A drive control method and system for preventing battery overheating in new energy vehicles

Abstract

This invention provides a drive control method and system for preventing battery overheating in new energy vehicles, including multi-dimensional data acquisition; risk prediction; risk level determination; and setting the overheating risk value R. ot Compared with a preset threshold, the system determines and classifies the corresponding risk level; flexible control adjusts the output power of the drive system according to the risk level and the vehicle's current power demand using a flexible control formula; thermal coordination adjusts the operating status of the thermal system according to the risk level; self-optimization is achieved through periodic optimization based on battery operating status feedback data, using a gradient descent algorithm to optimize and update model parameters and control formula parameters; repeating the above steps enables continuous battery over-temperature prevention and control monitoring; forming a closed-loop control system of acquisition-prediction-determination-execution-feedback-optimization, effectively preventing battery over-temperature faults, balancing driving performance and battery safety, and applicable to various new energy vehicle models and battery types.

Description

Technical Field

[0001] This invention relates to a drive control method and system for preventing battery overheating in new energy vehicles, and pertains to the field of vehicle control technology. Background Technology

[0002] With the rapid development of the new energy vehicle industry, the safety and reliability of power batteries, as core components, directly affect the operational safety of vehicles. Battery overheating is a common potential malfunction in the operation of new energy vehicles. Excessively high temperatures can lead to decreased battery performance, shortened lifespan, and in severe cases, even thermal runaway, causing safety accidents. Existing battery overheat protection technologies have several shortcomings: First, there is a significant lag in monitoring. Most rely on real-time temperature monitoring, which fails to identify overheating risks in advance, often only taking protective measures when the battery temperature is already close to the critical value, resulting in insufficient timeliness. Second, the control methods are rigid, often employing fixed threshold triggering. For example, once a preset temperature threshold is reached, the output power is directly reduced or stopped, failing to flexibly adjust according to the vehicle's actual power requirements and battery status, thus affecting vehicle performance. Third, adaptability and compatibility are poor. Different vehicle models and battery types have different operating characteristics, making it difficult for existing protection technologies to adapt to various scenarios and lacking versatility. Fourth, there is a lack of self-optimization capabilities and weak heat dissipation coordination. Protection parameters are fixed and cannot be dynamically optimized based on battery aging and changes in the operating environment. Furthermore, there is insufficient coordination with the cooling system, resulting in low heat dissipation efficiency. Summary of the Invention

[0003] To address the aforementioned problems arising from battery overheating, this invention provides a drive control method and system for preventing battery overheating in new energy vehicles. The specific technical solution is as follows: A drive control method for preventing battery overheating in new energy vehicles includes: S1, multi-dimensional data acquisition, collects the vehicle's current operating data and battery status data in real time at fixed intervals through the vehicle's CAN bus, battery management system (BMS) and various sensors, and calls the vehicle's historical operating data stored in the cloud through the wireless communication module; S2, Risk Prediction: Based on the multi-dimensional data collected in S1, the over-temperature risk value R is calculated using the constructed battery over-temperature risk prediction model. ot ; S3, Risk Level Determination, overheating risk value R ot The risk level is determined and classified by comparing the data with a preset threshold. S4, Flexible Control, adjusts the output power of the drive system according to the risk level and the current power demand of the vehicle through a flexible control formula; S5, heat dissipation coordination, adjusts the operating status of the heat dissipation system according to the risk level; S6, self-optimizing, is optimized periodically based on battery operating status feedback data, and uses the gradient descent algorithm to optimize and update model parameters and control formula parameters; Repeat the above steps to achieve continuous monitoring and control of battery over-temperature prevention; The vehicle's current operating data includes vehicle speed v, acceleration a, and drive motor output power P. m Road condition coefficient k l ; The current battery status data includes the current battery temperature T, battery SOC value S, battery cell voltage balance ΔU, and battery internal resistance R; Historical vehicle operating data includes historical vehicle speed sequences {v hi}, Historical battery temperature sequence {T hi}, Historical drive motor output power sequence {P mhi}, Historical SOC value sequence {S hi}

