Lithium battery life prediction method and device based on data analysis

Abstract

The invention discloses a lithium battery life prediction method and device based on data analysis. The method comprises the following steps: acquiring charging current, discharging current, battery voltage and timestamps of recorded data of each complete charging and discharging cycle; performing data analysis according to the charging current, the discharging current and the timestamp, and constructing a charging and discharging current sequence; performing voltage fluctuation amplitude analysis according to the timestamp, the charging and discharging current sequence and the battery voltage to obtain a voltage jump characteristic; performing fluctuation characteristic analysis according to the voltage abrupt change characteristic to obtain a voltage fluctuation characteristic; performing correlation analysis according to the charging and discharging current sequence to obtain an optimal charging and discharging current sequence; calculating a voltage attenuation factor according to the voltage fluctuation characteristics and the optimal charging and discharging current sequence; and according to the optimal charging and discharging current sequence and the voltage attenuation factor, constructing a life prediction model, and according to the life prediction model, calculating the residual cycle index, the future battery voltage and the battery life. The method can accurately predict the service life of the lithium battery.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a method and device for predicting the life of a lithium battery based on data analysis. Background Art

[0002] At present, lithium batteries, as an efficient chemical energy storage device, play a vital role in many fields of modern society. From portable electronic devices to electric vehicles to large-scale energy storage systems, lithium batteries are almost everywhere. Its high energy density, long cycle life and relatively low self-discharge rate make it one of the most popular energy storage solutions. However, with the expansion of the application scope of lithium batteries, the requirements for their performance are becoming more and more stringent. In particular, the cycle stability and life of lithium batteries are directly related to product safety and user cost. The capacity of the battery will inevitably decay during long-term use, which not only affects the efficiency of the battery, but also may lead to potential safety risks such as overheating or explosion. Therefore, accurately predicting the life of lithium batteries is of great significance for optimizing the battery management system (BMS), extending the battery life, reducing maintenance costs and reducing environmental pollution.

[0003] In the evaluation of the state of health (SOH) and remaining useful life (RUL) of lithium batteries, the method based on the change of direct current internal resistance (DCR) provides an effective and intuitive technical approach. First, an accurate initial DCR baseline value is established after the battery is first enabled or fully restored as the basis for subsequent analysis. As the battery is used, various operating parameters including temperature, voltage, and current are collected in real time through the online monitoring system, and the DCR is automatically measured at the end of each charge and discharge cycle. These data are compared with the initial baseline value to identify the resistance growth trend caused by aging. Using a specially designed data processing algorithm, the collected data is deeply analyzed, which can not only compare the DCR differences at different time points, but also predict the future DCR change trend in combination with a machine learning model, and then estimate the aging rate of the battery. According to the change in DCR and the preset aging model, the current battery health state is calculated, and a threshold is defined to determine whether the battery has entered the aging stage. In addition, a statistical method is used to predict the remaining life of the battery based on the existing DCR change rate and other variables.

[0004] However, the existing methods for predicting the health status and remaining service life of lithium batteries based on direct current resistance (DCR) mainly rely on the DCR value obtained through charging and discharging equipment testing to predict battery life. This ignores the storage time and working status differences of the battery and cannot accurately capture the actual aging process of the battery, resulting in inaccurate prediction results and difficulty in truly reflecting the actual life of the lithium battery. Summary of the invention

[0005] The present invention provides a lithium battery life prediction method and device based on data analysis, so as to achieve accurate prediction of lithium battery life.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a lithium battery life prediction method based on data analysis, comprising: Obtain the charge current, discharge current, battery voltage and timestamp of the recorded data for each complete charge and discharge cycle; Perform data analysis according to the charging current, the discharging current and the timestamp to construct a charging and discharging current sequence; Perform voltage fluctuation amplitude analysis according to the timestamp, the charge and discharge current sequence and the battery voltage to obtain voltage mutation characteristics; Performing fluctuation characteristic analysis according to the voltage mutation characteristics to obtain voltage fluctuation characteristics; Performing correlation analysis on the charge and discharge current sequence to obtain an optimal charge and discharge current sequence; Calculating a voltage attenuation factor according to the voltage fluctuation characteristics and the optimal charge and discharge current sequence; A life prediction model is constructed according to the optimal charge and discharge current sequence and the voltage attenuation factor, and the remaining number of cycles, future battery voltage and battery life are calculated according to the life prediction model.

[0007] In an optional implementation, performing data analysis according to the charging current, the discharging current and the timestamp to construct a charging and discharging current sequence includes: Calculate the time interval between adjacent timestamps, and compare the time interval with a preset time window. If the time interval is smaller than the time window, determine that the corresponding charging current and discharging current are invalid data. If the time interval is greater than the time window, the charging current and the discharging current are determined to be valid data; All the valid data are combined to construct a charge and discharge current sequence.

