Dynamic performance recovery method and device of vehicle battery, vehicle, medium and product

Abstract

The invention relates to the technical field of fuel cells, in particular to a dynamic performance recovery method and device for a vehicle battery, a vehicle, a medium and a product, and the method comprises the steps: obtaining road spectrum data and a current SOC of the vehicle; inputting the road spectrum data into a pre-trained LSTM neural network to obtain a battery SOC in a preset time period; and determining a dynamic performance recovery strategy of the electric pile of the vehicle according to the current SOC and the SOC of the battery in the preset time period, and performing dynamic performance recovery on the electric pile according to the dynamic performance recovery strategy, thereby solving the problem that the state of the SOC of the power battery is not predicted in the related technology. The problems that the working efficiency of the galvanic pile is low and the endurance mileage is reduced due to the fact that the galvanic pile cannot adapt to variable road conditions are solved, the working efficiency of the galvanic pile is improved, and the battery endurance mileage is increased.

Description

Technical Field

[0001] The present invention relates to the technical field of fuel cells, and in particular to a method, device, vehicle, medium and product for recovering the dynamic performance of a vehicle battery. Background Art

[0002] Fuel cell stacks experience performance degradation during long-term steady-state operation. The energy loss caused by the non-ideality of various physical and chemical processes can theoretically be recovered by changing the conditions.

[0003] In related technologies, the SOC value of the power battery is mainly estimated through the state of charge interpolation table, and the FCCU preset control algorithm is used to determine whether the power battery is allowed to be charged, the charging time, and the number of charging times. If charging is allowed, the dynamic recovery strategy is started. If charging is not allowed, the next charging opportunity is waited for to recover energy and reduce energy consumption.

[0004] However, the relevant technology does not predict the SOC state of the power battery and cannot adapt to changing road conditions, resulting in a decrease in the dynamic performance of the battery stack, a reduction in the life of the battery stack, and an impact on the cruising range, which urgently needs to be solved. Summary of the Invention

[0005] The present invention provides a method, device, vehicle, medium and product for recovering the dynamic performance of a vehicle battery, so as to solve the problems in the related art of low battery stack efficiency and reduced cruising range caused by the failure to predict the SOC state of the power battery and the inability to adapt to changing road conditions, thereby improving the battery stack efficiency and increasing the battery cruising range.

[0006] An embodiment of the first aspect of the present invention provides a method for dynamic performance recovery of a vehicle battery, comprising the following steps: acquiring the vehicle's road spectrum data and current SOC; inputting the road spectrum data into a pre-trained LSTM neural network to obtain the battery SOC within a preset time period; determining the dynamic performance recovery strategy of the vehicle's battery stack based on the current SOC and the battery SOC within the preset time period, and performing dynamic performance recovery on the battery stack based on the dynamic performance recovery strategy.

[0007] Furthermore, in some embodiments, the dynamic performance recovery strategy of the vehicle's battery stack is determined based on the current SOC and the battery SOC within the preset time period, and the dynamic performance recovery of the battery stack is performed according to the dynamic performance recovery strategy, including: based on the current SOC, determining the charging time required to fully charge the power battery; based on the battery SOC within the preset time period, judging whether the battery SOC corresponding to the next moment is less than or equal to a preset threshold, and taking the next moment as the starting moment, whether there is a preset rising trend in the battery SOC within the charging time; if the battery SOC corresponding to the next moment is less than or equal to the preset threshold, and the battery SOC within the charging time does not have the preset rising trend, then dynamic performance recovery is performed based on the preset pull-up power, and the interior of the battery stack is purged with atmospheric air until the voltage value of the battery stack after attenuation returns to the initial state.

[0008] Furthermore, in some embodiments, after determining whether the battery SOC corresponding to the next moment is less than or equal to a preset threshold value based on the battery SOC within the preset time period, and taking the next moment as the starting moment, and whether there is a preset increasing trend in the battery SOC within the charging time, it also includes: if the battery SOC corresponding to the next moment is greater than the preset threshold value, or the battery SOC within the charging time has the preset increasing trend, determining whether there is at least one time period that satisfies dynamic performance recovery; if there is at least one time period that satisfies the dynamic performance recovery, performing dynamic performance recovery in each time period.

[0009] Furthermore, in some embodiments, after determining whether there is at least one time period that satisfies the dynamic performance recovery, it also includes: if there is no at least one time period that satisfies the dynamic performance recovery, the power of the battery stack is reduced based on a preset power reduction strategy, and the battery stack and the power battery after power reduction output the power corresponding to the current power demand of the vehicle until the battery SOC corresponding to the next moment is less than or equal to the preset threshold, and after the battery SOC within the new charging time does not have the preset increasing trend, the battery stack is independently powered, and dynamic performance recovery is performed based on the preset high power, and the interior of the battery stack is purged with atmospheric air until the voltage value of the battery stack after attenuation returns to the initial state.

