A method and system for discharge optimization of a vehicle starting power supply

Abstract

The application relates to a discharge optimization method and system of a vehicle starting power supply, the method comprising the following steps: acquiring a vehicle starting signal; according to the vehicle starting signal, calling an energy distribution model to calculate a target current value required by current starting, and controlling discharge of an energy storage module according to the target current value; in the process of discharging the energy storage module, collecting real-time running state parameters of the energy storage module in real time; inputting the running state parameters into an energy storage health state evaluation model to output corresponding health score results; in the vehicle starting process, performing abnormality detection on an output current waveform of the energy storage module to determine whether abnormal deformation exists, and if the determination result is that abnormal deformation exists, performing a power supply path switching operation; after the vehicle starting is completed, generating a supply adjustment scheme according to the health score results and a user operation instruction, and dynamically adjusting an energy supply ratio of the energy storage module and an original battery of the vehicle according to the supply adjustment scheme. The application has the effect of improving the reliability of the vehicle starting process.

Description

Technical Field

[0001] This application relates to the technical field of vehicle power management, and in particular to a method and system for optimizing the discharge of a vehicle starting power supply. Background Technology

[0002] In traditional vehicles, the starting process relies on the original battery releasing a large current in a very short time to drive the starter motor and power the engine. However, in low-temperature environments, under conditions of battery aging, or frequent start-stop cycles, the original battery often cannot provide sufficient starting current, easily leading to vehicle starting failure. To improve starting reliability, some vehicles have introduced auxiliary energy storage modules (such as supercapacitors or lithium battery modules) connected in parallel with the original battery to enhance starting capability through coordinated discharge.

[0003] In existing technologies, energy management strategies for vehicle starting power supplies mostly employ fixed-ratio allocation or simple temperature threshold triggering mechanisms. This static control method is difficult to adapt to complex and changing operating conditions. For example, when the energy storage module's performance degrades due to increased cycle count or temperature drop, the fixed discharge strategy cannot dynamically match actual needs, easily leading to insufficient starting current or battery overload. Furthermore, existing solutions lack in-depth assessment of the energy storage module's health status, typically relying only on instantaneous voltage or current detection, which fails to promptly reflect potential problems such as capacity decay and increased internal resistance, resulting in inaccurate energy supply strategies.

[0004] The existing technical solutions mentioned above have the following drawbacks: the existing vehicle starting power supply control usually adopts a fixed or empirical discharge strategy, which lacks the ability to perceive and dynamically adjust the actual starting demand and the status of the energy storage module in real time. It is difficult to adapt to complex working conditions under different environments and energy storage health conditions, which increases the risk of starting failure. Therefore, there is room for improvement. Summary of the Invention

[0005] To improve the reliability of the vehicle starting process, this application provides a method and system for optimizing the discharge of the vehicle starting power supply.

[0006] The above-mentioned objective of this application is achieved through the following technical solution:

[0007] A method for optimizing the discharge of a vehicle starting power supply, the method comprising:

[0008] The system acquires a vehicle start signal, calculates the target current value required for the current start based on the vehicle start signal using an energy distribution model, and controls the energy storage module to discharge based on the target current value.

[0009] During the discharge process of the energy storage module, the real-time operating status parameters of the energy storage module are collected in real time. The operating status parameters include at least the cold start current capability parameter, the internal resistance parameter, and the temperature parameter.

[0010] The operating status parameters are input into the energy storage health status assessment model, and the corresponding health score results are output. The health score results include lifetime status parameters, capacity status parameters, and internal resistance status parameters.

[0011] During vehicle startup, the output current waveform of the energy storage module is subjected to anomaly detection to determine whether there is abnormal deformation. If the result indicates that there is an anomaly, a power supply path switching operation is performed.

[0012] After the vehicle starts, a supply adjustment plan is generated based on the health score and user operation instructions. During vehicle operation, the energy supply ratio between the energy storage module and the vehicle's primary battery is dynamically adjusted according to the supply adjustment plan.

[0013] Record the environmental parameters, control strategies, and response behaviors during the current startup process, and update the recorded data to the behavior history dataset to support the optimization and generation of subsequent startup strategies.

[0014] By adopting the above technical solution, and by acquiring the vehicle start-up signal and calling the energy distribution model to calculate the target current value, the required current can be accurately predicted before start-up, avoiding insufficient power supply or overload due to empirical value deviations, thereby improving the start-up success rate and reducing the pressure on the battery and energy storage module. By collecting operating status parameters in real time during discharge, the cold start capability, internal resistance, and temperature changes of the energy storage module can be dynamically monitored, providing reliable data support for health assessment and strategy adjustment. By inputting the operating status parameters into the health status assessment model and outputting health scores such as lifespan, capacity, and internal resistance, the performance degradation of the energy storage module can be comprehensively reflected, thus providing a scientific basis for subsequent adjustments. Extending module lifespan; by detecting abnormal current waveforms during vehicle startup and switching power supply paths when abnormalities occur, damage to the electrical system caused by sudden current changes can be effectively prevented, thereby improving the safety and stability of system operation; by generating a supply adjustment plan based on health score results and user operation commands after startup and dynamically adjusting the energy supply ratio, collaborative optimization between the energy storage module and the primary battery can be achieved, thus meeting the needs of different users and improving energy utilization efficiency; by recording environmental parameters, control strategies, and response behaviors during startup and writing them back to historical datasets, an adaptive startup optimization mechanism can be gradually formed, thereby achieving continuous optimization and intelligent evolution of the energy supply strategy.

[0015] In one example, this application can be further configured such that: the calculation of the target current value required for current startup by calling the energy allocation model includes:

[0016] Obtain vehicle startup condition characteristic parameters, which include vehicle type information, battery pack capacity, current ambient temperature and humidity, and historical startup current data;

[0017] The vehicle startup condition characteristic parameters are input into the energy distribution model, and the target current value required for the current startup is output.

[0018] By adopting the above technical solution, and by obtaining the characteristic parameters of the vehicle's starting condition and inputting them into the energy distribution model to calculate the target current value, it is possible to ensure that the target current calculation is based on multi-dimensional information such as the current vehicle type, battery capacity, ambient temperature and humidity, and historical data. This makes the current prediction more accurate, more adaptable to different vehicles and environmental conditions, and improves the rationality of dynamic energy supply scheduling.

