Intelligent automobile battery multi-dimensional detection method and device and medium

Abstract

The invention discloses an intelligent automobile battery multi-dimensional detection method and device and a medium, and relates to the technical field of automobile battery detection. The method comprises the following steps: collecting time sequence data of voltage, current, internal resistance and temperature of an automobile battery; carrying out fusion filtering processing on the time sequence data, inputting the time sequence data into a battery state evaluation model, and carrying out parallel calculation to obtain a joint estimation value of the SOH and the SOC of the battery; judging the current fault state and the potential fault state of the battery based on the joint estimation value and the instantaneous value of the time sequence data after fusion filtering processing; when it is judged that the current fault state and the potential fault state of the battery exist, an early warning instruction is generated. According to the method, battery parameter real-time collection, multi-dimensional analysis and fault automatic early warning are achieved, the detection timeliness and accuracy are improved, meanwhile, the operation threshold is lowered, and the method is suitable for common user use scenes.

Description

Technical Field

[0001] This application relates to the field of automotive battery testing technology, and in particular to a method, equipment and medium for multi-dimensional testing of intelligent automotive batteries. Background Technology

[0002] In the field of automotive electronics, the battery, as a core energy component of a vehicle, directly affects the overall operational safety and reliability of the vehicle. Currently, the testing of automotive batteries mostly adopts periodic, offline testing methods, relying on professionals using specialized testing equipment such as conductivity meters and internal resistance meters. This method cannot capture the dynamic changes in battery parameters under actual operating conditions such as driving and charging / discharging, making it difficult to detect potential faults such as gradual changes in internal resistance, micro-short circuits, and aging of internal active materials in real time. It has a serious lag and may lead to sudden battery failure, posing safety hazards.

[0003] Existing technologies include some on-board battery monitoring devices, which typically assess battery status roughly by monitoring single or limited parameters such as battery voltage and temperature. While these methods can achieve some online monitoring capabilities, they have significant limitations: insufficient monitoring parameters to comprehensively reflect the battery's true health status; simplistic data analysis, often based on fixed thresholds, failing to provide early prediction and trend analysis of battery performance degradation; and isolated operation between systems, lacking effective coordination with other vehicle control systems, thermal management, and energy management, resulting in limited intelligence and insufficient accuracy and foresight in early warning systems.

[0004] Based on the above analysis, the problems and shortcomings of the existing technology are as follows:

[0005] Current automotive battery testing technologies cannot perform real-time, multi-dimensional, and forward-looking intelligent diagnosis of automotive batteries and achieve proactive collaborative protection with vehicle systems. Summary of the Invention

[0006] This application provides a method, device, and medium for multi-dimensional detection of intelligent vehicle batteries, which can solve the problem that existing vehicle battery detection technologies cannot perform real-time, multi-dimensional, and forward-looking intelligent diagnosis of vehicle batteries and achieve proactive collaborative protection with vehicle systems.

[0007] In a first aspect, embodiments of this application provide a multi-dimensional detection method for intelligent vehicle batteries. The method includes: collecting time-series data of the battery's voltage, current, internal resistance, and temperature; performing fusion filtering on the time-series data and inputting it into a battery state assessment model to calculate a joint estimate of the battery's state of equilibrium (SOH) and state of charge (SOC) in parallel; determining the battery's current fault state and potential fault state based on the joint estimate and the instantaneous values ​​of the fusion-filtered time-series data; and generating a warning command when a current fault state and potential fault state of the battery are determined to exist.

[0008] In one implementation of this application, the time-series data is fused and filtered, specifically including: using a Kalman filter algorithm to suppress noise in current and voltage; using a time-series-based sliding window consistency check algorithm to remove abnormal sampling points for temperature and internal resistance; and performing timestamp alignment and spatial registration on the time-series data to form a unified battery status data frame.

[0009] In one implementation of this application, the joint estimate of battery SOH and SOC is obtained by parallel computing, specifically including: in the offline stage, collecting battery state data frames under various operating conditions throughout the battery's life cycle as a training set, and using machine learning algorithms to train a battery state assessment model; in the online stage, inputting the real-time collected and processed battery state data frames into the battery state assessment model, and outputting the joint estimate of SOH and SOC and the corresponding confidence interval; and dynamically adjusting the data collection frequency according to the confidence interval.