[0010] Furthermore, in some embodiments, before obtaining the road spectrum data and current SOC of the vehicle, it also includes: judging whether the battery stack meets the preset dynamic performance recovery conditions; if the battery stack meets the preset dynamic performance recovery conditions, judging whether the power battery has a charging fault; if the power battery has a charging fault, distributing the additional power generated by the battery stack during dynamic performance recovery through at least one load of the vehicle, otherwise, executing the step of obtaining the road spectrum data and current SOC of the vehicle.

[0011] Furthermore, in some embodiments, determining whether the fuel cell stack meets the preset dynamic performance recovery conditions includes: obtaining the current voltage attenuation value of the fuel cell stack; if the current voltage attenuation value reaches a preset attenuation threshold, determining that the fuel cell stack meets the preset dynamic performance recovery conditions.

[0012] According to the dynamic performance recovery method of a vehicle battery provided by an embodiment of the present invention, the vehicle's road spectrum data and the current battery state of charge are obtained, and then the road spectrum data is input into a pre-trained LSTM neural network to obtain the battery SOC within a preset time period. Finally, the dynamic performance recovery strategy of the vehicle battery stack is determined based on the current SOC and the predicted battery SOC within the preset time period, and the dynamic performance recovery of the battery stack is performed based on the strategy. This solves the problem in the related art of low battery stack working efficiency and reduced cruising range due to the failure to predict the power battery SOC state and the inability to adapt to changing road conditions, thereby improving the battery stack working efficiency and increasing the battery cruising range.

[0013] The second aspect of the present invention provides a dynamic performance recovery device for a vehicle battery, the device comprising: an acquisition module for acquiring the vehicle's road spectrum data and current SOC; a prediction module for inputting the road spectrum data into a pre-trained LSTM neural network to obtain the battery SOC within a preset time period; and a control module for determining the dynamic performance recovery strategy of the vehicle's battery stack based on the current SOC and the battery SOC within the preset time period, and performing dynamic performance recovery on the battery stack according to the dynamic performance recovery strategy.

[0014] Furthermore, in some embodiments, the control module is specifically used to: determine the charging time required to fully charge the power battery based on the current SOC; determine whether the battery SOC corresponding to the next moment is less than or equal to a preset threshold based on the battery SOC within the preset time period, and whether there is a preset rising trend in the battery SOC within the charging time period with the next moment as the starting moment; if the battery SOC corresponding to the next moment is less than or equal to the preset threshold, and the battery SOC within the charging time period does not have the preset rising trend, then perform dynamic performance recovery based on the preset pull-up power, and use the atmospheric volume to purge the inside of the battery stack until the voltage value of the battery stack after attenuation returns to the initial state.

[0015] Furthermore, in some embodiments, after judging whether the battery SOC corresponding to the next moment is less than or equal to a preset threshold value based on the battery SOC within the preset time period, and taking the next moment as the starting moment, judging whether there is a preset rising trend in the battery SOC within the charging time, the control module is further used to: if the battery SOC corresponding to the next moment is greater than the preset threshold value, or the battery SOC within the charging time has the preset rising trend, then judging whether there is at least one time period that satisfies dynamic performance recovery; if there is at least one time period that satisfies the dynamic performance recovery, then performing dynamic performance recovery in each time period.

[0016] Furthermore, in some embodiments, after determining whether there is at least one time period that satisfies the dynamic performance recovery, the control module is also used to: if there is no at least one time period that satisfies the dynamic performance recovery, reduce the power of the battery stack based on a preset power reduction strategy, and the battery stack and the power battery after power reduction output the power corresponding to the current power demand of the vehicle until the battery SOC corresponding to the next moment is less than or equal to the preset threshold, and after the battery SOC within the new charging time does not have the preset increasing trend, the battery stack is independently powered, and dynamic performance recovery is performed based on the preset high power, and the interior of the battery stack is purged with atmospheric air until the voltage value of the battery stack after attenuation returns to the initial state.

[0017] Furthermore, in some embodiments, before obtaining the road spectrum data and current SOC of the vehicle, the acquisition module is also used to: determine whether the battery stack meets the preset dynamic performance recovery conditions; if the battery stack meets the preset dynamic performance recovery conditions, determine whether the power battery has a charging fault; if the power battery has a charging fault, distribute the additional power generated by the battery stack during dynamic performance recovery through at least one load of the vehicle, otherwise, execute the step of obtaining the road spectrum data and current SOC of the vehicle.

[0018] Furthermore, in some embodiments, the acquisition module is further used to: acquire a current voltage attenuation value of the fuel cell stack; if the current voltage attenuation value reaches a preset attenuation threshold, determine that the fuel cell stack meets the preset dynamic performance recovery condition.

