A warehouse system of waste and old automobile power battery

Abstract

The application discloses a kind of warehouse systems of waste and old car power battery, it is related to warehouse management technical field, including, safety evaluation module, feature dataset is analyzed using artificial intelligence algorithm, the security risk grade label of power battery and recommended storage environment parameter are generated;Configuration scheme generation module, the security risk grade label of power battery is automatically classified and dispatched to matched warehouse area, and according to recommended storage environment parameter, temperature and humidity control device is configured, and dynamic warehouse configuration scheme is generated;Warehouse data record module, using multi-source data fusion algorithm, state monitoring data set and power battery tracking data, security risk grade label and dynamic warehouse configuration scheme are structured integrated, and warehouse data record is generated.The application realizes accurate classification and prediction, so as to dynamically adjust the storage condition of battery without manual intervention.

Description

Technical Field

[0001] This invention relates to the field of warehouse management technology, and in particular to a warehouse system for used automotive power batteries. Background Technology

[0002] With the rapid development of new energy vehicles, the recycling and reuse of used vehicle power batteries has become increasingly prominent. Power batteries undergo prolonged charge-discharge cycles during use, leading to performance degradation, particularly in remaining capacity and cycle life. Therefore, effectively managing used power batteries and ensuring that storage and recycling do not pose a threat to the environment or human safety has become a crucial issue for the industry. Currently, most used power battery storage systems rely on manual operation or simple parameter monitoring, lacking intelligent identification and dynamic adjustment for changes in battery performance. For example, changes in environmental factors such as temperature, humidity, and gas concentration directly affect battery safety and performance, but existing systems mostly use fixed parameters for environmental control, lacking real-time response and adjustment mechanisms based on the actual state of the batteries.

[0003] The shortcomings of existing technologies in power battery storage management mainly lie in the lack of intelligent battery monitoring and management functions, particularly in battery safety risk identification and environmental control. Traditional storage systems often rely on human experience to judge the battery storage environment, lacking accurate battery performance monitoring and dynamic environmental adaptation capabilities. They cannot adjust the storage environment in a timely manner according to changes in the battery during use. Since battery performance degradation is closely related to environmental factors such as temperature, humidity, and gas concentration, traditional systems cannot provide real-time and personalized solutions under changes in multiple factors, resulting in difficulty in maximizing battery performance and even potential safety hazards. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a storage system for waste automotive power batteries, which solves the problem of the lack of intelligent battery monitoring in the prior art.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] This invention provides a storage system for used automotive power batteries, comprising: a data acquisition module for collecting and preprocessing tracking data of used automotive power batteries to obtain a feature dataset; a safety assessment module for analyzing the feature dataset using artificial intelligence algorithms to generate safety risk level labels for the power batteries and recommended storage environment parameters; a configuration scheme generation module for automatically classifying and scheduling the power batteries according to their safety risk level labels to matching storage areas and configuring temperature and humidity control devices according to the recommended storage environment parameters to generate a dynamic storage configuration scheme; a status monitoring module for real-time collection of temperature, humidity, gas concentration, and power battery operating signals within the storage area to form a status monitoring dataset; a storage data recording module for using a multi-source data fusion algorithm to structurally integrate the status monitoring dataset with the power battery tracking data, safety risk level labels, and dynamic storage configuration scheme to generate storage data records; and a storage analysis module for analyzing the storage data records, assessing the remaining usable capacity, cycle life, and safety status of the power batteries, and outputting instructions based on the analysis results to automate the entire process from storage monitoring to disposal decision-making.

[0008] As a preferred embodiment of the waste automotive power battery storage system described in this invention, the system collects battery serial number, manufacturing date, charge / discharge cycles, temperature data, and usage history data to obtain power battery tracking data. It also employs fixed rules to complete missing data and remove abnormal data, and uses a maximum / minimum value normalization method to standardize the numerical data, thereby obtaining a feature dataset.

[0009] As a preferred embodiment of the waste automotive power battery storage system described in this invention, the specific steps for generating the power battery safety risk level label and recommended storage environment parameters are as follows:

[0010] The remaining capacity change trend, temperature response characteristics, discharge stability index and historical fault signals of the power battery are extracted from the feature dataset using feature extraction algorithms to form a two-dimensional feature matrix;

[0011] Artificial intelligence algorithms are used to perform discriminant analysis on the two-dimensional feature matrix, generate security risk level labels, and call the mapping rule table to generate recommended storage environment parameters.

[0012] As a preferred embodiment of the storage system for used automotive power batteries described in this invention, the following steps are taken: A feature extraction algorithm is used to extract the remaining capacity change trend, temperature response characteristics, discharge stability indicators, and historical fault signals of the power batteries from a feature dataset, forming a two-dimensional feature matrix.

[0013] The feature dataset is sliced ​​according to time windows to generate multiple time series samples;

[0014] The remaining capacity change rate, temperature response slope, discharge voltage standard deviation, and historical fault signal count for each time series sample are calculated and encoded to form a feature vector for a single sample.

[0015] Arrange all feature vectors in chronological order to generate a two-dimensional feature matrix.