[0010] In one implementation of this application, the current fault state and potential fault state of the battery are determined based on the joint estimate and the instantaneous value of the time series data after fusion filtering. Specifically, this includes: comparing the instantaneous value of the battery state data frame with a preset static threshold to perform preliminary anomaly screening; analyzing the changing trend and rate of change of the battery state data frame to identify potential performance degradation faults; and performing multi-parameter fusion decision-making based on the joint estimate output by the battery state assessment model to identify composite fault modes.

[0011] In one implementation of this application, when it is determined that there is a current fault state and a potential fault state of the battery, a warning instruction is generated, which specifically includes: based on the warning instruction including prompt, warning, and danger; for warning and danger, the local warning unit activates an adaptive audible and visual alarm, wherein the alarm frequency and intensity are positively correlated with the level; and the warning instruction and corresponding processing suggestions are pushed to the user terminal and the cloud server via wireless communication.

[0012] In one implementation of this application, after generating a warning instruction when it is determined that there is a current fault state and a potential fault state of the battery, the method further includes: if the warning information level is dangerous, limiting the battery's discharge power and prompting the driver to stop safely; based on the prompt including temperature abnormality, if the warning information is temperature abnormality, activating the thermal management system to forcibly dissipate heat or heat the battery.

[0013] In one implementation of this application, the method further includes: continuously monitoring and recording the number of charge-discharge cycles and historical data of the battery; based on the number of charge-discharge cycles and historical data, using data interpolation and extrapolation algorithms to predict the performance degradation trajectory and remaining service life of the battery over a preset time; and generating maintenance reminder information when the predicted remaining service life is lower than a threshold or the performance degradation rate exceeds a limit.

[0014] In one implementation of this application, the method further includes: establishing a correlation model between battery internal resistance growth, capacity decay, cycle count, and operating temperature; using a particle filter algorithm and real-time data to update and calibrate the parameters of the correlation model online; and predicting the remaining battery life based on the updated and calibrated correlation model.

[0015] Secondly, embodiments of this application also provide a multi-dimensional detection device for intelligent automotive batteries. The device includes at least one processor and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, which, when executed, enable the at least one processor to: collect time-series data of the battery's voltage, current, internal resistance, and temperature; perform fusion filtering on the time-series data and input it into a battery state assessment model to calculate a joint estimate of the battery's SOH and SOC in parallel; determine the current fault state and potential fault state of the battery based on the joint estimate and the instantaneous values ​​of the fusion-filtered time-series data; and generate a warning instruction when a current fault state and potential fault state of the battery are determined to exist.

[0016] Thirdly, this application also provides a non-volatile computer storage medium for multi-dimensional detection of intelligent vehicle batteries, storing computer-executable instructions. The computer-executable instructions are configured to: collect time-series data of the vehicle battery's voltage, current, internal resistance, and temperature; perform fusion filtering on the time-series data, input it into the battery state assessment model, and calculate in parallel the joint estimate of the battery's SOH and SOC; based on the joint estimate and the instantaneous values ​​of the time-series data after fusion filtering, determine the current fault state and potential fault state of the battery; and when it is determined that there is a current fault state and a potential fault state of the battery, generate a warning instruction.

[0017] This application provides a method, device, and medium for multi-dimensional detection of intelligent vehicle batteries. By simultaneously collecting multi-dimensional parameters such as voltage, current, internal resistance, and temperature and performing fusion filtering, it significantly improves data quality and reliability. By employing a trained battery state assessment model for parallel computation, it achieves high-precision joint estimation of battery health status and remaining capacity, and can output confidence intervals to assess the reliability of the estimation. By constructing multi-level fault reasoning logic, it can integrate instantaneous values, changing trends, and model outputs to achieve accurate identification and early warning of faults ranging from simple anomalies to complex composite faults. By deeply linking warning commands with the vehicle control system and leveraging a cloud-based big data platform to achieve continuous model evolution, it forms a complete closed-loop system from accurate perception, intelligent diagnosis, forward-looking warning to active protection, greatly improving the intelligence level of battery management, driving safety, and battery life. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0019] Figure 1 A flowchart illustrating a multi-dimensional detection method for intelligent vehicle batteries provided in this application embodiment;

[0020] Figure 2 This is a schematic diagram of the structure of a multi-dimensional detection method for intelligent vehicle batteries provided in an embodiment of this application;

[0021] Figure 3 This is a schematic diagram of the internal structure of a multi-dimensional detection device for intelligent vehicle batteries provided in an embodiment of this application. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] This application provides a method, device, and medium for multi-dimensional detection of intelligent vehicle batteries, which solves the problem in the prior art that vehicle battery detection cannot perform real-time, multi-dimensional, and forward-looking intelligent diagnosis of vehicle batteries and achieve active collaborative protection with the vehicle system.

