A method and system for testing the battery pack's range performance

Abstract

This invention discloses a method and system for testing the range performance of a battery pack, relating to the field of battery testing technology. The method includes: generating a dynamic test condition sequence based on real-world operating data from a target application scenario; applying the dynamic test condition sequence to the battery pack under test and capturing communication messages sent by the battery management system in real time using a message monitoring device; identifying the battery management system strategy by real-time parsing of the communication messages and performing forward-looking compensation on the dynamic test condition sequence based on the identification results; identifying compressible test windows and executing an intelligent energy consumption compression algorithm on the compressible test windows to shorten the test cycle; synchronously recording test data during the test process and generating a comprehensive range performance evaluation report coupled with the influence of the battery management system strategy. This invention effectively solves the problem of the disconnect between traditional standard operating conditions and actual conditions, shortens the test cycle, reduces costs, and provides precise support for product optimization.

Description

Technical Field

[0001] This invention relates to the field of battery testing technology, and in particular to a method and system for testing the range performance of a battery pack. Background Technology

[0002] With the rapid development of electric vehicles (including two-wheeled and three-wheeled electric vehicles) and energy storage systems, the performance of the power battery, as its core component, directly determines the vehicle's driving range and user experience. The battery pack, as the final product that combines multiple battery cells through series and parallel connections and integrates a battery management system (BMS), thermal management system, and structural components, has its overall driving range performance as a key indicator for evaluating the quality of the battery system. Therefore, accurate and reliable driving range performance testing of the battery pack is crucial in the R&D, production, and quality control stages.

[0003] Currently, the industry's testing methods for battery pack range performance typically rely on placing the battery pack in a laboratory environment on a high-precision charge and discharge testing device, and conducting cyclic tests according to preset charge and discharge rates or standard operating conditions (such as NEDC, WLTC, etc.) until the set termination voltage or cutoff condition is reached, thereby calculating the total capacity or energy released and evaluating the range capability.

[0004] However, existing testing methods have the following significant pain points and bottlenecks:

[0005] The testing conditions are severely out of sync with real-world scenarios, resulting in low data reliability. Most existing tests employ constant current discharge or simplified standard driving conditions. These conditions cannot accurately simulate the complex and dynamic load changes vehicles face in actual operation, such as rapid acceleration, rapid deceleration, hill climbing, air conditioning use under different temperature conditions, and the power consumption of onboard electronic devices. This leads to a significant discrepancy between the driving range obtained from laboratory tests and the actual user experience (i.e., "exaggerated range claims"), failing to provide reliable data support for product design and marketing claims.

[0006] The coupling effects of Battery Management System (BMS) strategies are not adequately considered. The driving range of a battery pack is not simply the sum of the cell performances, but rather deeply depends on the BMS's control strategies, such as the accuracy of SOC (State of Charge) estimation, balancing strategies, and the start-stop logic and power consumption of the thermal management system. Existing testing methods often treat the BMS as a black box or focus only on its basic functions, ignoring the significant impact of the BMS's dynamic adjustments under complex operating conditions (such as power limiting, energy recovery efficiency, and heating power consumption at low temperatures) on the final driving range. This results in test results that fail to accurately reflect the overall performance bottlenecks when the BMS and cells work together.

[0007] The long testing cycles and low efficiency of traditional testing methods make it difficult to meet the demands of rapid iteration. A complete battery pack endurance test typically takes tens of hours, or even several days, to complete. Given the rapid iteration of battery technology and the ever-shortening product development cycles, such lengthy testing times severely hinder R&D and verification progress, becoming a bottleneck to product launch. Furthermore, prolonged testing consumes significant amounts of energy, increasing testing costs.

[0008] There is a lack of dynamic analysis capabilities regarding performance degradation paths. Existing testing methods primarily focus on "endpoint" performance (i.e., total driving range or capacity), neglecting the dynamic evolution of the battery pack's internal state (such as cell voltage, temperature distribution, and internal resistance changes) during testing. This "black box" testing cannot reveal the specific causes of range degradation, such as premature failure of a particular cell, thermal runaway risk due to uneven temperature, or insufficient BMS balancing capabilities. This makes it difficult for R&D personnel to optimize pack design in a targeted manner, and problem localization becomes challenging.