[0016] As a preferred embodiment of the waste automotive power battery storage system of the present invention, the specific steps for automatically classifying and allocating the power batteries' safety risk level labels to matching storage areas are as follows:

[0017] Based on the safety risk level label of the power battery, query the storage area configuration table, identify the storage area number that matches the risk level, and extract the corresponding storage time limit parameters.

[0018] Retrieve the remaining capacity and operational status of the target area, filter out available storage areas, and sort them according to the scheduling priority of the storage areas;

[0019] Based on the safety risk level label of the power battery, storage time limit parameters, and the remaining capacity and operating status of the target area, scheduling instructions are generated by comprehensively considering preset strategy rules.

[0020] The system executes scheduling commands to automatically allocate power batteries to designated storage areas, adjusts the storage time limits within the storage areas according to storage time limit parameters, and updates the numbering and storage location records.

[0021] As a preferred embodiment of the waste automotive power battery storage system of the present invention, the specific steps for configuring a temperature and humidity control device according to recommended storage environment parameters to generate a dynamic storage configuration scheme are as follows:

[0022] Set the initial settings of the temperature and humidity control device according to the target temperature value, humidity range and ventilation frequency in the recommended storage environment parameters;

[0023] Input the initial settings into the temperature and humidity control device and adjust the target temperature and humidity range;

[0024] Based on the storage time limit parameters, configure the automatic adjustment cycle and running time of the temperature and humidity control device to generate a dynamic warehouse configuration scheme.

[0025] As a preferred embodiment of the waste automotive power battery storage system described in this invention, the system collects temperature, humidity, gas concentration, and power battery operation signals within the storage area through a status monitoring mechanism, and performs noise reduction, numerical standardization, and outlier removal operations, integrating the various processing results into a status monitoring data set.

[0026] As a preferred embodiment of the waste automotive power battery storage system of the present invention, the specific steps for generating storage data records are as follows:

[0027] The condition monitoring data set, power battery tracking data, safety risk level labels, and dynamic warehouse configuration scheme are time-aligned, missing data is filled in, and format is standardized to obtain a standardized data package with a unified format.

[0028] By extracting fields related to storage status, risk identification, and control strategies from standardized data packets, a fusion preparation dataset is output.

[0029] The dataset to be fused is input into the multi-source data fusion algorithm, which performs structure matching and logical linkage, and outputs the structured fusion result.

[0030] The structured fusion results are categorized and organized according to battery number to generate warehouse data records.

[0031] As a preferred embodiment of the waste automotive power battery storage system described in this invention, the specific steps for analyzing the storage data records and evaluating the remaining usable capacity, cycle life, and safety status of the power batteries are as follows.

[0032] Extract remaining available capacity, cycle life, and safety-related fields from warehouse data records, and normalize them to generate a standard evaluation dataset;

[0033] Based on the standard evaluation dataset, linear regression and exponential fitting methods are used to calculate the remaining capacity decline trend and performance degradation rate, and the cycle counter outputs capacity indicators and lifetime prediction values.

[0034] Statistical analysis is performed on abnormal temperature and humidity, gas concentration fluctuations, and fault signals to determine the safety status level.

[0035] The capacity indicators, life prediction values, and safety status levels are combined to form a comprehensive assessment report.

[0036] As a preferred embodiment of the waste automotive power battery storage system described in this invention, the step of automatically controlling the entire process from storage monitoring to disposal decision-making by outputting instructions based on analysis results includes the following specific steps.

[0037] Based on the comprehensive assessment report, identify the disposal type labels corresponding to capacity indicators, life prediction values, and safety status, and output disposal recommendations.

[0038] The disposal suggestions are matched with preset strategy rules to generate an operation instruction set, which is then sent to the warehouse scheduling and equipment control terminal to perform corresponding temperature and humidity adjustments and storage location adjustments.

[0039] The beneficial effects of this invention are as follows: Artificial intelligence algorithms can efficiently identify the state and potential risks of batteries, achieving accurate classification and prediction, thereby dynamically adjusting battery storage conditions without human intervention. This significantly improves the safety and intelligence level of the waste automotive power battery storage system, avoiding potential judgment errors and resource waste in traditional manual management, and enhancing the overall efficiency of storage management and the safety of battery storage. Attached Figure Description

[0040] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a schematic diagram of the storage system for used automotive power batteries in this invention.

[0042] Figure 2 This is a schematic diagram of the safety risk assessment process in this invention.

[0043] Figure 3 This is a schematic diagram of the dynamic warehouse configuration process in this invention.

[0044] Figure 4 This is a schematic diagram of the power battery state analysis in this invention. Detailed Implementation

[0045] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0046] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0047] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0048] Reference Figures 1-4 This embodiment provides a storage system for used automotive power batteries, including the following steps:

[0049] The data acquisition module collects tracking data of the power batteries of scrapped vehicles and preprocesses it to obtain a feature dataset.

[0050] Battery serial number, manufacturing date, charge / discharge cycles, temperature data, and usage history data are collected to obtain power battery tracking data. Missing data is filled in and abnormal data is removed using fixed rules. Numerical data is standardized using the maximum and minimum value normalization method to obtain a feature dataset.