[0004] Preferably, in S2, the over-temperature risk value R is calculated using the constructed battery over-temperature risk prediction model. ot for: R ot =ω1×f1(T,{T hi})+ω2×f2(P m ,{P mhi})+ω3×f3(S,{S hi})+ω4×f4(v,a,k l )+ω5×g(ΔU,R); In the formula, ω1, ω2, ω3, ω4, and ω5 are the weight coefficients of each influencing factor, and ω1+ω2+ω3+ω4+ω5=1; Where, f1(T,{T hi}) is the correlation function between the current battery temperature and the historical temperature series: f1(T,{T hi})=α×(TT av9h ) / T max ; In the formula, T is the current battery temperature, α is the temperature influence correction coefficient, and T av9h T is the average of the historical temperature series. max =60℃; Wherein, f2(P) m ,{P mhi}) is the correlation function between the current motor output power and the historical power sequence: f2(P m ,{P mhi})=β×(P m -P mav9h ) / Pmmax ; In the formula, P m β is the output power of the drive motor, P is the power influence correction coefficient, and P is the output power of the drive motor. mav9h P is the average of the historical power series. mmax This represents the maximum output power of the motor. Wherein, f3(S,{S hi}) is the association function between the current SOC value and the historical SOC sequence: f3(S,{S hi})=γ×|SS av9h | / S max ; In the formula, S is the battery SOC value, γ is the SOC influence correction coefficient, and S av9h The average value of the historical SOC series, S max =100%; Where, f4(v,a,k) l ) represents the function influencing vehicle operating status: f4(v,a,k l )=δ×k l ×(v×a) / (v max ×a max ); In the formula, v is the vehicle speed, a is the acceleration, δ is the operating state correction coefficient, and v max For the vehicle's maximum speed, a max This is the vehicle's maximum acceleration; Where g(ΔU,R) is the battery state health influence function: g(ΔU,R)=ε×(ΔU / ΔU max +R / R max ) / 2; In the formula, R is the battery internal resistance, ΔU is the battery cell voltage balance, ε is the battery health correction coefficient, and ΔU max =0.2V, R max This is the internal resistance threshold when the battery ages to the point of being unusable.

[0005] Preferably, in S3, the over-temperature risk value R is... ot Compared with the preset threshold, the corresponding risk level is determined as follows: The preset thresholds include R1 and R2. When R ot When the risk level is less than R1, it is classified as low risk. When R1≤R ot When the risk level is less than R2, it is classified as a medium risk level. When R ot When the value is ≥R2, it is classified as a high-risk level.

[0006] Preferably, in step S4, the flexible control formula is: P out =P neennent ×[1-λ×(R ot -R0) / R max-ot ]; In the formula, P out To drive the system output power, P neennent R0 is the current power demand of the vehicle, and R is the baseline risk value. max-ot λ represents the maximum risk value; λ is the correction coefficient corresponding to the risk level.

[0007] Preferably, the adjustment of the heat dissipation system operating state in S5 is as follows: Based on the cooling fan speed N1 under normal operating conditions of the cooling system, the heat dissipation coordination control strategy is as follows: Maintain cooling fan speed N1 during low-risk periods; At medium risk levels, the fan speed is adjusted to the cooling fan speed N2, where N2 = N1 × (1 + 0.3 × R). ot ); When the risk level is high, the fan speed is adjusted to the cooling fan speed N3, where N3 = N1 × (1 + 0.8 × R) ot At the same time, the water-cooled auxiliary heat dissipation system is activated; In the formula, R ot This represents the risk value for overheating.

[0008] Preferably, in step S6, the periodic optimization cycle is 24 hours, and the optimization parameters include the weight coefficients ω1, ω2, ω3, ω4, ω5 of each influencing factor and the correction coefficient λ corresponding to the risk level; The objective function to be optimized is: J=μ1×(R pre dR a c t ) 2 +μ2×(T max - a c t -T tpt ) 2 ; In the formula, R pre d represents the predicted risk value, R a c t For actual risk value, T max - a c t The actual highest temperature of the battery, T tpt The optimal operating temperature of the battery is given by μ1 and μ2, which are weighting coefficients, and μ1 + μ2 = 1.

[0009] A vehicle includes a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the method as described in any of the preceding claims.

