Powertrain health management system for new energy vehicles

Abstract

The present invention discloses a powertrain health management and control system for new energy vehicles, which relates to the field of battery health technology. The system includes: an initial state acquisition module, which obtains the initial state parameters of the battery pack and determines the initial health state; a health state prediction module, which collects charge and discharge data for health assessment and generates a baseline health state; a balancing simulation module, which establishes a simulation model based on the balancing strategy and generates balancing data; a health state correction module, which uses the balancing data to evaluate and correct the baseline health state and obtain a corrected state updated in real time; and a health management and control module, which performs management and control based on the corrected health state and generates a health management and control strategy. This achieves the technical effect of improving monitoring reliability, reducing monitoring difficulty and reducing management and control costs.

Description

Technical Field

[0001] The present invention relates to the field of battery health technology, and in particular to a powertrain health management and control system for new energy vehicles. Background Art

[0002] The powertrain of a new energy vehicle is the core component of the vehicle, and its performance and health are crucial to its performance and operational safety. Current powertrain health management systems typically rely on regular maintenance and monitoring of the status of each individual cell in the battery pack. This results in high sensor deployment costs, large amounts of data generated, and difficulty in data processing, increasing maintenance costs and impacting the powertrain's energy density. This leads to technical challenges such as difficulty in monitoring, low reliability, and high management and control costs. Summary of the Invention

[0003] The present invention provides a powertrain health management and control system for new energy vehicles to solve the technical problems of high monitoring difficulty, low reliability and high management and control costs in the existing technology, and achieve the technical effects of improving monitoring reliability, reducing monitoring difficulty and management and control costs.

[0004] The powertrain health management and control system for new energy vehicles provided by the present invention includes:

[0005] An initial state acquisition module is used to obtain initial state parameters of a target battery pack and determine an initial health state of the battery pack, wherein the target battery pack includes a plurality of battery cells.

[0006] A health status prediction module is used to collect charge and discharge data of the battery pack, perform health status assessment in combination with the initial health status, and generate a baseline health status.

[0007] A balancing simulation module is used to establish a balancing simulation model based on the charge and discharge balancing strategy of the target battery pack in combination with the initial health state, and to perform balancing simulation based on the balancing simulation model to generate simulated balancing data.

[0008] A health status correction module is used to evaluate and correct the reference health status using the simulation equalization data to obtain a corrected health status, wherein the corrected health status is updated in real time.

[0009] A health management and control module is used to perform health management and control of the target battery pack based on the corrected health status and generate a corresponding health management and control strategy.

[0010] In a feasible implementation, the initial state parameters of the target battery pack are obtained and the initial health state of the battery pack is determined. The execution steps include:

[0011] The interactive battery management component extracts the initial state parameters of multiple battery cells in the target battery pack, wherein the initial state parameters include at least capacity and internal resistance.

[0012] According to the initial state parameters, the initial cell health states of the plurality of cells are traversed and calculated, wherein the initial cell health states include absolute cell states and relative cell states.

[0013] Outputting the plurality of initial battery cell health states as the initial health states.

[0014] In a feasible implementation, before collecting the charge and discharge data of the battery pack and performing a health status assessment based on the initial health status to generate a baseline health status, the following steps are performed:

[0015] Obtain sample aging data of the cells in the target battery pack.

[0016] The sample aging data is parsed to extract a sample temperature sequence, a sample energy flow sequence, and a sample health state sequence, wherein the sequence interval of the sample health state sequence is greater than the sequence interval of the extracted sample temperature sequence and the sample energy flow sequence.

[0017] Taking the sample health state sequence as a division target, the sample temperature sequence and the sample energy flow sequence are synchronously divided, and the sample health state sequence is associated with the synchronous division result to obtain a plurality of standard sample data groups.

[0018] A health status prediction model is constructed and trained using the plurality of standard sample data groups as training data.

[0019] In a feasible implementation, the charging and discharging data of the battery pack is collected, and the health status is evaluated in combination with the initial health status to generate a baseline health status. The execution steps include:

[0020] The charge and discharge data are interactively acquired, where the charge and discharge data include a historical temperature sequence and a historical energy flow sequence.

