overcharge power adjustment value at time t, Pmax represents the overcharge power upper limit value, and Tmax represents the battery safety temperature upper limit value.

[0126] S42. The cooling system adjustment mechanism calculates and outputs the cooling power adjustment value Pcool through the battery temperature gradient △Tbat(t) at time t, the battery heat capacity Cbat(t) at time t, the ambient temperature Tenv(t) at time t, and the coolant cooling efficiency Ncoo(t) at time t, and combines the predicted temperature value Tb(t) at time t to dynamically adjust the power of the battery cooling system;

[0127] The cooling power adjustment value Pcool is calculated and output through the following algorithm formula;

[0128] ;

[0129] In the formula, Pcool(t) represents the cooling power adjustment value at time t.

[0130] In this embodiment, based on the temperature prediction evaluation result, when it is predicted that the battery temperature is abnormal, that is, the battery temperature is close to or exceeds the upper limit of the safe temperature, the collaborative mechanism of the adaptive charging power and the cooling system is automatically executed. This mechanism includes an adaptive charging power adjustment mechanism and a cooling system adjustment mechanism. Among them, the adaptive charging power adjustment mechanism dynamically adjusts by calculating the overcharge power adjustment value Pcha based on the predicted temperature value Tb of the battery at time t. If the predicted temperature value Tb is close to the upper limit of the safe temperature Tmax of the battery, the system will automatically adjust the charging power and reduce the overcharge power to prevent the battery from overheating. Next, the cooling system adjustment mechanism calculates the cooling power adjustment value Pcool. When the predicted temperature value Tb is too high, the cooling system will automatically increase the cooling power and reduce the battery temperature by adjusting the working state of the cooling system to ensure that the battery operates within a safe temperature range. The cooling power adjustment value Pcool is calculated and output through the following algorithm formula to dynamically adjust the cooling system power and effectively control the change of the battery temperature.

[0131] Embodiment 6

[0132] This embodiment is an explanatory description carried out in Embodiment 5. Please refer to Figure 1 , specifically: S5 includes S51 and S52;

[0133] S51. After the collaborative mechanism of the adaptive charging power and the cooling system is executed, the overcharge efficiency Eeff of the battery of the electric vehicle is comprehensively calculated to quantify the thermal management and overcharge power of the electric vehicle during the overcharge process;

[0134] The overcharge efficiency Eeff of the battery is calculated and output through the following algorithm formula;

[0135] ;

[0136] S52. Based on the standard of the charging temperature of the battery of the electric vehicle, that is, the designed temperature range of the battery usually stipulates the temperature at which the battery has the best charging efficiency, the efficiency threshold E is set, and then the overcharge efficiency Eeff of the battery is evaluated with the efficiency threshold E to analyze the thermal management and charging power during the overcharge process. The specific evaluation content is as follows;

[0137] When the overcharge efficiency Eeff of the battery ≥ the efficiency threshold E, the battery temperature is in a normal state under the current adjusted overcharge efficiency. At this time, there is no need to intervene and continue to monitor;

[0138] When the battery supercharging efficiency Eeff < the efficiency threshold E, the battery temperature is in an abnormal state at the current adjusted supercharging efficiency. At this time, the cooling system efficiency is automatically increased to 100%, and S5 is executed again to re-analyze the thermal management and charging power during the supercharging process. If an abnormal state is detected during the secondary analysis, the supercharging is automatically stopped. If the secondary analysis shows a normal state, the monitoring continues.

[0139] In this embodiment, after the collaborative mechanism of the adaptive charging power and the cooling system is completed, the battery supercharging efficiency Eeff is comprehensively calculated to quantify the thermal management and charging power conditions of the electric vehicle during the supercharging process. The calculation of the battery supercharging efficiency Eeff synthesizes multiple factors such as charging power, temperature control, and cooling efficiency to ensure the efficient operation of the battery throughout the charging process. The output of this efficiency calculation formula is Eeff, which reflects the overall performance of the battery during the supercharging process. Then, the efficiency threshold E is set according to the battery design temperature range and the charging efficiency standard, and the battery supercharging efficiency Eeff is compared and evaluated with the efficiency threshold E. According to the evaluation result, the system can determine whether the battery temperature and supercharging efficiency are in a normal state. By calculating and evaluating the battery supercharging efficiency Eeff, the system can continuously monitor the thermal management and power usage of the battery during the supercharging process, ensuring the high efficiency of the charging process. When the battery supercharging efficiency is lower than the set threshold, the system automatically adjusts the cooling system to improve the efficiency, avoiding overheating or damage of the battery due to excessive temperature or power, thus enhancing the safety of the charging process. By dynamically adjusting the working state of the cooling system and re-executing the efficiency analysis, it ensures the optimal adjustment of temperature and power during the charging process, avoiding low charging efficiency or battery damage caused by temperature control failure or improper charging power. By setting the efficiency threshold and implementing an automated intervention mechanism, the intelligent level of the system is significantly improved, reducing the need for manual intervention and enabling the electric vehicle to adaptively adjust in different working environments, thereby improving the user experience.