[0010] A drive control system for preventing battery overheating in new energy vehicles, used to implement any of the above methods, includes: The data acquisition module collects the vehicle's current operating data and the battery's current status data in real time at fixed intervals through the vehicle's CAN bus, battery management system (BMS), and various sensors. It also calls the vehicle's historical operating data stored in the cloud through the wireless communication module to obtain multi-dimensional data. The risk prediction module, based on multi-dimensional data, calculates the over-temperature risk value R using a constructed battery over-temperature risk prediction model. ot ; The risk level assessment module determines the over-temperature risk value R. ot The risk level is determined and classified by comparing the data with a preset threshold. The flexible control module adjusts the output power of the drive system according to the risk level and the current power demand of the vehicle through a flexible control formula; The heat dissipation coordination module adjusts the operating status of the heat dissipation system according to the risk level; The self-optimization module periodically optimizes based on battery operating status feedback data, and uses the gradient descent algorithm to optimize and update model parameters and control formula parameters.

[0011] The beneficial effects of this invention compared to the prior art are as follows: By integrating multi-dimensional data collection to address monitoring lag issues, a risk prediction model based on correlation functions enables early identification of over-temperature risks, hierarchical flexible control avoids rigid intervention, drive-heat dissipation synergy improves protection efficiency, and dynamic self-optimization algorithms enhance scenario adaptability, forming a closed-loop control of "collection-prediction-judgment-execution-feedback-optimization" to effectively prevent battery over-temperature faults, balance driving performance and battery safety, and is applicable to various new energy vehicle models and battery types. Attached Figure Description

[0012] Figure 1 This is a flowchart of the present invention. Detailed Implementation

[0013] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0014] Example 1 A drive control method for preventing battery overheating in new energy vehicles includes: S1, multi-dimensional data acquisition, collects the vehicle's current operating data and battery status data in real time at fixed intervals through the vehicle's CAN bus, battery management system (BMS) and various sensors, and calls the vehicle's historical operating data stored in the cloud through the wireless communication module; S2, Risk Prediction: Based on the multi-dimensional data collected in S1, the over-temperature risk value R is calculated using the constructed battery over-temperature risk prediction model. ot ; S3, Risk Level Determination, overheating risk value R ot The risk level is determined and classified by comparing the data with a preset threshold. S4, Flexible Control, adjusts the output power of the drive system according to the risk level and the current power demand of the vehicle through a flexible control formula; S5, heat dissipation coordination, adjusts the operating status of the heat dissipation system according to the risk level; S6, self-optimizing, is optimized periodically based on battery operating status feedback data, and uses the gradient descent algorithm to optimize and update model parameters and control formula parameters; Repeat the above steps to achieve continuous monitoring and control of battery over-temperature prevention; The vehicle's current operating data includes vehicle speed v, acceleration a, and drive motor output power P. m Road condition coefficient k l ; The current battery status data includes the current battery temperature T, battery SOC value S, battery cell voltage balance ΔU, and battery internal resistance R; Historical vehicle operating data includes historical vehicle speed sequences {v hi}, Historical battery temperature sequence {T hi}, Historical drive motor output power sequence {P mhi}, Historical SOC value sequence {S hi}

[0015] Historical SOC value sequence {S hi In the}, i=1,2,...,n, where n is the total number of historical data collections.