[0021] Based on the elbow method, the discrete degree of the temperature data in the historical temperature sequence is analyzed to determine the number of clusters, and the charge and discharge data are clustered according to the number of clusters to obtain multiple environmental charge and discharge data groups.

[0022] A plurality of the environmental charge and discharge data groups are respectively input into the health state prediction model to obtain a plurality of discrete prediction results, and the plurality of discrete prediction results are fitted to the initial health state to obtain the baseline health state.

[0023] In a feasible implementation, according to the charge and discharge balancing strategy of the target battery pack, a balancing simulation model is established in combination with the initial health state, and a balancing simulation is performed based on the balancing simulation model to generate simulated balancing data. The execution steps include:

[0024] An equivalent health state is defined by combining the initial health state and the reference health state, wherein the equivalent health state is between the initial health state and the reference health state.

[0025] A target battery pack digital model is constructed, and according to the charge and discharge balancing strategy, the target battery pack digital model is initialized to obtain the balancing simulation model.

[0026] The charge and discharge data are input into the balancing simulation model to perform balancing simulation of the target battery pack, and the balancing data is synchronously recorded and output as the simulated balancing data, wherein the simulated balancing data includes a balancing temperature sequence and a balancing energy flow sequence.

[0027] In a feasible implementation, the simulated equalization data is used to evaluate and correct the baseline health state to obtain a corrected health state, and the execution steps include:

[0028] The simulated equilibrium data is input into the health status prediction model to obtain an equilibrium prediction result.

[0029] The balanced prediction result is fitted to the reference state of health to obtain the revised state of health, wherein the revised state of health includes the health states of multiple cells in the target battery pack.

[0030] In one feasible implementation, health management of the target battery pack is performed based on the corrected health status, and a corresponding health management strategy is generated, including:

[0031] The remaining useful life is calculated, wherein the remaining useful life is the difference between a preset life control limit and the modified health state.

[0032] A health control determination is performed based on the remaining service life, and a health control solution library is called to generate the health control strategy, wherein the health control determination includes consistency evaluation and control direction determination.

[0033] In a feasible implementation, the sample aging data includes intrinsic aging data and homologous aging data, wherein the homologous aging data is aging data of cells of the same type as the target battery pack cells.

[0034] The present invention discloses a powertrain health management and control system for new energy vehicles, which solves the technical problems of high monitoring difficulty, low reliability and high management and control costs, and achieves the technical effects of improving monitoring reliability, reducing monitoring difficulty and management and control costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a schematic structural diagram of the powertrain health management and control system for new energy vehicles of the present invention;

[0036] Figure 2 The figure is a flow chart of health status assessment in the powertrain health management and control system of a new energy vehicle according to the present invention.

[0037] Description of the accompanying symbols: initial state acquisition module 11, health state prediction module 12, balance simulation module 13, health state correction module 14, health management and control module 15. DETAILED DESCRIPTION

[0038] The technical solutions provided in the embodiments of the present invention are designed to solve the technical problems of the existing technologies, such as high monitoring difficulty, low reliability, and high management and control costs. The overall approach adopted is as follows:

[0039] First, the initial state acquisition module obtains the initial state parameters of the target battery pack and determines the initial health state of the battery pack, where the target battery pack includes multiple cells. Next, the health state prediction module collects the battery pack's charge and discharge data, performs a health state assessment based on the initial health state, and generates a baseline health state. Next, the balancing simulation module establishes a balancing simulation model based on the target battery pack's charge and discharge balancing strategy and the initial health state, and performs a balancing simulation based on this balancing simulation model to generate simulated balancing data. Next, the health state correction module uses the simulated balancing data to assess and correct the baseline health state, obtaining a corrected health state that is updated in real time. Furthermore, the health management module performs health management on the target battery pack based on the corrected health state and generates a corresponding health management strategy. Finally, this health management strategy enables full lifecycle health management of the battery pack.

[0040] The above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods of the specification to better understand the above technical solution. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments used only to explain the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In addition, it should be noted that, for the convenience of description, only the parts related to the present invention, rather than all, are shown in the drawings.