[0008] In an optional implementation, the performing voltage fluctuation amplitude analysis according to the timestamp, the charge and discharge current sequence and the battery voltage to obtain a voltage mutation feature includes: Recording the battery voltage corresponding to the charge and discharge current sequence as the standard voltage; Perform a difference operation on the standard voltages at adjacent time stamps to obtain the voltage fluctuation amplitude; Comparing the voltage fluctuation amplitude with a preset voltage fluctuation threshold, and if the voltage fluctuation amplitude is less than the voltage fluctuation threshold, determining the voltage fluctuation amplitude as invalid fluctuation data; If the voltage fluctuation amplitude is greater than the voltage fluctuation threshold, determining the voltage fluctuation amplitude as valid fluctuation data; Sorting and combining all the valid fluctuation data according to corresponding timestamps to form a voltage fluctuation amplitude sequence; The voltage fluctuation amplitudes of adjacent time stamps in the voltage fluctuation amplitude sequence are subjected to a difference operation, and all the difference results are sorted and combined to obtain a voltage mutation feature.

[0009] In an optional implementation, performing fluctuation characteristic analysis according to the voltage mutation characteristic to obtain the voltage fluctuation characteristic includes: Applying wavelet transform to process the timestamp corresponding to the voltage mutation feature to obtain an approximate wavelet coefficient sequence; Multiplying the approximate wavelet coefficient sequence with the voltage mutation characteristic to obtain an optimal fluctuation sequence; The mutation characteristic is calculated based on the optimal fluctuation sequence to obtain the voltage fluctuation characteristic.

[0010] In an optional implementation, performing correlation analysis on the charge and discharge current sequence to obtain an optimal charge and discharge current sequence includes: Calculate the correlation coefficient between the charging current and discharging current at any time stamp in the charging and discharging current sequence of each charging and discharging cycle and the charging current and discharging current at other times in the same sequence; Selecting the charge and discharge current sequence with the largest correlation coefficient as the optimal charge and discharge current sequence; The correlation coefficient is calculated by the following formula: In the formula, Indicates the time interval is The correlation coefficient between the charge and discharge current series, Indicates the first The charging or discharging current of each time stamp, Indicates The time interval between timestamps is The charging current or discharging current, represents the number of timestamps in the charge and discharge current sequence, Indicates the time interval between two corresponding timestamps. Indicates the average value of the charging current or discharging current.

[0011] In an optional implementation, the calculating the voltage attenuation factor according to the voltage fluctuation characteristics and the optimal charge and discharge current sequence includes: Add a preset time interval to each timestamp in the optimal charge and discharge current sequence to obtain a future time; Using the charging current and discharging current in the optimal charging and discharging current sequence as the future charging current and future discharging current corresponding to the future moment; According to the future charging current, the future discharging current and the voltage fluctuation characteristics, a voltage attenuation factor at a future moment is calculated by linear regression analysis; Among them, the voltage attenuation factor is calculated by the following formula: in, Indicates future time The voltage attenuation factor is Indicates future time The charging current or discharging current, Indicates the pre-stored voltage attenuation factor at the current moment, Indicates the voltage fluctuation characteristics, and Represents the pre-stored linear regression coefficients.

[0012] In an optional implementation, the constructing a life prediction model according to the optimal charge and discharge current sequence and the voltage attenuation factor, and calculating the future battery voltage, the remaining number of cycles and the battery life according to the life prediction model, includes: The life expectancy model is as follows: in, Indicates the next moment to the future moment The number of moments, Indicates future time The voltage attenuation factor is represents the maximum current in the optimal charge and discharge current sequence, Indicates the battery voltage at the current moment, Indicates the voltage fluctuation characteristics, Indicates future time The future battery voltage, Indicates future time The remaining number of cycles, Indicates future time battery life.

[0013] In a second aspect, the present invention provides a lithium battery life prediction device based on data analysis, comprising: A data acquisition module is used to obtain the charging current, discharging current, battery voltage and the timestamp of the recorded data for each complete charge and discharge cycle; A current sequence construction module, used for performing data analysis according to the charging current, the discharging current and the timestamp to construct a charging and discharging current sequence; A voltage mutation analysis module, used to analyze the voltage fluctuation amplitude according to the timestamp, the charge and discharge current sequence and the battery voltage to obtain voltage mutation characteristics; A voltage fluctuation analysis module, used to perform fluctuation characteristic analysis according to the voltage mutation characteristics to obtain voltage fluctuation characteristics; An optimal sequence analysis module, used to perform correlation analysis according to the charge and discharge current sequence to obtain an optimal charge and discharge current sequence; An attenuation factor calculation module, used to calculate a voltage attenuation factor according to the voltage fluctuation characteristics and the optimal charge and discharge current sequence; A life prediction module is used to construct a life prediction model according to the optimal charge and discharge current sequence and the voltage attenuation factor, and calculate the remaining number of cycles, future battery voltage and battery life according to the life prediction model. In a third aspect, the present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, any one of the above-mentioned lithium battery life prediction methods based on data analysis is implemented.