[0016] In S2, the over-temperature risk value R is calculated using the constructed battery over-temperature risk prediction model. ot for: R ot =ω1×f1(T,{T hi})+ω2×f2(P m ,{P mhi})+ω3×f3(S,{S hi})+ω4×f4(v,a,k l )+ω5×g(ΔU,R); In the formula, ω1, ω2, ω3, ω4, and ω5 are the weight coefficients of each influencing factor, and ω1+ω2+ω3+ω4+ω5=1; Recommended weighting coefficients for each influencing factor are: ω1 = 0.3, ω2 = 0.25, ω3 = 0.15, ω4 = 0.2, and ω5 = 0.1. Where, f1(T,{T hi}) is the correlation function between the current battery temperature and the historical temperature series: f1(T,{T hi})=α×(TT av9h ) / T max ; In the formula, T is the current battery temperature, α is the temperature influence correction coefficient, and T av9h T is the average of the historical temperature series. max =60℃; The recommended value for the temperature effect correction factor α is 0.8; Wherein, f2(P) m ,{P mhi}) is the correlation function between the current motor output power and the historical power sequence: f2(P m ,{P mhi})=β×(P m -P mav9h ) / P mmax ; In the formula, P m β is the output power of the drive motor, P is the power influence correction coefficient, and P is the output power of the drive motor. mav9h P is the average of the historical power series. mmax This represents the maximum output power of the motor; the recommended value for the power effect correction factor β is 0.7. Wherein, f3(S,{S hi}) is the association function between the current SOC value and the historical SOC sequence: f3(S,{S hi})=γ×|SS av9h | / S max ; In the formula, S is the battery SOC value, γ is the SOC influence correction coefficient, and S av9h The average value of the historical SOC series, S max =100%; The recommended value for the SOC impact correction factor γ is 0.6. Where, f4(v,a,k) l ) represents the function influencing vehicle operating status: f4(v,a,k l )=δ×k l ×(v×a) / (v max ×a max ); In the formula, v is the vehicle speed, a is the acceleration, δ is the operating state correction coefficient, and v max For the vehicle's maximum speed, a max This is the vehicle's maximum acceleration; The recommended value for the operating status correction factor δ is 0.9; Where g(ΔU,R) is the battery state health influence function: g(ΔU,R)=ε×(ΔU / ΔU max +R / R max ) / 2; In the formula, R is the battery internal resistance, ΔU is the battery cell voltage balance, ε is the battery health correction coefficient, and ΔU max =0.2V, R max This is the internal resistance threshold when the battery ages to the point of being unusable.

[0017] The recommended value for the battery health correction factor ε is 0.5. In S3, the overheating risk value R will be... ot Compared with the preset threshold, the corresponding risk level is determined as follows: The preset thresholds include R1 and R2. When R ot When the risk level is less than R1, it is classified as low risk. When R1≤R ot When the risk level is less than R2, it is classified as a medium risk level. When R ot When the value is ≥R2, it is classified as a high-risk level.

[0018] The preset threshold R1 is 0.35, and its value ranges from 0.3 to 0.4. The preset threshold R² is 0.75, and its value ranges from 0.7 to 0.8. In S4, the flexible control formula is: P out =P neennent ×[1-λ×(R ot -R0) / R max-ot ]; In the formula, P out To drive the system output power, P neennent R0 is the current power demand of the vehicle, and R is the baseline risk value. max-ot λ represents the maximum risk value; λ is the correction coefficient corresponding to the risk level.

[0019] Where R0 is the benchmark risk value, which is 0; Rmax-ot The maximum risk value is set to 1. For low-risk levels, λ = 0.1; for medium-risk levels, λ = 0.3; and for high-risk levels, λ = 0.6.

[0020] For example, when P neennent =100kW, R ot When P = 0.5 (medium risk level), out =100×[1-0.3×(0.5-0)]=85kW; In S5, adjust the cooling system's operating status as follows: Based on the cooling fan speed N1 under normal operating conditions of the cooling system, the heat dissipation coordination control strategy is as follows: Maintain cooling fan speed N1 during low-risk periods; At medium risk levels, the fan speed is adjusted to the cooling fan speed N2, where N2 = N1 × (1 + 0.3 × R). ot ); When the risk level is high, the fan speed is adjusted to the cooling fan speed N3, where N3 = N1 × (1 + 0.8 × R) ot At the same time, the water-cooled auxiliary heat dissipation system is activated; In the formula, R ot This represents the risk value for overheating.

[0021] The default operating speed of the cooling system under normal conditions is 1500 r / min for the cooling fan, i.e.: Maintain the cooling fan speed at 1500 r / min during low-risk periods; For medium risk, N² = 1500 × (1 + 0.3 × R) ot ); At high risk, N3 = 1500 × (1 + 0.8 × R) ot At the same time, the water-cooled auxiliary heat dissipation system is activated.

[0022] In S6, the periodic optimization cycle is 24 hours, and the optimization parameters include the weight coefficients ω1, ω2, ω3, ω4, ω5 of each influencing factor and the correction coefficient λ corresponding to the risk level; The objective function to be optimized is: J=μ1×(R pre dR a c t ) 2 +μ2×(T max - a c t -T tpt ) 2 ; In the formula, R pre d represents the predicted risk value, R a c tFor actual risk value, T max - a c t The actual highest temperature of the battery, T tpt The optimal operating temperature of the battery is given by μ1 and μ2, which are weighting coefficients, and μ1 + μ2 = 1.