[0051] Specifically, a data field integrity verification table is established as the preset basis for judging missing data, corresponding to battery number, manufacturing date, charge / discharge cycles, temperature data, and usage history data. According to the verification table, the data source is scanned field by field to locate missing items. For missing data, a completion process is performed according to fixed rules. The preset rules include filling missing temperature data with the average temperature of the same battery number within adjacent time windows (for example, if the sampling frequency is 1 hour, the effective values ​​within 5 hours before and after are averaged); for the missing charge / discharge cycle field, the average charge / discharge cycle of power battery samples with the same manufacturing date and usage type is used as the filling value.

[0052] An anomaly judgment threshold table is established as the basis for rejection. The table defines the upper and lower limits of each numerical field. For example, the normal range of the temperature field is preset to -20℃ to 65℃, and the effective range of the charge and discharge number field is preset to 0 to 6000 times. According to the verification table, the data records are traversed. Records that exceed the upper or lower limit range of each numerical field in the anomaly judgment threshold table are marked as anomalies and rejected.

[0053] The maximum and minimum values ​​of each field are calculated as reference benchmarks for normalization. Then, the values ​​in each field are transformed using the maximum-minimum value normalization method. For example, if the original temperature data of a power battery is in the range of [-10℃, 50℃], and the current value is 40℃, then the normalized value is 0.833. Finally, the feature dataset after all fields have been normalized is obtained.

[0054] The safety assessment module uses artificial intelligence algorithms to analyze feature datasets and generate safety risk level labels for power batteries and recommended storage environment parameters.

[0055] By using feature extraction algorithms, the remaining capacity change trend, temperature response characteristics, discharge stability indicators and historical fault signals of the power battery are extracted from the feature dataset to form a two-dimensional feature matrix.

[0056] Furthermore, the feature dataset is sliced ​​according to time windows to generate multiple time series samples.

[0057] Specifically, all records are sorted chronologically based on the timestamp field in the feature dataset to ensure the continuity of the time series. Then, the time window length and step size are set as preset parameters for the slicing operation; for example, the time window length is set to 24 hours and the step size to 1 hour. Starting from the start time of the feature dataset, all records with timestamps within the first time window interval are extracted to form the first time series sample. The start time is moved forward by one step, and records within the next window interval are extracted again to form the second time series sample. This process is repeated, sliding the window and extracting data records within the corresponding intervals until the time range of the feature dataset ends. Finally, multiple time series samples are generated, each containing all feature field records within a complete time window.

[0058] The remaining capacity change rate, temperature response slope, discharge voltage standard deviation, and historical fault signal count for each time series sample are calculated and encoded to form a feature vector for a single sample.

[0059] Specifically, the remaining capacity field sequence is extracted from the time series sample, and the ratio of the difference between the first and last values ​​of the field sequence to the initial value is calculated as the remaining capacity change rate. The temperature field sequence is extracted from the time series sample, and the temperature change over time is linearly fitted using the least squares method to obtain the slope parameter, which is used as the temperature response slope. The discharge voltage field sequence is extracted from the time series sample, and the standard deviation of the discharge voltage field sequence is calculated as the discharge voltage standard deviation. Then, the number of non-zero records in the historical fault signal field of the time series sample is counted as the historical fault signal count value. Finally, the remaining capacity change rate, temperature response slope, discharge voltage standard deviation, and historical fault signal count value are concatenated and encoded in a fixed order to form the feature vector of a single sample.

[0060] Arrange all feature vectors in chronological order to generate a two-dimensional feature matrix.

[0061] It should be noted that all time series samples are sorted in ascending order according to the timestamp field to ensure that the time sequence of the samples is consistent; then, the extracted feature vectors of each time series sample are arranged as a row of data according to the sorting result; next, a two-dimensional data structure is constructed using the field order in each feature vector as the column index name; finally, all feature vectors are concatenated row by row to generate a two-dimensional feature matrix with the number of rows as the number of time series samples and the dimension of a single feature vector as the number of columns.

[0062] Artificial intelligence algorithms are used to perform discriminant analysis on the two-dimensional feature matrix, generate security risk level labels, and call the mapping rule table to generate recommended storage environment parameters.

[0063] Specifically, each row of the two-dimensional feature matrix, together with its corresponding known security risk level label, forms a training sample. Then, an artificial intelligence algorithm, such as a support vector machine classification algorithm, a random forest classification algorithm, or an LSTM-based discriminant network, is selected to supervise the learning of the training samples. The cross-entropy loss function is used for error calculation, and the parameters are iteratively updated using backpropagation until the loss converges. After training, the trained artificial intelligence algorithm is fixed for subsequent inference. Next, the two-dimensional feature matrix to be analyzed is used as input and loaded into the trained artificial intelligence algorithm. Discriminant operations are performed on each row of feature vectors, outputting the corresponding security risk level label, such as "low risk," "medium risk," or "high risk." Then, each security risk level label is used as a key to call a mapping rule table to obtain recommended storage environment parameters matching the security risk level label, such as a temperature range of 15–25 degrees Celsius, a humidity range of 40%–60%, and ventilation status as on.

[0064] The configuration scheme generation module automatically classifies and assigns the safety risk level labels of the power batteries to the matching storage areas, and configures temperature and humidity control devices according to the recommended storage environment parameters to generate a dynamic storage configuration scheme.