[0014] In a fourth aspect, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned lithium battery life prediction methods based on data analysis.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses a lithium battery life prediction method based on data analysis, comprising obtaining the charging current, discharging current, battery voltage and the timestamp of recording data of each complete charge and discharge cycle; performing data analysis according to the charging current, the discharging current and the timestamp to construct a charge and discharge current sequence; performing voltage fluctuation amplitude analysis according to the timestamp, the charge and discharge current sequence and the battery voltage to obtain voltage mutation characteristics; performing fluctuation characteristic analysis according to the voltage mutation characteristics to obtain voltage fluctuation characteristics; performing correlation analysis according to the charge and discharge current sequence to obtain an optimal charge and discharge current sequence; calculating a voltage attenuation factor according to the voltage fluctuation characteristics and the optimal charge and discharge current sequence; constructing a life prediction model according to the optimal charge and discharge current sequence and the voltage attenuation factor, and calculating the remaining number of cycles, future battery voltage and battery life according to the life prediction model. The present invention collects the charging current, discharging current, battery voltage and timestamp in each complete charge and discharge cycle of the lithium battery, then constructs a charging and discharging current sequence based on these data and analyzes the voltage mutation characteristics and voltage fluctuation characteristics, and performs correlation analysis to determine the optimal charging and discharging current sequence. According to the analysis results, the voltage attenuation factor is calculated and a life prediction model is constructed to predict the battery life, thereby achieving accurate prediction of the lithium battery life. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the flow of a lithium battery life prediction method based on data analysis provided by the first embodiment of the present invention; Figure 2 It is a schematic diagram of the structure of a lithium battery life prediction device based on data analysis provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0018] Reference Figure 1 The first embodiment of the present invention provides a lithium battery life prediction method based on data analysis, comprising the following steps: S11, obtaining the charging current, discharging current, battery voltage and the timestamp of the recorded data for each complete charge and discharge cycle; S12, performing data analysis according to the charging current, the discharging current and the timestamp to construct a charging and discharging current sequence; S13, performing voltage fluctuation amplitude analysis according to the timestamp, the charge and discharge current sequence and the battery voltage to obtain voltage mutation characteristics; S14, performing fluctuation characteristic analysis according to the voltage mutation characteristic to obtain voltage fluctuation characteristics; S15, performing correlation analysis according to the charge and discharge current sequence to obtain an optimal charge and discharge current sequence; S16, calculating a voltage attenuation factor according to the voltage fluctuation characteristics and the optimal charge and discharge current sequence; S17, constructing a life prediction model according to the optimal charge and discharge current sequence and the voltage attenuation factor, and calculating the remaining number of cycles, future battery voltage and battery life according to the life prediction model.

[0019] In step S11, the charging current, discharging current, battery voltage and the timestamp of the recorded data of each complete charge and discharge cycle are obtained.

[0020] First, the data of charging current and discharging current are obtained by current sensors installed in the battery charging and discharging circuit. These sensors are Hall effect sensors or shunts that can accurately measure the current intensity passing through the battery and transmit the data to the battery management system (BMS). For the monitoring of battery voltage, it relies on voltage sensors, which are usually directly connected to the positive and negative poles of the battery to ensure that the battery voltage level at each moment can be accurately measured. The timestamp is generated by the system's built-in high-precision clock module, which stamps each recorded data with an accurate time stamp to ensure that all data points correspond to a specific point in time.

[0021] In step S12, data analysis is performed based on the charging current, the discharging current and the timestamp to construct a charging and discharging current sequence.

[0022] In a specific implementation, performing data analysis according to the charging current, the discharging current and the timestamp to construct a charging and discharging current sequence includes: Calculate the time interval between adjacent timestamps, and compare the time interval with a preset time window. If the time interval is smaller than the time window, determine that the corresponding charging current and discharging current are invalid data. If the time interval is greater than the time window, the charging current and the discharging current are determined to be valid data; All the valid data are combined to construct a charge and discharge current sequence.

[0023] Specifically, first, the battery management system (BMS) performs adjacent timestamp and Process and calculate the time interval between them : Then, the time interval With preset time window Compare. Preset time window It is a threshold value set based on actual application scenarios, which is used to filter out data loss or inconsistency caused by sensor failure or other abnormal conditions. Less than time window , the corresponding charge current and discharge current data points are considered invalid, because this indicates that there may be data acquisition problems or signal interruptions during this period; conversely, if Greater than , then these current data are determined to be valid data, indicating that the data collection during this period is normal and continuous.

[0024] For example, assuming the preset time window Set to 1 second, and the interval between two adjacent timestamps If the time interval is 0.5 seconds, the charge current and discharge current in this time period are marked as invalid data and will not be included in the final charge and discharge current sequence. If the timeout period is 2 seconds, the corresponding data is considered valid and will be retained.

[0025] After the above screening process, all valid data will be combined to form a complete charge and discharge current sequence. This sequence not only includes the charge current and discharge current at each moment, but also contains the corresponding timestamp information, so that the time dynamics of current changes can be accurately tracked. The charge and discharge current sequence constructed in this way can truly reflect the current fluctuation of the battery throughout the charge and discharge cycle.

[0026] Through strict screening and verification of the original data, the data set used for subsequent analysis is ensured to have high reliability and integrity. Only when the data meets certain continuity and stability standards can the validity and accuracy of subsequent analysis results be guaranteed.

