Lithium battery aging detection method and system

Abstract

The invention relates to the technical field of battery detection, in particular to a lithium battery aging detection method and system, and the method comprises the steps: collecting the operation parameters of a lithium battery through a sensor in the working process of the lithium battery, and analyzing the collected parameters to obtain the changes of the lithium battery in different working states; grouping the collected lithium battery operation parameters according to a set time interval, wherein the parameters in each time interval form a fused lithium battery operation parameter feature vector; enabling the lithium battery to be in different charge states, performing electrochemical impedance spectroscopy measurement on the battery by using an electrochemical workstation to obtain an impedance spectrogram, extracting features, and fusing the features with the multi-parameter feature vectors to obtain a fused feature set; and constructing a lithium battery aging detection model, and taking the fused feature set as input to obtain a corresponding lithium battery aging degree evaluation result. According to the method, lithium battery operation parameters are combined with electrochemical impedance spectroscopy characteristic analysis, so that the lithium battery aging is accurately detected, and the detection efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of battery detection, and in particular to a lithium battery aging detection method and system. Background Art

[0002] Lithium batteries, with their high energy density, long cycle life, and low self-discharge, are widely used in electronic devices, electric vehicles, and energy storage systems. However, with increased use and the passage of time, lithium batteries inevitably age, gradually degrading their performance through issues such as capacity decay, increased internal resistance, and reduced charge and discharge efficiency. These aging issues not only affect the normal operation of equipment but can also pose safety risks.

[0003] Currently, common methods for detecting lithium battery aging include capacity testing and internal resistance measurement. The capacity test method assesses the degree of aging by fully charging and discharging the battery and measuring the ratio of its actual discharge capacity to its initial capacity. However, this method is time-consuming and requires the battery to be removed from the device for offline testing, making real-time online monitoring impossible. While the internal resistance measurement method is relatively simple to operate and can quickly obtain battery internal resistance data, changes in internal resistance do not fully reflect battery aging and are easily affected by the measurement environment and battery usage status, resulting in poor accuracy.

[0004] Furthermore, existing detection methods mostly rely on single-parameter analysis, making it difficult to fully and accurately capture the complex changes that occur during lithium battery aging. In real-world applications, lithium batteries operate in complex and variable conditions. Factors such as temperature and charge / discharge rates can affect battery aging, and traditional detection methods often overlook these dynamic factors. Therefore, developing a lithium battery aging detection method that overcomes these limitations is of great practical significance. Summary of the Invention

[0005] In response to the above-mentioned technical deficiencies, the present invention provides a lithium battery aging detection method and system to achieve comprehensive and accurate detection of lithium battery aging.

[0006] The present invention is achieved through the following technical solutions:

[0007] A method for detecting aging of a lithium battery is provided, the method comprising the following steps:

[0008] Step S10: During normal operation of the lithium battery, the operating parameters of the lithium battery, including voltage, current, and temperature, are collected through sensors. The charge and discharge rates are obtained by monitoring the control signals in the battery management system (BMS). The parameters are dynamically monitored to obtain changes in the lithium battery under different operating conditions.

[0009] Step S20: grouping the collected lithium battery operating parameters according to the set time intervals, and forming a fused lithium battery operating parameter feature vector with the parameters in each time interval;

[0010] Step S30: placing the lithium battery at different states of charge, performing electrochemical impedance spectroscopy on the battery using an electrochemical workstation to obtain an electrochemical impedance spectrum, extracting features from the electrochemical impedance spectrum, and fusing them with a fusion lithium battery operating parameter feature vector to obtain a fusion feature set;

[0011] Step S40: Build a lithium battery aging detection model based on the machine learning algorithm, take the fusion feature set as input, output the corresponding lithium battery aging degree assessment result, set the lithium battery aging degree threshold, and when the output lithium battery aging degree is greater than or equal to the set threshold, send an aging signal and prompt to replace the lithium battery or take corresponding maintenance measures to ensure the normal operation and safe use of the equipment.

[0012] Preferably, in step S10, the operating parameters of the lithium battery are collected by sensors, and a high-precision current sensor is connected in series in the working circuit of the lithium battery to measure the charge and discharge current of the lithium battery; a high-resolution voltage sensor is connected in parallel at the positive and negative terminals of the lithium battery to monitor the lithium battery voltage in real time; a temperature sensor is installed at a suitable position on the lithium battery casing or inside to obtain the temperature information of the lithium battery, and the data collected by these sensors is transmitted to the host computer through a data acquisition card for storage and processing. The data acquisition frequency is set according to actual needs.