[0023] It is feasible; the optimal operating temperature of the battery is T. tpt With a temperature of 35℃, μ1 of 0.6, and μ2 of 0.4, the parameters are dynamically optimized by minimizing the objective function J.

[0024] Example 2 A vehicle includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of any of the methods described above.

[0025] Example 3 A drive control system for preventing battery overheating in new energy vehicles, used to implement any of the above methods, includes: The data acquisition module collects the vehicle's current operating data and the battery's current status data in real time at fixed intervals through the vehicle's CAN bus, battery management system (BMS), and various sensors. It also calls the vehicle's historical operating data stored in the cloud through the wireless communication module to obtain multi-dimensional data. The risk prediction module, based on multi-dimensional data, calculates the over-temperature risk value R using a constructed battery over-temperature risk prediction model. ot ; The risk level assessment module determines the over-temperature risk value R. ot The risk level is determined and classified by comparing the data with a preset threshold. The flexible control module adjusts the output power of the drive system according to the risk level and the current power demand of the vehicle through a flexible control formula; The heat dissipation coordination module adjusts the operating status of the heat dissipation system according to the risk level; The self-optimization module periodically optimizes based on battery operating status feedback data, and uses the gradient descent algorithm to optimize and update model parameters and control formula parameters.

Claims

1. A drive control method for preventing battery overheating in new energy vehicles, characterized in that, include: S1, multi-dimensional data acquisition, collects the vehicle's current operating data and battery status data in real time at fixed intervals through the vehicle's CAN bus, battery management system (BMS) and various sensors, and calls the vehicle's historical operating data stored in the cloud through the wireless communication module; S2, Risk Prediction: Based on the multi-dimensional data collected in S1, the over-temperature risk value R is calculated using the constructed battery over-temperature risk prediction model. ot ; S3, Risk Level Determination, overheating risk value R ot The risk level is determined and classified by comparing it with a preset threshold. S4, Flexible Control, adjusts the output power of the drive system according to the risk level and the current power demand of the vehicle through a flexible control formula; S5, heat dissipation coordination, adjusts the operating status of the heat dissipation system according to the risk level; S6, self-optimizing, is optimized periodically based on battery operating status feedback data, and uses the gradient descent algorithm to optimize and update model parameters and control formula parameters; Repeat the above steps to achieve continuous monitoring and control of battery over-temperature prevention; The vehicle's current operating data includes vehicle speed v, acceleration a, and drive motor output power P. m Road condition coefficient k l ; The current battery status data includes the current battery temperature T, battery SOC value S, battery cell voltage balance ΔU, and battery internal resistance R; Historical vehicle operating data includes historical vehicle speed sequences {v hi }, Historical battery temperature sequence {T hi }, Historical drive motor output power sequence {P mhi }, Historical SOC value sequence {S hi } 2. The drive control method for preventing battery overheating in new energy vehicles according to claim 1, characterized in that, In S2, the over-temperature risk value R is calculated using the constructed battery over-temperature risk prediction model. ot for: R ot =ω1×f1(T,{T hi })+ω2×f2(P m ,{P mhi })+ω3×f3(S,{S hi })+ω4×f4(v,a,k l )+ω5×g(ΔU,R); In the formula, ω1, ω2, ω3, ω4, and ω5 are the weight coefficients of each influencing factor, and ω1+ω2+ω3+ω4+ω5=1; Where, f1(T,{T hi }) is the correlation function between the current battery temperature and the historical temperature series: f1(T,{T hi })=α×(T-T av9h ) / T max ; In the formula, T is the current battery temperature, α is the temperature influence correction coefficient, and T av9h T is the average of the historical temperature series. max =60℃; Wherein, f2(P) m ,{P mhi }) is the correlation function between the current motor output power and the historical power sequence: f2(P m ,{P mhi })=β×(P m -P mav9h ) / P mmax ; In the formula, P m β is the output power of the drive motor, P is the power influence correction coefficient, and P is the output power of the drive motor. mav9h P is the average of the historical power series. mmax This represents the maximum output power of the motor. Among them, f3(S,{S hi }) is the association function between the current SOC value and the historical SOC sequence: f3(S,{S hi })=γ×|S-S av9h | / S max ; In the formula, S is the battery SOC value, γ is the SOC influence correction coefficient, and S av9h The average value of the historical SOC series, S max =100%; Where, f4(v,a,k) l ) represents the function influencing vehicle operating status: f4(v,a,k l )=δ×k l ×(v×a) / (v max ×a max ); In the formula, v is the vehicle speed, a is the acceleration, δ is the operating state correction coefficient, and v max For the vehicle's maximum speed, a max This is the vehicle's maximum acceleration; Where g(ΔU,R) is the battery state health influence function: g(ΔU,R)=ε×(ΔU / ΔU max +R / R max ) / 2; In the formula, R is the battery internal resistance, ΔU is the battery cell voltage balance, ε is the battery health correction coefficient, and ΔU max =0.2V, R max This is the internal resistance threshold when the battery ages to the point of being unusable.