[0019] In one example, this application can be further configured such that the discharge optimization method for a vehicle starting power supply also includes:

[0020] The operating status parameters and corresponding health scores of multiple historical energy storage modules were extracted as training samples.

[0021] A neural network evaluation model is constructed using a supervised learning algorithm and trained based on the training samples. During the training process, the network weights are iteratively optimized through an error backpropagation mechanism to finally obtain the energy storage health status evaluation model.

[0022] By adopting the above technical solution, and by extracting historical operating status parameters and health score results to form training samples, and by using supervised learning to build an evaluation model, a health status evaluation mechanism with self-learning ability can be established, thereby achieving accurate determination of the health status of energy storage modules under different states and improving the system's intelligence level and generalization ability.

[0023] In one example, this application can be further configured such that: inputting the operating status parameters into the energy storage health status assessment model and outputting the corresponding health score results includes:

[0024] The operating status parameters are preprocessed to obtain preprocessed operating status parameters. The preprocessing includes normalization, noise reduction and outlier removal.

[0025] The preprocessed operating status parameters are input into the energy storage health status assessment model, and the corresponding health score results are output.

[0026] By adopting the above technical solutions, and performing preprocessing operations such as normalization, denoising, and outlier removal on the operating status parameters, the stability of the input data and the accuracy of the model evaluation can be improved, thereby avoiding judgment errors caused by fluctuations in the original signal. By inputting the preprocessed data into the evaluation model and outputting health score results, clear status reference indicators can be provided, thereby providing effective support for power supply adjustment and strategy optimization.

[0027] In one example, this application can be further configured such that the anomaly detection of the output current waveform of the energy storage module includes:

[0028] During vehicle startup, waveform data of the output current of the energy storage module changing over time are collected in real time.

[0029] The characteristic parameters of the current waveform are extracted and compared with a preset normal waveform template. The characteristic parameters include amplitude, slope, rate of change and fluctuation frequency.

[0030] When non-steady-state features are detected in the feature parameters, it is determined that the current waveform has abnormal deformation. The non-steady-state features include sudden current surges, violent fluctuations, and abnormal oscillations.

[0031] By adopting the above technical solution, the dynamic changes in the discharge process can be completely recorded by real-time acquisition of the current waveform data of the energy storage module, thus providing an accurate data source for waveform analysis. By extracting characteristic parameters such as current amplitude, slope, and rate of change and comparing them with normal templates, abnormal features in the waveform can be identified in a timely manner, thereby improving the sensitivity of fault diagnosis. When non-steady-state features such as sudden rises, violent fluctuations, or oscillations are detected, the waveform is determined to be abnormal, and a timely warning can be issued before the energy storage module shows signs of running out of control, thereby improving the safety of system operation.

[0032] In one example, this application can be further configured such that generating the supply adjustment plan based on the health score result and user operation instructions includes:

[0033] The maximum allowable discharge current of the energy storage module is estimated based on the health score results.

[0034] The target energy distribution tendency between the energy storage module and the vehicle's primary battery is determined based on the user's operation instructions.

[0035] Based on the maximum allowable discharge current limit and the target energy distribution tendency, combined with the current environmental state parameters and the current remaining capacity of the vehicle's primary battery, the supply adjustment scheme is generated. The supply adjustment scheme includes the energy distribution ratio between the energy storage module and the vehicle's primary battery, the current limit, and whether to trigger the current limiting protection strategy.

[0036] By adopting the above technical solutions, and estimating the maximum allowable discharge current limit of the energy storage module based on the health score results, damage to the energy storage module caused by over-discharge can be effectively avoided, thereby extending the life of the energy storage module. By determining the target energy supply allocation tendency between the energy storage module and the primary battery based on user operation instructions, differentiated strategies can be formulated in combination with the user's actual needs, thereby achieving personalization and flexibility in the energy supply process. By combining the current limit and allocation tendency with environmental conditions and the remaining capacity of the primary battery to generate a supply adjustment scheme, safety, adaptability, and energy efficiency can be taken into account, thereby ensuring the starting reliability and energy supply optimization of the vehicle under different operating conditions.

[0037] In one example, this application can be further configured such that the discharge optimization method for a vehicle starting power supply also includes:

[0038] After performing the power supply path switching operation, the energy storage module is controlled to enter the protection state, which includes disconnecting the energy storage output path, limiting the subsequent discharge capacity, or enabling a low-power standby mode.

[0039] After the energy storage module enters the protection state, it sends a switching status feedback signal to update the current power supply status of the system and prevent repeated switching or false triggering. The protection state is maintained until the vehicle starts up.

[0040] By adopting the above technical solution, after the power supply path is switched, the energy storage module is controlled to enter the protection state, which can cut off the abnormal discharge path or limit its output capacity in a timely manner, thereby preventing the fault from expanding further and ensuring the safe operation of other system components. By sending a switching status feedback signal for power supply status update, the control chaos caused by repeated switching or false triggering can be avoided, thereby maintaining the consistency of system logic and execution stability. The protection state is maintained until the end of vehicle startup, which can ensure the power safety of the entire critical power supply stage, thereby improving the overall reliability of the vehicle startup process.

[0041] The second objective of this invention is achieved through the following technical solution:

[0042] The start signal parsing module is used to acquire the vehicle start signal, calculate the target current value required for the current start based on the vehicle start signal, and control the energy storage module to discharge based on the target current value.

[0043] The operation status acquisition module is used to acquire the real-time operation status parameters of the energy storage module during the discharge process of the energy storage module. The operation status parameters include cold start current capability parameters, internal resistance parameters and temperature parameters.

[0044] The health status assessment module is used to input the operating status parameters into the energy storage health status assessment model and output the corresponding health score results. The health score results include at least lifetime status parameters, capacity status parameters and internal resistance status parameters.

[0045] The waveform anomaly detection module is used to detect anomalies in the output current waveform of the energy storage module during vehicle startup, determine whether there is abnormal deformation, and if the determination result is that there is an anomaly, then perform a power supply path switching operation.

[0046] The energy supply strategy adjustment module is used to generate a supply adjustment plan based on the health score results and user operation instructions after the vehicle starts, and to dynamically adjust the energy supply ratio between the energy storage module and the vehicle's primary battery according to the supply adjustment plan during vehicle operation.