[0019] According to the dynamic performance recovery device of the vehicle battery provided by the embodiment of the present invention, the vehicle's road spectrum data and the current battery state of charge are obtained, and then the road spectrum data is input into a pre-trained LSTM neural network to obtain the battery SOC within a preset time period. Finally, the dynamic performance recovery strategy of the vehicle battery stack is determined according to the current SOC and the predicted battery SOC within the preset time period, and the dynamic performance recovery of the battery stack is performed according to the strategy. This solves the problem in the related art of low battery stack working efficiency and reduced cruising range due to the failure to predict the power battery SOC state and the inability to adapt to changing road conditions, thereby improving the battery stack working efficiency and increasing the battery cruising range.

[0020] A third aspect of the present invention provides a vehicle comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for recovering the dynamic performance of a vehicle battery as described in the above embodiment.

[0021] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the method for recovering the dynamic performance of a vehicle battery as described in the above embodiment.

[0022] A fifth aspect of the present invention provides a computer program product, comprising a computer program, which is executed to implement the method for recovering the dynamic performance of a vehicle battery as described in the above embodiment.

[0023] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0025] Figure 1 A flowchart of a method for recovering dynamic performance of a vehicle battery according to an embodiment of the present invention;

[0026] Figure 2 A flowchart of an LSTM neural network training process according to a specific embodiment of the present invention;

[0027] Figure 3 A schematic diagram of a neural network structure according to a specific embodiment of the present invention;.

[0028] Figure 4 A flowchart of a dynamic performance recovery strategy for a vehicle battery according to a specific embodiment of the present invention;

[0029] Figure 5 A block diagram of a dynamic performance recovery device for a vehicle battery according to an embodiment of the present invention;

[0030] Figure 6 A schematic structural diagram of a vehicle provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0032] The following describes the dynamic performance recovery method, device, vehicle, medium and product of the vehicle battery according to the embodiment of the present invention with reference to the accompanying drawings. In response to the problem in the related art mentioned in the above background technology that the SOC state of the power battery is not predicted and the battery stack cannot adapt to changing road conditions, resulting in low working efficiency and reduced cruising range, the present invention provides a dynamic performance recovery method for a vehicle battery, which obtains the vehicle's road spectrum data and the current battery state of charge, and then inputs the road spectrum data into a pre-trained LSTM neural network to obtain the battery SOC within a preset time period, and finally determines the dynamic performance recovery strategy of the vehicle battery stack based on the current SOC and the predicted battery SOC within the preset time period, and performs dynamic performance recovery on the battery stack based on the strategy, thereby solving the problem in the related art that the SOC state of the power battery is not predicted and the battery stack cannot adapt to changing road conditions, thereby improving the working efficiency of the battery stack and increasing the battery cruising range.

[0033] Specifically, Figure 1 The present invention is a flowchart of a method for recovering the dynamic performance of a vehicle battery according to an embodiment of the present invention.

[0034] like Figure 1 As shown, the dynamic performance recovery method of the vehicle battery includes the following steps:

[0035] In step S101 , the vehicle's road spectrum data and current SOC are obtained.

[0036] Among them, road spectrum data refers to various dynamic data related to driving road conditions that are used to characterize the characteristics and regularities of the vehicle's driving environment during actual driving. The current SOC is the current state of charge of the battery, that is, the percentage of the current remaining power of the battery to its total capacity.

[0037] Specifically, road spectrum data can include real-time motion data such as vehicle speed, acceleration, vehicle braking signal, steering angle information, and can also include data such as road slope, bumpiness, and curve curvature. Among them, road spectrum data can be collected through sensors installed on the vehicle, such as collecting road slope and bumpiness through lidar, and collecting vehicle speed and acceleration through speed sensors. At the same time, the battery SOC value at the corresponding moment can be recorded as a real label through high-precision battery testing equipment.

[0038] In step S102, the road spectrum data is input into a pre-trained LSTM neural network to obtain the battery SOC within a preset time period.

[0039] Among them, the pre-trained LSTM neural network is a prediction model obtained by using the collected road spectrum data of the vehicle under different driving conditions, including vehicle speed, acceleration, battery current, battery voltage, and ambient temperature, as a training set, and after preprocessing and training. The battery SOC within the preset time period refers to the battery SOC predicted value within the future limited time period obtained by prediction by the LSTM model.

[0040] For example, Figure 2 Schematic diagram of the LSTM neural network training process according to a specific embodiment of the present invention. Figure 2 As shown in the figure, the LSTM neural network training process includes the following steps:

[0041] In step S201, the fuel cell's road data under different driving conditions is collected and the corresponding battery SOC value is recorded. The collected road data includes information such as vehicle speed, acceleration, battery current, battery voltage, and ambient temperature. The sampling frequency is 1 Hz and the sampling lasts for 10 hours.