[0041] Example 1

[0042] Figure 1 The figure is a flow chart of the powertrain health management system for a new energy vehicle according to the present invention, wherein the system includes:

[0043] The initial state acquisition module 11 is used to obtain initial state parameters of a target battery pack and determine the initial health state of the battery pack, wherein the target battery pack includes a plurality of battery cells.

[0044] Specifically, the target battery pack is the system being monitored within the powertrain of a new energy vehicle. It consists of multiple individual cells, typically connected in series or parallel, that collectively provide the required power output. Therefore, the performance and health of individual cells directly impact the overall performance of the battery pack.

[0045] Specifically, the initial state parameters refer to the cell state parameters of the target battery pack that are detected and recorded during the initial assembly or charging and discharging of the battery pack. By obtaining these parameters, the system can evaluate the operating status of the battery pack to obtain the health level of the battery cell in the initial state, which is the basic data of the battery cell performance.

[0046] In some embodiments, the initial state parameters of the target battery pack are obtained and the initial health state of the battery pack is determined. The execution steps of the initial state acquisition module 11 include:

[0047] The interactive battery management component extracts the initial state parameters of multiple battery cells in the target battery pack, wherein the initial state parameters include at least capacity and internal resistance.

[0048] According to the initial state parameters, the initial cell health states of the plurality of cells are traversed and calculated, wherein the initial cell health states include absolute cell states and relative cell states.

[0049] Outputting the plurality of initial battery cell health states as the initial health states.

[0050] Specifically, the system interacts with the battery management system (BMS) to obtain the initial state parameters of each cell in the target battery pack. These initial state parameters are the state parameters of the cells during battery pack packaging or manufacturing, and reflect the basic performance indicators of each cell in the battery pack. In other words, the initial state parameters are the physical parameters of multiple cells in the target battery pack.

[0051] Specifically, the extracted initial state parameters are used to calculate the health status of multiple cells in the target battery pack one by one. The health status of each cell is assessed in two ways: absolute cell status and relative cell status, respectively evaluating the cell's initial state and relative performance to a standard. The absolute cell status refers to the actual performance data of the cell. For example, the capacity of a cell (e.g., an actual capacity of 10Ah) is its absolute cell status, reflecting the cell's direct performance. Preferably, the cell capacity or internal resistance is used as the absolute cell status to determine the cell's absolute health status.

[0052] Specifically, relative cell health refers to the absolute cell health of a cell relative to its rated state. For example, the percentage of a cell's capacity achieved relative to its rated capacity is the relative health of the cell. If the actual capacity of a cell is 10Ah (absolute cell health) and the rated capacity of the cell model is 9Ah, the relative cell health of the cell is 111%.

[0053] For example, in addition to capacity, the relative change in internal resistance is also an important indicator for evaluating the health of a battery cell. Therefore, the initial internal resistance of a battery cell can be compared with a standard value to determine the relative health of the battery cell.

[0054] Specifically, a traversal calculation is performed on each battery cell to determine its absolute and relative health status. After completing the traversal calculation for multiple cells, the system aggregates the health status results for each cell to generate the initial health status of the target battery pack. This initial health status reflects the health and performance level of the battery pack at the time of manufacture, that is, the health status of the battery pack before use, and serves as a key reference for subsequent use.

[0055] The health state prediction module 12 is used to collect the charge and discharge data of the battery pack, perform health state assessment based on the initial health state, and generate a baseline health state.

[0056] Specifically, the charge and discharge data of the battery pack is obtained. The charge and discharge data includes all charge and discharge parameters of the target battery pack during use, such as current, voltage, temperature and corresponding timestamps, reflecting the energy flow and load conditions of the target battery pack during use.

[0057] Specifically, the initial health state is combined with charge and discharge data, and the health state of the target battery pack after the charge and discharge data is predicted based on energy flow, load level, and environmental conditions. This is used as the baseline health state. Compared to collecting the status parameters of each battery cell, this step omits the process of collecting data from a large number of battery cells and analyzing and processing the acquired data, helping to reduce the computational and sensing costs required to obtain the target battery pack's health state.