[0047] The behavior recording and write-back module is used to record the environmental parameters, control strategies and response behaviors during the current startup process, and update the recorded data to the behavior history dataset to support the optimization and generation of subsequent startup strategies.

[0048] By adopting the above technical solution, and by acquiring the vehicle start-up signal and calling the energy distribution model to calculate the target current value, the required current can be accurately predicted before start-up, avoiding insufficient power supply or overload due to empirical value deviations, thereby improving the start-up success rate and reducing the pressure on the battery and energy storage module. By collecting operating status parameters in real time during discharge, the cold start capability, internal resistance, and temperature changes of the energy storage module can be dynamically monitored, providing reliable data support for health assessment and strategy adjustment. By inputting the operating status parameters into the health status assessment model and outputting health scores such as lifespan, capacity, and internal resistance, the performance degradation of the energy storage module can be comprehensively reflected, thus providing a scientific basis for subsequent adjustments. Extending module lifespan; by detecting abnormal current waveforms during vehicle startup and switching power supply paths when abnormalities occur, damage to the electrical system caused by sudden current changes can be effectively prevented, thereby improving the safety and stability of system operation; by generating a supply adjustment plan based on health score results and user operation commands after startup and dynamically adjusting the energy supply ratio, collaborative optimization between the energy storage module and the primary battery can be achieved, thus meeting the needs of different users and improving energy utilization efficiency; by recording environmental parameters, control strategies, and response behaviors during startup and writing them back to historical datasets, an adaptive startup optimization mechanism can be gradually formed, thereby achieving continuous optimization and intelligent evolution of the energy supply strategy.

[0049] In summary, this application includes the following beneficial technical effects:

[0050] 1. By acquiring the vehicle start signal and calling the energy distribution model to calculate the target current value, the required current can be accurately predicted before start-up, avoiding insufficient power supply or overload due to deviations in empirical values, thereby improving the start-up success rate and reducing the pressure on the battery and energy storage module; by collecting operating status parameters in real time during discharge, the cold start capability, internal resistance, and temperature changes of the energy storage module can be dynamically monitored, thus providing reliable data support for health assessment and strategy adjustment; by inputting operating status parameters into the health status assessment model and outputting health scores such as lifespan, capacity, and internal resistance, the performance degradation of the energy storage module can be comprehensively reflected, thereby providing a scientific basis for subsequent adjustments and extending the module's service life.

[0051] 2. By detecting abnormal current waveforms during vehicle startup and switching power supply paths when abnormalities occur, damage to the electrical system caused by sudden current changes can be effectively prevented, thereby improving the safety and stability of system operation. After startup, by generating a supply adjustment plan based on health score results and user operation commands and dynamically adjusting the energy supply ratio, collaborative optimization of the energy storage module and the primary battery can be achieved, thus taking into account the needs of different users and improving energy utilization efficiency. By recording environmental parameters, control strategies, and response behaviors during startup and writing them back to the historical dataset, an adaptive startup optimization mechanism can be gradually formed, thereby achieving continuous optimization and intelligent evolution of the energy supply strategy. Attached Figure Description

[0052] Figure 1 This is a flowchart of a method for optimizing the discharge of a vehicle starting power supply according to an embodiment of this application;

[0053] Figure 2 This is a flowchart illustrating the implementation of step S10 in a method for optimizing the discharge of a vehicle starting power supply according to an embodiment of this application.

[0054] Figure 3 This is a flowchart of an implementation of a discharge optimization method for a vehicle starting power supply according to an embodiment of this application;

[0055] Figure 4 This is a flowchart illustrating the implementation of step S30 in a method for optimizing the discharge of a vehicle starting power supply according to an embodiment of this application.

[0056] Figure 5 This is a flowchart illustrating the implementation of step S40 in a method for optimizing the discharge of a vehicle starting power supply according to an embodiment of this application.

[0057] Figure 6 This is a flowchart illustrating the implementation of step S50 in a method for optimizing the discharge of a vehicle starting power supply according to an embodiment of this application.

[0058] Figure 7This is another implementation flowchart of a method for optimizing the discharge of a vehicle starting power supply according to one embodiment of this application;

[0059] Figure 8 This is a schematic diagram of a discharge optimization system for a vehicle starting power supply according to one embodiment of this application. Detailed Implementation

[0060] The present application will be further described in detail below with reference to the accompanying drawings.

[0061] In one embodiment, such as Figure 1 As shown, this application discloses a method for optimizing the discharge of a vehicle starting power supply, which specifically includes the following steps:

[0062] S10: Obtain the vehicle start signal, and based on the vehicle start signal, call the energy distribution model to calculate the target current value required for the current start, and control the energy storage module to discharge according to the target current value.

[0063] Specifically, after receiving the start-up trigger signal generated by the vehicle ignition control system, the energy distribution algorithm module is woken up through the communication bus. The calculation process is triggered by combining the current system time and power initialization state, and the preset energy distribution model is retrieved. The model estimates the peak starting current required by the motor according to the starting scenario. For example, in a low temperature environment of -10℃, the model predicts that the initial starting current of the motor may be as high as 380A. The target current value will be set to 400A to ensure redundancy. The target current value output by the model is used to instruct the energy storage module to adjust the output current through the DC-DC converter to ensure that the overall power supply meets the high current demand of the motor at the moment of starting, while avoiding the risk of excessive voltage drop caused by independent battery discharge.

[0064] In this embodiment, the energy storage module is connected in parallel with the vehicle's existing starting power system via an electrical connection structure. Specifically, the positive output terminal of the energy storage module is connected to the positive terminal of the vehicle's power bus via a first discharge relay, and the negative terminal is connected to the vehicle's negative terminal via a common ground wire. This allows the energy storage module to work with the primary battery to provide power to the vehicle's starting system when the circuit is closed. A bidirectional current detection unit is configured in the parallel structure to monitor changes in the discharge current of the energy storage module. An independent current control switch or electronic current limiting unit is also set in the energy storage path to achieve dynamic adjustment and protection control of the energy storage output. In addition, to prevent voltage backflow and high-voltage transient impact, a soft-start resistor and a TVS protection device are connected in series in the energy storage output circuit to ensure stable and reliable energy coupling between the energy storage module and the primary battery during the initial startup phase. This connection method balances rapid response capability and system safety, and is conducive to achieving refined energy regulation and system redundancy switching control.

