Storage battery circulation full-period management method and system

Abstract

The invention provides a storage battery circulation full-period management method and system, and the method comprises the steps: firstly obtaining batch data, environment monitoring data, path node data, real-time state parameters and physical detection indexes; then, based on an electrolyte proportioning parameter and a pole plate thickness parameter in batch data, dynamically associating the charge-discharge cycle times and the voltage attenuation rate in the real-time state parameters, and generating a cross-link tracking link; according to a geographic position switching time sequence in the path node data and a temperature and humidity fluctuation interval in the environment monitoring data, a circulation track code is generated; and when the ratio of the internal resistance value to the residual capacity in the physical detection index exceeds a preset range corresponding to the charge and discharge state latch mark in the transfer track code, triggering reverse traceability processing, and updating the storage safety verification mark in the transfer track code as an abnormal mark, thereby realizing accurate positioning and real-time early warning of the cross-link risk root cause, and improving the safety of the storage safety verification mark in the transfer track code. And the cooperative processing efficiency of the full life cycle management of the storage battery is effectively improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of battery management, and in particular, to a method and system for the full-cycle management of battery transfer. Background Art

[0002] With the rapid development of the new energy industry, the large-scale application of storage batteries in the fields of energy storage systems, electric vehicles, etc. has put forward higher requirements for full-cycle management. The multi-source heterogeneous data generated in the production, storage, transportation, use, and recycling links of storage batteries (such as electrolyte ratio, transportation vibration, storage temperature and humidity, charge and discharge cycles, etc.) are significantly correlated. However, the existing technology lacks the ability to dynamically analyze cross-link data collaboratively, resulting in low root cause location efficiency of recycling indicators such as abnormal internal resistance and capacity attenuation, and it is difficult to achieve accurate traceability and risk warning of abnormal events. Summary of the Invention

[0003] The embodiments of the present application provide a method and system for the full-cycle management of battery transfer, which are used to solve the problems of low abnormal traceability efficiency caused by cross-link data fragmentation in the existing technology, the inability of static thresholds to adapt to dynamic attenuation characteristics, and the unquantified risk of spatio-temporal coupling in transportation and storage.

[0004] In a first aspect, the embodiments of the present application provide a method for the full-cycle management of battery transfer, including:

[0005] Obtaining batch data of the battery in the production link, environmental monitoring data in the storage link, path node data in the transportation link, real-time state parameters in the use link, and physical detection indicators in the recycling link;

[0006] Based on the electrolyte ratio parameter and plate thickness parameter in the batch data, dynamically associate the charge and discharge cycle times and voltage attenuation rate in the real-time state parameters, and generate a cross-link tracking link indexed by the unique identification code of the single battery;

[0007] According to the time sequence of geographical location switching in the path node data and the temperature and humidity fluctuation range in the environmental monitoring data, generate a transfer trajectory code bound to the unique identification code of the single battery;

[0008] When the ratio of the internal resistance value to the remaining capacity in the physical detection indicators exceeds the preset range corresponding to the charge and discharge state latch mark in the transfer trajectory code, trigger reverse traceability processing based on the cross-link tracking link, and update the storage safety check mark in the transfer trajectory code to an abnormal mark.

[0009] Optionally, based on the electrolyte ratio parameter and plate thickness parameter in the batch data, dynamically associate the charge and discharge cycle times and voltage attenuation rate in the real-time state parameters, and generate a cross-link tracking link indexed by the unique identification code of the single battery, including:

[0010] Calculate the initial capacity attenuation coefficient of the corresponding batch of storage batteries according to the sulfuric acid concentration gradient and additive proportion in the electrolyte ratio parameters, and fuse the initial capacity attenuation coefficient with the grid density distribution data in the plate thickness parameters to generate a batch attenuation reference value;

[0011] Divide the number of charge-discharge cycles into segment cumulative values according to the depth of discharge. Based on the slope of the polarization voltage recovery curve at the end of each charge-discharge, extract the voltage offset amount matching the batch attenuation reference value, and normalize the voltage offset amount according to the exponential growth trend of the segment cumulative values to generate a normalized voltage offset amount;