[0009] Therefore, there is an urgent need in the field for a battery pack performance testing method that can simulate real complex working conditions, fully consider the BMS coupling effect, be efficient and fast, and be able to deeply diagnose the root causes of performance degradation, so as to overcome the above-mentioned defects of the prior art. Summary of the Invention

[0010] This invention provides a method for testing the battery pack's range performance, comprising:

[0011] Step 1: Generate a dynamic test condition sequence based on real-world operational data from the target application scenario;

[0012] Step 2: Apply the dynamic test condition sequence to the battery pack under test, and use the message monitoring device to capture the communication messages sent by the battery management system in real time.

[0013] Step 3: Identify the battery management system strategy by parsing the communication messages in real time, and perform forward compensation on the dynamic test condition sequence based on the identification results;

[0014] Step 4: Identify compressible test windows and execute an intelligent energy-saving compression algorithm on the compressible test windows to shorten the test cycle;

[0015] Step 5: Synchronously record the test data during the test process and generate a comprehensive evaluation report on the range performance affected by the coupled battery management system strategy.

[0016] The battery pack range performance testing method described above, which generates a dynamic test condition sequence based on real-world operating data from the target application scenario, consists of the following sub-steps:

[0017] Collect long-term operational data using vehicle-mounted terminals;

[0018] The collected actual operating data is processed into a demand power time series;

[0019] The demand power time series is segmented and clustered to construct a library of typical operating condition segments;

[0020] Dynamic test condition sequences are synthesized from a library of typical operating condition segments based on a Markov chain model.

[0021] The battery pack range performance testing method described above, which identifies the battery management system strategy by real-time parsing of the communication messages and performs look-ahead compensation on the dynamic test condition sequence based on the identification results, specifically includes the following sub-steps:

[0022] At each sampling time t, a feature vector representing the internal state of the battery pack is extracted from the real-time collected battery pack data.

[0023] The extracted feature vectors are input into the battery management system policy identifier, which outputs the predicted probability of the battery management system imposing constraints.

[0024] Based on the predicted probability of the battery management system imposing restrictions, the planned power in the dynamic test condition sequence is compensated in advance.

[0025] The system analyzes the monitored battery management system communication messages in real time and optimizes the battery management system policy identifier online based on the analysis results.

[0026] The battery pack endurance performance testing method described above, which identifies compressible test windows and executes an intelligent energy consumption compression algorithm on the compressible test windows, specifically includes the following sub-steps:

[0027] During the testing process, compressible test windows are identified in real time based on dynamic stability factors;

[0028] The identified test window is divided into several sub-segments;

[0029] The optimal compression time for each sub-segment is calculated using an energy-efficient intelligent compression algorithm, and the compressed power trajectory is generated.

[0030] The new power trajectory generated under the optimal compression time is returned to the original test window.

[0031] The present invention also provides a battery pack range performance testing system, comprising: a test condition sequence generation module, a test execution module, a battery management system coupling module, a test window compression module, and a test result generation module;

[0032] The test execution module is used to apply a dynamic test condition sequence to the battery pack under test and to capture the communication messages sent by the battery management system in real time using a message listening device.

[0033] The battery management system coupling module is used to parse the communication messages in real time to identify the battery management system strategy, and to perform forward compensation on the dynamic test condition sequence based on the identification results.

[0034] The test window compression module is used to identify compressible test windows and perform an energy-efficient intelligent compression algorithm on the compressible test windows to shorten the test cycle.

[0035] The test result generation module is used to synchronously record test data during the test process and generate a comprehensive evaluation report on range performance that is coupled with the influence of the battery management system strategy.