[0065] S20: During the discharge process of the energy storage module, the real-time operating status parameters of the energy storage module are collected in real time. The operating status parameters include cold start current capability parameters, internal resistance parameters, and temperature parameters.

[0066] Specifically, during the discharge process, the control logic periodically calls the embedded sensing unit to collect key parameters within the energy storage module. This includes using a Hall current sensor to obtain the current maximum release current as a cold-start capability indicator, acquiring real-time temperature information through built-in or attached thermistors, and obtaining the equivalent internal resistance value through voltage and current response curve fitting. The sampling frequency is dynamically adjusted according to the discharge stage, using a high-frequency mode to capture key changes in the early stages of discharge and reducing the frequency during stable periods to decrease system load. All parameters are buffered as feature quantities in real-time into data frames and pushed to subsequent processing modules. For example, if the module's current cold-start capability is 310A, and the current module surface temperature is 45℃, the equivalent internal resistance is calculated as 12mΩ by fitting the module's output voltage and actual current. The sampling frequency is increased to 10Hz within the first 3 seconds of startup to enhance response capability. The sampled data is buffered and transmitted to the subsequent model interface for health status assessment.

[0067] S30: Input the operating status parameters into the energy storage health status assessment model and output the corresponding health score results.

[0068] Specifically, the collected cold-start current capability, internal resistance, and temperature parameters are sequentially encoded as input vectors and fed into a deployed health status assessment model. This model, pre-trained based on a deep learning architecture, outputs numerical scores across multiple dimensions. The primary output is a quantified value serving as a comprehensive health score, representing the current availability and degradation level of the energy storage module. This score ranges from 0 to 100; a higher score indicates the module's performance is closer to its initial state. The scoring process is completed on a local edge processing chip to ensure real-time response. For example, when the temperature is high and the internal resistance increases, the model outputs a health score of 72, indicating the energy storage module is in a moderately high state. The scoring process is completed within the local edge computing chip, with a response latency of less than 100ms, ensuring real-time performance.

[0069] S40: During vehicle startup, anomaly detection is performed on the output current waveform of the energy storage module to determine if there is any abnormal deformation. If the result indicates that there is an abnormality, a power supply path switching operation is executed.

[0070] Specifically, during the startup phase, the current waveform at the output of the energy storage module is continuously monitored. Parameters such as the amplitude, slope, and rate of change of the current over time are extracted and compared with pre-stored standard waveform templates to determine if any abnormal deformation characteristics exist, such as sudden jumps, abnormal continuous fluctuation frequencies, or hysteresis. If any characteristic exceeds a set threshold range, an abnormal flag is immediately triggered, and a power supply path switching command is activated, allowing the primary battery to temporarily assume independent power supply. Simultaneously, the energy storage module is forced into current-limiting or protection mode to prevent potential cell failures from escalating further. For example, if instantaneous current fluctuations exceed ±100A or the slope jump exceeds twice the normal template for three consecutive cycles, it is judged as abnormal oscillation, triggering a power supply switching command to switch the output path from "energy storage + primary battery" mode to "primary battery exclusive power supply" mode, preventing the risk of abnormal energy storage discharge from escalating.

[0071] S50: After the vehicle starts, it generates a supply adjustment plan based on the health score and user operation instructions, and dynamically adjusts the energy supply ratio between the energy storage module and the vehicle's primary battery according to the supply adjustment plan during vehicle operation.

[0072] Specifically, after the vehicle starts and enters the driving phase, the energy supply ratio between the energy storage module and the primary battery is dynamically adjusted based on the vehicle's real-time operating conditions and the user's operation commands on the central control interface or driving mode selection switch. When the user selects Sport mode, the supply adjustment scheme increases the discharge ratio of the energy storage module under acceleration conditions to ensure that the vehicle's electrical equipment and drive unit receive sufficient current under instantaneous high load. When the user selects Eco mode, the supply adjustment scheme reduces the intervention frequency of the energy storage module, allowing the primary battery to bear more conventional loads, thereby extending the life of the energy storage module and reducing overall energy consumption. In special situations such as long-distance driving or heavy air conditioning load, the supply adjustment scheme will adjust the allocation ratio in real time based on the health score results. For example, when the energy storage module's capacity decay or internal resistance increases, its discharge ratio is automatically reduced to avoid the risk of failure caused by over-discharge. Under low-temperature conditions, if the health score shows a decline in the performance of the primary battery, the participation of the energy storage module is increased to maintain stable power supply. Through this dynamic adjustment during driving, the system can meet the user's driving habits while taking into account both energy storage life and vehicle operation stability.

[0073] S60: Records the environmental parameters, control strategies, and response behaviors during the current startup process, and updates the recorded data to the behavior history dataset to support the optimization and generation of subsequent startup strategies.

[0074] Specifically, upon detecting a successful vehicle start signal or a start-up process termination signal, all environmental state quantities collected during the current control process, such as external temperature, humidity, voltage curve, target current, and energy storage health score, are immediately frozen. At the same time, behavioral response information such as the energy supply ratio adjustment path, the number of abnormal flag triggers, and the switching response delay are recorded. All data is packaged into a structured behavioral record and uploaded to a local historical dataset or a remote server for use by subsequent model training or strategy optimization modules, thereby realizing the system's adaptive learning and continuous optimization capabilities.

[0075] By adopting the above technical solution, and by acquiring the vehicle start-up signal and calling the energy distribution model to calculate the target current value, the required current can be accurately predicted before start-up, avoiding insufficient power supply or overload due to empirical value deviations, thereby improving the start-up success rate and reducing the pressure on the battery and energy storage module. By collecting operating status parameters in real time during discharge, the cold start capability, internal resistance, and temperature changes of the energy storage module can be dynamically monitored, providing reliable data support for health assessment and strategy adjustment. By inputting the operating status parameters into the health status assessment model and outputting health scores such as lifespan, capacity, and internal resistance, the performance degradation of the energy storage module can be comprehensively reflected, thus providing a scientific basis for subsequent adjustments. Extending module lifespan; by detecting abnormal current waveforms during vehicle startup and switching power supply paths when abnormalities occur, damage to the electrical system caused by sudden current changes can be effectively prevented, thereby improving the safety and stability of system operation; by generating a supply adjustment plan based on health score results and user operation commands after startup and dynamically adjusting the energy supply ratio, collaborative optimization between the energy storage module and the primary battery can be achieved, thus meeting the needs of different users and improving energy utilization efficiency; by recording environmental parameters, control strategies, and response behaviors during startup and writing them back to historical datasets, an adaptive startup optimization mechanism can be gradually formed, thereby achieving continuous optimization and intelligent evolution of the energy supply strategy.