[0042] In step S202, median filtering is used to remove outliers and noise from the data. The median filter uses a sliding window of fixed length to move on the signal. At each window position, the signal values ​​in the window are sorted, and then the middle value of the sorting is taken as the new signal value at the center of the window. As the window continues to move, the entire signal is processed. Let the one-dimensional signal be x[n], n=0,1,…,N-1, N is the signal length. Select a sliding window of length 2k+1 (k is a non-negative integer). For each position n in the signal, the output y[n] after median filtering can be expressed as:

[0043]

[0044] Among them, Median means taking the median.

[0045] In step S203, the Pearson correlation coefficient is used to analyze the correlation between each feature and the SOC. Vehicle speed, acceleration, battery current, and ambient temperature are used as model input features, and the Pearson correlation coefficient is used to analyze the correlation between each feature and the SOC. The Pearson correlation coefficient is used to measure the degree of linear correlation between two variables, and its value range is between -1 and 1. -1 indicates a perfect negative correlation, 1 indicates a perfect positive correlation, and 0 indicates no linear correlation.

[0046] In step S204, the processed data is divided into a training set, a validation set, and a test set in a ratio of 7:2:1 and normalized. The normalization method normalizes all data to the interval [0, 1]. For each value x in the original data set, the "min-max" normalization converts it to a new value x norm , the calculation formula is as follows:

[0047]

[0048] Among them, x is a specific index in the original data set, x min is the minimum value in the original data set, x max is the maximum value in the original data set.

[0049] In step S205, an LSTM neural network is constructed, wherein the number of neurons in the input layer of the LSTM neural network is set to 4, corresponding to four input features; two hidden layers are set, the first hidden layer has 64 neurons, and the second hidden layer has 32 neurons, both of which use the ReLU activation function, and their mathematical expressions are shown in formula (3); the output layer has 1 neuron, and uses the Sigmoid activation function to output a battery SOC prediction value between 0 and 1, and its mathematical expression is shown in formula (3):

[0050] ReLU(x)=max(0,x) (3)

[0051]

[0052] in, Figure 3 A schematic diagram of a neural network structure according to a specific embodiment of the present invention is shown in FIG. Figure 3As shown in the figure, the original data, such as speed, displacement, and angle, are first "set / standardized", formatted, and scaled to the appropriate range, and then "mapped to high-dimensional space / vectorized" to convert the original signal into a vector form that can be read by the network. The input layer receives the preprocessed vector and performs feature extraction through the "ReLU activation function". After that, more complex high-order features are extracted through multi-layer encoding, and the "sparse" result is output.

[0053] In step S206, the LSTM neural network is trained and evaluated. The training set data is input into the model. Each epoch (referring to the process of performing a complete training on the entire training data set) contains 100 batches (referring to a small set of samples selected from the entire training data set when training the neural network). The size of each batch is 32. 500 epochs are trained. Finally, the LSTM neural network is evaluated using the validation set. It should be noted that in order to prevent overfitting, L2 regularization is used, the regularization parameter is set to 0.001, and the early stopping method is applied. When the validation set loss no longer decreases within 10 consecutive epochs, the training is stopped to obtain the trained LSTM neural network.

[0054] As a feasible method, after the LSTM neural network is trained, the pre-trained LSTM neural network can be deployed on the actual vehicle to predict the battery SOC value. During the actual driving of the vehicle, the road spectrum data is collected in real time and pre-processed, and then input into the pre-trained LSTM neural network to obtain the battery SOC within the preset time period, that is, the real-time prediction value of the battery SOC.

[0055] In step S103 , a dynamic performance recovery strategy for the vehicle's battery stack is determined based on the current SOC and the battery SOC within a preset time period, and the dynamic performance recovery of the battery stack is performed according to the dynamic performance recovery strategy.

[0056] The current SOC refers to the battery SOC value of the vehicle at the current moment, and the battery SOC within the preset time period refers to the battery SOC value at each time point in the future time period.

[0057] Furthermore, in some embodiments, a dynamic performance recovery strategy of the vehicle's battery stack is determined based on the current SOC and the battery SOC within a preset time period, and the battery stack is dynamically restored according to the dynamic performance recovery strategy, including: based on the current SOC, determining the charging time required to fully charge the power battery; based on the battery SOC within the preset time period, judging whether the battery SOC corresponding to the next moment is less than or equal to a preset threshold, and taking the next moment as the starting moment, whether there is a preset rising trend in the battery SOC within the charging time; if the battery SOC corresponding to the next moment is less than or equal to the preset threshold, and there is no preset rising trend in the battery SOC within the charging time, dynamic performance recovery is performed based on the preset pull-up power, and the interior of the battery stack is purged with atmospheric air until the voltage value of the battery stack after attenuation returns to the initial state.