[0013] Preferably, the step S20 of grouping the collected lithium battery operating parameters according to a set time interval includes:

[0014] Set time interval: Set the time interval to 1 minute. Within the set 1 minute, the collected lithium battery voltage, current, temperature data and charge and discharge rate will be statistically analyzed;

[0015] Feature calculation: Calculate parameters such as the average voltage, average current, voltage fluctuation range, current fluctuation range, maximum temperature, minimum temperature, and temperature change rate within a 1-minute time interval. For the charge and discharge rate, record the maximum charge and discharge rate, minimum charge and discharge rate, and the number of charge and discharge rate changes within a 1-minute time interval. Traverse each minute within the sampling time to obtain n lithium battery operating parameter feature vectors within 1-minute time intervals;

[0016] Fusion lithium battery operating parameter characteristics: The characteristic parameters calculated within a 1-minute time interval are combined in a certain order to obtain a fusion lithium battery operating parameter characteristic vector within a 1-minute time interval. Each minute within the sampling time is traversed to obtain n fusion lithium battery operating parameter characteristic vectors within a 1-minute time interval.

[0017] Preferably, in step S30, the step of measuring the electrochemical impedance spectroscopy of the battery using an electrochemical workstation to obtain an electrochemical impedance spectrum includes:

[0018] Measurement preparation: Select a suitable electrochemical workstation and ensure that its performance meets the measurement requirements. Perform calibration and preheating. Prepare the test fixture and wires for connecting the lithium battery to ensure reliable connections and good contact. Fully charge the lithium battery to be tested. According to the preset discharge strategy, discharge the lithium battery to a state of charge (SOC) of 20%, 50%, and 80%. At each target SOC state, let the lithium battery stand for a period of time (e.g., 30 minutes) to allow the battery to reach a stable state and reduce measurement errors.

[0019] Connect the lithium battery to the electrochemical workstation: Correctly connect the positive and negative electrodes of the lithium battery at the target SOC state to the corresponding electrode interfaces of the electrochemical workstation. Usually, the working electrode (WE) is connected to the positive electrode of the battery, and the reference electrode (RE) and the counter electrode (CE) are short-circuited before connecting to the negative electrode of the battery. Be careful to avoid short circuits and false connections during the connection process. After the connection is completed, check the stability of the connection again.

[0020] Set measurement parameters: In the electrochemical workstation's operating software, set the parameters for electrochemical impedance spectroscopy measurement. Set the measurement frequency range to 0.01Hz-10kHz, which covers the main electrochemical processes within the lithium battery. Set the AC excitation signal amplitude to 5mV, which not only ensures the accuracy of the measurement signal but also does not significantly interfere with the electrochemical balance within the lithium battery. Set other parameters such as the number of measurement points and measurement time according to actual needs to ensure sufficient and accurate data.

[0021] Measurement and recording: After confirming that all parameters are set correctly, start the measurement program of the electrochemical workstation. During the measurement process, keep the measurement environment stable and avoid external interference, such as electromagnetic interference and temperature fluctuations. The electrochemical workstation applies sinusoidal AC signals of different frequencies in the set frequency range and collects the impedance response data of the battery at the corresponding frequency, including real impedance (reflecting resistance characteristics) and imaginary impedance (reflecting capacitance and inductance characteristics). Draw the electrochemical impedance spectrum based on the impedance response data, export it from the electrochemical workstation, and save it. The data storage format should be convenient for subsequent analysis and processing. At the same time, mark the electrochemical impedance spectrum and indicate key information such as the SOC state of the lithium battery and the measurement time during the measurement to facilitate subsequent data collation and comparative analysis;

[0022] Repeated measurement and verification: To ensure the reliability and accuracy of the measurement data, multiple measurements are performed on lithium batteries at the same SOC state, and the repeatability and consistency of the measurement data are checked. When the data differs greatly, the cause is analyzed and re-measured. The batteries at different SOC states (20%, 50% and 80%) are measured and verified according to the above steps.

[0023] Preferably, the step of extracting electrochemical impedance spectroscopy features and fusing them with the fusion lithium battery operating parameter feature vector to obtain a fusion feature set in step S30 includes:

[0024] Electrochemical impedance spectroscopy feature extraction: Extract key characteristic parameters such as charge transfer resistance Rct, Warburg impedance Zw, and double layer capacitance Cdl from electrochemical impedance spectroscopy.