[0065] Based on the safety risk level label of the power battery, query the storage area configuration table, identify the storage area number that matches the risk level, and extract the corresponding storage time limit parameters.

[0066] It should be noted that the safety risk level label of the power battery is input into the storage area configuration table as a query field. The record row corresponding to the safety risk level label is located in the storage area configuration table, and the storage area number field contained in the record row is extracted as the storage area number that matches the safety risk level label. Then, the storage time limit parameter field corresponding to the same record row is read as the maximum allowed storage time of the power battery in the matched storage area. For example, for a power battery with a safety risk level label of "medium risk", the storage area number in the query result is "B03" and the storage time limit parameter is "72 hours". Finally, the storage area number and storage time limit parameter are structured and encapsulated as the basic configuration information for storage scheduling.

[0067] Retrieve the remaining capacity and operational status of the target area, filter out available storage areas, and sort them according to their scheduling priority.

[0068] Specifically, the process reads the record row corresponding to the target area number from the warehouse area status record table, extracts the remaining capacity field and the operation status field from the record row; compares the remaining capacity field with the preset minimum available capacity threshold, filters out all record rows below the minimum available capacity threshold, then filters out record rows with the operation status as "under maintenance" or "disabled" based on the operation status field, and retains the record rows with the status as "available"; then extracts the scheduling priority field from the retained record rows, and sorts them in ascending or descending order according to the value of the scheduling priority field, for example, the smaller the value of the scheduling priority field, the higher the priority, so it is sorted in ascending order; finally, the sorted warehouse area numbers are output as the subsequent scheduling call list.

[0069] It should also be noted that the preset minimum available capacity threshold is first determined by analyzing historical data within the storage area to collect the remaining capacity distribution of different areas and different battery types; secondly, based on the safety performance standards of power batteries and storage environment requirements, combined with actual usage scenarios, a minimum safe capacity requirement is set; finally, based on the working efficiency, life cycle, and safety requirements of the application field of the power battery, the minimum available capacity threshold is determined. For example, a battery with a remaining capacity of less than 20% may be considered unable to continue to be used normally, thus the minimum available capacity threshold is set to 20%.

[0070] Based on the safety risk level label of the power battery, storage time limit parameters, and the remaining capacity and operating status of the target area, scheduling instructions are generated by comprehensively considering preset strategy rules.

[0071] Specifically, based on the safety risk level label of the power battery, the system searches for the priority scheduling rule group corresponding to the safety risk level label from the preset strategy rules; then, it extracts the storage time limit constraints that match the safety risk level label from the corresponding priority scheduling rule group and compares them with the extracted storage time limit parameters to determine the time limit adaptability; subsequently, it combines the remaining capacity field and operation status field of the selected target area to determine whether the target area meets the continuous availability requirements and capacity carrying capacity within the storage time limit. For example, if the remaining capacity of the target area is greater than or equal to the minimum available capacity requirement and the operation status is "available", and the storage time limit of the target area can meet the storage time limit requirements of the battery, then the area meets the requirements; if it does, the system matches the corresponding scheduling operation code from the rule group according to the scheduling priority, such as "schedule handling", "delayed warehousing" or "transfer to temporary area"; finally, the operation code is combined with the storage area number, safety risk level label and timestamp field to form a scheduling instruction record line, which is output to the scheduling task call interface.

[0072] It should also be noted that the priority scheduling rule group consists of scheduling strategies developed based on the statistical analysis results of historical storage data, industry operating standards, and expert experience. The priority scheduling rule group clearly defines the storage time limit requirements, acceptable job status, remaining capacity lower limit, and corresponding scheduling priority under each level label, which is used to guide the subsequent scheduling instruction generation process.

[0073] The system executes scheduling commands to automatically allocate power batteries to designated storage areas, adjusts the storage time limits within the storage areas according to storage time limit parameters, and updates the numbering and storage location records.

[0074] It should be noted that, based on the storage area number, safety risk level label, and storage time limit parameters in the scheduling instruction, the storage control device is invoked to execute the handling action, automatically transporting the power battery to the corresponding storage area entrance. After the power battery arrives at the storage area entrance, it is guided into the corresponding storage location according to the preset path, and the current entry time is recorded. Subsequently, the time stamp for the power battery to be released from storage is calculated based on the storage time limit parameters. For example, if the entry time is 10:00:00 on May 7, 2025, and the storage time limit parameter is 72 hours, then the time stamp for release from storage should be 10:00:00 on May 10, 2025. Next, the record with the corresponding storage area number is searched in the storage area configuration table, and the power battery number is bound and updated with the corresponding storage area number, storage location code, entry time stamp, and release time stamp. Finally, the power battery information record table is updated synchronously with the fields of number, current storage location, entry time, and planned release time.

[0075] Set the initial settings of the temperature and humidity control device based on the target temperature value, humidity range, and ventilation frequency in the recommended storage environment parameters.

[0076] Specifically, based on the target temperature, humidity range, and ventilation frequency in the recommended storage environment parameters, the corresponding target temperature, humidity range, and ventilation frequency are first extracted from the storage environment parameter table. For example, the target temperature is 22℃, the humidity range is 40%–60%, and the ventilation frequency is 3 times per hour. Then, based on the target temperature, the initial setting of the temperature and humidity control device is set to 22℃. Subsequently, the humidity control device is set within the range of 40% to 60%, and adjusted according to the actual environment within the range. Finally, the initial start frequency of the ventilation equipment is set to 3 times per hour to ensure that the air circulation in the storage area meets the requirements. The settings are monitored in real time to ensure that the equipment operates according to the predetermined parameters.