[0058] Among them, the preset threshold is the battery SOC threshold obtained by optimizing, adjusting, verifying, testing and calibrating the equipment performance parameters in a bench test environment. The preset rising trend means that the battery SOC value in the future time period has an increasing trend relative to the battery SOC value at the current time point. The preset high power refers to actively increasing the power output to allow the system load to run at a higher power.

[0059] Specifically, determine whether the battery SOC value in the future time period is lower than the battery SOC threshold, and there is no increasing trend in the battery SOC value in the future time period. When the battery SOC value in the future time period is lower than the battery SOC threshold, and there is no increasing trend in the battery SOC value in the future time period, it indicates that the current power cannot meet the demand for improving the battery SOC. Therefore, it is necessary to directly increase the power for dynamic performance recovery, and use the atmospheric volume to purge the inside of the battery stack until the attenuated voltage value returns to the initial state.

[0060] For example, it is determined whether the battery SOC value in the future time period t0 is lower than the battery SOC threshold value Y%, and there is no upward trend in the battery SOC value within the required charging time t, then the power is directly increased to perform dynamic performance recovery, and the inside of the battery stack is purged with atmospheric air until the attenuated voltage value returns to the initial state, (1-Y%) is the corresponding electrical value in the power battery of the additional energy generated by a dynamic performance recovery, for example, it is determined that the time required to fully charge the battery at this time is 20 minutes, assuming that within the next 1 minute, the battery SOC is 25%, which is less than or equal to 30%, and within the next 10 minutes, there is no upward trend in the battery SOC, then the power is directly increased to perform dynamic performance recovery, and the inside of the battery stack is purged with atmospheric air until the attenuated voltage value returns to the initial state.

[0061] Furthermore, in some embodiments, after determining whether the battery SOC corresponding to the next moment is less than or equal to a preset threshold value based on the battery SOC within a preset time period, and taking the next moment as the starting moment, and whether there is a preset increasing trend in the battery SOC within the charging time, it also includes: if the battery SOC corresponding to the next moment is greater than the preset threshold value, or the battery SOC within the charging time has a preset increasing trend, then determining whether there is at least one time period that meets the requirements for dynamic performance recovery; if there is at least one time period that meets the requirements for dynamic performance recovery, then performing dynamic performance recovery in each time period.

[0062] The at least one time period satisfying dynamic performance recovery refers to a continuous or discontinuous time interval that can be used to perform a dynamic recovery operation.

[0063] Specifically, when the battery SOC value in the future time period is greater than the battery SOC threshold, or the battery SOC value in the future time period is less than the battery SOC threshold but the battery SOC value in the future time period has an increasing trend, it is continued to be determined whether there is a period or segmented accumulation time period and energy storage space for the battery SOC value in the future time period. If so, the dynamic performance of the battery stack can be directly restored once or in segments or multiple times in the corresponding time period.

[0064] For example, when the battery SOC value in a future time period is higher than the battery SOC threshold Y%, or although the SOC value at the next moment is lower than the battery SOC threshold Y%, but there is an upward trend subsequently, it is determined whether the battery has a period or segmented cumulative time period and energy storage space in the future period T. If so, the dynamic performance of the battery stack can be directly restored once or in segments or multiple times in the corresponding time period. For example: when the battery SOC at the next moment of 5 minutes is 40%, which is greater than the battery SOC threshold of 30%, or the battery SOC at the next moment of 5 minutes is 20%, which is less than the battery SOC threshold of 30%, but the battery SOC has an upward trend in the next 5 minutes, then there can be 1 / 2 (1-30%) of energy storage space in the first half of the next 5 minutes, and there is an uphill section in the middle, which requires the power battery to assist in providing power. After the power battery outputs a certain amount of electricity, 1 / 2 (1-30%) or even more energy storage space is available again, and the dynamic performance of the battery stack can be restored in two times and two sections.

[0065] Furthermore, in some embodiments, after determining whether there is at least one time period that satisfies the dynamic performance recovery, it also includes: if there is no at least one time period that satisfies the dynamic performance recovery, the power of the battery stack is reduced based on a preset power reduction strategy, and the battery stack and power battery after power reduction output power corresponding to the current power demand of the vehicle until the battery SOC corresponding to the next moment is less than or equal to the preset threshold, and after there is no preset increasing trend in the battery SOC within the new charging time, the battery stack is independently powered, and dynamic performance recovery is performed based on the preset high power, and the inside of the battery stack is purged with atmospheric air until the voltage value of the battery stack after attenuation returns to the initial state.