[0076] In one embodiment, such as Figure 2 As shown, in step S10, the energy allocation model is invoked to calculate the target current value required for current startup, which specifically includes:

[0077] S11: Obtain vehicle startup condition characteristic parameters, including vehicle type information, battery pack capacity, current ambient temperature and humidity, and historical startup current data.

[0078] Specifically, after the vehicle enters the standby state, the vehicle identifier information and model parameters are obtained through the vehicle control network as vehicle type information. The rated capacity and real-time SOC (state of charge) of the current main battery pack are read through the battery management module to estimate the current available capacity. Then, the current external ambient temperature and air humidity parameters are obtained through the integrated environmental monitoring module. For example, the current detected ambient temperature is -5℃ and the humidity is 70%. At the same time, historical starting current data under the same or similar operating conditions are retrieved from the local cache or remote database as sample reference values. For example, the average starting current of this type of vehicle under similar conditions in history is 320A. All the collected vehicle starting condition characteristic parameters are used as complete input feature vectors for subsequent model calculations.

[0079] S12: Input the vehicle startup condition characteristic parameters into the energy distribution model and output the target current value required for current startup.

[0080] Specifically, the vehicle type, battery capacity, ambient temperature and humidity, and historical starting current data are standardized and encoded according to preset dimensions, and then input into the loaded energy distribution model for inference calculation. This model is a regression model built on gradient enhancement tree or neural network, which has the ability to fit complex relationships between nonlinear variables. For example, the target current predicted by the model under the current operating conditions is 345A. Then, the target current is used as the basis for control commands to guide the load distribution between the energy storage module and the original vehicle battery, thereby achieving on-demand discharge and precise starting guarantee.

[0081] The energy allocation model predicts the target current required for starting a vehicle based on its starting conditions and characteristic parameters. Its construction process is based on multi-dimensional, multi-condition historical starting data for modeling and training. Model inputs include, but are not limited to, vehicle type information, battery pack capacity parameters, current ambient temperature and humidity data, the vehicle's current load status, and historical starting current records under similar conditions. The output is the target discharge current required for the starting phase. To improve the model's fitting accuracy and generalization ability, a gradient boosting tree is used as the main model architecture during training, and mean squared error is used as the loss function. The model outputs continuous target current predictions via regression.

[0082] In one embodiment, such as Figure 3 As shown, the method for optimizing the discharge of a vehicle starting power supply further includes:

[0083] S301: Extract the operating status parameters and corresponding health scores of multiple historical energy storage modules as training samples.

[0084] Specifically, historical operating status parameters are extracted from energy storage modules operating under different batches and conditions as model training samples, including but not limited to core indicators such as module cold start current capability, internal equivalent resistance, operating temperature, and voltage response curve. At the same time, the health scores obtained by manual annotation or actual evaluation corresponding to these operating states are summarized as training target values. The health scores can be obtained through manual detection, cell degradation testing, or laboratory standard life testing. For example, after 12 months of use, the cold start capability of a module decreases by 20%, and the internal resistance increases to 15mΩ. The offline evaluation health score is 68 points. All collected samples are structured and then used to form a training dataset, which ultimately forms a sample set containing thousands of sample pairs to support the supervised learning process.

[0085] S302: A neural network evaluation model is constructed using a supervised learning algorithm and trained based on training samples. During the training process, the network weights are iteratively optimized through the error backpropagation mechanism to finally obtain the energy storage health status evaluation model.

[0086] Specifically, a feedforward neural network was chosen as the model structure. The network consists of an input layer, two hidden layers, and an output layer. The number of nodes in the input layer is consistent with the dimension of the running state parameters, for example, it contains 6 input features. The output layer is a health score regression value. The ReLU activation function and Adam optimizer are used for model training. During training, the mean squared error (MSE) is used as the loss function to evaluate the deviation between the model's prediction results and the actual scores. In each round of training, the connection weights and bias values ​​of the neurons in each layer are automatically adjusted through the error backpropagation mechanism. The iteration continues until the validation set error tends to stabilize or the set stopping condition is reached. For example, after 100 rounds of training, the model achieves an average error of 1.8 points on the validation set. After the model training is completed, it is exported and deployed to the vehicle control system to realize rapid health assessment and score output of real-time running status.

[0087] In one embodiment, such as Figure 4 As shown, in step S30, the operating status parameters are input into the energy storage health status assessment model, and the corresponding health score results are output, specifically including:

[0088] S31: Preprocess the operating status parameters to obtain preprocessed operating status parameters. Preprocessing includes normalization, noise reduction and outlier removal.

[0089] Specifically, after the operating status parameters of the energy storage module are collected, a standardized processing procedure is performed on the data of each dimension in sequence. First, the cold start current capability, internal resistance and temperature parameters are normalized so that their values ​​fall within the unified range of [0,1], so as to avoid model bias due to differences in the units of measurement between features. For example, the internal resistance is normalized from the original 12mΩ to 0.24. At the same time, a sliding window filtering method is used to remove short-term high-frequency noise. The continuously measured temperature signal is smoothed by a 5-point weighted average. In addition, the IQR method is introduced to identify outliers. When a current capability parameter exceeds three times the upper limit of historical data, it is judged as an anomaly and removed. Finally, a preprocessed parameter sequence with complete structure, suppressed noise and controllable values ​​is generated.

[0090] S32: Input the preprocessed operating status parameters into the energy storage health status assessment model and output the corresponding health score results.

[0091] Specifically, the parameter set after normalization, denoising, and anomaly removal is concatenated into a feature vector according to the model input format and input into the energy storage health status assessment model. This model is a pre-trained multi-layer feedforward neural network structure. During the forward inference process of the model, activation values ​​are calculated by neurons in each layer and passed layer by layer. Finally, a health score value between 0 and 100 is generated at the output layer. For example, when the input internal resistance increases, the temperature is too high, and the current capacity decreases, the model determines that the current energy storage unit is in a moderately weak state, and the corresponding output health score is 62 points. This score will serve as an important basis for the generation of subsequent power supply adjustment strategies.