[0012] According to the non-linear correlation between the normalized voltage offset amount and the segment cumulative values, establish a dynamic compensation factor. Iteratively fit the dynamic compensation factor and the batch attenuation reference value according to the time series of production batches to generate a set of tracking link parameters including the electrolyte activity attenuation gradient and the plate corrosion rate. Based on the set of tracking link parameters, establish a multi-dimensional mapping relationship using the unique identification code of the single storage battery, batch data, and real-time status parameters;

[0013] Based on the multi-dimensional mapping relationship, associate and calibrate the electrolyte activity attenuation gradient with the charge-discharge state latch mark in the transfer trajectory code, and perform reverse verification on the plate corrosion rate and the residual plate thickness in the physical detection index to generate a verification difference value. Feed the verification difference value back into the multi-dimensional mapping relationship to generate a cross-link tracking link.

[0014] Optionally, according to the non-linear correlation between the normalized voltage offset amount and the segment cumulative values, establish a dynamic compensation factor. Iteratively fit the dynamic compensation factor and the batch attenuation reference value according to the time series of production batches to generate a set of tracking link parameters including the electrolyte activity attenuation gradient and the plate corrosion rate. Based on the set of tracking link parameters, establish a multi-dimensional mapping relationship using the unique identification code of the single storage battery, batch data, and real-time status parameters, including:

[0015] Based on the logarithmic growth trend of the normalized voltage offset amount and the segment cumulative values, use the product coefficient of the increment of the segment cumulative values and the change rate of the voltage offset amount within a sliding time window to construct an initial weight matrix of the dynamic compensation factor;

[0016] Align the initial weight matrix of the dynamic compensation factor with the batch attenuation reference value according to the time stamp of the production batch, and generate a dynamic attenuation compensation coefficient through the convolution operation of the fluctuation amplitude of the attenuation reference value and the weight matrix within the sliding time window;

[0017] Based on the spatial correlation between the dynamic decay compensation coefficient and the grid density distribution data in the plate thickness parameter, a calculation model for the electrolyte activity decay gradient is established. Using the calculation model of the electrolyte activity decay gradient, the decay slope of the electrolyte activity decay with the number of charge-discharge cycles is output, and the difference between the decay slope and the slope of the polarization voltage recovery curve is used as the initial estimate of the plate corrosion rate;

[0018] Based on the initial estimate of the plate corrosion rate and the historical degradation trend of the residual plate thickness in the physical detection index, the weight distribution of the dynamic decay compensation coefficient is optimized by the backpropagation algorithm to generate a tracking link parameter set including the correction amount of the electrolyte activity decay gradient and the optimized value of the plate corrosion rate;

[0019] Perform a time-axis superposition operation on the correction amount of the electrolyte activity decay gradient in the tracking link parameter set and the sulfuric acid concentration gradient in the batch data, and perform a spatial interpolation matching on the optimized value of the plate corrosion rate and the voltage decay rate in the real-time state parameters to generate a multi-dimensional mapping relationship.

[0020] Optionally, according to the geographical location switching timing in the path node data and the temperature and humidity fluctuation range in the environmental monitoring data, a transfer trajectory code bound to the unique identification code of the single battery is generated, including:

[0021] Based on the transport vehicle type and residence duration of adjacent nodes in the geographical location switching timing, the path switching frequency factor is calculated, and the geographical location compression code is generated using the path switching frequency factor according to the inverse proportional relationship between the impact coefficient corresponding to the transport vehicle type and the residence duration, where the geographical location compression code contains the spatio-temporal distribution characteristics of the transport impact accumulation value;

[0022] Extract the continuous over-standard duration and the peak value of the fluctuation amplitude exceeding the preset warehousing safety threshold within the temperature and humidity fluctuation range, calculate the temperature and humidity impact factor, and use the temperature and humidity impact factor to generate the initial assignment of the warehousing safety check mark through the product of the continuous over-standard duration and the peak value of the fluctuation amplitude;