[0077] Input the initial settings into the temperature and humidity control device and adjust the target temperature and humidity range.

[0078] Specifically, based on the preset initial settings, input the target temperature value in the operation interface of the temperature and humidity control device, and set the target value of the temperature regulator to the desired temperature; then input the humidity range in the humidity control panel, and adjust the humidity regulator so that the humidity value in the storage environment operates within the target humidity range input in the humidity control panel, for example, a relative humidity range of 40% to 60%; input the start / stop frequency setting value of the ventilation device in the operation interface, for example, setting it to ventilate twice per hour, and confirm the start / stop frequency setting value through the interface operation, so that the ventilation device automatically starts and stops according to the start / stop frequency to regulate the air circulation in the storage environment; finally, after checking and confirming that all input values ​​are correct, start the temperature and humidity control device to make the adjustment of the target temperature and humidity range effective.

[0079] Based on the storage time limit parameters, configure the automatic adjustment cycle and running time of the temperature and humidity control device to generate a dynamic warehouse configuration scheme.

[0080] Specifically, based on the storage time limit parameter, the automatic adjustment cycle of the temperature and humidity control device is determined, and the operating time of the temperature and humidity control device is adjusted according to the set time range. First, the storage time limit parameter is input into the temperature and humidity control device. Combined with the target temperature and humidity requirements, the required temperature and humidity change amplitude and frequency for each time period are determined. Then, the automatic adjustment cycle of the temperature and humidity control device is set to ensure that the temperature and humidity are adjusted as needed within each time period. Next, the operating time for each time period is calculated to ensure that the temperature and humidity control device automatically adjusts within the set time limit. Finally, a dynamic storage configuration plan is generated and confirmed, including detailed configurations of the adjustment cycle and operating time, and the configuration settings are saved.

[0081] The status monitoring module collects temperature, humidity, gas concentration, and power battery operation signals in the storage area in real time, forming a status monitoring data set.

[0082] Through the condition monitoring mechanism, the temperature, humidity, gas concentration and power battery operation signals in the storage area are collected, and noise reduction, numerical standardization and outlier removal are performed. The results of various processing are integrated into a condition monitoring data set.

[0083] Specifically, a condition monitoring mechanism is activated to collect temperature, humidity, gas concentration, and power battery operating signals within the storage area. The collected temperature and humidity data are then denoised, for example, using low-pass filtering or moving averages to remove high-frequency noise. A similar denoising process is performed on the gas concentration data. For the power battery operating signals, an appropriate algorithm (such as Kalman filtering) is used for denoising to ensure the stability of the signals. Next, all collected data undergoes numerical standardization to unify data from different dimensions to the same scale range. For example, maximum-minimum standardization or Z-score standardization methods are used. Outliers are then identified and removed using methods such as IQR (interquartile range) or Z-score to detect and eliminate them. Finally, the processed data are integrated into a condition monitoring dataset.

[0084] The warehouse data recording module uses a multi-source data fusion algorithm to structurally integrate the status monitoring data set with the power battery tracking data, safety risk level labels and dynamic warehouse configuration schemes to generate warehouse data records.

[0085] The condition monitoring data set, power battery tracking data, safety risk level labels, and dynamic warehouse configuration scheme are time-aligned, missing data is filled in, and format is standardized to obtain a standardized data package with a unified format.

[0086] Specifically, for the condition monitoring data set, power battery tracking data, safety risk level labels, and dynamic warehouse configuration scheme, data is aligned according to timestamps to ensure consistency across all data sources in the time dimension. Specifically, the time of one data source can be used as a reference point, and other data sources can be interpolated or aligned according to time intervals. For missing data, appropriate completion methods are used, such as forward padding, backward padding, or linear interpolation and Lagrange interpolation, to ensure all data points have valid values. Next, format standardization is performed to ensure compliance with unified format requirements. For numerical data, standardization can be achieved by using fixed decimal places, units, or ranges; for categorical data, all category labels can be converted to unified identifiers. Finally, the condition monitoring data set, power battery tracking data, safety risk level labels, and dynamic warehouse configuration scheme are merged to generate a standardized data package with a unified format.

[0087] By extracting fields related to storage status, risk identification, and control strategies from standardized data packets, a fusion preparation dataset is output.

[0088] Specifically, from the standardized data package, data related to storage status, risk identification, and control strategies are filtered to extract specific data. For example, storage status-related fields include temperature and humidity, gas concentration, and power battery operating signals; risk identification-related fields may include safety risk level labels and power battery health status; and control strategy-related fields include temperature and humidity control strategies and warehouse area scheduling strategies. Next, the extracted fields are checked for format validation and format conversion to ensure structural uniformity and consistency. Then, the filtered fields are merged to form a new dataset containing core information related to storage status, risk identification, and control strategies, ultimately outputting a fused preparation dataset.