[0058] In some embodiments, before collecting the charge and discharge data of the battery pack and performing a health status assessment based on the initial health status to generate a baseline health status, the system may execute the following steps:

[0059] Obtain sample aging data of the cells in the target battery pack.

[0060] The sample aging data is parsed to extract a sample temperature sequence, a sample energy flow sequence, and a sample health state sequence, wherein the sequence interval of the sample health state sequence is greater than the sequence interval of the extracted sample temperature sequence and the sample energy flow sequence.

[0061] Taking the sample health state sequence as a division target, the sample temperature sequence and the sample energy flow sequence are synchronously divided, and the sample health state sequence is associated with the synchronous division result to obtain a plurality of standard sample data groups.

[0062] A health status prediction model is constructed and trained using the plurality of standard sample data groups as training data.

[0063] Specifically, sample aging data is historical data on battery cell degradation characteristics, including records from experimental testing or long-term operation. By analyzing and learning the sample aging data of the battery cells in the target battery pack, we can understand the mapping between the battery's operating status and the cell's aging process.

[0064] Specifically, sample aging data includes the following core parameters: Temperature, which reflects the temperature changes of the battery cell under different operating environments. Temperature has a significant impact on battery cell aging, and high temperatures accelerate aging. Energy flow: The energy flow of the battery cell refers to the changes in electrical energy during the charge and discharge process, including charging energy and discharging energy. This data can reflect the load level of the battery cell during cyclic use. Health status, which reflects the degree of battery cell aging over cycles, such as battery cell capacity and internal resistance.

[0065] Specifically, after obtaining the sample aging data, the time series of various key indicators, including temperature, energy flow and health status, are parsed and extracted for subsequent model training. Among them, the temperature series is the temperature change data of the battery cell in different time periods, which is arranged in chronological order according to the temperature values ​​in the aging data. The temperature series is used to introduce the contribution of the temperature environment to the performance degradation of the battery cell. The energy flow series is the energy change during the charging and discharging process of the battery cell, reflecting the charging and discharging rate, voltage, and current of the battery cell in each cycle, and represents the load level of the battery cell during the charging and discharging process (such as the charge and discharge rate). Charging and discharging under high load will accelerate the decline in the health of the battery cell. The sample health status sequence is the change in the health status of the battery cell during the aging process, and is expressed as the ratio of the actual capacity of the battery cell to the rated capacity.

[0066] Optionally, the data interval of the sample health status sequence is larger than that of the temperature sequence and the energy flow sequence, because the health status of the battery cell usually changes over a longer time period, while the temperature and energy flow data change more frequently. At the same time, the measurement of the actual capacity of the battery cell is more complicated and is not suitable for a higher data collection frequency.

[0067] Specifically, using the time point of each data point in the sample health status sequence as a landmark, the sample temperature sequence and sample energy flow sequence are synchronously divided within the corresponding time period, and the synchronous division results are aligned with the sample health status sequence to form a standardized data set. This standardized data set includes multiple data groups, each of which corresponds to a measurable and perceptible change in the health status of the battery cell. In other words, each standard sample data group contains the temperature, energy flow characteristics, and health status of the battery cell within a specific time period.

[0068] The above division process helps to divide complex and continuous sample data into multiple relatively simple and small data groups, which are convenient for subsequent training.

[0069] Furthermore, a health status prediction model is constructed and trained based on a standard sample data set. This model is used to predict the future health status of the battery pack. Specifically, it uses data such as temperature and energy flow during battery use to predict the health status of the battery pack at a later point in time. The model's input features include a sequence of sample temperatures and a sequence of sample energy flows, and its target output is a sequence of sample health status. By learning the implicit mapping relationships in the standard sample data set, the model gradually grasps the cell aging pattern.

[0070] For example, the health status prediction model can adopt a variety of machine learning or deep learning algorithms, such as random forest, support vector machine (SVM), neural network (such as LSTM or RNN), etc. The specific choice depends on the scale and complexity of the dataset.