[0140] Embodiment 7

[0141] Please refer to Figure 1 and Figure 2 , a supercharging control system for an electric vehicle, including a supercharging data acquisition module, a feature extraction module, a heat and temperature analysis module, an adaptive adjustment module, and a supercharging efficiency and temperature analysis module;

[0142] The supercharging data acquisition module automatically activates the built-in sensor group through the battery management system BMS of the electric vehicle after the start of supercharging, real-time collects the battery data during the supercharging process, transmits it to the battery control system, and preprocesses the battery data to obtain a normalized data set;

[0143] The feature extraction module extracts charging feature vectors from the normalized dataset, and at the same time connects to the cloud server, constructs a cloud database in the cloud server, and transmits the charging feature vector set to the cloud database for storage;

[0144] The heat and temperature analysis module extracts the charging feature vector set and inputs it into the heat and temperature algorithm model by constructing a heat and temperature algorithm model, calculates and outputs the heat generation value Qgen and the predicted temperature value Tb, sets the temperature threshold T, and performs temperature prediction evaluation on the temperature threshold T and the predicted temperature value Tb to analyze the temperature change of the battery of the electric vehicle during the supercharging process;

[0145] When the adaptive adjustment module predicts and evaluates that the battery temperature is abnormal, it executes the collaborative mechanism of the adaptive charging power and the cooling system, and calculates and outputs the supercharging power adjustment value Pcha and the cooling power adjustment value Pcool respectively;

[0146] After the collaborative mechanism of the adaptive charging power and the cooling system is executed, the supercharging efficiency and temperature analysis module calculates and outputs the battery supercharging efficiency Eeff, sets the efficiency threshold E, and then performs efficiency evaluation on the efficiency threshold E and the battery supercharging efficiency Eeff to judge the efficiency status and temperature adjustment situation during the supercharging process.

[0147] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principle and spirit of the present invention.

Claims

1. A supercharging control method for an electric vehicle, characterized in that: The following steps are involved: S1. After supercharging starts, the built-in sensor group is automatically turned on through the battery management system BMS of the electric vehicle to collect battery data in real time during the supercharging process, transmit it to the battery control system, and pre-process the battery data to obtain a normalized data set; S2, extracting features from the normalized data set to obtain a charging feature vector set, connecting to a cloud server, building a cloud database in the cloud server, and transmitting the charging feature vector set to the cloud database for storage; S3, construct a heat and temperature algorithm model, extract the charging feature vector set and input it into the heat and temperature algorithm model, calculate the output heat generation value Qgen and the predicted temperature value Tb, and set the temperature threshold T, perform temperature prediction evaluation on the temperature threshold T and the predicted temperature value Tb, and analyze the temperature change of the battery of the electric vehicle during supercharging; The charging feature vector set includes the battery internal resistance Rbat(t) at time t, the battery temperature gradient △Tbat(t) at time t, the battery heat capacity Cbat(t) at time t, the ambient temperature Tenv(t) at time t, the coolant cooling efficiency Ncoo(t) at time t and the charging current Icha(t) at time t; S4. When the temperature prediction and evaluation show that the battery temperature is abnormal, the adaptive charging power and cooling system coordination mechanism is executed to calculate the output supercharging power adjustment value Pcha and the cooling power adjustment value Pcool respectively; The supercharge power adjustment value Pcha is calculated and output by the following algorithm formula: ； Where Pcha(t) represents the supercharge power adjustment value at time t, Pmax represents the supercharge power upper limit, and Tmax represents the battery's safe temperature upper limit; The cooling power adjustment value Pcool is calculated and output by the following algorithm formula; ； Where Pcool(t) represents the cooling power adjustment value at time t, represents the thermal conductivity of the battery; S5. After the adaptive charging power and cooling system coordination mechanism is executed, the battery supercharging efficiency Eeff is calculated and output, and the efficiency threshold E is set. Then, the efficiency threshold E and the battery supercharging efficiency Eeff are evaluated to determine the efficiency status and temperature adjustment status during the supercharging process.