[0066] Specifically, when the battery SOC value in the future time period is higher than the battery SOC threshold Y%, or although the battery SOC value in the future time period is lower than the battery SOC threshold Y% but the battery SOC has an upward trend in the future time period, determine whether the battery has a period or segmented cumulative time period and energy storage space in the future time period. If not, the battery stack power is actively reduced, and the power battery bears part of the power demand until the battery SOC value drops to the battery SOC threshold Y% and there is no upward trend in the battery power in the future time period. Otherwise, continue this step, and finally restore the independent power supply of the battery stack, increase the power to restore dynamic performance.

[0067] Furthermore, in some embodiments, before obtaining the road spectrum data and current SOC of the vehicle, it also includes: determining whether the battery stack meets the preset dynamic performance recovery conditions; if the battery stack meets the preset dynamic performance recovery conditions, determining whether the power battery has a charging fault; if the power battery has a charging fault, distributing the additional power generated when the battery stack performs dynamic performance recovery through at least one load of the vehicle, otherwise, executing the step of obtaining the road spectrum data and current battery SOC of the vehicle.

[0068] Among them, the dynamic performance recovery condition refers to the restriction conditions for executing the dynamic recovery strategy, the charging failure refers to the abnormal state or functional failure of the battery during the charging process, and the current SOC step refers to the judgment of the preset dynamic performance recovery conditions and whether there is a charging failure in the battery.

[0069] For example, when the battery temperature is abnormal or fails, the stack outlet temperature is detected. If it is less than 65°C, the additional power can be used to drive the PTC heater for heating. If the stack outlet temperature is greater than 65°C, the additional power can be used to assist in driving the air compressor. If the air compressor power is too large at this time, the bypass throttle can be opened to bypass the excess air flow.

[0070] Furthermore, in some embodiments, determining whether the fuel cell stack meets preset dynamic performance recovery conditions includes: obtaining a current voltage attenuation value of the fuel cell stack; if the current voltage attenuation value reaches a preset attenuation threshold, determining that the fuel cell stack meets the preset dynamic performance recovery conditions.

[0071] Among them, the current voltage attenuation value of the fuel cell stack refers to the decrease in voltage over time during the operation of the fuel cell stack, and the preset attenuation threshold refers to the minimum limit of the decrease in voltage over time during the operation of the fuel cell stack.

[0072] For example, after the fuel cell stack has been running stably for a long time, the voltage attenuation value is obtained. For example, the preset attenuation threshold is 30mV. When the voltage attenuation value is 10mV, it does not reach the preset attenuation threshold, and the fuel cell stack is judged to not meet the preset dynamic performance recovery conditions; if the current voltage attenuation value is 40mV, which exceeds the preset attenuation threshold, the fuel cell stack is judged to meet the preset dynamic performance recovery conditions.

[0073] In order to enable relevant persons skilled in the art to better understand the method for recovering the dynamic performance of a vehicle battery according to an embodiment of the present invention, it will be explained below in conjunction with specific embodiments.

[0074] Figure 4 This is a flow chart of a dynamic performance recovery strategy for a vehicle battery according to a specific embodiment of the present invention.

[0075] When the system triggers a state recovery condition (such as voltage decay), the power battery state recovery process is initiated. First, it determines whether the power supply can support charging. If not, loads such as air compressors and DC / DC controllers are used to consume power. If supported, the LSTM neural network model is used to predict the power supply SOC state at the next moment. If the SOC is lower than 70% and no platform frame drops occur, recovery is performed based on power. If not, the system further determines whether the rechargeable power within a future period of time T meets the dynamic performance recovery requirements. If so, recovery is performed in multiple stages. If not, the step-down circuit is activated to allow the power battery to supply power until the power level reaches 1% and does not increase within T. The recovery circuit then independently supplies power, and the process ends.

[0076] According to the dynamic performance recovery method of a vehicle battery provided by an embodiment of the present invention, the vehicle's road spectrum data and the current battery state of charge are obtained, and then the road spectrum data is input into a pre-trained LSTM neural network to obtain the battery SOC within a preset time period. Finally, the dynamic performance recovery strategy of the vehicle battery stack is determined based on the current SOC and the predicted battery SOC within the preset time period, and the dynamic performance recovery of the battery stack is performed based on the strategy. This solves the problem in the related art of low battery stack working efficiency and reduced cruising range due to the failure to predict the power battery SOC state and the inability to adapt to changing road conditions, thereby improving the battery stack working efficiency and increasing the battery cruising range.

[0077] Next, a dynamic performance recovery device for a vehicle battery according to an embodiment of the present invention will be described with reference to the accompanying drawings.

[0078] Figure 5 The block diagram is a device for recovering the dynamic performance of a vehicle battery according to an embodiment of the present invention.

[0079] like Figure 5 As shown, the dynamic performance recovery device 10 of a vehicle battery includes: an acquisition module 100 , a prediction module 200 and a control module 300 .