[0092] In one embodiment, such as Figure 5 As shown, in step S40, anomaly detection is performed on the output current waveform of the energy storage module, specifically including:

[0093] S41: During vehicle startup, waveform data of the output current of the energy storage module changing over time is collected in real time.

[0094] Specifically, when the vehicle enters the startup phase, the data acquisition interface is invoked to start a high-frequency current sampling task. The sampling period is set to a range of 10ms to 20ms. The output current of the energy storage module is continuously sampled using a Hall sensor or a high-precision shunt, and the waveform change data is recorded according to the time series. At the same time, the waveform data is cached in a ring data structure to support subsequent rapid analysis operations. For example, during a cold start, the current change of the energy storage module is collected, which rises rapidly from 0A to 220A, accompanied by several instantaneous drop segments. This waveform data is completely retained in the designated cache channel.

[0095] S42: Extract the characteristic parameters of the current waveform and compare the characteristic parameters with the preset normal waveform template. The characteristic parameters include amplitude, slope, rate of change and fluctuation frequency.

[0096] Specifically, the collected current waveform data is processed using windowed analysis. The maximum amplitude, rising slope, rate of change of difference between adjacent sampling points, and number of oscillations per unit time are calculated for each sampling period. These indicators are extracted as feature parameter vectors. At the same time, a locally preset normal waveform template is called. The template is constructed based on a large number of measured samples and reflects the current change range and dynamic characteristics under typical startup phase. For example, the maximum slope of the normal waveform during startup phase should be less than 120A / s, and the fluctuation frequency should be less than 5Hz. If the actual feature parameters exceed the threshold range set by the template, it is marked as an abnormal risk.

[0097] S43: When non-steady-state features are detected in the characteristic parameters, it is determined that the current waveform has abnormal deformation. Non-steady-state features include sudden current surge, violent fluctuations and abnormal oscillations.

[0098] Specifically, when obvious nonlinear or abrupt changes appear in the waveform characteristic parameters during a certain period, such as a sudden increase in current exceeding 80A between two consecutive sampling points, or multiple positive and negative fluctuations with a frequency greater than 10Hz within 5 seconds, the system identifies it as a sudden increase in current and abnormal oscillation. It immediately determines that the waveform has a serious abnormal deformation and triggers an early warning flag. At the same time, the current abnormal data is recorded and uploaded to the central diagnostic module for subsequent behavior tracking and strategy backtracking support. For example, during the startup process in extremely cold weather, the system detected a violent oscillation signal with a waveform slope of 160A / s, confirming an anomaly and then executing subsequent protection strategies.

[0099] In one embodiment, such as Figure 6 As shown, in step S50, a supply adjustment plan is generated based on the health score results and user operation instructions, specifically including:

[0100] S51: Estimate the maximum allowable discharge current limit of the energy storage module based on the health score results.

[0101] Specifically, after the vehicle starts, the operating status parameters of the energy storage module in the previous stage are retrieved and calculated in conjunction with the life status and internal resistance status in the health score results. By judging the actual capacity retention rate and the increase in internal resistance of the energy storage module, its safe discharge limit current value under the current temperature and operating conditions is estimated. For example, when the health score shows that the capacity decay exceeds 20% and the internal resistance increases by 30% compared with the initial value, the maximum allowable discharge current limit is set to 70% of the nominal value. If the health score results show that the energy storage module is in good condition and the temperature is within the normal temperature range, the allowable discharge current limit can be close to the nominal rated value, thereby maximizing the performance of the energy storage module while ensuring safety.

[0102] S52: Determine the target energy distribution tendency between the energy storage module and the vehicle's primary battery based on user operation instructions.

[0103] Specifically, during vehicle operation, the system recognizes user input commands via the driving mode selection switch or central control interface. When the user selects Sport mode, the target energy distribution is set to have the energy storage module handle a larger proportion of the instantaneous high-power load to ensure acceleration response and high current demand. When the user selects Eco mode, the target energy distribution is set to have the primary battery handle the main load, with the energy storage module only intervening when the current exceeds a certain threshold to extend the lifespan of the energy storage module. When the user does not select a specific mode or is in the default mode, the target energy distribution is set to an intermediate state of balanced energy supply between the two to balance performance and durability.

[0104] S53: Based on the maximum allowable discharge current limit and the target energy distribution tendency, combined with the current environmental state parameters and the current remaining capacity of the vehicle's primary battery, generate a supply adjustment plan. The supply adjustment plan includes the energy distribution ratio between the energy storage module and the vehicle's primary battery, the current limit, and whether to trigger the current limiting protection strategy.

[0105] Specifically, based on obtaining the maximum allowable discharge current limit and the target energy distribution tendency, the system further combines environmental parameters such as current ambient temperature and humidity, as well as the remaining capacity and discharge capability of the vehicle's primary battery, to calculate the coordinated energy supply ratio of the two during driving. For example, if the performance of the primary battery deteriorates under low temperature conditions, its distribution ratio will be appropriately increased while ensuring that the current of the energy storage module does not exceed the safety limit. Under high temperature or long-term heavy load conditions, the continuous discharge ratio of the energy storage module will be reduced to avoid overheating. The final supply adjustment scheme includes precise energy distribution ratio parameters, current limit thresholds for each path, and conditions for triggering current limiting protection. When the current exceeds the set limit or the temperature exceeds the safe range during operation, the current limiting protection strategy is immediately triggered, thereby ensuring the safety and stability of the vehicle's energy supply under different environments and operating conditions.

[0106] In one embodiment, such as Figure 7As shown, the method for optimizing the discharge of a vehicle starting power supply further includes:

[0107] S70: After performing the power supply path switching operation, control the energy storage module to enter the protection state. The protection state includes disconnecting the energy storage output path, limiting the subsequent discharge capacity, or enabling the low-power standby mode.

[0108] Specifically, after an abnormal waveform is detected and triggers a power supply path switching action, the main discharge relay of the energy storage module is immediately shut down via a control command to physically disconnect the energy storage from the power bus. At the same time, the internal current limiting mechanism of the module is activated to reduce the discharge output capability to 0A, or switch to a low-power mode to maintain the lowest logic level operation to wait for a wake-up event. The triggering basis for the protection state includes the waveform change level, the duration of the abnormal current, or the temperature rise. For example, if a continuous and severe fluctuation is detected during a startup process, accompanied by a sudden rise in current to over 300A, the system controls the energy storage module to forcibly cut off the output and lock it in a low-power state to prevent further damage.