2. The supercharging control method of an electric vehicle according to claim 1, characterized in that: Said S1 includes S11 and S12; S11, directly connect to the electric vehicle through the supercharging cable, and access the battery management system BMS of the electric vehicle, automatically turn on the built-in sensor group of the electric vehicle, and collect the battery data of the electric vehicle in real time during the supercharging process; The built-in sensor group includes a voltage sensor, a current sensor, a temperature sensor, and a thermistor; The battery data includes voltage Vbat, charging current Icha, battery temperature T, battery heat transfer Q, ambient temperature Tenv and coolant temperature Tcoo; S12, transmitting the battery data to a battery control system of the electric vehicle, and preprocessing the battery data in the battery control system to obtain a normalized data set, wherein the preprocessing includes denoising, outlier detection, timestamp marking, missing value filling, and normalization; The denoising is performed by using a sliding average method to denoise the battery data; The outlier detection is performed by using a Z-score standard deviation method to identify outliers in the battery data and remove the outliers; The timestamp marking is performed by marking the battery data with a timestamp based on the acquisition time of the built-in sensor group; The missing value filling is performed by using data at adjacent moments; The normalization method maps the value of each parameter in the battery data to a fixed interval through the Min-Max normalization method, thereby eliminating the dimension differences of each parameter in the battery data. The normalized data set includes the voltage Vbat(t) at time t, the charging current Icha(t) at time t, the battery temperature T(t) at time t, the battery transfer heat Q(t) at time t, the ambient temperature Tenv(t) at time t, and the coolant temperature Tcoo(t) at time t.

3. The supercharging control method of an electric vehicle according to claim 2, characterized in that: The S2 includes S21 and S22; S21. Perform feature extraction based on the normalized data set to obtain a charging feature vector set; The charging feature vector set includes the battery internal resistance Rbat(t) at time t, the battery temperature gradient △Tbat(t) at time t, the battery heat capacity Cbat(t) at time t, the ambient temperature Tenv(t) at time t, the coolant cooling efficiency Ncoo(t) at time t and the charging current Icha(t) at time t; The battery internal resistance Rbat(t) at time t is extracted by combining the voltage Vbat(t) at time t and the charging current Icha(t) at time t. The specific feature extraction algorithm formula is: ; Wherein, Vopen represents the open circuit voltage of the battery; The battery temperature gradient △Tbat(t) at time t is extracted by calculating the temperature difference of the battery temperature T at different positions of the battery. The specific feature extraction algorithm formula is: ; Among them, Tbat max Indicates the upper limit of the battery temperature, Tbat min Indicates the lower limit of the temperature inside the battery; The battery heat capacity Cbat(t) at time t is calculated and extracted by using the heat balance equation, combining the battery temperature T(t) at time t and the battery transfer heat Q(t) at time t. The specific feature extraction algorithm formula is: ; Where d represents a small variable, dQ(t) represents a small change in the amount of heat transferred by the battery at time t, and dT(t) represents a small change in the battery temperature at time t; The coolant cooling efficiency Ncoo(t) at time t is calculated and extracted by monitoring the temperature change of the cooling system. The specific feature extraction algorithm formula is: , where △Tcoo(t) represents the change in coolant temperature at time t, Tx max Indicates the upper limit of the design temperature difference of the cooling system; S22, connecting the cloud server to the battery control system via a communication network, building a cloud database in the cloud server, uploading the charging feature vector set to the cloud database via the communication network, and performing cloud storage on the charging feature vector set.

4. The supercharging control method of an electric vehicle according to claim 3, characterized in that: The S3 includes S31, S32 and S33; S31, constructing the heat and temperature algorithm model in the cloud server, the heat and temperature algorithm model includes a heat algorithm model and a temperature algorithm model, extracting a charging feature vector set and inputting it into the heat algorithm model, calculating and outputting a heat generation value Qgen, and predicting the heat generated by the battery of the electric vehicle during the supercharging process; The heat generation value Qgen is calculated and output by the following heat algorithm model; ； Where Qgen(t) represents the heat generation value at time t.

5. The method for controlling supercharging of an electric vehicle according to claim 4, characterized in that: S32, based on the heat generation value Qgen, combined with the charging feature vector set, input into the temperature algorithm model, calculate and output the predicted temperature value Tb, and perform prediction and analysis on the temperature of the battery of the electric vehicle during the supercharging process; The predicted temperature value Tb is calculated and output by the following temperature algorithm model; ； Where Tb(t) represents the predicted temperature value at time t; S33, initially setting a temperature threshold T based on the battery temperature standard of the electric vehicle, and then performing temperature prediction evaluation on the predicted temperature value Tb(t) at the time t and the temperature threshold T, analyzing the abnormal change of the battery temperature during the supercharging process, and generating trigger conditions for the adaptive charging power and cooling system coordination mechanism based on the evaluation results. The specific evaluation contents are as follows; When the predicted temperature value Tb(t) at time t is greater than the temperature threshold T, it indicates that the battery temperature is predicted to change abnormally during the supercharging process, and the adaptive charging power and cooling system coordination mechanism is triggered. When the predicted temperature value Tb(t) at time t ≤ the temperature threshold T, it indicates that the predicted temperature change of the battery during the overcharging process is normal and no intervention and continuous monitoring are required.