[0036] The beneficial effects achieved by this invention are as follows: it solves the problem of the disconnect between traditional standard operating conditions and actual conditions, and improves the reliability of range test data; it couples the BMS strategy in real time and performs look-ahead compensation to avoid test interruptions and accurately reflect the collaborative performance of BMS and battery cells; it intelligently compresses the test window, significantly shortens the test cycle and reduces costs; the report includes BMS impact analysis, which helps to locate performance bottlenecks and provides precise support for product optimization. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0038] Figure 1 This is a flowchart of a battery pack range performance testing method provided in Embodiment 1 of this application;

[0039] Figure 2 This is a schematic diagram of a battery pack range performance testing system provided in Embodiment 1 of this application. Detailed Implementation

[0040] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] Example 1

[0042] like Figure 1As shown, Embodiment 1 of this application provides a method for testing the battery pack's range performance, including:

[0043] Step S10: Generate a dynamic test condition sequence based on real-world operational data from the target application scenario;

[0044] The purpose of this step is to construct a test load curve that can highly replicate the working state of the battery pack in the real world. The specific implementation process is as follows:

[0045] Step S11: Collect actual operating data over a long period of time using the vehicle-mounted terminal;

[0046] The data acquisition frequency should be no less than 1Hz to ensure that dynamic details can be captured; the acquired data should include at least: timestamp, vehicle speed (km / h), acceleration (m / s²), latitude and longitude coordinates (for calculating slope), and power of key vehicle accessories (such as air conditioning, heating, audio, etc.).

[0047] Step S12: Process the collected actual operating data into a demand power time series;

[0048] Using latitude and longitude coordinates and elevation data, the road slope (%) is calculated through differential calculation. Based on the road slope, vehicle mass, speed, and acceleration, combined with the vehicle dynamics model, the required power for driving / braking is calculated, and the time series of required power is formed after spatiotemporal alignment.

[0049] Step S13: Segment and cluster the demand power time series to construct a library of typical operating condition segments;

[0050] The continuous power demand time series is automatically divided into multiple short time periods (e.g., 180 seconds) of operating conditions. Based on the characteristics of the segments (including average power, power standard deviation, maximum power, and duration), the segments are classified into several representative typical operating condition segments through clustering algorithms, including but not limited to: urban congestion segments, high-speed cruising segments, rapid acceleration segments, and long downhill recovery segments.

[0051] Step S14: Synthesize dynamic test condition sequences from a typical working condition segment library based on a Markov chain model;

[0052] A Markov chain model is used to simulate the random transition characteristics between different operating conditions in real driving. The probability of mutual transformation between typical operating conditions is statistically analyzed to construct a state transition probability matrix. Based on this probability matrix, a long, non-fixed sequence of operating conditions is randomly generated. This sequence is no longer a simple loop but has randomness and uncertainty, thus simulating real-world usage scenarios more realistically. Then, the accessory power consumption model (i.e., the curve of accessory power changing over time) is superimposed on the above-synthesized sequence of operating conditions to form the final dynamic test operating condition sequence containing the total load. This sequence is output in the form of time-total power demand for the test equipment to execute.

[0053] Step S20: Apply the dynamic test condition sequence to the battery pack under test, and use the message monitoring device to capture the communication messages sent by the battery management system in real time;

[0054] This step involves building the test system and executing tests, while also acquiring key data for subsequent battery management system (BMS) strategy coupling. The specific implementation process is as follows:

[0055] Step S21: Connect the battery pack under test to the test system;

[0056] The closed-loop test system mainly includes: a charge / discharge test device (programmable, with an accuracy better than 0.1%FS), a battery pack under test, a message monitoring device, and a host computer (running test control and data acquisition software).

[0057] Connection method: The positive and negative terminals of the charge and discharge test equipment are connected to the total positive and total negative terminals of the battery pack under test; the high-frequency (CAN_H) and low-frequency (CAN_L) signal lines of the message monitoring equipment are connected in parallel to the BMS communication CAN bus of the battery pack; all devices communicate with the host computer via Ethernet or USB and are synchronously controlled by the host computer.