[0109] S80: After the energy storage module enters the protection state, it sends a switching status feedback signal to update the current power supply status of the system, prevent repeated switching or false triggering, and maintain the protection state until the vehicle starts.

[0110] Specifically, when the energy storage module switches to the protection state, it sends a feedback signal to the main control communication bus containing the current power supply path status, the type of abnormality, and the protection mode identifier. For example, the feedback frame contains information such as "protection mode = on", "current power supply path = primary battery", and "switching reason = output oscillation". After receiving the signal, the main control unit updates the internal power supply status mapping table and blocks subsequent repeated switching requests or manual reset operations until the vehicle start-up status end flag is detected, such as the start-up completion flag or the engine stable operation signal. Only then is the system allowed to exit the protection state and restore normal power supply logic, thereby avoiding system instability caused by repeated switching or accidental triggering in a short period of time.

[0111] In another alternative implementation, the energy storage module and the small-capacity battery are integrated into a casing of the same size as the original vehicle battery, maintaining visual consistency and allowing for direct replacement by the user. This integrated battery houses both the energy storage module and a non-starting battery. The capacity of the non-starting battery can be selected based on the vehicle's regular electrical needs, and its material is not limited to lead-acid, lithium, sodium, or other energy storage materials. When the vehicle requires high current for ignition and starting, the energy storage module independently handles the discharge, ensuring smooth engine startup. During normal vehicle operation, the embedded small-capacity battery provides energy, preventing frequent cycling of the energy storage module. This integrated design allows for coordinated management of the energy storage module and embedded battery under the unified scheduling of the intelligent battery management system (BMS), improving system intelligence and safety. Furthermore, by eliminating the need for a high-cost starting battery and using only a standard battery, manufacturing costs are reduced while still meeting power requirements. Additionally, the integrated battery's identical appearance to the original vehicle battery facilitates market sales and user replacement, and its integrated structure enhances overall operational safety and reliability.

[0112] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0113] In one embodiment, a discharge optimization system for a vehicle starting power supply is provided, which corresponds one-to-one with the discharge optimization method for a vehicle starting power supply described in the above embodiments. For example... Figure 8 As shown, this vehicle starting power supply discharge optimization system includes a starting signal analysis module, an operating status acquisition module, a health status assessment module, a power supply strategy adjustment module, a waveform anomaly detection module, and a behavior recording and write-back module. Detailed descriptions of each functional module are as follows:

[0114] The start signal parsing module is used to acquire the vehicle start signal, and based on the vehicle start signal, it calls the energy distribution model to calculate the target current value required for the current start, and controls the energy storage module to discharge according to the target current value. The energy storage module is connected in parallel with the vehicle's primary battery.

[0115] The operation status acquisition module is used to acquire the real-time operation status parameters of the energy storage module during the discharge process. The operation status parameters include cold start current capability parameters, internal resistance parameters, and temperature parameters.

[0116] The health status assessment module is used to input operating status parameters into the energy storage health status assessment model and output the corresponding health score results.

[0117] The waveform anomaly detection module is used to detect anomalies in the output current waveform of the energy storage module during vehicle startup, determine whether there is abnormal deformation, and if the result is that there is an anomaly, then a power supply path switching operation is performed.

[0118] The energy supply strategy adjustment module is used to generate a supply adjustment plan based on the health score and user operation instructions after the vehicle starts up, and dynamically adjust the energy supply ratio between the energy storage module and the vehicle's primary battery according to the supply adjustment plan during vehicle operation.

[0119] The behavior recording and write-back module is used to record the environmental parameters, control strategies and response behaviors during the current startup process, and update the recorded data to the behavior history dataset to support the optimization and generation of subsequent startup strategies.

[0120] Optionally, the startup signal parsing module includes:

[0121] The operating condition parameter acquisition submodule is used to acquire vehicle starting operating condition characteristic parameters, including vehicle type information, battery pack capacity, current ambient temperature and humidity, and historical starting current data.

[0122] The target current calculation submodule is used to input the vehicle's starting condition characteristic parameters into the energy distribution model and output the target current value required for the current start-up.

[0123] Optionally, the discharge optimization system for a vehicle starting power supply further includes:

[0124] The sample training module is used to extract the operating status parameters and corresponding health score results of multiple historical energy storage modules as training samples.

[0125] The evaluation model building module is used to construct a neural network evaluation model using a supervised learning algorithm and train it based on training samples. During the training process, the network weights are iteratively optimized through an error backpropagation mechanism to finally obtain the energy storage health status evaluation model.

[0126] Optional, the health status assessment module includes:

[0127] The parameter preprocessing submodule is used to preprocess the running status parameters to obtain the preprocessed running status parameters. The preprocessing includes normalization, noise reduction and outlier removal.

[0128] The health score output submodule is used to input the preprocessed operating status parameters into the energy storage health status assessment model and output the corresponding health score results.

[0129] Optionally, the power supply strategy adjustment module includes:

[0130] The energy supply ratio calculation submodule is used to calculate the optimal energy supply ratio of the energy storage module during vehicle startup based on the health score results and the current environmental conditions.

[0131] The current limiting capability estimation submodule is used to estimate the maximum allowable discharge current limit of the energy storage module based on the lifetime status parameters in the health score results.

[0132] The supply strategy generation submodule is used to generate a supply adjustment plan based on the optimal energy supply ratio and the maximum allowable discharge current limit, combined with the current remaining capacity and output capability of the vehicle's primary battery. The supply adjustment plan includes the energy distribution ratio between the energy storage module and the vehicle's primary battery, the current limit, and whether to trigger the current limiting protection strategy.

[0133] Optionally, the waveform anomaly detection module includes:

[0134] The waveform data acquisition submodule is used to acquire waveform data of the output current of the energy storage module changing over time in real time during vehicle startup.

[0135] The waveform feature extraction submodule is used to extract the feature parameters of the current waveform and compare the feature parameters with the preset normal waveform template. The feature parameters include amplitude, slope, rate of change and fluctuation frequency.

[0136] The anomaly detection submodule is used to determine that the current waveform has abnormal deformation when non-steady-state features are detected in the feature parameters. Non-steady-state features include sudden current surges, violent fluctuations, and abnormal oscillations.