[0071] In some implementations, the sample aging data includes intrinsic aging data and homologous aging data, wherein the homologous aging data is aging data of cells of the same type as the target battery pack cells.

[0072] Specifically, intrinsic aging data is the aging data accumulated by the internal cells themselves in the long-term charge and discharge cycles in the target battery pack scenario. During use, each cell will gradually age with the increase of usage time. The intrinsic aging data reflects the process of capacity attenuation and internal resistance increase of multiple cells belonging to different battery packs in the same target battery pack model.

[0073] Specifically, homologous aging data is derived from aging data on other battery cells of the same model or series as the target battery pack. This data can be used to expand the volume and richness of the sample aging data obtained, thereby helping to infer the aging patterns of the target battery cells under similar conditions. This data can be used to supplement the aging cycle of certain battery packs, ensuring the complete coverage and accuracy of the generated health status prediction model for the battery cell operating conditions.

[0074] In some embodiments, as Figure 2 As shown, the charge and discharge data of the battery pack is collected, and the health status is evaluated in combination with the initial health status to generate a baseline health status. The execution steps include:

[0075] The charge and discharge data are interactively acquired, where the charge and discharge data include a historical temperature sequence and a historical energy flow sequence.

[0076] Based on the elbow method, the discrete degree of the temperature data in the historical temperature sequence is analyzed to determine the number of clusters, and the charge and discharge data are clustered according to the number of clusters to obtain multiple environmental charge and discharge data groups.

[0077] A plurality of the environmental charge and discharge data groups are respectively input into the health state prediction model to obtain a plurality of discrete prediction results, and the plurality of discrete prediction results are fitted to the initial health state to obtain the baseline health state.

[0078] Specifically, the system first interacts with a battery management system (BMS) or other data acquisition equipment to obtain historical charge and discharge data for the target battery pack. This data includes key parameters such as temperature and energy flow recorded during multiple charge and discharge processes since the battery pack was put into use.

[0079] Specifically, the elbow method is used to analyze the degree of discreteness of the temperature data in the historical temperature series, determine the appropriate number of clusters, and cluster the charge and discharge data, thereby structuring the acquired historical charge and discharge data and reducing the complexity of the data. For example, the sum of squared errors (SSE) of clusters under different numbers of clusters is calculated and a curve is drawn. As the number of clusters increases, the sum of squared errors (SSE) of clusters will gradually decrease. When the number of clusters increases to a certain critical point, the rate of decline of SSE slows down significantly. Reflected on the curve, the turning point where the curve gradually flattens is the elbow, which corresponds to the optimal number of clusters.

[0080] Furthermore, the charge and discharge data are clustered according to the determined number of clusters. By grouping the charge and discharge data according to different operating conditions, multiple groups of environmental charge and discharge data with similar environmental conditions can be obtained, which facilitates improving the continuity of mapping relationship calls in subsequent predictions.

[0081] Specifically, after obtaining multiple environmental charge and discharge data sets, these data sets are input into the health status prediction model to predict the impact of each environmental charge and discharge data set on the health status of the battery cell, and the output is a discrete prediction result. In other words, the discrete prediction result can be understood as the impact of multiple charge and discharge conditions on the health status of the battery cell (such as a 1% drop in SOH).

[0082] Optionally, each set of environmental charge and discharge data corresponds to calling a different prediction layer or prediction channel in the health status prediction model. Different prediction layers or prediction channels are obtained after specialized and enhanced training for different environments and working conditions, which helps to improve the prediction accuracy under different environments and working conditions.

[0083] After obtaining multiple discrete prediction results, these results are then fitted with the battery pack's initial health state. For example, the vector sum of the initial health state and the multiple discrete prediction results is calculated to generate the battery pack's baseline health state. The baseline health state is a comprehensive prediction result based on multiple different environmental and load conditions, reflecting the battery pack's health level during its current life cycle.

[0084] The balancing simulation module 13 is used to establish a balancing simulation model based on the charge and discharge balancing strategy of the target battery pack in combination with the initial health state, and perform balancing simulation based on the balancing simulation model to generate simulated balancing data.