[0023] Perform a spatio-temporal superposition operation on the transport impact accumulation value in the geographical location compression code and the temperature and humidity impact factor to generate a mixed trajectory feature vector, where the mixed trajectory feature vector embeds the activation condition threshold of the charge-discharge state latch mark associated with the unique identification code of the single battery;

[0024] According to the mutation gradient of the transport impact accumulation value between adjacent nodes and the temporal continuity of the continuous over-standard duration within the temperature and humidity fluctuation range, the trajectory anomaly coefficient is calculated;

[0025] Compare the trajectory anomaly coefficient with the activation condition threshold of the charge and discharge status latch flag to generate multi-dimensional verification data, and synchronously write the initial assignment of the warehousing safety verification flag, the temperature and humidity impact factor, and the multi-dimensional verification data into the dynamic verification field to generate a transfer trajectory code bound to the unique identification code of the single battery.

[0026] Optionally, extract the continuous over-standard duration and the peak value of the fluctuation amplitude exceeding the preset warehousing safety threshold within the temperature and humidity fluctuation range, calculate the temperature and humidity impact factor, and use the temperature and humidity impact factor to generate the initial assignment of the warehousing safety verification flag through the product of the continuous over-standard duration and the peak value of the fluctuation amplitude, including:

[0027] Based on the monitoring time points continuously exceeding the preset warehousing safety threshold within the temperature and humidity fluctuation range, extract the time interval and the over-standard duration between adjacent over-standard events, and calculate the time decay coefficient of the over-standard events;

[0028] Extract the maximum value of the peak value of the fluctuation amplitude and the fluctuation slope between adjacent peaks, and combine the time decay coefficient to calculate the dynamic weighting factor;

[0029] Perform segmented attenuation compensation on the continuous over-standard duration according to the time decay coefficient to generate the compensated over-standard duration, and perform amplitude normalization processing on the peak value of the fluctuation amplitude according to the dynamic weighting factor to generate the normalized fluctuation peak value;

[0030] Generate the temperature and humidity impact factor according to the product relationship between the compensated over-standard duration and the normalized fluctuation peak value, and perform linear superposition on the temperature and humidity impact factor and the dynamic weighting factor to generate the initial assignment of the warehousing safety verification flag.

[0031] Optionally, when the ratio of the internal resistance to the remaining capacity in the physical detection index exceeds the preset range corresponding to the charge and discharge status latch flag in the transfer trajectory code, trigger the reverse traceability process based on the cross-link tracking link, and update the warehousing safety verification flag in the transfer trajectory code to an abnormal identifier, including:

[0032] Based on the logarithmic attenuation characteristic of the ratio of the internal resistance to the remaining capacity, calculate the internal resistance capacity attenuation coefficient, and dynamically adjust the boundary value of the preset range corresponding to the charge and discharge status latch flag according to the historical change trend of the electrolyte activity attenuation gradient in the cross-link tracking link to generate a dynamic threshold interval;

[0033] When the internal resistance capacity attenuation coefficient exceeds the dynamic threshold interval, trigger the reverse traceability process, extract the spatio-temporal correlation characteristics of the cumulative value of the plate corrosion rate and the cumulative value of the transportation impact in the transfer trajectory code in the cross-link tracking link, and generate a traceability deviation value;

[0034] Calculate the parameter traceability weight distribution coefficient according to the matching degree between the traceability deviation value and the historical change trend of the electrolyte activity attenuation gradient. Based on the parameter traceability weight distribution coefficient, perform reverse interpolation operations on the grid density distribution data of the plate thickness parameter and the sulfuric acid concentration gradient of the electrolyte ratio parameter in the cross-link tracking link to generate a dynamic traceability matrix;

[0035] Perform a difference check on the predicted value of the residual plate thickness in the dynamic traceability matrix and the measured value of the residual plate thickness in the physical detection index to generate a check error factor, and linearly superimpose the check error factor with the initial assignment of the warehousing safety check mark to update the warehousing safety check mark to an abnormal identifier.