[0024] The technical solutions proposed in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0025] Figure 1 This is a flowchart illustrating a multi-dimensional detection method for intelligent vehicle batteries, provided as an embodiment of this application. Figure 1 As shown in the figure, the multi-dimensional detection method for smart car batteries provided in this application embodiment specifically includes the following steps:

[0026] Step 10: Collect time-series data of the car battery's voltage, current, internal resistance, and temperature, such as... Figure 2 As shown;

[0027] Step 20: Perform fusion filtering on the time series data and input it into the battery state assessment model to obtain the joint estimate of battery SOH and SOC in parallel calculation;

[0028] As an optional embodiment, the time-series data is fused and filtered, which may specifically include: Step 201: using the Kalman filter algorithm to suppress noise in current and voltage; Step 202: using a time-series-based sliding window consistency check algorithm to remove abnormal sampling points for temperature and internal resistance; Step 203: performing timestamp alignment and spatial registration on the time-series data to form a unified battery status data frame.

[0029] In this step, Kalman filtering is applied to the acquired current and voltage signals to suppress measurement noise and electromagnetic interference, outputting smooth, high-precision voltage and current time-series data. A sliding window consistency check algorithm is used for temperature and internal resistance signals to remove obviously abnormal sampling points, and interpolation is performed when necessary to ensure continuous and reliable data. Voltage, current, temperature, and internal resistance data are unified onto the same time axis, and spatial identifiers are added according to sensor locations, forming a battery status data frame containing timestamps, location information, and multi-parameter measurement values. The fused and filtered data frame is input into the battery state assessment model, and parallel computation yields the joint estimate of SOH and SOC and their confidence intervals, providing a basis for subsequent fault diagnosis and early warning.

[0030] As an optional embodiment, parallel computation is used to obtain the joint estimate of battery SOH and SOC, which may specifically include: Step 204: In the offline stage, battery state data frames under various operating conditions throughout the battery's life cycle are collected as a training set, and a battery state assessment model is trained using a machine learning algorithm; Step 205: In the online stage, the battery state data frames collected and processed in real time are input into the battery state assessment model, and the joint estimate of SOH and SOC and the corresponding confidence interval are output; Step 206: The data collection frequency is dynamically adjusted according to the confidence interval.

[0031] In this step, battery state data frames are collected and processed throughout the battery's entire lifecycle and under various operating conditions: fast charging, slow charging, different temperatures, different depths of discharge, and different discharge rates, to construct a training dataset. A battery state assessment model is trained using machine learning algorithms, which can simultaneously output joint estimates of SOH and SOC and their corresponding confidence intervals. Online inference computation inputs the real-time collected and fused-filtered battery state data frames into the trained battery state assessment model. Through parallel computation, such as multi-core CPU or GPU acceleration, the joint estimates of SOH and SOC and their confidence intervals are obtained simultaneously, ensuring low-latency output. When the confidence level is low and the error range is large, the sampling frequency is increased to obtain more information and improve estimation accuracy. When the confidence level is high and the error range is small, the sampling frequency is appropriately reduced to reduce computation and communication overhead.

[0032] Step 30: Based on the joint estimate and the instantaneous values ​​of the time series data after fusion filtering, determine the current fault state and potential fault state of the battery;

[0033] As an optional embodiment, the current fault state and potential fault state of the battery are determined based on the joint estimate and the instantaneous value of the time series data after fusion filtering. Specifically, this may include: Step 301: Comparing the instantaneous value of the battery status data frame with a preset static threshold to perform preliminary anomaly screening; Step 302: Analyzing the changing trend and rate of change of the battery status data frame to identify potential performance degradation faults; Step 303: Based on the joint estimate output by the battery status assessment model, performing multi-parameter fusion decision-making to identify composite fault modes.