[0085] Specifically, the balancing strategy is used to ensure that each battery cell maintains consistent voltage and capacity during the charging and discharging process, avoiding rapid degradation of the battery cell or inconsistent capacity. The balancing strategy can be active balancing or passive balancing, both of which involve charging and discharging the battery cells in the battery pack, and therefore also affect the health of the battery cells.

[0086] In some embodiments, according to the charge and discharge balancing strategy of the target battery pack, a balancing simulation model is established in combination with the initial health state, and a balancing simulation is performed based on the balancing simulation model to generate simulated balancing data. The execution steps include:

[0087] An equivalent health state is defined by combining the initial health state and the reference health state, wherein the equivalent health state is between the initial health state and the reference health state.

[0088] A target battery pack digital model is constructed, and according to the charge and discharge balancing strategy, the target battery pack digital model is initialized to obtain the balancing simulation model.

[0089] The charge and discharge data are input into the balancing simulation model to perform balancing simulation of the target battery pack, and the balancing data is synchronously recorded and output as the simulated balancing data, wherein the simulated balancing data includes a balancing temperature sequence and a balancing energy flow sequence.

[0090] Specifically, in actual use, the health status of a battery pack changes dynamically. Therefore, an equivalent health status (e.g., a weighted average of the initial and baseline health statuses) is defined as a state between the initial and baseline health statuses. This equivalent health status reflects the dynamic equilibrium health of the battery pack during the simulation, thereby improving the accuracy of the equilibrium simulation. Optionally, the equivalent health status can be defined based on the degree of dispersion of historical charge and discharge data (e.g., entropy or variance of the data).

[0091] Specifically, a digital model of the target battery pack is constructed based on the physical characteristics of the battery pack and the charge and discharge balancing strategy. This model can accurately simulate the behavior of the battery pack under different charge and discharge conditions, and serves as the basis for the balancing simulation model. For example, first, physical characteristic modeling is performed to reflect the actual physical structure of the battery pack, including the arrangement of multiple battery cells, the capacity of each battery cell, internal resistance and other key parameters. Then, the balancing working mode of the battery pack is set according to the predetermined balancing strategy, such as the balancing rate, balancing current, etc., to achieve initialization. The generated simulation model reflecting the overall balancing state of the battery pack is used to simulate the balancing process under different charge and discharge conditions, so as to determine the battery cell cycling caused by balancing.

[0092] Furthermore, the charge and discharge data is fed into a balancing simulation model to simulate the balancing of the target battery pack. During the simulation, simulated balancing data is simultaneously recorded and output, including the balancing temperature series and the balancing energy flow series. In other words, the simulated balancing data reflects the cell cycling caused by balancing, such as the actual number of charge and discharge cycles per cell in the battery pack during the balancing process. This simulated balancing data is used to analyze the cycling of different cells and evaluate the impact of balancing strategies on cell lifespan.

[0093] The health status correction module 14 is used to evaluate and correct the reference health status using the simulation equalization data to obtain a corrected health status, wherein the corrected health status is updated in real time.

[0094] Specifically, because some cells may experience faster capacity decay or increased internal resistance due to frequent balancing during the balancing process, it is necessary to revise the baseline health status based on the balancing prediction results to obtain a more realistic battery pack health status. The revised health status takes into account the losses caused by balancing operations between cells, resulting in a more accurate battery pack health status.

[0095] In some embodiments, the simulated equalization data is used to evaluate and correct the baseline health state to obtain a corrected health state, and the execution steps include:

[0096] The simulated equilibrium data is input into the health status prediction model to obtain an equilibrium prediction result.

[0097] The balanced prediction result is fitted to the reference state of health to obtain the revised state of health, wherein the revised state of health includes the health states of multiple cells in the target battery pack.

[0098] Specifically, the simulated balancing data is first fed into a trained health state prediction model to capture changes in the battery pack's health state due to factors such as energy transfer and temperature changes during balancing, outputting the balancing prediction result. Then, based on the same principles and steps as previously described, the balancing prediction result is fitted to the previous baseline health state. By accounting for losses caused by the balancing operation, the overall health state of the battery pack is corrected to generate a revised health state. This revised health state more accurately reflects the current usage of the battery pack, especially after multiple balancing operations.