[0025] Feature fusion: fusing the fusion lithium battery operating parameter feature vector obtained in step S20 with the electrochemical impedance spectroscopy feature parameters to obtain a fusion feature set;

[0026] Data processing: The obtained fusion feature set is standardized so that each feature in the fusion feature set has zero mean and unit variance, ensuring the consistency of weights of different features in subsequent analysis and avoiding deviations caused by different feature dimensions; after data standardization, the covariance matrix is calculated. The covariance matrix can reflect the correlation between different features. The covariance matrix is decomposed to calculate its eigenvalues and eigenvectors. The eigenvalues reflect the variance contribution of each principal component, and the eigenvectors reflect the direction of the principal component. The eigenvalues and corresponding eigenvectors are sorted in descending order of the eigenvalues. The principal components are selected according to the cumulative contribution rate. Usually, the principal components with a cumulative contribution rate of more than 90% are selected. According to the calculated eigenvalues and eigenvectors, the original fusion feature set is linearly transformed and the data is reconstructed to obtain the fusion feature set after dimensionality reduction. While retaining the main information, the data dimension is reduced, thereby improving the efficiency and accuracy of subsequent analysis.

[0027] Preferably, the step of constructing a lithium battery aging detection model based on a machine learning algorithm in step S40 includes:

[0028] Training sample collection: Training samples are obtained by testing and monitoring lithium batteries from different batches, different usage times, and different charge and discharge cycle times;

[0029] Lithium battery aging detection model construction and training: Using a machine learning algorithm, with the fused feature set obtained in step S30 as input and the actual aging degree of the lithium battery as output, a lithium battery aging prediction model is established. The model is trained and optimized using the training samples obtained in the training sample collection step, so that the model learns the mapping relationship between the fused features and the aging degree of the lithium battery;

[0030] Lithium battery aging detection: The fusion feature set obtained in step S30 is input into the trained lithium battery aging detection model. The model outputs the corresponding lithium battery aging degree. According to the evaluation results, the aging status of the battery can be timely understood. The lithium battery aging threshold is set according to the actual aging degree indicators of the lithium battery, such as capacity decay rate, internal resistance growth rate, etc. When the lithium battery aging degree corresponding to the model output is greater than or equal to the set lithium battery aging threshold, it is determined that the corresponding lithium battery has aged. When the lithium battery aging degree corresponding to the model output is less than the set lithium battery aging threshold, it is determined that the corresponding lithium battery has not aged.

[0031] In addition, to achieve the above-mentioned purpose, the present invention further proposes a lithium battery aging detection system, which includes:

[0032] Lithium battery operating parameter acquisition module: used to collect lithium battery operating parameters, including voltage, current, and temperature, through sensors during the normal operation of the lithium battery. It also obtains the charge and discharge rates by monitoring the control signals in the battery management system (BMS). It dynamically monitors the parameters to obtain changes in the lithium battery under different operating conditions.

[0033] Fusion lithium battery operating parameter feature vector acquisition module: used to group the collected lithium battery operating parameters according to the set time interval, and the parameters in each time interval form a fusion lithium battery operating parameter feature vector;

[0034] Electrochemical impedance spectrum and fusion feature set acquisition module: used to measure the electrochemical impedance spectrum of the lithium battery at different states of charge using an electrochemical workstation to obtain the electrochemical impedance spectrum, extract the electrochemical impedance spectrum features, and fuse them with the fusion lithium battery operating parameter feature vector to obtain the fusion feature set;

[0035] Lithium battery aging detection model construction and detection module: used to build a lithium battery aging detection model based on machine learning algorithm, take the fusion feature set as input, output the corresponding lithium battery aging degree assessment result, set the lithium battery aging degree threshold, and when the output lithium battery aging degree is greater than or equal to the set threshold, send an aging signal and prompt to replace the lithium battery or take corresponding maintenance measures to ensure the normal operation and safe use of the equipment.

[0036] In addition, to achieve the above-mentioned purpose, the present invention also proposes a lithium battery aging detection device, which includes: a memory, a processor, and programs such as a lithium battery aging detection algorithm stored in the memory and capable of running on the processor. The programs such as the lithium battery aging detection algorithm are steps for implementing a lithium battery aging detection method as described above.

[0037] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer program product, which includes programs such as a lithium battery aging detection algorithm. When the programs such as the lithium battery aging detection algorithm are executed by a processor, a lithium battery aging detection method as described above is implemented.

[0038] The advantages and effects of the present invention are:

[0039] The present invention proposes a lithium battery aging detection method and system. Based on multi-parameter dynamic monitoring and electrochemical impedance spectroscopy feature analysis, it integrates information such as voltage, current, temperature, and charge and discharge rate, and combines it with electrochemical impedance spectroscopy data feature analysis to capture aging characteristics from multiple dimensions of the battery's working state and internal electrochemical process. In the feature extraction and fusion stage, principal component analysis is optimized to make aging detection more accurate, effectively avoid misjudgment, and provide a reliable basis for battery maintenance and replacement. In addition, combined with an efficient machine learning algorithm, it can quickly process data and evaluate the degree of lithium battery aging, significantly shortening detection time, reducing manpower and equipment resource consumption, improving detection efficiency, and reducing detection costs in large-scale battery pack detection scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 The present invention is a flow chart of a lithium battery aging detection method.