[0058] Step S22: Load the dynamic test condition sequence into the test system to start the test, and synchronously listen to and record the communication messages sent by the battery management system;

[0059] The dynamic test condition sequence generated in step S10 is loaded into the host computer, and the test is started. The charge and discharge test equipment will strictly apply the current load according to the sequence.

[0060] Collect total voltage and total current from the charge / discharge test equipment; collect readings of voltage and temperature sensors of all cells from the battery pack BMS via the CAN bus (or via an additional data acquisition device); and use a message monitoring device to monitor and record all communication messages sent by the BMS on the CAN bus in real time.

[0061] Step S23: In real time, package the recorded communication messages and the bus database file of the battery management system and send them to the next processing step;

[0062] The battery management system's bus database file (DBC) defines the mapping relationship between message IDs and signals, as well as the scaling, offset, and physical meaning of the signals, for subsequent message parsing steps.

[0063] Step S30: Identify the battery management system strategy by parsing the communication messages in real time, and perform forward compensation on the dynamic test condition sequence based on the identification results;

[0064] This step is the core of the invention's deep coupling of BMS strategy. By identifying the BMS's decision-making logic in real time during testing and proactively adjusting the load, it ensures that the testing process truly reflects the interaction between the BMS and the battery cell. The specific implementation process is as follows:

[0065] Step S31: At each sampling time t, extract the feature vector representing the internal state of the battery pack from the real-time collected data.

[0066] Feature vectors representing the internal state of the battery pack Defined as: ,in It is the range of voltages of all individual cells within the tested battery pack. It is the temperature range of all individual cells within the tested battery pack. It is the rate of change of the average temperature of the battery pack within a short time window (the past 30 seconds). It is the integral of the absolute value of the current within the short-term window, and the calculation formula is: ,in For short-term window length, For at any time The total current value of the battery pack was collected and read from the charge / discharge testing equipment. This is the battery pack's SOC (State of Charge) estimated in real time using the ampere-hour integration method.

[0067] Step S32: Input the extracted feature vector into the battery management system policy identifier and output the predicted probability of the battery management system imposing constraints;

[0068] The battery management system policy identifier first determines the input feature vector. Calculate the decision value Z(t+1) at the next time step t+1, and then use the formula The predicted probability of the output battery management system imposing a constraint at time t+1. The formula for calculating the decision value Z(t+1) is as follows: Among the identifier parameters Fine-tuning is achieved through an online optimization mechanism to gradually bring the decision values ​​closer to the actual decision boundaries of the current BMS.

[0069] Step S33: Based on the predicted probability of the battery management system imposing a limit, perform look-ahead compensation on the original planned power in the dynamic test condition sequence;

[0070] First, calculate the limitation sensitivity factor based on the predicted probability of the battery management system imposing limitations. The calculation formula is: ,in This represents the planned power of the original dynamic test condition sequence at time t+1. It is the average power limit of the BMS within a historical window (within 5 trigger time points); then based on the limiting sensitivity factor. Calculate the power after look-ahead compensation Then use Replace the planned power at time t+1 in the original dynamic test condition sequence. The calculation formula is expressed as:

[0071] in To adjust the gain coefficient for the steepness of the compensation curve, With a preset sensitivity threshold, forward-looking compensation can effectively avoid test terminal, power step and unrealistic dynamic response caused by BMS forced limitation.

[0072] Step S34: Real-time analysis of the monitored battery management system communication messages, and online optimization of the battery management system policy identifier based on the analysis results;

[0073] The received communication messages are parsed in real time using a bus database file, and the parsed instructions are used for online optimization: if the BMS does not issue a constraint instruction at time t+1, it means the true boundary is looser than the prediction, and the feature vector at this time is marked as a negative sample (label 0); if the BMS issues a constraint instruction, it means the model prediction is close to the true boundary, and the feature vector at this time is immediately marked as a positive sample (label 1). Using these real-time generated samples, the identifier parameters are fine-tuned online using stochastic gradient descent. This method allows the test system to be quickly coupled with the current BMS to adapt to different models of BMS.