[0099] The health management and control module 15 is used to perform health management and control of the target battery pack based on the corrected health status and generate a corresponding health management and control strategy.

[0100] In some embodiments, health management of the target battery pack is performed based on the modified health status, and a corresponding health management strategy is generated, including:

[0101] The remaining useful life is calculated, wherein the remaining useful life is the difference between a preset life control limit and the modified health state.

[0102] A health control determination is performed based on the remaining service life, and a health control solution library is called to generate the health control strategy, wherein the health control determination includes consistency evaluation and control direction determination.

[0103] Specifically, the remaining useful life (RUS) of the battery pack is first calculated based on its corrected state of health. This RUS refers to the distance from the preset end of life (life control limit) of the battery pack under its current corrected state of health. It is used to predict how long the battery pack can still be used normally. For example, the current corrected state of health of the battery pack is compared with the preset life control limit to calculate the difference in RUS. For example, if the life control limit is 80% of the rated capacity and the current corrected state of health is 85% of the rated capacity, the RUS is 5%.

[0104] Specifically, health control judgment refers to evaluating whether control measures are needed for the battery pack based on the remaining service life, including consistency evaluation and control direction judgment. Among them, consistency evaluation refers to the system's evaluation of whether the health status of each battery cell in the battery pack remains consistent. If the capacity, internal resistance and other parameters of each battery cell vary too much, it may be necessary to adjust the balancing strategy or limit the charge and discharge rate. Control direction judgment refers to judging whether to take measures to extend the life or to optimize the performance based on the overall health status of the battery pack. For example, when the battery pack is close to exhaustion, the system will tend to reduce losses, and when the battery pack is in good condition, the system can allow higher performance output.

[0105] Specifically, the health management solution library contains a variety of management and control measures for different health states of battery packs. Based on the management and control judgment results, the system selects appropriate strategies from the solution library and implements them. For example, health management strategies include limiting the charge and discharge rate (limiting the rate of charging or discharging, reducing the pressure on the battery cell, and delaying its capacity decay), adjusting the temperature control domain (adjusting the cooling system or limiting high-load operations to ensure that the battery pack operates within a suitable temperature range, thereby extending its service life), and prompting battery life (sending prompts to users, suggesting replacing the battery pack or taking maintenance measures). The health management strategy generated based on the correction of health status and health management judgment helps to extend the service life and safety of the battery pack.

[0106] In summary, the powertrain health management and control system for new energy vehicles provided by the present invention has the following technical effects:

[0107] The initial state acquisition module obtains the initial state parameters of the target battery pack and determines its initial health status. The target battery pack contains multiple cells. The health state prediction module collects the charge and discharge data of the battery pack, evaluates it in combination with the initial health status, and generates a baseline health status. The balancing simulation module establishes a balancing simulation model based on the battery pack's charge and discharge balancing strategy and the initial health status, and simulates it using this model to generate simulated balancing data. The health state correction module evaluates and corrects the baseline health status based on the simulated balancing data, and updates the corrected health status of the battery pack in real time. The health management and control module manages the health of the target battery pack based on the corrected health status and generates a corresponding health management and control strategy. This achieves the technical effect of improving monitoring reliability and reducing monitoring difficulty and management costs.

[0108] It should be understood that the embodiments disclosed in the present invention and the above description can enable those skilled in the art to use the present invention to implement the present invention. At the same time, the present invention is not limited to the embodiments mentioned above. It should be understood that those skilled in the art can still modify the technical solutions described in the above embodiments or replace some of the technical features therein with equivalents; and such modifications or replacements do not deviate from the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention and are all included in the scope of protection of the present invention.