[0042] Figure 2 The figure is a structural diagram of a lithium battery aging detection system of the present invention.

[0043] Figure 3 This is a schematic block diagram of the structure of an electronic device for detecting aging of a lithium battery according to the present invention. DETAILED DESCRIPTION

[0044] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0045] like Figure 1 As shown, in one embodiment of the present invention, a lithium battery aging detection method includes the following steps:

[0046] Step S10: During the normal operation of the lithium battery, the operating parameters of the lithium battery, including voltage, current and temperature, are collected through sensors. The charge and discharge rates are obtained by monitoring the control signals in the battery management system (BMS). The parameters are dynamically monitored to obtain changes in the lithium battery under different operating conditions.

[0047] Specifically, in step S10, the operating parameters of the lithium battery are collected through sensors, and a high-precision current sensor is connected in series in the working circuit of the lithium battery to measure the charge and discharge current of the lithium battery; a high-resolution voltage sensor is connected in parallel at the positive and negative terminals of the lithium battery to monitor the lithium battery voltage in real time; a temperature sensor is installed at a suitable position on the lithium battery casing or inside to obtain the temperature information of the lithium battery, and the data collected by these sensors is transmitted to the host computer through a data acquisition card for storage and processing. The data acquisition frequency is set according to actual needs. For example, when the battery working state changes rapidly, the acquisition frequency can be set to once per second; when the working state is relatively stable, it can be reduced to once every 10 seconds.

[0048] Step S20: Grouping the collected lithium battery operating parameters according to set time intervals, and the parameters in each time interval form a fused lithium battery operating parameter feature vector.

[0049] Specifically, in step S20, the collected lithium battery operating parameters are grouped according to a set time interval, and the steps include:

[0050] Set time interval: Set the time interval to 1 minute. Within the set 1 minute, the collected lithium battery voltage, current, temperature data and charge and discharge rate will be statistically analyzed;

[0051] Feature calculation: Calculate parameters such as the average voltage, average current, voltage fluctuation range, current fluctuation range, maximum temperature, minimum temperature, and temperature change rate within a 1-minute time interval. For the charge and discharge rate, record the maximum charge and discharge rate, minimum charge and discharge rate, and the number of charge and discharge rate changes within a 1-minute time interval. Traverse each minute within the sampling time to obtain n lithium battery operating parameter feature vectors within 1-minute time intervals;

[0052] Fusion lithium battery operating parameter characteristics: The characteristic parameters calculated within a 1-minute time interval are combined in a certain order to obtain a fusion lithium battery operating parameter characteristic vector within a 1-minute time interval. For example, according to the arrangement order of [average voltage, average current, voltage fluctuation range, current fluctuation range, maximum temperature, minimum temperature, temperature change rate, maximum charge and discharge rate, minimum charge and discharge rate, number of charge and discharge rate changes], every minute within the sampling time is traversed to obtain n fusion lithium battery operating parameter characteristic vectors within 1-minute time intervals.

[0053] Step S30: placing the lithium battery in different states of charge, performing electrochemical impedance spectroscopy on the battery using an electrochemical workstation to obtain an electrochemical impedance spectrum, extracting electrochemical impedance spectrum features, and fusing them with the fusion lithium battery operating parameter feature vector to obtain a fusion feature set.

[0054] Specifically, in step S30, the electrochemical impedance spectroscopy of the battery is measured using an electrochemical workstation to obtain an electrochemical impedance spectrum, which includes:

[0055] Measurement preparation: Select a suitable electrochemical workstation and ensure that its performance meets the measurement requirements. Perform calibration and preheating. Prepare the test fixture and wires for connecting the lithium battery to ensure reliable connections and good contact. Fully charge the lithium battery to be tested. According to the preset discharge strategy, discharge the lithium battery to a state of charge (SOC) of 20%, 50%, and 80%. At each target SOC state, let the lithium battery stand for a period of time (e.g., 30 minutes) to allow the battery to reach a stable state and reduce measurement errors.