[0036] Optionally, calculating the parameter traceability weight distribution coefficient according to the matching degree between the traceability deviation value and the historical change trend of the electrolyte activity attenuation gradient, and based on the parameter traceability weight distribution coefficient, performing reverse interpolation operations on the grid density distribution data of the plate thickness parameter and the sulfuric acid concentration gradient of the electrolyte ratio parameter in the cross-link tracking link to generate a dynamic traceability matrix, including:

[0037] Extract the attenuation slope and fluctuation period within a continuous time window in the historical change trend of the electrolyte activity attenuation gradient, calculate the trend matching degree, and calculate the parameter traceability weight distribution coefficient according to the time attenuation coefficient of the spatio-temporal correlation feature between the trend matching degree and the cumulative value of transportation shock;

[0038] Spatially interpolate the grid density distribution data of the plate thickness parameter according to the parameter traceability weight distribution coefficient to generate an initial distribution matrix of the predicted value of the residual plate thickness, and perform time-axis reverse compensation on the sulfuric acid concentration gradient according to the historical change trend of the electrolyte activity attenuation gradient to generate a compensated sulfuric acid concentration distribution matrix;

[0039] Adjust the grid density weight in the initial distribution matrix of the predicted value of the residual plate thickness according to the mutation gradient of the cumulative value of transportation shock and the spatial correlation of the compensated sulfuric acid concentration distribution matrix to generate a dynamically adjusted predicted matrix of the residual plate thickness;

[0040] Perform spatio-temporal coupling operations on the dynamically adjusted predicted matrix of the residual plate thickness and the compensated sulfuric acid concentration distribution matrix to generate a dynamic traceability matrix.

[0041] In a second aspect, an embodiment of the present application provides a full-cycle management system for battery transfer, including:

[0042] An acquisition module, configured to acquire batch data of the storage battery in the production link, environmental monitoring data in the warehousing link, path node data in the transportation link, real-time status parameters in the usage link, and physical detection indicators in the recycling link;

[0043] An association module, configured to dynamically associate the charge and discharge cycle times and voltage attenuation rate in the real-time status parameters based on the electrolyte ratio parameter and plate thickness parameter in the batch data, and generate a cross-link tracking link indexed by the unique identification code of the single storage battery;

[0044] A generation module, configured to generate a transfer trajectory code bound to the unique identification code of the single storage battery according to the geographical location switching time sequence in the path node data and the temperature and humidity fluctuation range in the environmental monitoring data;

[0045] A trigger module, configured to trigger reverse traceability processing based on the cross-link tracking link and update the warehousing safety verification mark in the transfer trajectory code to an abnormal mark when the ratio of the internal resistance value to the remaining capacity in the physical detection indicators exceeds the preset range corresponding to the charge and discharge status latch mark in the transfer trajectory code.

[0046] In a third aspect, an embodiment of the present application provides a computing device, including a processor and a memory, where a computer program is stored in the memory, and the processor is configured to run the computer program to execute a method for managing the entire life cycle of storage battery transfer according to any one of the first aspects.

[0047] In a fourth aspect, an embodiment of the present application provides a computer storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, a method for managing the entire life cycle of storage battery transfer according to any one of the first aspects is implemented.

[0048] In the embodiment of the present application, batch data of the storage battery in the production link, environmental monitoring data in the warehousing link, path node data in the transportation link, real-time status parameters in the usage link, and physical detection indicators in the recycling link are acquired; based on the electrolyte ratio parameter and plate thickness parameter in the batch data, the charge and discharge cycle times and voltage attenuation rate in the real-time status parameters are dynamically associated, and a cross-link tracking link indexed by the unique identification code of the single storage battery is generated; according to the geographical location switching time sequence in the path node data and the temperature and humidity fluctuation range in the environmental monitoring data, a transfer trajectory code bound to the unique identification code of the single storage battery is generated; when the ratio of the internal resistance value to the remaining capacity in the physical detection indicators exceeds the preset range corresponding to the charge and discharge status latch mark in the transfer trajectory code, reverse traceability processing based on the cross-link tracking link is triggered, and the warehousing safety verification mark in the transfer trajectory code is updated to an abnormal mark.