Claims

1. A powertrain health management and control system for new energy vehicles, characterized in that: The system comprises: An initial state acquisition module, configured to acquire initial state parameters of a target battery pack and determine an initial health state of the battery pack, wherein the target battery pack includes a plurality of battery cells; A health status prediction module, configured to collect charge and discharge data of the battery pack, perform a health status assessment based on the initial health status, and generate a baseline health status; A balancing simulation module, the balancing simulation module is used to establish a balancing simulation model based on the charge and discharge balancing strategy of the target battery pack in combination with the initial health state, and perform balancing simulation based on the balancing simulation model to generate simulated balancing data; a health status correction module, configured to evaluate and correct the baseline health status using the simulated equalization data to obtain a corrected health status, wherein the corrected health status is updated in real time; A health management and control module, configured to perform health management and control of the target battery pack based on the corrected health status and generate a corresponding health management and control strategy; Collecting the charge and discharge data of the battery pack, performing a health status assessment based on the initial health status, and generating a baseline health status, before executing the steps include: Obtain sample aging data of the cells in the target battery pack; Parsing the sample aging data to extract a sample temperature sequence, a sample energy flow sequence, and a sample health state sequence, wherein a sequence interval of the sample health state sequence is greater than a sequence interval of the extracted sample temperature sequence and the sample energy flow sequence; Taking the sample health state sequence as a division target, synchronously dividing the sample temperature sequence and the sample energy flow sequence, and associating the sample health state sequence with the synchronous division result to obtain a plurality of standard sample data groups; Using the plurality of standard sample data groups as training data, constructing and training a health status prediction model; Collecting the charge and discharge data of the battery pack, performing a health status assessment based on the initial health status, and generating a baseline health status, the execution steps include: interactively acquiring the charge and discharge data, wherein the charge and discharge data includes a historical temperature sequence and a historical energy flow sequence; Based on the elbow method, the degree of dispersion of the temperature data in the historical temperature series is analyzed to determine the number of clusters, and the charge and discharge data are clustered according to the number of clusters to obtain multiple environmental charge and discharge data groups; A plurality of the environmental charge and discharge data groups are respectively input into the health state prediction model to obtain a plurality of discrete prediction results, and the plurality of discrete prediction results are fitted to the initial health state to obtain the baseline health state.

2. The system according to claim 1, wherein Obtain the initial state parameters of the target battery pack and determine the initial health state of the battery pack. The execution steps include: An interactive battery management component extracts the initial state parameters of multiple cells in a target battery pack, wherein the initial state parameters include at least capacity and internal resistance; According to the initial state parameters, traversing and calculating the initial cell health states of the plurality of cells, wherein the initial cell health states include absolute cell states and relative cell states; Outputting the plurality of initial battery cell health states as the initial health states.

3. The system according to claim 1, wherein: According to the charge and discharge balancing strategy of the target battery pack, a balancing simulation model is established in combination with the initial health state, and a balancing simulation is performed based on the balancing simulation model to generate simulation balancing data. The execution steps include: Defining an equivalent health state by combining the initial health state and the reference health state, wherein the equivalent health state is between the initial health state and the reference health state; Constructing a target battery pack digital model, and initializing the target battery pack digital model according to the charge and discharge balancing strategy, and obtaining the balancing simulation model; The charge and discharge data are input into the balancing simulation model to perform balancing simulation of the target battery pack, and the balancing data is synchronously recorded and output as the simulated balancing data, wherein the simulated balancing data includes a balancing temperature sequence and a balancing energy flow sequence.

4. The system according to claim 3, wherein: The benchmark health state is evaluated and corrected using the simulated equalization data to obtain a corrected health state, and the execution steps include: Inputting the simulated equilibrium data into the health status prediction model to obtain an equilibrium prediction result; The balanced prediction result is fitted to the reference state of health to obtain the revised state of health, wherein the revised state of health includes the health states of multiple cells in the target battery pack.

5. The system according to claim 1, wherein: Perform health control on the target battery pack based on the corrected health status and generate corresponding health control strategies, including: Calculating a remaining useful life, wherein the remaining useful life is the difference between a preset life control limit and the modified health state; A health control determination is performed based on the remaining service life, and a health control solution library is called to generate the health control strategy, wherein the health control determination includes consistency evaluation and control direction determination.

6. The system of claim 1, wherein the sample aging data comprises intrinsic aging data and homologous aging data, wherein: The homologous aging data is aging data of the same type of cells as the target battery pack cells.

Images