3. The drive control method for preventing battery overheating in new energy vehicles according to claim 1, characterized in that, In S3, the overheating risk value R will be... ot Compared with the preset threshold, the corresponding risk level is determined as follows: The preset thresholds include R1 and R2. When R ot When the risk level is less than R1, it is classified as low risk. When R1≤R ot When the risk level is less than R2, it is classified as a medium-risk level. When R ot When the value is ≥R2, it is classified as a high-risk level.

4. The drive control method for preventing battery overheating in new energy vehicles according to claim 1, characterized in that, In step S4, the flexible control formula is: P out =P neennent ×[1-λ×(R ot -R0) / R max-ot ]; In the formula, P out To drive the system output power, P neennent R0 is the current power demand of the vehicle, and R is the baseline risk value. max-ot λ represents the maximum risk value, and λ is the correction coefficient corresponding to the risk level.

5. The drive control method for preventing battery overheating in new energy vehicles according to claim 1, characterized in that, The operation status of the heat dissipation system is adjusted in S5 as follows: Based on the cooling fan speed N1 under normal operating conditions of the cooling system, the heat dissipation coordination control strategy is as follows: Maintain cooling fan speed N1 during low-risk periods; At medium risk levels, the fan speed is adjusted to the cooling fan speed N2, where N2 = N1 × (1 + 0.3 × R). ot ); When the risk level is high, the fan speed is adjusted to the cooling fan speed N3, where N3 = N1 × (1 + 0.8 × R) ot At the same time, the water-cooled auxiliary heat dissipation system is activated; In the formula, R ot This represents the risk value for overheating.

6. The drive control method for preventing battery overheating in new energy vehicles according to claim 1, characterized in that, In S6, the periodic optimization cycle is 24 hours, and the optimization parameters include the weight coefficients ω1, ω2, ω3, ω4, ω5 of each influencing factor and the correction coefficient λ corresponding to the risk level; The objective function to be optimized is: J=μ1×(R pre d-R a c t ) 2 +μ2×(T max-a c t -T tpt ) 2 ; In the formula, R pre d represents the predicted risk value, R a c t For actual risk value, T max-a c t The actual highest temperature of the battery, T tpt The optimal operating temperature of the battery is given by μ1 and μ2, which are weighting coefficients, and μ1 + μ2 = 1.

7. A new energy vehicle, characterized in that, The system includes a control system comprising a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method as described in any one of claims 1 to 6.

8. A drive control system for preventing battery overheating in new energy vehicles, used to implement the method described in any one of claims 1-6, characterized in that, include: The data acquisition module collects the vehicle's current operating data and the battery's current status data in real time at fixed intervals through the vehicle's CAN bus, battery management system (BMS), and various sensors. It also calls the vehicle's historical operating data stored in the cloud through the wireless communication module to obtain multi-dimensional data. The risk prediction module, based on multi-dimensional data, calculates the over-temperature risk value R using a constructed battery over-temperature risk prediction model. ot ; The risk level assessment module determines the over-temperature risk value R. ot The risk level is determined and classified by comparing it with a preset threshold. The flexible control module adjusts the output power of the drive system according to the risk level and the current power demand of the vehicle through a flexible control formula; The heat dissipation coordination module adjusts the operating status of the heat dissipation system according to the risk level; The self-optimization module periodically optimizes based on battery operating status feedback data, and uses the gradient descent algorithm to optimize and update model parameters and control formula parameters.

Images