[0089] The dataset to be fused is input into the multi-source data fusion algorithm, which performs structure matching and logical linkage to output the structured fusion result.

[0090] Specifically, after inputting the dataset for fusion into the multi-source data fusion algorithm, the data structure is first matched to identify the correspondence between fields in different data sources. For example, it may be necessary to categorize storage status, risk identification, and control strategy information from different data sources and ensure that data fields correspond structurally. Next, logical linkage is implemented to ensure that relevant information from different data sources can effectively coordinate. For example, if storage status data changes, it may affect the results of risk identification, thus requiring adjustments to control strategies. After completing structure matching and logical linkage, data integration is performed, merging the results from different data sources into a unified, structured dataset, ultimately outputting a structured fusion result.

[0091] The structured fusion results are categorized and organized according to battery number to generate warehouse data records.

[0092] It should be noted that the data in the structured fusion results is sorted according to the battery number to ensure that data from the same lifecycle stage of each power battery can be aggregated together during processing. Next, the relevant data fields for each power battery are checked to ensure that information such as temperature and humidity, gas concentration, safety risk level label, storage time limit, and power battery operating status is included. Then, the data for each power battery is integrated into a single record, forming a data row containing all relevant information. For each battery number, an independent storage data record is created, and the corresponding data fields are assigned to the corresponding positions in each record. Finally, all processed battery numbers and their corresponding storage data records are categorized and organized according to the battery number to ensure that the storage data record for each power battery is complete and accurate.

[0093] The warehouse analysis module analyzes warehouse data records, assesses the remaining usable capacity, cycle life, and safety status of power batteries, and outputs instructions based on the analysis results to automate the entire process from storage monitoring to disposal decision-making.

[0094] Extract remaining available capacity, cycle life, and safety-related fields from warehouse data records, and normalize them to generate a standard evaluation dataset.

[0095] Specifically, the remaining usable capacity, cycle life, and safety-related fields for each power battery are extracted from the warehouse data records. Next, the data type of each field is checked to ensure data completeness and absence of missing values. If missing values ​​exist, they are filled in as needed. Then, the extracted remaining usable capacity, cycle life, and safety-related fields are normalized. For remaining usable capacity, it is standardized to a range of [0,1] using a min-max normalization method. For cycle life, it is normalized to the maximum value to ensure all values ​​are on a uniform scale. Finally, safety-related fields are processed; if they are discrete, standardization or encoding methods can be used. After normalization, the results are integrated to generate a standard evaluation dataset.

[0096] Based on the standard evaluation dataset, linear regression and exponential fitting methods are used to calculate the remaining capacity decline trend and performance degradation rate, and the capacity index and lifetime prediction value are output by combining the cycle counter.

[0097] Specifically, the relationship between remaining available capacity and time is extracted, with time set as the independent variable and remaining available capacity as the dependent variable. The least squares method is used to calculate the linear regression equation, which is expressed as follows:

[0098] C(t) = a·t + b;

[0099] Where C(t) represents the remaining capacity at time t, a represents the linear slope, b represents the intercept, and t represents time;

[0100] By fitting the remaining capacity data using the least squares method, the optimal values ​​of a and b are calculated, thus obtaining the linear decreasing trend of the capacity.

[0101] Next, the performance degradation rate is calculated using an exponential fitting method. The relationship between remaining capacity and time is set as an exponential degradation model, expressed as:

[0102]

[0103] Where k represents the performance degradation rate, C0 represents the initial capacity, and ln represents the natural logarithm function;

[0104] The remaining capacity data for each time point in the collected time-series samples is fitted using a nonlinear least squares method, based on the exponential decay expression:

[0105] C(t) = C0·e -kt ;

[0106] Where e represents the base of the natural logarithm, with time t as the independent variable and remaining capacity C(t) as the dependent variable, the sum of squared residuals is minimized to find the parameter pair (C0,k) that minimizes the residuals, i.e. the optimal initial capacity C0 and performance decay rate k; then, by substituting the fitted C0 and k into the exponential decay expression, a fitting trend function of the remaining capacity changing with time can be established, representing the performance decay trend;

[0107] Finally, combining the capacity index output by the cycle counter, the predicted lifespan is calculated to predict the remaining battery life. The expression is as follows:

[0108]

[0109] Among them, T life C represents the predicted lifespan. threshold This indicates the set capacity threshold (derived from the safety constraints on the lower limit of capacity in the power battery storage management strategy, determined based on industry standards or algorithm training results).

[0110] It should also be noted that the capacity index output by the cycle counter is calculated by recording the number of charge-discharge cycles of the battery and combining it with the remaining capacity data after each charge-discharge cycle. Each time the battery completes a charge-discharge cycle, the remaining capacity is recorded. The remaining capacity data after each cycle is accumulated and analyzed to obtain the remaining capacity for each cycle number. By analyzing the remaining capacity data under different cycle numbers, the change in battery capacity under different cycle numbers can be calculated, ultimately outputting a capacity index that reflects the degree of performance degradation of the battery after a certain number of charge-discharge cycles.

[0111] Statistical analysis is performed on abnormal temperature and humidity, gas concentration fluctuations, and fault signals to determine the safety status level.