[0049] The technical solution of this application realizes the multi-dimensional dynamic association of production parameters, transportation impacts, storage environments, and usage statuses by obtaining multi-link data throughout the entire life cycle of the battery and constructing a cross-linkage tracking link and a transfer trajectory code, thus solving the problem of data islands caused by traditional segmented management. Based on the dynamic association between the electrolyte ratio and the plate thickness parameters, the charge and discharge cycle times and the voltage attenuation rate are used to generate a tracking link with a unique identification code index, significantly improving the prediction accuracy of the battery attenuation characteristics. At the same time, by generating a transfer trajectory code through the spatio-temporal superposition of the transportation path and the storage temperature and humidity, and dynamically triggering the reverse traceability of abnormal internal resistance and capacity attenuation, combined with the dynamic threshold interval correction and safety mark update mechanism, the accurate positioning and real-time warning of the root cause of cross-linkage risks are realized, effectively improving the collaborative processing efficiency of the full life cycle management of the battery.

[0050] Furthermore, by fusing the electrolyte sulfuric acid concentration gradient and the plate grid density data to generate a batch attenuation reference value, and combining the voltage offset normalization processing of different charge and discharge depths, a dynamic compensation factor and a tracking link parameter set are constructed to realize the non-linear association modeling of production parameters and usage status. Based on the dynamic iterative fitting of the polarization voltage recovery curve slope and the batch attenuation reference value, the synergistic mechanism of the electrolyte activity attenuation gradient and the plate corrosion rate is quantified, solving the problem that traditional static models cannot adapt to the differences of multi-batch batteries. Further, through the multi-dimensional mapping relationship, the attenuation gradient is calibrated with the charge and discharge latch marks in the transfer trajectory code, and combined with the reverse verification of the remaining plate thickness to form a data closed-loop, significantly improving the analysis ability of the cross-linkage tracking link for complex attenuation modes and providing high-precision dynamic parameter support for abnormal traceability.

[0051] These aspects or other aspects of this application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0053] Figure 1 It is a flowchart of a method for managing the entire life cycle of battery transfer provided by an embodiment of this application;

[0054] Figure 2 It is a schematic structural diagram of a system for managing the entire life cycle of battery transfer provided by an embodiment of this application;

[0055] Figure 3 It is a schematic structural diagram of a computing device provided by an embodiment of this application. Detailed implementation manners

[0056] In order to enable those skilled in the art of the present technology to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application.

[0057] In some processes described in the specification, claims and the above-mentioned accompanying drawings of the present application, a plurality of operations that appear in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish each different operation, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit that "first" and "second" are of different types.

[0058] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0059] Figure 1 A flowchart of a full-cycle management method for battery transfer is provided for the embodiments of the present application, as Figure 1 shown, the method includes:

[0060] Step 101, obtaining batch data of the battery in the production link, environmental monitoring data in the storage link, path node data in the transportation link, real-time state parameters in the use link, and physical detection indicators in the recycling link;

[0061] In this step, the batch data refers to manufacturing parameters such as electrolyte ratio and plate thickness recorded during the production of the battery; the environmental monitoring data is the time-series record of the temperature and humidity sensors during storage; the path node data includes the type of transportation tool, the timestamp of geographical location switching, and the residence duration; the real-time state parameters refer to operation indicators such as the number of charge and discharge cycles and the voltage attenuation rate collected through the battery management system (BMS); the physical detection indicators are degradation parameters such as the internal resistance value, remaining capacity, and residual plate thickness measured during recycling.

[0062] In this embodiment, the whole-process data collection and trusted storage are realized through Internet of Things devices and blockchain technology: the MES system in the production link records the electrolyte ratio parameters (such as sulfuric acid concentration gradient) and the plate thickness grid density distribution data; a temperature and humidity sensor array is deployed in the warehousing link, and the fluctuation range is recorded at 5-minute intervals and the over-standard events are marked; the GPS and vibration sensors in the transportation link upload the path node coordinates, transportation tool types (such as truck / ship codes) and vibration shock peaks in real time; the BMS in the usage link collects the charge and discharge cycle times and the polarization voltage recovery curve slope every 30 seconds through the CAN bus; in the recycling link, an electrochemical workstation is used to measure the ratio of the internal resistance value to the remaining capacity, and the spatial distribution of the residual plate thickness is obtained through laser scanning.