[0034] In this step, the instantaneous values ​​of voltage, current, temperature, and internal resistance in the battery status data frame are compared with preset static thresholds to quickly determine whether there are abnormal parameters exceeding the normal range. If they exceed the threshold, they are marked as preliminary anomalies. Potential performance degradation identification performs trend analysis on the time-series changes of the battery status data frame, and calculates the rate of parameter change using methods such as sliding window fitting and first-order difference. If phenomena such as continuous temperature increase, rapid increase in internal resistance, and accelerated capacity decay are found, they are identified as potential performance degradation faults. Composite fault mode identification is based on the joint estimate of SOH and SOC output by the battery status assessment model. Combining instantaneous values ​​and trend characteristics, a multi-parameter fusion decision is used to comprehensively determine whether there are composite fault modes, and the final fault judgment result is output.

[0035] Step 40: When it is determined that there is a current fault state and a potential fault state of the battery, generate a warning command.

[0036] As an optional embodiment, when it is determined that there is a current fault state and a potential fault state of the battery, a warning instruction is generated, which may include: Step 401: Based on the warning instruction, including prompt, warning, and danger; Step 402: For warning and danger, the local warning unit activates an adaptive audible and visual alarm, wherein the alarm frequency and intensity are positively correlated with the level; Step 403: Push the warning instruction and corresponding processing suggestions to the user terminal and the cloud server through wireless communication.

[0037] In this step, warnings are divided into three levels based on the fault type and risk level: **Important:** Minor parameter abnormalities that do not affect current use but require attention; **Warning:** Obvious abnormalities or performance degradation trends that may affect battery life or performance; **Danger:** Serious safety hazards or functional failure risks that require immediate action. For warning and danger levels, the local warning unit activates adaptive audible and visual alarms via the vehicle's instrument panel, indicator lights, and buzzer. The frequency and intensity of the alarms are positively correlated with the warning level: the higher the level, the more urgent and intense the alarm. Warning commands and corresponding handling suggestions are pushed to user terminals, including mobile apps and vehicle systems, via wireless communication modules (4G / 5G, Bluetooth, Wi-Fi) and simultaneously uploaded to the cloud server for remote monitoring and recording.

[0038] As an optional embodiment, after generating a warning command when it is determined that there is a current fault state and a potential fault state of the battery, the method may further include: if the warning information level is dangerous, limiting the battery's discharge power and prompting the driver to stop safely; based on the prompt including temperature abnormality, if the warning information is temperature abnormality, activating the thermal management system to forcibly dissipate heat or heat the battery.

[0039] In this step, if the risk level of the warning information is "dangerous," the vehicle control system limits the battery's discharge power through the BMS, reducing the vehicle's power output. At the same time, a safe stopping prompt is issued to the driver on the instrument panel or central control screen, suggesting that the driver immediately pull over and turn off the power to avoid a safety accident. If the warning content is "abnormal temperature," the vehicle control system automatically activates the thermal management system. If the temperature is too high, forced cooling is performed, such as turning on the cooling fan or starting the liquid cooling cycle. If the temperature is too low, heating is performed, activating the PTC heater or heat pump system to restore the battery temperature to a safe operating range.

[0040] As an optional embodiment, the method further includes: continuously monitoring and recording the number of charge-discharge cycles and historical data of the battery; based on the number of charge-discharge cycles and historical data, using data interpolation and extrapolation algorithms to predict the performance degradation trajectory and remaining service life of the battery over a preset time; and generating maintenance reminder information when the predicted remaining service life is lower than a threshold or the performance degradation rate exceeds a limit.

[0041] In this step, historical data such as the number of charge-discharge cycles, the combined estimated state of health (SOH) / state of charge (SOC), voltage, current, temperature, and internal resistance of the battery are continuously collected and recorded. This data is stored in time-series format, forming an operational database covering the entire battery lifecycle. Based on the number of charge-discharge cycles and historical data, data interpolation and extrapolation algorithms, such as polynomial fitting and exponential fitting, are used to predict the battery performance degradation trajectory and remaining lifespan within a preset timeframe. Maintenance reminders can be pushed to users via the vehicle's infotainment system, user terminal app, or cloud platform, prompting them to promptly perform battery checks, maintenance, or replacement.