[0027] In step S13, a voltage fluctuation amplitude analysis is performed according to the timestamp, the charge and discharge current sequence and the battery voltage to obtain a voltage mutation feature.

[0028] In a specific implementation, the voltage fluctuation amplitude analysis is performed according to the timestamp, the charge and discharge current sequence and the battery voltage to obtain the voltage mutation feature, including: Recording the battery voltage corresponding to the charge and discharge current sequence as the standard voltage; Perform a difference operation on the standard voltages at adjacent time stamps to obtain the voltage fluctuation amplitude; Comparing the voltage fluctuation amplitude with a preset voltage fluctuation threshold, and if the voltage fluctuation amplitude is less than the voltage fluctuation threshold, determining the voltage fluctuation amplitude as invalid fluctuation data; If the voltage fluctuation amplitude is greater than the voltage fluctuation threshold, determining the voltage fluctuation amplitude as valid fluctuation data; Sorting and combining all the valid fluctuation data according to corresponding timestamps to form a voltage fluctuation amplitude sequence; The voltage fluctuation amplitudes of adjacent time stamps in the voltage fluctuation amplitude sequence are subjected to a difference operation, and all the difference results are sorted and combined to obtain a voltage mutation feature.

[0029] Specifically, the system first records the battery voltage corresponding to the charge and discharge current sequence as the standard voltage These standard voltages are based on actual measurements at different time points in each charge and discharge cycle, ensuring the authenticity and accuracy of the data. Next, the system performs a difference operation on the standard voltages at adjacent timestamps to calculate the voltage fluctuation amplitude. : In the formula, Indicates the timestamp To timestamp The voltage fluctuation amplitude at and Respectively indicated in timestamp and In this way, the system can quantify the voltage variation during each time interval.

[0030] The system then compares these voltage fluctuations with the preset voltage fluctuation thresholds. The preset voltage fluctuation threshold is a parameter set based on experience and experiments to distinguish between normal small fluctuations and large fluctuations that may indicate battery abnormalities. Less than the voltage fluctuation threshold , then the voltage fluctuation is determined to be invalid fluctuation data, because it may be caused by measurement noise or other non-critical factors; on the contrary, if Greater than , it is judged as valid fluctuation data, which indicates that a significant voltage change did occur during this period of time.

[0031] All voltage fluctuation data that are judged to be valid will be sorted and combined according to the corresponding timestamps to form a voltage fluctuation amplitude sequence This sequence not only contains the specific value of each effective voltage fluctuation, but also preserves the time order in which they occur, so that the temporal dynamics of the voltage changes can be tracked.

[0032] In order to further refine the voltage mutation characteristics, the system will perform a difference operation on the voltage fluctuation amplitudes of adjacent timestamps in the voltage fluctuation amplitude sequence, and sort and combine all the difference results. Specifically, for each effective voltage fluctuation amplitude , calculate its fluctuation amplitude with the next effective voltage The difference between : The results of these secondary differences The results are organized into a new sequence called voltage mutation characteristic sequence, which reflects the changing trend of voltage fluctuation amplitude over time, especially those drastic changes that occur in a short period of time.

[0033] The voltage data is screened and analyzed at multiple levels to extract key features that reflect the health status of the battery. Voltage mutation features provide important clues about the battery's operating conditions, such as whether there is overcharging or overdischarging, and whether there is a short circuit risk inside the battery.

[0034] In step S14, a fluctuation characteristic analysis is performed based on the voltage mutation characteristic to obtain a voltage fluctuation characteristic.

[0035] In a specific implementation, performing fluctuation characteristic analysis according to the voltage mutation characteristic to obtain the voltage fluctuation characteristic includes: Applying wavelet transform to process the timestamp corresponding to the voltage mutation feature to obtain an approximate wavelet coefficient sequence; Multiplying the approximate wavelet coefficient sequence with the voltage mutation characteristic to obtain an optimal fluctuation sequence; The mutation characteristic is calculated based on the optimal fluctuation sequence to obtain the voltage fluctuation characteristic.

[0036] Specifically, the system first applies wavelet transform to process the timestamps corresponding to the voltage mutation characteristics to obtain an approximate wavelet coefficient sequence. The original voltage mutation characteristics are decomposed into an approximate wavelet coefficient sequence and a detail wavelet coefficient sequence of different frequency components through the following discrete wavelet transform function: in, Indicates the preset decomposition scale level, represents the approximate wavelet coefficients, represents the detail wavelet coefficients, Indicates the voltage mutation characteristics.

[0037] Next, the system multiplies the obtained approximate wavelet coefficient sequence with the voltage mutation characteristics to obtain the optimal fluctuation sequence. It is expressed by the following formula: In the formula, Represents the timestamp in the optimal volatility sequence The corresponding optimal volatility element, represents the approximate wavelet coefficients, and Then it represents the voltage mutation feature. Through this multiplication operation, the system not only retains the time information of the voltage mutation feature, but also enhances those parts that are identified as important in the wavelet transform, thereby constructing a more representative fluctuation sequence.