[0056] Connect the lithium battery to the electrochemical workstation: Correctly connect the positive and negative electrodes of the lithium battery at the target SOC state to the corresponding electrode interfaces of the electrochemical workstation. Usually, the working electrode (WE) is connected to the positive electrode of the battery, and the reference electrode (RE) and the counter electrode (CE) are short-circuited before connecting to the negative electrode of the battery. Be careful to avoid short circuits and false connections during the connection process. After the connection is completed, check the stability of the connection again.

[0057] Set measurement parameters: In the electrochemical workstation's operating software, set the parameters for electrochemical impedance spectroscopy measurement. Set the measurement frequency range to 0.01Hz-10kHz, which covers the main electrochemical processes within the lithium battery. Set the AC excitation signal amplitude to 5mV, which not only ensures the accuracy of the measurement signal but also does not significantly interfere with the electrochemical balance within the lithium battery. Set other parameters such as the number of measurement points and measurement time according to actual needs to ensure sufficient and accurate data.

[0058] Measurement and recording: After confirming that all parameters are set correctly, start the measurement program of the electrochemical workstation. During the measurement process, keep the measurement environment stable and avoid external interference, such as electromagnetic interference and temperature fluctuations. The electrochemical workstation applies sinusoidal AC signals of different frequencies in the set frequency range and collects the impedance response data of the battery at the corresponding frequency, including real impedance (reflecting resistance characteristics) and imaginary impedance (reflecting capacitance and inductance characteristics). Draw the electrochemical impedance spectrum based on the impedance response data and export and save it from the electrochemical workstation. The data storage format should be convenient for subsequent analysis and processing, such as commonly used image file formats (.jpg) or formats supported by data processing software (such as .opj format of Origin software). At the same time, mark the electrochemical impedance spectrum and indicate key information such as the SOC state of the lithium battery and measurement time during the measurement to facilitate subsequent data collation and comparative analysis;

[0059] Repeated measurement and verification: To ensure the reliability and accuracy of the measurement data, the lithium battery in the same SOC state is measured multiple times, such as 3 times, and the repeatability and consistency of the measurement data are checked each time. When the data differs greatly, the cause is analyzed and re-measured, such as checking whether the connection is loose and whether the battery is stable. The measurement and verification are completed according to the above steps for batteries in different SOC states (20%, 50% and 80%).

[0060] Specifically, the steps of extracting electrochemical impedance spectroscopy features and fusing them with the fusion lithium battery operating parameter feature vector to obtain a fusion feature set in step S30 include:

[0061] Electrochemical impedance spectroscopy feature extraction: Extract key characteristic parameters such as charge transfer resistance Rct, Warburg impedance Zw, and double layer capacitance Cdl from electrochemical impedance spectroscopy.

[0062] Feature fusion: fusing the fused lithium battery operating parameter feature vector obtained in step S20 with the electrochemical impedance spectroscopy feature parameters to obtain a fused feature set. For example, the chemical impedance spectroscopy feature parameters are added to the end of the fused lithium battery operating parameter feature vector in a certain order to form a fused feature set that includes the lithium battery operating state and the internal electrochemical characteristics of the lithium battery.

[0063] Data processing: The obtained fusion feature set is standardized so that each feature in the fusion feature set has zero mean and unit variance, ensuring the consistency of weights of different features in subsequent analysis and avoiding deviations caused by different feature dimensions; after data standardization, the covariance matrix is calculated. The covariance matrix can reflect the correlation between different features. The covariance matrix is eigendecomposed to calculate its eigenvalues and eigenvectors. The eigenvalues reflect the variance contribution of each principal component, and the eigenvectors reflect the direction of the principal component. The eigenvalues and corresponding eigenvectors are sorted in descending order of the eigenvalues. The principal components are selected according to the cumulative contribution rate. Usually, the principal components with a cumulative contribution rate of more than 90% are selected. For example, when the cumulative contribution rate of the current m principal components meets the requirements, these m principal components are retained. The eigenvectors corresponding to the selected principal components are used. According to the calculated eigenvalues and eigenvectors, the original fusion feature set is linearly transformed to reconstruct the data to obtain the fusion feature set after dimensionality reduction. While retaining the main information, the data dimension is reduced, thereby improving the efficiency and accuracy of subsequent analysis.

[0064] Step S40: Build a lithium battery aging detection model based on the machine learning algorithm, take the fusion feature set as input, output the corresponding lithium battery aging degree assessment result, set the lithium battery aging degree threshold, and when the output lithium battery aging degree is greater than or equal to the set threshold, send an aging signal and prompt to replace the lithium battery or take corresponding maintenance measures to ensure the normal operation and safe use of the equipment.