[0074] Note that the following steps should be executed after the test system has been coupled to the current BMS, i.e. after the identifier has converged.

[0075] Step S40: Identify compressible test windows and execute an energy-efficient intelligent compression algorithm on the compressible test windows to shorten the test cycle;

[0076] By intelligently identifying low-sensitivity intervals during the testing process and compressing them while ensuring testing accuracy, the total testing time is shortened. The specific implementation process is as follows:

[0077] Step S41: During the test, identify compressible test windows in real time based on the dynamic stability factor;

[0078] During the test, a dynamic stability factor is calculated in real time. This factor comprehensively reflects the electrical, thermodynamic, and BMS interaction stability of the battery pack at the current moment, and its calculation formula is as follows:

[0079] in This represents the standard deviation of the battery pack's output power within a sliding time window (60 seconds). It is the standard deviation of the rate of change of the highest temperature of the battery pack within the sliding time window. To restrict sensitive factors for BMS, These are preset weighting parameters used to adjust the contribution of each component;

[0080] when When the value continuously exceeds the preset stability threshold and the duration exceeds the preset minimum duration, the current time period (the next sliding time window starting from the current moment) is determined to be a compressible window. This window represents the battery pack being in a "comfort zone" where the load is stable, the thermal state is stable, and the risk of BMS intervention is extremely low.

[0081] Step S42: Divide the identified test window into several sub-segments;

[0082] The compressible test window is divided into several shorter sub-segments, and for each sub-segment, its feature vector is extracted. ,in The average power of the sub-segment, The discharge energy of the sub-segment. These are the start times of the i-th sub-segment and the (i+1)-th sub-segment, respectively. The ripple coefficient of the power within the sub-segment. , These are the maximum and minimum power values ​​within the i-th sub-segment, respectively.

[0083] Step S43: Calculate the optimal compression time for each sub-segment using the energy-efficient intelligent compression algorithm, and generate the compressed power trajectory;

[0084] Extracted feature vectors Strategy function of energy-efficient intelligent compression algorithm In the process, the optimal compression time is solved. ,in Let i be the original duration of the i-th sub-segment. The estimated ripple coefficient for the compressed sub-segment. For adjustable balance coefficients, under constraints and Below, the quadratic programming algorithm is used to solve the problem. smallest , It refers to based on The maximum power value in the new power trajectory generated for the i-th sub-segment;

[0085] based on The process for generating a new power trajectory for the i-th sub-segment is as follows:

[0086] ① Establish a time point mapping relationship before and after compression based on the time scaling ratio of the sub-segments;

[0087] Time scaling of the i-th sub-segment For any moment on the compressed trajectory The time corresponding to the original trajectory is .

[0088] ② Extract the original power sequence corresponding to the sub-segment from the original dynamic test condition sequence;

[0089] ③ For each discrete moment on the compressed time axis, the power value at that moment is obtained from the original power sequence through linear interpolation;

[0090] Right now If the total energy of the new trajectory is not equal to the total energy of the atomic fragment, it needs to be adjusted proportionally. The value of is used to ensure the conservation of energy.

[0091] Step S44: Take the new power trajectory generated at the optimal compression time and return it to the original test window.

[0092] Step S50: Synchronously record test data during the test process and generate a comprehensive evaluation report on the range performance affected by the coupled battery management system strategy;

[0093] Using the test start time as the baseline zero point, the timestamps of all collected data are synchronously calibrated to ensure precise timing alignment of data such as voltage, current, temperature, and BMS messages. Battery pack parameters, test environment conditions, and dynamic test condition sequences are populated into the test information module of the comprehensive evaluation report. The basic performance parameters of the battery pack are calculated and populated into the basic module of the comprehensive evaluation report by field, including: total driving range, total discharge energy, average energy consumption rate, and capacity retention rate. The total number of power limits issued by the BMS during the test (including cases with a predicted probability greater than 95%) and their cumulative duration are statistically analyzed. The frequency of limit triggering under different SOC ranges, temperature ranges, and voltage ranges is also statistically analyzed. The distribution pattern of power limit values ​​and their relationship with battery state are statistically analyzed. These statistical results are populated into the BMS strategy analysis module of the comprehensive evaluation report. The completed comprehensive evaluation report is then output in standard PDF format.