[0063] For example, a certain type of lead-acid battery generates a unique identification code "BAT-2023-05A1" in the production link, records its electrolyte ratio as sulfuric acid concentration 36%, additive ratio 2%, and the plate thickness is 1.2mm ± 0.05mm (grid density 120 meshes); during storage, it is stored in the warehouse numbered WH-07, and the environmental monitoring data shows that the temperature exceeds 35°C (threshold 30°C) for 3 consecutive days and the humidity peak is 85% (threshold 80%); the transportation route is "City S → City W → City C", the truck transportation tool code is TRK-009, and the residence times are 2 hours (City S) and 5 hours (City W) respectively; in the usage link, the cumulative charge and discharge cycles are 152 times, and the voltage attenuation rate drops from 3.65V to 3.52V (the polarization voltage recovery slope decreases by 0.8mV / s after each cycle); during recycling, the measured internal resistance value rises from the initial 12mΩ to 28mΩ, the remaining capacity is 62% of the nominal value, and the residual plate thickness is 0.9mm.

[0064] Step 102: Based on the electrolyte ratio parameters and plate thickness parameters in the batch data, dynamically associate the charge and discharge cycle times and voltage attenuation rate in the real-time state parameters, and generate a cross-link tracking link indexed by the unique identification code of the single battery.

[0065] In this step, the electrolyte ratio parameters include the sulfuric acid concentration gradient and the additive ratio, which are used to quantify the electrolyte activity attenuation rate; the plate thickness parameters refer to the plate grid density distribution data, which reflects the spatial non-uniformity of the plate corrosion rate; dynamic association means establishing a mapping relationship between production parameters and usage state parameters through a non-linear model; the cross-link tracking link is a data chain indexed by the unique identification code, integrating the key parameters of the production, usage and recycling links, and supporting the reverse traceability of abnormal events.

[0066] In this embodiment, first, find the sulfuric acid concentration of the electrolyte and the content of the additive from the production data, and then combine the thickness of the electrode plate and the density of the internal grid to calculate an initial capacity attenuation coefficient as a reference benchmark. Then, according to the number of charge and discharge cycles and the depth of each discharge during battery use, divide the data into segments, and then combine the change of voltage attenuation. Calculate a voltage offset through the speed of voltage recovery after each charge and discharge, and adjust it to a standard value. Finally, use the relationship between this standard value and the number of charge and discharge cycles to calculate a dynamically adjusted coefficient, and then combine it with the previous reference benchmark to calculate repeatedly to obtain the speed of electrolyte activity attenuation and the speed of electrode plate corrosion, and finally generate a data chain indexed by the unique ID of the battery to facilitate finding the root cause of battery problems in the future.

[0067] For example, the unique identification code of a certain single battery is "BAT-2023-05A1", its sulfuric acid concentration in the electrolyte is 36%, the additive proportion is 2%, the grid density of the electrode plate is 120 mesh, and the calculated initial capacity attenuation coefficient is 0.85; in the usage process, the cumulative number of charge and discharge cycles is 152, and the proportion of cycles with a discharge depth of 80% is 60%. The voltage attenuation rate drops from 3.65V to 3.52V, and the slope of the polarization voltage recovery curve drops from 1.2mV / s to 0.8mV / s. The extracted voltage offset is 0.15V and is normalized to 0.92; based on the non-linear relationship between the normalized voltage offset and the segmented cumulative value, a dynamic compensation factor of 1.12 is generated. After iterative fitting with the batch attenuation reference value, the electrolyte activity attenuation gradient is 0.08% / cycle, and the electrode plate corrosion rate is 0.002mm / cycle. Finally, a cross-link tracking link indexed by "BAT-2023-05A1" is generated to support subsequent anomaly tracing and dynamic threshold correction.