[0065] Specifically, the step of constructing a lithium battery aging detection model based on a machine learning algorithm in step S40 includes:

[0066] Training sample collection: Training samples are obtained by testing and monitoring lithium batteries from different batches, different usage times, and different charge and discharge cycle times;

[0067] Lithium battery aging detection model construction and training: using machine learning algorithms, such as support vector machines (SVM), neural networks (NN), etc., with the fusion feature set obtained in step S30 as input and the actual aging degree of the lithium battery (such as capacity decay rate, internal resistance growth rate, etc.) as output, a lithium battery aging prediction model is established, and the training samples obtained in the training sample collection step are used to train and optimize the model so that the model learns the mapping relationship between the fusion features and the aging degree of the lithium battery. For example, a neural network model with an input layer, a hidden layer, and an output layer is constructed. The number of input layer nodes is determined according to the dimension of the fusion feature set. For example, if the fusion feature set contains 15 feature parameters, the number of input layer nodes is 15; the hidden layer is set to 2-3 layers, and the number of nodes in each layer is adjusted according to experience and actual conditions, generally between 10-50; the number of output layer nodes is 1, which is used to output the aging degree of the battery;

[0068] Lithium battery aging detection: The fusion feature set obtained in step S30 is input into the trained lithium battery aging detection model. The model outputs the corresponding lithium battery aging degree. According to the evaluation results, the aging status of the battery can be timely understood. The lithium battery aging threshold is set according to the actual aging degree indicators of the lithium battery, such as capacity decay rate, internal resistance growth rate, etc. When the lithium battery aging degree corresponding to the model output is greater than or equal to the set lithium battery aging threshold, it is determined that the corresponding lithium battery has aged. When the lithium battery aging degree corresponding to the model output is less than the set lithium battery aging threshold, it is determined that the corresponding lithium battery has not aged.

[0069] In addition, if Figure 2 As shown, in one embodiment of the present invention, a lithium battery aging detection system is provided, and the lithium battery aging detection system includes:

[0070] Lithium battery operating parameter acquisition module: used to collect lithium battery operating parameters, including voltage, current, and temperature, through sensors during the normal operation of the lithium battery. It also obtains the charge and discharge rates by monitoring the control signals in the battery management system (BMS). It dynamically monitors the parameters to obtain changes in the lithium battery under different operating conditions.

[0071] Fusion lithium battery operating parameter feature vector acquisition module: used to group the collected lithium battery operating parameters according to the set time interval, and the parameters in each time interval form a fusion lithium battery operating parameter feature vector;

[0072] Electrochemical impedance spectrum and fusion feature set acquisition module: used to measure the electrochemical impedance spectrum of the lithium battery at different states of charge using an electrochemical workstation to obtain the electrochemical impedance spectrum, extract the electrochemical impedance spectrum features, and fuse them with the fusion lithium battery operating parameter feature vector to obtain the fusion feature set;

[0073] Lithium battery aging detection model construction and detection module: used to build a lithium battery aging detection model based on machine learning algorithm, take the fusion feature set as input, output the corresponding lithium battery aging degree assessment result, set the lithium battery aging degree threshold, and when the output lithium battery aging degree is greater than or equal to the set threshold, send an aging signal and prompt to replace the lithium battery or take corresponding maintenance measures to ensure the normal operation and safe use of the equipment.

[0074] The present application provides a lithium battery aging detection system that utilizes a lithium battery aging detection method described in the aforementioned embodiment, capable of resolving the technical issues of low detection efficiency and accuracy associated with conventional lithium battery aging detection methods. Compared to the prior art, the present application provides the same beneficial effects as the lithium battery aging detection method described in the aforementioned embodiment. Other technical features of the present application are the same as those disclosed in the aforementioned embodiment and are not further elaborated upon here.

[0075] The present application provides a lithium battery aging detection device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform a lithium battery aging detection method in the above-mentioned embodiment 1.

[0076] like Figure 3 As shown, in one embodiment of the present invention, a schematic diagram of the structure of a lithium battery aging detection device suitable for implementing the embodiments of the present application is shown. A lithium battery aging detection device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), etc., as well as fixed terminals such as digital TVs and desktop computers. Figure 3 The lithium battery aging detection device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0077] Figure 3The illustrated lithium battery aging detection device may include a processing system 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage system 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the lithium battery aging detection device. Processing system 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to I / O interface 1006: an input system 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; an output system 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; a storage system 1003 including, for example, a magnetic tape, hard disk, etc.; and a communication system 1009. Communication system 1009 can allow a lithium battery aging detection device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a lithium battery aging detection device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have alternatively.