[0112] Specifically, historical data on temperature, humidity, gas concentration, and fault signals are extracted from warehouse data records. Each type of extracted data is traversed chronologically. For temperature and humidity fields, the values ​​are compared to see if they exceed preset normal temperature and humidity ranges (e.g., normal temperature range is -20℃ to 65℃, normal humidity range is 30% to 85%). For gas concentration fields, the values ​​are compared to see if they exceed preset upper limits (e.g., the upper limit for volatile gas concentration is set at 100ppm). For fault signal fields, non-zero values ​​are checked; if a value is non-zero, a fault is considered to have occurred. The total number of occurrences, duration, and fluctuation range of outliers within the abnormal range are statistically analyzed for each field (e.g., temperature exceeding the upper limit by more than 10℃ for 10 consecutive minutes). Based on the frequency, duration, and degree of deviation of the anomalies, temperature anomalies, humidity anomalies, gas concentration anomalies, and fault signals are classified into low, medium, and high risk levels.

[0113] The statistical results of abnormal temperature, humidity, gas concentration, and fault signals are scored according to preset risk level scoring rules. During scoring, the degree of abnormality of each statistical indicator is matched with a corresponding risk level and assigned a corresponding score; for example, a temperature anomaly level corresponds to a medium risk level and 50 points. After completing each scoring, the scores are weighted and calculated. The weighting coefficients are determined based on the degree of influence of each factor on battery storage safety; for example, the weights for temperature, gas concentration, and fault signals can be set to 0.3, 0.3, and 0.4, respectively. The weighted scores are summed to obtain a comprehensive risk score, and the corresponding safety status level is determined based on the comprehensive risk score; for example, a comprehensive score greater than 80 is considered high risk.

[0114] The capacity indicators, life prediction values, and safety status levels are combined to form a comprehensive assessment report.

[0115] Specifically, the capacity, predicted lifespan, and safety status level data for each power battery are extracted from the storage records. Next, the capacity and predicted lifespan are analyzed to assess the battery's performance status and remaining lifespan. Then, combined with the safety status level, the capacity, predicted lifespan, and safety status level of each power battery are combined to form a complete assessment report. For example, if a power battery has a low capacity, a short predicted lifespan, and a high-risk safety status level, the assessment report will indicate that the power battery needs to be prioritized for handling or replacement. Finally, a comprehensive assessment report is generated.

[0116] The comprehensive assessment report identifies the disposal type labels corresponding to capacity indicators, life prediction values, and safety status, and outputs disposal recommendations.

[0117] Specifically, the analysis of capacity indicators, predicted lifespan, and safety status level data in the comprehensive evaluation report, based on pre-set rules or empirical standards and analysis results of power battery storage safety requirements and industry standards, establishes reasonable ranges or critical value intervals for various sensor parameters. For example, temperature is set to 5℃~30℃, humidity to 30%~60%, hydrogen concentration to no more than 1% volume fraction, and fault signal voltage to no more than 12V, etc., determined by professionals in conjunction with equipment performance, safety boundaries, and statistical data. Different combinations of power battery types (e.g., high capacity, low lifespan; high capacity, high safety status) are matched. Based on each matching, a corresponding disposal type label is determined. For example, if a power battery has low capacity and a short predicted lifespan, but a high safety status level, it can be labeled "Replace"; if the capacity is normal, the lifespan is long, and the safety status level is high, it is labeled "Continue to Use". Then, the identified disposal type labels are combined with the evaluation results of each power battery to output corresponding disposal recommendations.

[0118] The disposal suggestions are matched with preset strategy rules to generate an operation instruction set, which is then sent to the warehouse scheduling and equipment control terminal to perform corresponding temperature and humidity adjustments and storage location adjustments.

[0119] Specifically, each disposal suggestion is compared with the preset strategy rules to determine the specific action to be taken for each suggestion. For example, if the disposal suggestion is "continue to use," the operation instruction set might include maintaining the current temperature and humidity settings; if the disposal suggestion is "replace," it might involve adjusting the temperature and humidity to suitable conditions for storing the new battery and rearranging the storage location. Then, a specific operation instruction set is generated, including temperature and humidity adjustment parameters, storage location change requirements, etc., and sent to the warehouse scheduling and equipment control terminal according to the operation steps. After receiving the instructions, the equipment control terminal executes the corresponding temperature and humidity adjustment and storage location adjustment operations to ensure that each battery is properly managed and stored.

[0120] In summary, this invention utilizes artificial intelligence algorithms to efficiently identify the state and potential risks of batteries, achieving accurate classification and prediction. This allows for dynamic adjustment of battery storage conditions without human intervention. It significantly improves the safety and intelligence of the used automotive power battery storage system, avoiding potential judgment errors and resource waste inherent in traditional manual management, and enhancing the overall efficiency of storage management and the safety of battery storage.