[0042] As an optional embodiment, the method further includes: establishing a correlation model between battery internal resistance growth, capacity decay, cycle count, and operating temperature; using a particle filtering algorithm and real-time data to update and calibrate the parameters of the correlation model online; and predicting the remaining battery life based on the updated and calibrated correlation model.

[0043] In this step, a correlation model is constructed between the battery's core performance degradation and influencing factors. Using the battery's charge-discharge cycle count and operating temperature as input variables, and the battery's internal resistance growth rate and capacity degradation degree as output variables, the nonlinear mapping relationship among these three factors is quantified, forming a basic model that can describe the long-term aging pattern of the battery. Online parameter calibration using particle filtering utilizes the particle filtering algorithm, a filtering method suitable for nonlinear and non-Gaussian systems. Combined with real-time acquired battery state data, including real-time internal resistance, instantaneous capacity, current temperature, and cycle count, key parameters of the correlation model, including the degradation coefficient and temperature sensitivity coefficient, are dynamically updated and calibrated. This eliminates prediction biases caused by initial model errors and individual battery differences, ensuring that the model matches the actual aging state of the battery in real time. Based on the calibrated model, the remaining service life is predicted. The updated and calibrated correlation model is used as the prediction core, inputting the battery's current cycle count, historical operating temperature statistics, and estimated parameters for future usage scenarios. Through model deduction, the future change curves of battery internal resistance growth and capacity degradation are obtained, thereby inferring the remaining service life of the battery before reaching the performance retirement threshold, providing an accurate basis for battery replacement or tiered utilization.

[0044] The above are embodiments of the method proposed in this application. Based on the same inventive concept, embodiments of this application also provide a multi-dimensional detection device for intelligent vehicle batteries, the structure of which is as follows: Figure 3 As shown.

[0045] Figure 3 This is a schematic diagram of the internal structure of a multi-dimensional testing device for intelligent automotive batteries, provided as an embodiment of this application. Figure 3 As shown, the device includes:

[0046] At least one processor 301;

[0047] And a memory 302 that is communicatively connected to at least one processor;

[0048] The memory 302 stores instructions executable by at least one processor. These instructions are executed by at least one processor 301 to enable the processor 301 to: acquire time-series data of the vehicle battery's voltage, current, internal resistance, and temperature; perform fusion filtering on the time-series data and input it into the battery state assessment model to calculate a joint estimate of the battery's SOH and SOC in parallel; determine the battery's current fault state and potential fault state based on the joint estimate and the instantaneous values ​​of the fusion-filtered time-series data; and generate a warning instruction when a current fault state and potential fault state of the battery are determined to exist.

[0049] Some embodiments of this application provide corresponding to Figure 1 A non-volatile computer storage medium for multi-dimensional detection of intelligent vehicle batteries stores computer-executable instructions. The computer-executable instructions are configured to: collect time-series data of the vehicle battery's voltage, current, internal resistance, and temperature; perform fusion filtering on the time-series data and input it into a battery state assessment model to calculate a joint estimate of the battery's SOH and SOC in parallel; based on the joint estimate and the instantaneous values ​​of the fusion-filtered time-series data, determine the battery's current fault state and potential fault state; and generate a warning instruction when a current fault state or potential fault state is determined to exist.

[0050] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments for IoT devices and media are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0051] The systems, media, and methods provided in this application are one-to-one correspondences. Therefore, the systems and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media will not be repeated here.

[0052] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0053] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0054] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0055] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0056] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0057] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0058] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0059] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0060] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A multi-dimensional detection method for intelligent vehicle batteries, characterized in that, The method includes: Collect time-series data on the voltage, current, internal resistance, and temperature of the car battery; The time-series data is fused and filtered, then input into the battery state assessment model to obtain a joint estimate of the battery's SOH and SOC in parallel calculations. Based on the joint estimate and the instantaneous value of the time series data after fusion filtering, the current fault state and potential fault state of the battery are determined. When it is determined that the battery is in a current fault state or a potential fault state, an early warning command is generated.

2. The method for multi-dimensional detection of intelligent vehicle batteries according to claim 1, characterized in that, The fusion filtering process for the time-series data specifically includes: The Kalman filter algorithm is used to suppress noise in the current and voltage. For the aforementioned temperature and internal resistance, a time-series-based sliding window consistency check algorithm is used to eliminate abnormal sampling points; The time-series data is timestamped and spatially registered to form a unified battery status data frame.