6. The supercharging control method of an electric vehicle according to claim 5, characterized in that: The S4 includes S41 and S42; S41. When the temperature change is abnormal, the temperature prediction and evaluation are performed, and the adaptive charging power and cooling system coordination mechanism is executed. The adaptive charging power and cooling system coordination mechanism includes an adaptive charging power adjustment mechanism and a cooling system adjustment mechanism. The adaptive charging power adjustment mechanism calculates and outputs the supercharging power adjustment value Pcha according to the predicted temperature value Tb(t) of the battery at time t during the supercharging process. When the battery temperature is close to the upper limit, the supercharging power adjustment value Pcha is sent to the battery control system through the cloud server, and the supercharging power is controlled by the battery control system. The supercharge power adjustment value Pcha is calculated and output by the following algorithm formula: ； Where Pcha(t) represents the supercharging power adjustment value at time t, Pmax represents the supercharging power upper limit, and Tmax represents the safe temperature upper limit of the battery.

7. The supercharging control method of an electric vehicle according to claim 6, characterized in that: S42, the cooling system adjustment mechanism dynamically adjusts the battery cooling system power by calculating the output cooling power adjustment value Pcool according to the battery temperature gradient △Tbat(t) at time t, the battery heat capacity Cbat(t) at time t, the ambient temperature Tenv(t) at time t and the coolant cooling efficiency Ncoo(t) at time t, and the predicted temperature value Tb(t) at time t; The cooling power adjustment value Pcool is calculated and output by the following algorithm formula; ； Where Pcool(t) represents the cooling power adjustment value at time t, Represents the thermal conductivity of the battery.

8. The method for controlling supercharging of an electric vehicle according to claim 6, characterized in that: The S5 includes S51 and S52; S51, after the adaptive charging power and cooling system coordination mechanism is executed, the battery supercharging efficiency Eeff of the electric vehicle is comprehensively calculated to quantify the thermal management and supercharging power of the electric vehicle during the supercharging process; The battery supercharge efficiency Eeff is calculated and output by the following algorithm formula: 。 9. The method for controlling supercharging of an electric vehicle according to claim 8, characterized in that: S52, based on the standard of the electric vehicle battery charging temperature, set the efficiency threshold E, then compare the battery supercharging efficiency Eeff with the efficiency threshold E, perform efficiency evaluation, analyze the thermal management and charging power during the supercharging process, and the specific evaluation content is as follows; When the battery supercharge efficiency Eeff ≥ efficiency threshold E, the battery temperature is in a normal state under the currently adjusted supercharge efficiency, and no intervention is required to continue monitoring; When the battery supercharging efficiency Eeff is less than the efficiency threshold E, the battery temperature is in an abnormal state under the currently adjusted supercharging efficiency. At this time, the cooling system efficiency is automatically increased to 100%, and S5 is re-executed to re-analyze the thermal management and charging power during the supercharging process. If the secondary analysis shows an abnormal state, the supercharging is automatically stopped. If the secondary analysis shows a normal state, monitoring continues.

10. A supercharging control system for an electric vehicle, applied to a supercharging control method for an electric vehicle according to any one of claims 1 to 9, characterized in that: It includes supercharging data acquisition module, feature extraction module, heat and temperature analysis module, adaptive adjustment module and supercharging efficiency and temperature analysis module; The supercharging data acquisition module automatically turns on the built-in sensor group through the battery management system BMS of the electric vehicle after supercharging starts, collects the battery data in real time during the supercharging process, transmits it to the battery control system, and pre-processes the battery data to obtain a normalized data set; The feature extraction module extracts features from the normalized data set to obtain a charging feature vector set, and simultaneously connects to a cloud server, builds a cloud database in the cloud server, and transmits the charging feature vector set to the cloud database for storage; The heat and temperature analysis module constructs a heat and temperature algorithm model, extracts the charging feature vector set and inputs it into the heat and temperature algorithm model, calculates and outputs a heat generation value Qgen and a predicted temperature value Tb, and sets a temperature threshold T, performs temperature prediction evaluation on the temperature threshold T and the predicted temperature value Tb, and analyzes the temperature change of the battery of the electric vehicle during supercharging; When the temperature prediction and evaluation of the battery temperature is abnormal, the adaptive adjustment module executes the adaptive charging power and cooling system coordination mechanism to calculate the output supercharging power adjustment value Pcha and the cooling power adjustment value Pcool respectively; After the adaptive charging power and cooling system collaborative mechanism is executed, the supercharging efficiency and temperature analysis module calculates and outputs the battery supercharging efficiency Eeff, sets the efficiency threshold E, and then performs efficiency evaluation on the efficiency threshold E and the battery supercharging efficiency Eeff to determine the efficiency status and temperature adjustment status during the supercharging process.

Images