[0094] Through this complete process, the generated comprehensive evaluation report not only provides traditional range performance data, but more importantly, it deeply reveals the impact mechanism of BMS strategy on battery pack performance, providing accurate data support for product optimization and strategy debugging.

[0095] Example 2

[0096] like Figure 2 As shown, Embodiment 2 of this application provides a battery pack range performance testing system, including: a test condition sequence generation module 21, a test execution module 22, a battery management system coupling module 23, a test window compression module 24, and a test result generation module 25;

[0097] The test condition sequence generation module 21 is used to generate a dynamic test condition sequence based on real operating data of the target application scenario.

[0098] Test execution module 22 is used to apply a dynamic test condition sequence to the battery pack under test and to capture communication messages sent by the battery management system in real time using a message listening device.

[0099] The battery management system coupling module 23 is used to parse the communication messages in real time to identify the battery management system strategy, and to perform forward compensation on the dynamic test condition sequence based on the identification results.

[0100] The test window compression module 24 is used to identify compressible test windows and perform an energy-efficient intelligent compression algorithm on the compressible test windows to shorten the test cycle.

[0101] The test result generation module 25 is used to synchronously record test data during the test process and generate a comprehensive evaluation report on the range performance coupled with the influence of the battery management system strategy.

[0102] Corresponding to the above embodiments, the present invention provides a computer storage medium, including: at least one memory and at least one processor;

[0103] The memory is used to store one or more program instructions;

[0104] A processor is used to run one or more program instructions to execute a battery pack endurance performance test method.

[0105] Corresponding to the above embodiments, this embodiment of the invention provides a computer-readable storage medium containing one or more program instructions, which are executed by a processor to provide a battery pack endurance performance testing method.

[0106] The embodiments disclosed in this invention provide a computer-readable storage medium storing computer program instructions, which, when executed on a computer, cause the computer to perform the aforementioned battery pack endurance performance testing method.

[0107] In this embodiment of the invention, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0108] The various methods, steps, and logic diagrams disclosed in the embodiments of this invention can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor reads information from the storage medium and, in conjunction with its hardware, completes the steps of the above methods.

[0109] The storage medium can be memory, such as volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0110] Among them, non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory.

[0111] Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0112] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0113] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in this invention can be implemented using a combination of hardware and software. When applied as software, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of computer programs from one place to another. Storage media can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0114] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solution of the present invention should be included within the scope of protection of the present invention.

Claims

1. A battery pack endurance performance testing method, characterized in that, Comprise: Step1, based on the real running data of the target application scenario, generate dynamic test working condition sequence; Step2, apply the dynamic test working condition sequence to the battery pack to be tested, and use the message monitoring device to capture the communication messages sent by the battery management system in real time; Step3, identify the battery management system strategy by real-time analysis of the communication messages, and make forward-looking compensation to the dynamic test working condition sequence according to the identification result; Step4, identify the compressible test window, and execute the energy consumption intelligent compression algorithm on the compressible test window to shorten the test period; Step5, record the test data in the test process synchronously, and generate a comprehensive evaluation report of the endurance performance coupled with the influence of the battery management system strategy; By real-time analysis of the communication messages to identify the battery management system strategy, and according to the identification result, the dynamic test working condition sequence is forward-looking compensated, which is specifically divided into the following sub-steps: At each sampling time t, the feature vector representing the internal state of the battery pack is extracted from the real-time collected battery pack data; The extracted feature vector is input into the battery management system strategy identifier, and the predicted probability of the battery management system applying restrictions is output; According to the predicted probability of the battery management system applying restrictions, the original planned power in the dynamic test working condition sequence is forward-looking compensated; Real-time analysis of the monitored battery management system communication messages, and online optimization of the battery management system strategy identifier according to the analysis result; if the battery management system does not issue a restriction instruction at t+1, mark the feature vector at this time as a negative sample, and the label is 0; if the battery management system issues a restriction instruction at t+1, immediately mark the feature vector at this time as a positive sample, and the label is 1; using these real-time generated samples, the identifier parameters are fine-tuned online through stochastic gradient descent method.