[0078] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication system, or installed from a storage system 1003, or installed from a ROM 1002. When the computer program is executed by the processing system 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0079] The present application provides a lithium battery aging detection device that utilizes a lithium battery aging detection method described in the aforementioned embodiment, capable of resolving the technical issues of low detection efficiency and accuracy associated with conventional lithium battery aging detection methods. Compared to the prior art, the present application provides the same beneficial effects as the lithium battery aging detection method described in the aforementioned embodiment, and the other technical features of the present application are the same as those disclosed in the aforementioned embodiment, and are not further elaborated upon here.

[0080] The various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any appropriate manner in any one or more embodiments or examples.

[0081] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned lithium battery aging detection method when executed by a processor.

[0082] The computer program product provided in this application can address the technical issues of low efficiency and accuracy in conventional lithium battery aging detection methods. Compared to the prior art, the beneficial effects of the computer program product provided in this application are similar to those of the lithium battery aging detection method provided in the aforementioned embodiment, and are not further elaborated here.

[0083] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A lithium battery aging detection method, characterized in that: The method comprises the following steps: Step S10: During normal operation of the lithium battery, the operating parameters of the lithium battery, including voltage, current, and temperature, are collected through sensors. The charge and discharge rates are obtained by monitoring the control signals in the battery management system (BMS). The parameters are dynamically monitored to obtain changes in the lithium battery under different operating conditions. Step S20: grouping the collected lithium battery operating parameters according to the set time intervals, and forming a fused lithium battery operating parameter feature vector with the parameters in each time interval; Step S30: placing the lithium battery at different states of charge, performing electrochemical impedance spectroscopy on the battery using an electrochemical workstation to obtain an electrochemical impedance spectrum, extracting features from the electrochemical impedance spectrum, and fusing them with a fusion lithium battery operating parameter feature vector to obtain a fusion feature set; Step S40: Build a lithium battery aging detection model based on a machine learning algorithm, take the fused feature set as input, output the corresponding lithium battery aging degree assessment result, set the lithium battery aging degree threshold, and when the output lithium battery aging degree is greater than or equal to the set threshold, send an aging signal and prompt to replace the lithium battery or take corresponding maintenance measures.

2. A lithium battery aging detection method according to claim 1, characterized in that: In step S10, the operating parameters of the lithium battery are collected through sensors, a current sensor is connected in series in the working circuit of the lithium battery to measure the charge and discharge current of the lithium battery; a voltage sensor is connected in parallel at the positive and negative terminals of the lithium battery to monitor the lithium battery voltage in real time; and a temperature sensor is installed in the outer shell or inside the lithium battery to obtain the temperature information of the lithium battery.

3. The lithium battery aging detection method according to claim 1, characterized in that: The step S20 groups the collected lithium battery operating parameters according to a set time interval, and the steps include: Set time interval: Set the time interval to 1 minute. Within the set 1 minute, the collected lithium battery voltage, current, temperature data and charge and discharge rate will be statistically analyzed; Feature calculation: Calculate the average voltage, average current, voltage fluctuation range, current fluctuation range, maximum temperature, minimum temperature, and temperature change rate parameters within a 1-minute time interval. For the charge and discharge rate, record the maximum charge and discharge rate, minimum charge and discharge rate, and the number of charge and discharge rate changes within a 1-minute time interval. Traverse each minute within the sampling time to obtain n lithium battery operating parameter feature vectors within 1-minute time intervals; Fusion lithium battery operating parameter characteristics: The characteristic parameters calculated within a 1-minute time interval are combined in a certain order to obtain a fusion lithium battery operating parameter characteristic vector within a 1-minute time interval. Each minute within the sampling time is traversed to obtain n fusion lithium battery operating parameter characteristic vectors within a 1-minute time interval.

4. A lithium battery aging detection method according to claim 1, characterized in that: In step S30, the electrochemical impedance spectroscopy (EIS) of the battery is measured using an electrochemical workstation to obtain an EIS graph, which includes: Measurement preparation: Select a suitable electrochemical workstation, calibrate and preheat it, prepare the test fixture and wires for connecting the lithium battery, fully charge the lithium battery to be tested, and discharge the lithium battery to a state of charge (SOC) of 20%, 50%, and 80% according to the preset discharge strategy. Let the lithium battery rest for a period of time at each target SOC state. Connect the lithium battery to the electrochemical workstation: Correctly connect the positive and negative electrodes of the lithium battery at the target SOC state to the corresponding electrode interfaces of the electrochemical workstation; Set measurement parameters: In the operating software of the electrochemical workstation, set the parameters for electrochemical impedance spectroscopy measurement. Set the number of measurement points and measurement time according to actual needs. Measurement and recording: After confirming that all parameters are set correctly, start the measurement program of the electrochemical workstation. During the measurement process, keep the measurement environment stable. The electrochemical workstation applies sinusoidal AC signals of different frequencies in the set frequency range and collects the impedance response data of the battery at the corresponding frequency, including real impedance and imaginary impedance. Draw the electrochemical impedance spectrum based on the impedance response data, export it from the electrochemical workstation, and save it. At the same time, mark the electrochemical impedance spectrum to indicate the SOC state of the lithium battery and the measurement time during the measurement; Repeated measurement and verification: Perform multiple measurements on lithium batteries at the same SOC state and check the repeatability and consistency of the measurement data each time. Follow the above steps to complete measurement and verification for batteries at different SOC states.