[0080] Among them, the acquisition module 100 is used to obtain the vehicle's road spectrum data and current SOC; the prediction module 200 is used to input the road spectrum data into the pre-trained LSTM neural network to obtain the battery SOC within a preset time period; the control module 300 is used to determine the dynamic performance recovery strategy of the vehicle's battery stack based on the current SOC and the battery SOC within a preset time period, and perform dynamic performance recovery of the battery stack according to the dynamic performance recovery strategy.

[0081] Furthermore, in some embodiments, the control module 300 is specifically used to: determine the charging time required to fully charge the power battery based on the current SOC; determine whether the battery SOC corresponding to the next moment is less than or equal to a preset threshold value based on the battery SOC within a preset time period, and whether there is a preset increasing trend in the battery SOC within the charging time period with the next moment as the starting moment; if the battery SOC corresponding to the next moment is less than or equal to the preset threshold value, and there is no preset increasing trend in the battery SOC within the charging time period, then perform dynamic performance recovery based on the preset pull-up power, and use the atmospheric volume to purge the inside of the battery stack until the voltage value of the battery stack after attenuation returns to the initial state.

[0082] Furthermore, in some embodiments, after determining whether the battery SOC corresponding to the next moment is less than or equal to a preset threshold value based on the battery SOC within a preset time period, and taking the next moment as the starting moment, and determining whether there is a preset rising trend in the battery SOC within the charging time, the control module 300 is further used to: if the battery SOC corresponding to the next moment is greater than the preset threshold value, or there is a preset rising trend in the battery SOC within the charging time, determine whether there is at least one time period that satisfies dynamic performance recovery; if there is at least one time period that satisfies dynamic performance recovery, perform dynamic performance recovery in each time period.

[0083] Furthermore, in some embodiments, after determining whether there is at least one time period that satisfies dynamic performance recovery, the control module 300 is also used to: if there is no at least one time period that satisfies dynamic performance recovery, reduce the power of the battery stack based on a preset power reduction strategy, and the battery stack and power battery after power reduction output power corresponding to the current power demand of the vehicle until the battery SOC corresponding to the next moment is less than or equal to the preset threshold, and after there is no preset rising trend in the battery SOC within the new charging time, the battery stack is independently powered, and dynamic performance recovery is performed based on the preset high power, and the interior of the battery stack is purged with atmospheric air until the voltage value of the battery stack after attenuation returns to the initial state.

[0084] Furthermore, in some embodiments, before obtaining the road spectrum data and current SOC of the vehicle, the acquisition module 100 is also used to: determine whether the battery stack meets the preset dynamic performance recovery conditions; if the battery stack meets the preset dynamic performance recovery conditions, determine whether the power battery has a charging fault; if the power battery has a charging fault, distribute the additional power generated when the battery stack performs dynamic performance recovery through at least one load of the vehicle, otherwise, execute the step of obtaining the road spectrum data and current SOC of the vehicle.

[0085] Furthermore, in some embodiments, the acquisition module 100 is further used to: obtain a current voltage attenuation value of the fuel cell stack; if the current voltage attenuation value reaches a preset attenuation threshold, determine that the fuel cell stack meets a preset dynamic performance recovery condition.

[0086] It should be noted that the above explanation of the embodiment of the method for recovering the dynamic performance of a vehicle battery is also applicable to the device for recovering the dynamic performance of a vehicle battery in this embodiment, and will not be repeated here.

[0087] According to the dynamic performance recovery device of the vehicle battery provided by the embodiment of the present invention, the vehicle's road spectrum data and the current battery state of charge are obtained, and then the road spectrum data is input into a pre-trained LSTM neural network to obtain the battery SOC within a preset time period. Finally, the dynamic performance recovery strategy of the vehicle battery stack is determined according to the current SOC and the predicted battery SOC within the preset time period, and the dynamic performance recovery of the battery stack is performed according to the strategy. This solves the problem in the related art of low battery stack working efficiency and reduced cruising range due to the failure to predict the power battery SOC state and the inability to adapt to changing road conditions, thereby improving the battery stack working efficiency and increasing the battery cruising range.

[0088] Figure 6 This is a schematic diagram of the structure of a vehicle provided according to an embodiment of the present invention. The vehicle may include:

[0089] A memory 601 , a processor 602 , and a computer program stored in the memory 601 and executable on the processor 602 .

[0090] When the processor 602 executes the program, the dynamic performance recovery method of the vehicle battery provided in the above embodiment is implemented.

[0091] Furthermore, the vehicle further comprises:

[0092] The communication interface 603 is used for communication between the memory 601 and the processor 602 .

[0093] The memory 601 is used to store computer programs that can be run on the processor 602 .

[0094] The memory 601 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0095] If the memory 601, processor 602, and communication interface 603 are implemented independently, the communication interface 603, memory 601, and processor 602 can be connected to each other via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0096] Optionally, in a specific implementation, if the memory 601, the processor 602 and the communication interface 603 are integrated on a chip, the memory 601, the processor 602 and the communication interface 603 can communicate with each other through an internal interface.