[0137] Optionally, the discharge optimization system for a vehicle starting power supply further includes:

[0138] The protection control module is used to control the energy storage module to enter the protection state after the power supply path switching operation is performed. The protection state includes disconnecting the energy storage output path, limiting the subsequent discharge capacity, or enabling the low power standby mode.

[0139] The status feedback module is used to send a switching status feedback signal after the energy storage module enters the protection state. This is used to update the current power supply status of the system, prevent repeated switching or false triggering, and maintain the protection state until the vehicle starts up.

[0140] Specific limitations regarding the discharge optimization system for a vehicle starting power supply can be found in the limitations of the discharge optimization method for a vehicle starting power supply described above, and will not be repeated here. Each module in the aforementioned discharge optimization system for a vehicle starting power supply can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0141] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0142] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for optimizing the discharge of a vehicle starting power supply, characterized in that, The method for optimizing the discharge of a vehicle starting power supply includes: The system acquires a vehicle start signal, calculates the target current value required for the current start based on the vehicle start signal using an energy distribution model, and controls the energy storage module to discharge based on the target current value. During the discharge process of the energy storage module, the real-time operating status parameters of the energy storage module are collected in real time. The operating status parameters include at least the cold start current capability parameter, the internal resistance parameter, and the temperature parameter. The operating status parameters are input into the energy storage health status assessment model, and the corresponding health score results are output. The health score results include lifetime status parameters, capacity status parameters, and internal resistance status parameters. During vehicle startup, the output current waveform of the energy storage module is subjected to anomaly detection to determine whether there is abnormal deformation. If the result indicates that there is an anomaly, a power supply path switching operation is performed. After the vehicle starts, a supply adjustment plan is generated based on the health score and user operation instructions. During vehicle operation, the energy supply ratio between the energy storage module and the vehicle's primary battery is dynamically adjusted according to the supply adjustment plan. Record the environmental parameters, control strategies, and response behaviors during the current startup process, and update the recorded data to the behavior history dataset to support the optimization and generation of subsequent startup strategies.

2. The method for optimizing the discharge of a vehicle starting power supply according to claim 1, characterized in that, The calculation of the target current value required for current startup by calling the energy allocation model includes: Obtain vehicle startup condition characteristic parameters, which include vehicle type information, battery pack capacity, current ambient temperature and humidity, and historical startup current data; The vehicle startup condition characteristic parameters are input into the energy distribution model, and the target current value required for the current startup is output.

3. The method for optimizing the discharge of a vehicle starting power supply according to claim 1, characterized in that, The method for optimizing the discharge of a vehicle starting power supply further includes: The operating status parameters and corresponding health scores of multiple historical energy storage modules were extracted as training samples. A neural network evaluation model is constructed using a supervised learning algorithm and trained based on the training samples. During the training process, the network weights are iteratively optimized through an error backpropagation mechanism to finally obtain the energy storage health status evaluation model.

4. The method for optimizing the discharge of a vehicle starting power supply according to claim 1, characterized in that, The step of inputting the operating status parameters into the energy storage health status assessment model and outputting the corresponding health score results includes: The operating status parameters are preprocessed to obtain preprocessed operating status parameters. The preprocessing includes normalization, noise reduction and outlier removal. The preprocessed operating status parameters are input into the energy storage health status assessment model, and the corresponding health score results are output.

5. The method for optimizing the discharge of a vehicle starting power supply according to claim 1, characterized in that, The abnormal detection of the output current waveform of the energy storage module includes: During vehicle startup, waveform data of the output current of the energy storage module changing over time are collected in real time. The characteristic parameters of the current waveform are extracted and compared with a preset normal waveform template. The characteristic parameters include amplitude, slope, rate of change and fluctuation frequency. When non-steady-state features are detected in the feature parameters, it is determined that the current waveform has abnormal deformation. The non-steady-state features include sudden current surges, violent fluctuations, and abnormal oscillations.

6. The method for optimizing the discharge of a vehicle starting power supply according to claim 1, characterized in that, The step of generating a supply adjustment plan based on the health score results and user operation instructions includes: The maximum allowable discharge current of the energy storage module is estimated based on the health score results. The target energy distribution tendency between the energy storage module and the vehicle's primary battery is determined based on the user's operation instructions. Based on the maximum allowable discharge current limit and the target energy distribution tendency, combined with the current environmental state parameters and the current remaining capacity of the vehicle's primary battery, the supply adjustment scheme is generated. The supply adjustment scheme includes the energy distribution ratio between the energy storage module and the vehicle's primary battery, the current limit, and whether to trigger the current limiting protection strategy.

7. The method for optimizing the discharge of a vehicle starting power supply according to claim 1, characterized in that, The method for optimizing the discharge of a vehicle starting power supply further includes: After performing the power supply path switching operation, the energy storage module is controlled to enter the protection state, which includes disconnecting the energy storage output path, limiting the subsequent discharge capacity, or enabling a low-power standby mode. After the energy storage module enters the protection state, it sends a switching status feedback signal to update the current power supply status of the system and prevent repeated switching or false triggering. The protection state is maintained until the vehicle starts up.

8. A discharge optimization system for a vehicle starting power supply, characterized in that, The vehicle starting power supply discharge optimization system includes: The start signal parsing module is used to acquire the vehicle start signal, calculate the target current value required for the current start based on the vehicle start signal, and control the energy storage module to discharge based on the target current value. The operation status acquisition module is used to acquire the real-time operation status parameters of the energy storage module during the discharge process of the energy storage module. The operation status parameters include cold start current capability parameters, internal resistance parameters and temperature parameters. The health status assessment module is used to input the operating status parameters into the energy storage health status assessment model and output the corresponding health score results. The health score results include at least lifetime status parameters, capacity status parameters and internal resistance status parameters. The waveform anomaly detection module is used to detect anomalies in the output current waveform of the energy storage module during vehicle startup, determine whether there is abnormal deformation, and if the determination result is that there is an anomaly, then perform a power supply path switching operation. The energy supply strategy adjustment module is used to generate a supply adjustment plan based on the health score results and user operation instructions after the vehicle starts, and to dynamically adjust the energy supply ratio between the energy storage module and the vehicle's primary battery according to the supply adjustment plan during vehicle operation. The behavior recording and write-back module is used to record the environmental parameters, control strategies and response behaviors during the current startup process, and update the recorded data to the behavior history dataset to support the optimization and generation of subsequent startup strategies.

Images