5. The lithium battery aging detection method according to claim 1, characterized in that: The steps of extracting electrochemical impedance spectroscopy features and fusing them with the fusion lithium battery operating parameter feature vector to obtain a fusion feature set in step S30 include: Electrochemical impedance spectroscopy feature extraction: Extract the characteristics of the electrochemical impedance spectroscopy to extract the characteristic parameters of charge transfer resistance Rct, Warburg impedance Zw and double layer capacitance Cdl; Feature fusion: fusing the fusion lithium battery operating parameter feature vector obtained in step S20 with the electrochemical impedance spectroscopy feature parameters to obtain a fusion feature set; Data processing: The obtained fusion feature set is standardized so that each feature in the fusion feature set has zero mean and unit variance. After data standardization, the covariance matrix is calculated, and the covariance matrix is decomposed to calculate its eigenvalues and eigenvectors. According to the calculated eigenvalues and eigenvectors, the fusion feature set is linearly transformed and the data is reconstructed to obtain the fusion feature set after dimensionality reduction.

6. A lithium battery aging detection method according to claim 1, characterized in that: The step of constructing a lithium battery aging detection model based on a machine learning algorithm in step S40 includes: Training sample collection: Training samples are obtained by testing and monitoring lithium batteries from different batches, different usage times, and different charge and discharge cycle times; Lithium battery aging detection model construction and training: Using a machine learning algorithm, with the fused feature set obtained in step S30 as input and the actual aging degree of the lithium battery as output, a lithium battery aging prediction model is established. The model is trained and optimized using the training samples obtained in the training sample collection step, so that the model learns the mapping relationship between the fused features and the aging degree of the lithium battery; Lithium battery aging detection: The fusion feature set obtained in step S30 is input into the trained lithium battery aging detection model. The model outputs the corresponding lithium battery aging degree. The lithium battery aging threshold is set according to the actual aging degree index of the lithium battery. When the lithium battery aging degree corresponding to the model output is greater than or equal to the set lithium battery aging threshold, the corresponding lithium battery is determined to have aged. When the lithium battery aging degree corresponding to the model output is less than the set lithium battery aging threshold, the corresponding lithium battery is determined to have not aged.

7. A lithium battery aging detection system, characterized in that: The lithium battery aging detection system comprises: Lithium battery operating parameter acquisition module: used to collect lithium battery operating parameters, including voltage, current, and temperature, through sensors during the normal operation of the lithium battery. It also obtains the charge and discharge rates by monitoring the control signals in the battery management system (BMS). It dynamically monitors the parameters to obtain changes in the lithium battery under different operating conditions. Fusion lithium battery operating parameter feature vector acquisition module: used to group the collected lithium battery operating parameters according to the set time interval, and the parameters in each time interval form a fusion lithium battery operating parameter feature vector; Electrochemical impedance spectrum and fusion feature set acquisition module: used to measure the electrochemical impedance spectrum of the lithium battery at different states of charge using an electrochemical workstation to obtain the electrochemical impedance spectrum, extract the electrochemical impedance spectrum features, and fuse them with the fusion lithium battery operating parameter feature vector to obtain the fusion feature set; Lithium battery aging detection model construction and detection module: used to build a lithium battery aging detection model based on machine learning algorithm, take the fusion feature set as input, output the corresponding lithium battery aging degree assessment result, set the lithium battery aging degree threshold, and when the output lithium battery aging degree is greater than or equal to the set threshold, send an aging signal and prompt to replace the lithium battery or take corresponding maintenance measures.

8. A lithium battery aging detection device, characterized in that: The lithium battery aging detection device comprises: A memory, a processor, and a lithium battery aging detection program stored in the memory and executable on the processor, wherein the lithium battery aging detection program, when executed by the processor, implements a lithium battery aging detection method according to any one of claims 1 to 6.

9. A computer program product, characterized in that The computer program product includes a lithium battery aging detection program, which, when executed by a processor, implements a lithium battery aging detection method according to any one of claims 1 to 6.

Images