2. The battery pack range test method according to claim 1, characterized in that, Based on the real running data of the target application scenario, generate dynamic test working condition sequence, which is specifically divided into the following sub-steps: Collect long time series of actual running data using vehicle-mounted terminal; The collected actual running data is processed into a demand power time sequence; Cut and cluster analysis of the demand power time sequence to construct a typical working condition segment library; Based on Markov chain model, a dynamic test working condition sequence is synthesized from the typical working condition segment library.

3. The battery pack range test method according to claim 2, characterized in that, Based on Markov chain model, a dynamic test working condition sequence is synthesized from the typical working condition segment library, which is specifically divided into the following sub-steps: Use Markov chain model to simulate the random transfer characteristics between different working condition segments in real driving; Statistical analysis of the mutual conversion probability of each typical working condition segment to construct a state transition probability matrix; According to the state transition probability matrix, a working condition segment sequence is randomly generated; Then, the accessory power consumption model is superimposed on the above synthesized working condition segment sequence to form the final dynamic test working condition sequence containing the total load.

4. The battery pack range test method of claim 1, wherein, Identify the compressible test window, and execute the energy consumption intelligent compression algorithm on the compressible test window, which is specifically divided into the following sub-steps: Identify the compressible test window in real time during the test process according to the dynamic stability factor; The identified test window is divided into several sub-segments; The optimal compression time of each sub-fragment is calculated by using the energy consumption intelligent compression algorithm, and a compressed power trajectory is generated. The new power trajectory generated under the optimal compression time is returned to the original test window.

5. The battery pack range test method according to claim 4, characterized in that, The process of generating a new power trajectory is as follows: according to the time scaling ratio of the sub-fragment, the mapping relationship between the time points before and after compression is established. The original power sequence corresponding to the sub-fragment is extracted from the original dynamic test working condition sequence; for each discrete time on the compressed time axis, the power value at that time is obtained from the original power sequence through linear interpolation.

6. A battery pack endurance test system, comprising: It comprises: a test working condition sequence generation module, a test execution module, a battery management system coupling module, a test window compression module, and a test result generation module; The test execution module is used to apply the dynamic test working condition sequence to the battery pack under test, and to capture the communication messages sent by the battery management system in real time using a message monitoring device. The battery management system coupling module is used to analyze the communication messages in real time to identify the battery management system strategy, and to compensate the dynamic test working condition sequence in advance according to the identification result. The test window compression module is used to identify compressible test windows and execute an energy consumption intelligent compression algorithm on the compressible test windows to shorten the test period. The test result generation module is used to record the test data during the test process in synchronization and generate a comprehensive evaluation report on the endurance performance of the battery pack under the influence of the battery management system strategy. The battery management system coupling module is specifically configured to: at each sampling time t, extract a feature vector representing the internal state of the battery pack from the real-time collected battery pack data; input the extracted feature vector into a battery management system strategy identifier to output a predicted probability of the battery management system imposing a restriction; compensate the originally planned power in the dynamic test working condition sequence in advance according to the predicted probability of the battery management system imposing a restriction; analyze the monitored battery management system communication messages in real time and optimize the battery management system strategy identifier online according to the analysis result; if the battery management system does not issue a restriction instruction at time t+1, mark the feature vector at this time as a negative sample with a label of 0; if the battery management system issues a restriction instruction at time t+1, immediately mark the feature vector at this time as a positive sample with a label of 1; and use these real-time generated samples to fine-tune the identifier parameters online through the stochastic gradient descent method.

7. A computer storage medium, comprising, It comprises: at least one memory and at least one processor; a memory for storing one or more program instructions; a processor for running one or more program instructions to execute a battery pack endurance performance test method according to any one of claims 1-5.

Images