3. The method for multi-dimensional detection of intelligent vehicle batteries according to claim 2, characterized in that, The parallel computation yields joint estimates of the battery's SOH and SOC, specifically including: In the offline phase, battery status data frames are collected throughout the battery's life cycle and under various operating conditions as a training set, and the battery status assessment model is trained using machine learning algorithms. During the online phase, the battery state data frame, which is collected and processed in real time, is input into the battery state assessment model, and the joint estimate of SOH and SOC and the corresponding confidence interval are output. The data acquisition frequency is dynamically adjusted based on the confidence interval.

4. The method for multi-dimensional detection of intelligent vehicle batteries according to claim 3, characterized in that, The determination of the current fault state and potential fault state of the battery based on the joint estimated value and the instantaneous value of the time-series data after fusion filtering specifically includes: The instantaneous value of the battery status data frame is compared with a preset static threshold to perform preliminary anomaly screening; Analyze the changing trends and rates of change of the battery status data frames to identify potential performance degradation faults; Based on the joint estimate output by the battery state assessment model, multi-parameter fusion decision-making is performed to identify composite fault modes.

5. The method for multi-dimensional detection of intelligent vehicle batteries according to claim 1, characterized in that, When it is determined that the battery is in a current fault state or a potential fault state, a warning instruction is generated, specifically including: The aforementioned warning instructions include prompts, warnings, and dangers; In response to the aforementioned warnings and dangers, the local early warning unit activates an adaptive audible and visual alarm, wherein the alarm frequency and intensity are positively correlated with the alarm level. The warning instructions and corresponding processing suggestions are pushed to the user terminal and cloud server via wireless communication.

6. The method for multi-dimensional detection of intelligent vehicle batteries according to claim 1, characterized in that, After generating a warning command when it is determined that the battery is in a current fault state or a potential fault state, the method further includes: If the warning information level is dangerous, the battery discharge power will be limited, and the driver will be prompted to stop safely. Based on the above prompts, including temperature abnormality, if the warning information indicates a temperature abnormality, the thermal management system will be activated to force heat dissipation or heating of the battery.

7. The method for multi-dimensional detection of intelligent vehicle batteries according to claim 1, characterized in that, The method further includes: Continuously monitor and record the number of charge-discharge cycles and historical data of the battery; Based on the number of charge-discharge cycles and historical data, data interpolation and extrapolation algorithms are used to predict the performance degradation trajectory and remaining service life of the battery at a preset time. A maintenance reminder message is generated when the predicted remaining useful life is below a threshold or the performance degradation rate exceeds a limit.

8. The method for multi-dimensional detection of intelligent vehicle batteries according to claim 1, characterized in that, The method further includes: Establish a correlation model between battery internal resistance growth, capacity decay, cycle number, and operating temperature; The parameters of the correlation model are updated and calibrated online using a particle filter algorithm combined with real-time data. Based on the updated and calibrated correlation model, the remaining battery life is predicted.

9. A multi-dimensional testing device for intelligent automotive batteries, characterized in that, The device includes: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to: Collect time-series data on the voltage, current, internal resistance, and temperature of the car battery; The time-series data is fused and filtered, then input into the battery state assessment model to obtain a joint estimate of the battery's SOH and SOC in parallel calculations. Based on the joint estimate and the instantaneous value of the time series data after fusion filtering, the current fault state and potential fault state of the battery are determined. When it is determined that the battery is in a current fault state or a potential fault state, an early warning command is generated.

10. A non-volatile computer storage medium for multi-dimensional detection of intelligent vehicle batteries, storing computer-executable instructions, characterized in that, The computer-executable instructions are set as follows: Collect time-series data on the voltage, current, internal resistance, and temperature of the car battery; The time-series data is fused and filtered, then input into the battery state assessment model to obtain a joint estimate of the battery's SOH and SOC in parallel calculations. Based on the joint estimate and the instantaneous value of the time series data after fusion filtering, the current fault state and potential fault state of the battery are determined. When it is determined that the battery is in a current fault state or a potential fault state, an early warning command is generated.

Images