[0038] Finally, the mutation characteristic is calculated based on the optimal fluctuation sequence to obtain the final voltage fluctuation characteristic. The voltage fluctuation characteristic is calculated by the following formula: in, Indicates the voltage fluctuation characteristics, represents the number of elements of the optimal volatility sequence, Represents the timestamp in the optimal volatility sequence The corresponding optimal volatility element, Indicates a timestamp.

[0039] By deeply analyzing the voltage mutation characteristics, the system can extract deeper fluctuation characteristics that reflect the complex physical and chemical processes inside the battery. For example, certain specific fluctuation patterns may be associated with the aging mechanism of the battery or indicate an impending failure.

[0040] In step S15, correlation analysis is performed based on the charge and discharge current sequence to obtain an optimal charge and discharge current sequence.

[0041] In a specific implementation, performing correlation analysis on the charge and discharge current sequence to obtain an optimal charge and discharge current sequence includes: Calculate the correlation coefficient between the charging current and discharging current at any time stamp in the charging and discharging current sequence of each charging and discharging cycle and the charging current and discharging current at other times in the same sequence; Selecting the charge and discharge current sequence with the largest correlation coefficient as the optimal charge and discharge current sequence; The correlation coefficient is calculated by the following formula: In the formula, Indicates the time interval is The correlation coefficient between the charge and discharge current series, Indicates the first The charging or discharging current of each time stamp, Indicates The time interval between timestamps is The charging current or discharging current, represents the number of timestamps in the charge and discharge current sequence, Indicates the time interval between two corresponding timestamps. Indicates the average value of the charging current or discharging current.

[0042] Specifically, the system first calculates the correlation coefficient between the charging current and discharging current at any time stamp in the charging and discharging current sequence of each charging and discharging cycle and the charging current and discharging current at other times in the same sequence. Represents the difference between two timestamps and can be a fixed or varying value, used to evaluate current correlation at different time delays.

[0043] Assume there is a charge and discharge current sequence , which includes The current measurement value at each time stamp. , the system will calculate the correlation coefficient as shown in the following formula : In the formula, Indicates the time interval is The correlation coefficient between the charge and discharge current series, Indicates the first The charging or discharging current of each time stamp, Indicates The time interval between timestamps is The charging current or discharging current, represents the number of timestamps in the charge and discharge current sequence, Indicates the time interval between two corresponding timestamps. Indicates the average value of the charging current or discharging current.

[0044] Through the above formula, the system can calculate the current correlation coefficients at different time intervals. These correlation coefficients reflect the similarity of the charge and discharge currents at different time points: a correlation coefficient close to 1 indicates a high positive correlation, close to -1 indicates a high negative correlation, and close to 0 indicates almost no correlation.

[0045] Next, the system compares all the calculated correlation coefficients and selects the charge and discharge current sequence corresponding to the maximum correlation coefficient as the optimal charge and discharge current sequence. Selecting the maximum correlation coefficient means selecting the current patterns that show the strongest consistency and stability at different time points. This pattern not only represents the most typical current behavior during the charge and discharge process, but also reveals the optimal configuration of the internal working state of the battery.

[0046] By performing correlation analysis on the charge and discharge current sequences, the system can identify the current pattern that best reflects the battery's health status and performance characteristics. The optimal charge and discharge current sequence not only provides important clues about the battery's operation, but can also be used to optimize charging strategies, predict battery life, and detect potential problems in advance. For example, if the current in a certain charge and discharge mode always shows high stability, it may be the performance of the battery under optimal working conditions; conversely, if the current fluctuates greatly in certain modes, it may indicate a risk of failure or other abnormal phenomena.

[0047] In step S16, a voltage attenuation factor is calculated according to the voltage fluctuation characteristics and the optimal charge and discharge current sequence.

[0048] In a specific implementation, the calculating the voltage attenuation factor according to the voltage fluctuation characteristics and the optimal charge and discharge current sequence includes: Add a preset time interval to each timestamp in the optimal charge and discharge current sequence to obtain a future time; Using the charging current and discharging current in the optimal charging and discharging current sequence as the future charging current and future discharging current corresponding to the future moment; According to the future charging current, the future discharging current and the voltage fluctuation characteristics, a voltage attenuation factor at a future moment is calculated by linear regression analysis; Among them, the voltage attenuation factor is calculated by the following formula: in, Indicates future time The voltage attenuation factor is Indicates future time The charging current or discharging current, Indicates the pre-stored voltage attenuation factor at the current moment, Indicates the voltage fluctuation characteristics, and Represents the pre-stored linear regression coefficients.

[0049] Specifically, the system first adds a preset time interval to each timestamp in the optimal charge and discharge current sequence to obtain a future moment. The time interval here is set based on the application scenario, for example, it can be a time unit of 1 minute or less, which is used to predict the behavior of the battery in a short period of time in the future. This future moment will serve as the basis for subsequent analysis.

[0050] Next, the system uses the charging current and discharging current in the optimal charging and discharging current sequence as the future charging current and future discharging current corresponding to the future moment. This is because in the short term, the change in the current mode is relatively small, and it can be considered that the current optimal current mode is still applicable in the short term in the future.