[0097] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0098] In addition, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-mentioned method for recovering the dynamic performance of a vehicle battery when executed by a processor.

[0099] In addition, an embodiment of the present invention further provides a computer program product, including a computer program, which is executed to implement the above-mentioned method for recovering the dynamic performance of a vehicle battery.

[0100] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction.

[0101] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "N" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0102] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing a custom logical function or step of a process, and the scope of the preferred embodiments of the invention includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of the invention pertain.

[0103] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0104] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

Claims

1. A method for restoring the dynamic performance of a vehicle battery, characterized in that: The following steps are involved: Obtain the vehicle's road data and current SOC; Input the road spectrum data into a pre-trained LSTM neural network to obtain the battery SOC within a preset time period; A dynamic performance recovery strategy for the battery stack of the vehicle is determined based on the current SOC and the battery SOC within the preset time period, and dynamic performance recovery is performed on the battery stack based on the dynamic performance recovery strategy.

2. The method according to claim 1, characterized in that The determining a dynamic performance recovery strategy of the vehicle's battery stack according to the current SOC and the battery SOC within the preset time period, and performing dynamic performance recovery on the battery stack according to the dynamic performance recovery strategy, includes: Determining a charging time required to fully charge the power battery based on the current SOC; Based on the battery SOC within the preset time period, determining whether the battery SOC corresponding to a next moment is less than or equal to a preset threshold, and whether there is a preset increasing trend of the battery SOC within the charging time period, starting from the next moment; If the battery SOC corresponding to the next moment is less than or equal to the preset threshold value, and the battery SOC within the charging time does not have the preset increasing trend, dynamic performance recovery is performed based on the preset pull-up power, and the interior of the battery stack is purged with atmospheric air until the voltage value of the battery stack after attenuation returns to the initial state.

3. The method according to claim 2, characterized in that After determining whether the battery SOC corresponding to a next moment is less than or equal to a preset threshold based on the battery SOC within the preset time period, and whether there is a preset increasing trend of the battery SOC within the charging time period with the next moment as the starting moment, the method further includes: If the battery SOC corresponding to the next moment is greater than the preset threshold, or the battery SOC within the charging time has the preset increasing trend, determining whether there is at least one time period that satisfies dynamic performance recovery; If there is at least one time period that satisfies the dynamic performance recovery requirement, dynamic performance recovery is performed in each time period.

4. The method according to claim 3, characterized in that After determining whether there is at least one time period that satisfies the dynamic performance recovery, the method further includes: If there is no at least one time period that satisfies the dynamic performance recovery, the power of the battery stack is reduced based on the preset power reduction strategy, and the battery stack and the power battery after power reduction output the power corresponding to the current power demand of the vehicle until the battery SOC corresponding to the next moment is less than or equal to the preset threshold, and after the battery SOC within the new charging time does not have the preset increasing trend, the battery stack is independently powered, and dynamic performance recovery is performed based on the preset high power, and the interior of the battery stack is purged with atmospheric air until the voltage value of the battery stack after attenuation returns to the initial state.

5. The method according to claim 1, characterized in that Before obtaining the road spectrum data and current SOC of the vehicle, the following steps are also included: Determining whether the fuel cell stack meets preset dynamic performance recovery conditions; If the battery stack meets the preset dynamic performance recovery condition, determining whether the power battery has a charging fault; If there is a charging fault in the power battery, the additional power generated by the battery stack when recovering dynamic performance is distributed through at least one load of the vehicle; otherwise, the step of obtaining the road spectrum data and current SOC of the vehicle is executed.

6. The method according to claim 5, characterized in that The determining whether the fuel cell stack meets a preset dynamic performance recovery condition includes: Obtaining a current voltage attenuation value of the fuel cell stack; If the current voltage attenuation value reaches a preset attenuation threshold, it is determined that the fuel cell stack meets the preset dynamic performance recovery condition.

7. A dynamic performance recovery device for a vehicle battery, characterized in that: The device comprises: Acquisition module, used to obtain the vehicle's road spectrum data and current SOC; A prediction module, configured to input the road spectrum data into a pre-trained LSTM neural network to obtain the battery SOC within a preset time period; A control module is used to determine a dynamic performance recovery strategy for the vehicle's battery stack based on the current SOC and the battery SOC within the preset time period, and to perform dynamic performance recovery on the battery stack based on the dynamic performance recovery strategy.

8. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for recovering the dynamic performance of a vehicle battery according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the dynamic performance recovery method of a vehicle battery as described in any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for recovering the dynamic performance of a vehicle battery according to any one of claims 1 to 6 is implemented.

Images