[0121] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A warehouse system for used automotive traction batteries, characterized in that: The application relates to a dynamic storage configuration method and system for power batteries of end-of-life vehicles. The data acquisition module collects power battery tracking data of end-of-life vehicles and performs preprocessing to obtain a feature data set, including, Collecting battery number, factory time, charge-discharge times, temperature data and use history data to obtain power battery tracking data, and using fixed rules to complete missing data and remove abnormal data, using the maximum and minimum value normalization method to standardize numerical value type data to obtain a feature data set; The safety evaluation module analyzes the feature data set using an artificial intelligence algorithm to generate a safety risk level label for the power battery and recommend storage environment parameters, and the specific steps are as follows, Using a feature extraction algorithm to extract the residual capacity change trend, temperature response feature, discharge stability index and historical fault signal of the power battery from the feature data set to form a two-dimensional feature matrix, and the specific steps are as follows, Slicing the feature data set according to a time window to generate multiple time series samples; Calculating the residual capacity change rate, temperature response slope, discharge voltage standard deviation and historical fault signal count value of each time series sample and performing encoding combination to form a feature vector of a single sample; Arranging all the feature vectors in time sequence to generate a two-dimensional feature matrix; Using an artificial intelligence algorithm to perform discriminant analysis on the two-dimensional feature matrix to generate a safety risk level label, and calling a mapping rule table to generate recommended storage environment parameters; The configuration scheme generation module automatically classifies and schedules the power battery to a matched storage area according to the safety risk level label, configures a temperature and humidity control device according to the recommended storage environment parameters, and generates a dynamic storage configuration scheme; The state monitoring module collects temperature and humidity, gas concentration and power battery operation signals in the storage area in real time to form a state monitoring data set; The storage data recording module uses a multi-source data fusion algorithm to structure and integrate the state monitoring data set, power battery tracking data, safety risk level label and dynamic storage configuration scheme to generate a storage data record; The storage analysis module analyzes the storage data record to evaluate the residual available capacity, cycle life and safety state of the power battery, and outputs instructions according to the analysis result to automatically control the whole process from storage monitoring to disposal decision.

2. The warehouse system of the used automotive power battery according to claim 1, characterized in that: The power battery is automatically classified and scheduled to a matched storage area according to the safety risk level label, and the specific steps are as follows, According to the safety risk level label of the power battery, the storage area configuration table is queried to identify the storage area number matched with the risk level and extract the corresponding storage time limit parameter; The residual capacity and operation state of the target area are retrieved, and the available storage area is selected and sorted according to the scheduling priority of the storage area; According to the safety risk level label of the power battery, the storage time limit parameter and the residual capacity and operation state of the target area, the scheduling instruction is generated by comprehensively considering the preset strategy rule; The scheduling instruction is implemented to automatically distribute the power battery to the specified storage area, adjust the storage time limit in the storage area according to the storage time limit parameter, and update the number and storage location record.

3. The warehouse system of the used automotive power battery according to claim 1, characterized in that: The temperature and humidity control device is configured according to the recommended storage environment parameters to generate a dynamic storage configuration scheme, and the specific steps are as follows, According to the target temperature value, humidity range and ventilation frequency in the recommended storage environment parameters, the initial setting value of the temperature and humidity control device is set; The initial setting value is input to the temperature and humidity control device, and the target temperature and humidity range are adjusted; According to the storage time limit parameter, the automatic adjustment cycle and operation time of the temperature and humidity control device are configured, and a dynamic warehouse configuration scheme is generated.

4. The warehouse system of the used automotive power battery according to claim 1, characterized in that: Through the state monitoring mechanism, the temperature and humidity, gas concentration and power battery operation signals in the warehouse area are collected, and denoising processing, numerical standardization and outlier rejection operations are performed, and various processing results are integrated into a state monitoring data set.

5. The warehouse system of the used automotive power battery according to claim 1, characterized in that: The warehouse data record is generated, and the specific steps are as follows, The state monitoring data set, power battery tracking data, safety risk level label and dynamic warehouse configuration scheme are respectively time-aligned, missing completed and format-standardized to obtain a standardized data package in a unified format; By extracting the fields related to storage state, risk identification and control strategy from the standardized data package, a fusion preparation data set is output; The fusion preparation data set is input into a multi-source data fusion algorithm for structure matching and logic linkage, and a structured fusion result is output; The structured fusion result is classified and arranged according to the battery number to generate a warehouse data record.

6. The warehouse system of old car power battery of claim 1, wherein: The warehouse data record is analyzed, and the remaining available capacity, cycle life and safety state of the power battery are evaluated, and the specific steps are as follows, The remaining available capacity, cycle life and safety related fields are extracted from the warehouse data record, and normalized to generate a standard evaluation data set; Based on the standard evaluation data set, the linear regression and exponential fitting methods are used to calculate the remaining capacity decline trend and performance decay rate, and the cycle counter outputs the capacity index and life prediction value; Statistical analysis is performed on the temperature and humidity abnormalities, gas concentration fluctuations and fault signals to determine the safety state level; The capacity index, life prediction value and safety state level are combined to form a comprehensive evaluation report.

7. The warehouse system of old car power battery of claim 1, wherein: According to the analysis results, the instructions are output, and the whole process from storage monitoring to disposal decision is automatically controlled, and the specific steps are as follows, Through the comprehensive evaluation report, the capacity index, life prediction value and safety state corresponding to the disposal type label are identified, and a disposal suggestion item is output; The disposal suggestion item is matched with the preset strategy rule to generate an operation instruction set, which is sent to the warehouse scheduling and equipment control terminal for corresponding temperature and humidity adjustment and storage location adjustment.

Images