[0051] In order to obtain the voltage attenuation factor at a future time, the system uses linear regression analysis method, combined with future charging current or future discharge current and voltage fluctuation characteristics for prediction. Linear regression is a statistical method used to establish a linear relationship between variables to predict the change of the dependent variable (voltage attenuation factor). The linear regression coefficients pre-stored by the system and It is the best fitting parameter obtained by training on historical data.

[0052] The specific voltage attenuation factor calculation formula is as follows: in, Indicates future time The voltage attenuation factor is Indicates future time The charging current or discharging current, Indicates the pre-stored voltage attenuation factor at the current moment, Indicates the voltage fluctuation characteristics, and Represents the pre-stored linear regression coefficients.

[0053] Through the above formula, the system can predict the voltage attenuation factor at future times. This prediction not only takes into account the future current changes, but also combines the voltage fluctuation characteristics, making the prediction results more accurate and reliable. The voltage attenuation factor reflects the aging trend of the battery over time under different charging and discharging conditions.

[0054] By combining the voltage fluctuation characteristics and the optimal charge and discharge current sequence, the system can predict the future voltage decay in advance. Accurate prediction of the voltage decay factor helps to identify potential aging problems, optimize the charge and discharge strategy, extend the battery life, and improve the overall performance and safety of the system.

[0055] In step S17, a life prediction model is constructed according to the optimal charge and discharge current sequence and the voltage attenuation factor, and the remaining number of cycles, future battery voltage and battery life are calculated according to the life prediction model.

[0056] In a specific implementation, constructing a life prediction model according to the optimal charge and discharge current sequence and the voltage attenuation factor, and calculating the future battery voltage, remaining number of cycles and battery life according to the life prediction model, includes: The life expectancy model is as follows: in, Indicates the next moment to the future moment The number of moments, Indicates future time The voltage attenuation factor is represents the maximum current in the optimal charge and discharge current sequence, Indicates the battery voltage at the current moment, Indicates the voltage fluctuation characteristics, Indicates future time The future battery voltage, Indicates future time The remaining number of cycles, Indicates future time battery life.

[0057] Specifically, the system first builds a life prediction model to describe the voltage change of the battery at different time points. This model takes into account the changes from the current moment to the future moment. The voltage attenuation cumulative effect is calculated by the following formula at the future moment Future battery voltage: in, Indicates the next moment to the future moment The number of moments, Indicates future time The voltage attenuation factor is Indicates the battery voltage at the current moment, Indicates future time The future battery voltage.

[0058] Next, to calculate the future time The remaining number of cycles , the system introduces the maximum current and voltage fluctuation characteristics . Maximum current Derived from the optimal charge and discharge current sequence, it indicates the maximum current value that the battery can reach during the charge and discharge process. Voltage fluctuation characteristics It reflects the degree of voltage mutation. The remaining number of cycles can be calculated by the following formula: in, Indicates future time The voltage attenuation factor is represents the maximum current in the optimal charge and discharge current sequence, Indicates the voltage fluctuation characteristics, Indicates future time The number of remaining cycles.

[0059] Finally, to evaluate future moments Battery life , the system combines the number of remaining cycles with the difference between the current and predicted battery voltage. The battery life can be calculated by the following formula: in, Indicates the battery voltage at the current moment, Indicates future time The future battery voltage, Indicates future time The remaining number of cycles, Indicates future time battery life.

[0060] By building a life prediction model and using the optimal charge and discharge current sequence and voltage decay factor, the system can comprehensively evaluate the performance changes of the battery in future use. This prediction not only helps to identify potential aging problems, but also optimizes the charge and discharge strategy, prolongs the battery life, and improves the overall performance and safety of the system.

[0061] The following describes the working process of the present invention using a relatively common scenario as an example. Figure 1 , a lithium battery life prediction method based on data analysis, comprising the following steps: First, the battery management system collects complete charging and discharging data through Hall effect sensors and voltage sensors, including charging current, discharging current, battery voltage and corresponding timestamps.

[0062] Next, the battery management system analyzes the acquired data, with the preset time window set to 1 second. After screening, all data with a time interval greater than 1 second are determined to be valid data, and finally a charge and discharge current sequence containing 500 valid data points is constructed, covering the entire charge and discharge cycle.

[0063] The system recorded the battery voltage corresponding to these 500 valid data points as the standard voltage. By comparing the standard voltages at adjacent timestamps, it was found that 30 voltage fluctuations exceeded the preset voltage fluctuation threshold and were considered valid voltage fluctuation data. They were combined into a voltage fluctuation sequence in chronological order. After further processing, a voltage mutation feature sequence consisting of these valid voltage fluctuations was obtained, showing a significant voltage change trend.

[0064] Next, the system processed the voltage mutation characteristics with wavelet transform, extracted the approximate wavelet coefficient sequence, and multiplied it with the voltage mutation characteristics to obtain the optimal fluctuation sequence. After calculation based on this sequence, the voltage fluctuation characteristic was obtained, and the characteristic value was 0.025, indicating that there were slight signs of aging inside the battery but it was still within the normal working range.

[0065] Then, the system calculated the correlation coefficient of the charge and discharge current sequence and found that when the time interval was 5 minutes, the correlation coefficient reached a maximum value of 0.98. Therefore, the charge and discharge current sequence at this time interval was selected as the optimal charge and discharge current sequence.

[0066] According to the above voltage fluctuation characteristics and the optimal charge and discharge current sequence, the voltage attenuation factor at the future moment (the next hour) is predicted to be 0.97, indicating that the battery will have a slight voltage drop in the next hour.

[0067] Finally, in step S17, a life prediction model is constructed based on the optimal charge and discharge current sequence and the voltage decay factor. The model predicts that within the next hour, the future voltage of the battery will drop from the current 3.8 volts to 3.75 volts, and the remaining number of cycles is expected to be 400 times, while the battery life, expressed as the product of the number of charge and discharge cycles and the voltage difference, is estimated to support about 150 units of workload.

[0068] In summary, through a series of carefully designed data collection and analysis steps, the charging and discharging behavior of lithium-ion batteries can be fully monitored and evaluated. Starting from obtaining accurate charging current, discharging current and battery voltage data, combined with high-precision timestamp records, the accuracy and time relevance of each piece of data are ensured. Subsequently, through the effective screening and processing of these data, a reliable charging and discharging current sequence is constructed, and the voltage fluctuation characteristics are further analyzed to identify significant voltage change trends, revealing possible signs of aging inside the battery. On this basis, correlation analysis is used to determine the optimal charging and discharging current mode, and statistical methods such as linear regression are used to predict future voltage decay. Finally, with the help of the life prediction model, the remaining number of cycles and expected life of the battery in the future can be calculated, which proves that this method can accurately predict the life of lithium batteries.

[0069] Reference Figure 2 The second embodiment of the present invention provides a lithium battery life prediction device based on data analysis, comprising: A data acquisition module is used to obtain the charging current, discharging current, battery voltage and the timestamp of the recorded data for each complete charge and discharge cycle; A current sequence construction module, used for performing data analysis according to the charging current, the discharging current and the timestamp to construct a charging and discharging current sequence; A voltage mutation analysis module, used to analyze the voltage fluctuation amplitude according to the timestamp, the charge and discharge current sequence and the battery voltage to obtain voltage mutation characteristics; A voltage fluctuation analysis module, used to perform fluctuation characteristic analysis according to the voltage mutation characteristics to obtain voltage fluctuation characteristics; An optimal sequence analysis module, used to perform correlation analysis according to the charge and discharge current sequence to obtain an optimal charge and discharge current sequence; An attenuation factor calculation module, used to calculate a voltage attenuation factor according to the voltage fluctuation characteristics and the optimal charge and discharge current sequence; The life prediction module is used to construct a life prediction model according to the optimal charge and discharge current sequence and the voltage attenuation factor, and calculate the remaining number of cycles, future battery voltage and battery life according to the life prediction model. It should be noted that the lithium battery life prediction device based on data analysis provided in the embodiment of the present invention is used to execute all the process steps of the lithium battery life prediction method based on data analysis in the above embodiment. The working principles and beneficial effects of the two correspond one to one, so they are not repeated here.

[0070] The embodiment of the present invention also provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a lithium battery life prediction program based on data analysis. When the processor executes the computer program, the steps in the above-mentioned lithium battery life prediction method based on data analysis are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as a lithium battery life prediction module based on data analysis.

[0071] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0072] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0073] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0074] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0075] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0076] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0077] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A lithium battery life prediction method based on data analysis, characterized in that: Executed by a computer, including: Obtain the charge current, discharge current, battery voltage and timestamp of the recorded data for each complete charge and discharge cycle; Perform data analysis according to the charging current, the discharging current and the timestamp to construct a charging and discharging current sequence; Perform voltage fluctuation amplitude analysis according to the timestamp, the charge and discharge current sequence and the battery voltage to obtain voltage mutation characteristics; Performing fluctuation characteristic analysis according to the voltage mutation characteristics to obtain voltage fluctuation characteristics; Performing correlation analysis on the charge and discharge current sequence to obtain an optimal charge and discharge current sequence; Calculating a voltage attenuation factor according to the voltage fluctuation characteristics and the optimal charge and discharge current sequence; A life prediction model is constructed according to the optimal charge and discharge current sequence and the voltage attenuation factor, and the remaining number of cycles, future battery voltage and battery life are calculated according to the life prediction model.

2. The lithium battery life prediction method based on data analysis according to claim 1 is characterized in that: The performing data analysis according to the charging current, the discharging current and the timestamp to construct a charging and discharging current sequence includes: Calculate the time interval between adjacent timestamps, and compare the time interval with a preset time window. If the time interval is smaller than the time window, determine that the corresponding charging current and discharging current are invalid data. If the time interval is greater than the time window, the charging current and the discharging current are determined to be valid data; All the valid data are combined to construct a charge and discharge current sequence.

3. The lithium battery life prediction method based on data analysis according to claim 1 is characterized in that: The voltage fluctuation amplitude analysis is performed according to the timestamp, the charge and discharge current sequence and the battery voltage to obtain voltage mutation characteristics, including: Recording the battery voltage corresponding to the charge and discharge current sequence as the standard voltage; Perform a difference operation on the standard voltages at adjacent time stamps to obtain the voltage fluctuation amplitude; Comparing the voltage fluctuation amplitude with a preset voltage fluctuation threshold, and if the voltage fluctuation amplitude is less than the voltage fluctuation threshold, determining the voltage fluctuation amplitude as invalid fluctuation data; If the voltage fluctuation amplitude is greater than the voltage fluctuation threshold, determining the voltage fluctuation amplitude as valid fluctuation data; Sorting and combining all the valid fluctuation data according to corresponding timestamps to form a voltage fluctuation amplitude sequence; The voltage fluctuation amplitudes of adjacent time stamps in the voltage fluctuation amplitude sequence are subjected to a difference operation, and all the difference results are sorted and combined to obtain a voltage mutation feature.

4. The lithium battery life prediction method based on data analysis according to claim 1, characterized in that: The performing fluctuation characteristic analysis according to the voltage mutation characteristic to obtain the voltage fluctuation characteristic includes: Applying wavelet transform to process the timestamp corresponding to the voltage mutation feature to obtain an approximate wavelet coefficient sequence; Multiplying the approximate wavelet coefficient sequence with the voltage mutation characteristic to obtain an optimal fluctuation sequence; The mutation characteristic is calculated based on the optimal fluctuation sequence to obtain the voltage fluctuation characteristic.

5. The lithium battery life prediction method based on data analysis according to claim 1, characterized in that: The performing correlation analysis according to the charge and discharge current sequence to obtain the optimal charge and discharge current sequence includes: Calculate the correlation coefficient between the charging current and discharging current at any time stamp in the charging and discharging current sequence of each charging and discharging cycle and the charging current and discharging current at other times in the same sequence; Selecting the charge and discharge current sequence with the largest correlation coefficient as the optimal charge and discharge current sequence; The correlation coefficient is calculated by the following formula: In the formula, Indicates the time interval is The correlation coefficient between the charge and discharge current series, Indicates the first The charging or discharging current of each time stamp, Indicates The time interval between timestamps is The charging current or discharging current, represents the number of timestamps in the charge and discharge current sequence, Indicates the time interval between two corresponding timestamps. Indicates the average value of the charging current or discharging current.

6. The lithium battery life prediction method based on data analysis according to claim 1, characterized in that: The calculating of the voltage attenuation factor according to the voltage fluctuation characteristics and the optimal charge and discharge current sequence comprises: Add a preset time interval to each timestamp in the optimal charge and discharge current sequence to obtain a future time; Using the charging current and discharging current in the optimal charging and discharging current sequence as the future charging current and future discharging current corresponding to the future moment; According to the future charging current, the future discharging current and the voltage fluctuation characteristics, a voltage attenuation factor at a future moment is calculated by linear regression analysis; Among them, the voltage attenuation factor is calculated by the following formula: in, Indicates future time The voltage attenuation factor is Indicates future time The charging current or discharging current, Indicates the pre-stored voltage attenuation factor at the current moment, Indicates the voltage fluctuation characteristics, and Represents the pre-stored linear regression coefficients.

7. The lithium battery life prediction method based on data analysis according to claim 1, characterized in that: The method of constructing a life prediction model according to the optimal charge and discharge current sequence and the voltage attenuation factor, and calculating the future battery voltage, the remaining number of cycles and the battery life according to the life prediction model, includes: The life expectancy model is as follows: in, Indicates the next moment to the future moment The number of moments, Indicates future time The voltage attenuation factor is represents the maximum current in the optimal charge and discharge current sequence, Indicates the battery voltage at the current moment, Indicates the voltage fluctuation characteristics, Indicates future time The future battery voltage, Indicates future time The remaining number of cycles, Indicates future time battery life.

8. A lithium battery life prediction device based on data analysis, characterized in that: include: A data acquisition module is used to obtain the charging current, discharging current, battery voltage and the timestamp of the recorded data for each complete charge and discharge cycle; A current sequence construction module, used for performing data analysis according to the charging current, the discharging current and the timestamp to construct a charging and discharging current sequence; A voltage mutation analysis module, used to analyze the voltage fluctuation amplitude according to the timestamp, the charge and discharge current sequence and the battery voltage to obtain voltage mutation characteristics; A voltage fluctuation analysis module, used to perform fluctuation characteristic analysis according to the voltage mutation characteristics to obtain voltage fluctuation characteristics; An optimal sequence analysis module, used to perform correlation analysis according to the charge and discharge current sequence to obtain an optimal charge and discharge current sequence; An attenuation factor calculation module, used to calculate a voltage attenuation factor according to the voltage fluctuation characteristics and the optimal charge and discharge current sequence; The life prediction module is used to construct a life prediction model according to the optimal charge and discharge current sequence and the voltage attenuation factor, and calculate the remaining number of cycles, future battery voltage and battery life according to the life prediction model.

9. An electronic device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the lithium battery life prediction method based on data analysis as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the lithium battery life prediction method based on data analysis as described in any one of claims 1 to 7.

Images