[0068] Step 103: Generate a transfer trajectory code bound to the unique identification code of the single battery according to the geographical location switching time sequence in the path node data and the temperature and humidity fluctuation range in the environmental monitoring data;

[0069] In this step, the geographical location switching time sequence refers to the path nodes passed by the battery during transportation and their time stamp sequence, which is used to reflect the spatial distribution and time continuity of the transportation path; the temperature and humidity fluctuation range refers to the duration and fluctuation amplitude range of the over-standard events recorded by the temperature and humidity sensors in the warehousing link, which is used to quantify the impact of the warehousing environment on the battery performance; the transfer trajectory code is a dynamic data structure that integrates the key features of the transportation path and the warehousing environment, and is bound to the single battery with the unique identification code as the index, supporting real-time monitoring of the full-cycle transfer status and anomaly tracing.

[0070] In this embodiment, first, according to the switching times and residence durations of various locations in the transportation route, combined with the type of transportation vehicle (such as trucks, ships), a route switching frequency factor is calculated to reflect the cumulative situation of vibration and shock during transportation; then, the time and peak values when the temperature and humidity exceed the safety thresholds are found from the warehouse environment data, and a temperature and humidity impact factor is calculated to reflect the potential risks of the warehouse environment on the battery; then, the cumulative value of transportation shock and the temperature and humidity impact factor are combined to generate a mixed feature vector, and this vector is bound to the unique identification code of the battery to form a transfer trajectory code.

[0071] For example, the unique identification code of a single battery is "BAT-2023-05A1", its transportation route is "City S → City W → City C", the transportation vehicle is a truck (impact coefficient 1.2), and the residence durations are 2 hours (in City S) and 5 hours (in City W) respectively, generating a geographical location compression code; during storage, it is stored in Warehouse No. WH-07. The temperature and humidity monitoring data shows that the temperature exceeds 35°C (threshold 30°C) continuously for 3 days and the humidity peak is 85% (threshold 80%). The calculated temperature and humidity impact factor is 0.75; the cumulative value of transportation shock and the temperature and humidity impact factor are superimposed to generate a mixed trajectory feature vector, and the trajectory anomaly coefficient is calculated to be 1.15; finally, a transfer trajectory code indexed by "BAT-2023-05A1" is generated, including dynamic verification fields such as the transportation route, warehouse environment, and charge and discharge latching marks, supporting reverse traceability of subsequent internal resistance anomalies and capacity attenuation.

[0072] Step 104, when the ratio of the internal resistance value to the remaining capacity in the physical detection index exceeds the preset range corresponding to the charge and discharge state latching mark in the transfer trajectory code, trigger the reverse traceability process based on the cross-link tracking link, and update the warehouse safety verification mark in the transfer trajectory code to an abnormal identifier;

[0073] In this step, the ratio of the internal resistance value to the remaining capacity is a key index detected in the recycling link, reflecting the health status of the battery; the charge and discharge state latching mark is a dynamic field in the transfer trajectory code, used to record the abnormal risk of the battery charge and discharge state; the reverse traceability process refers to analyzing the impact of production, transportation, storage and other links on the battery performance in reverse from the recycling link through the cross-link tracking link; the warehouse safety verification mark is an identification field in the transfer trajectory code, used to mark whether there is an abnormal risk in the warehouse environment.

[0074] In this embodiment, first, an internal resistance-capacity attenuation coefficient is calculated based on the internal resistance value and remaining capacity detected during recovery to determine whether the health state of the battery is abnormal; then, based on the historical data of the attenuation of electrolyte activity in the cross-link tracking link, the preset range of the charge and discharge state latching mark is dynamically adjusted to generate a dynamic threshold interval; next, if the internal resistance-capacity attenuation coefficient exceeds this dynamic threshold interval, reverse traceability processing is triggered to find the relationship between the plate corrosion rate and the cumulative value of transportation shock in the cross-link tracking link and calculate a traceability deviation value; finally, based on this deviation value and the historical trend of electrolyte activity attenuation, the warehousing safety verification mark is adjusted to an abnormal mark, and the relevant fields in the transfer track code are updated.

[0075] For example, the unique identification code of a certain single battery is "BAT-2023-05A1". The internal resistance value detected during recovery increases from the initial 12 mΩ to 28 mΩ, and the remaining capacity is 62% of the nominal value. The calculated internal resistance-capacity attenuation coefficient is 1.5; based on the historical data of the electrolyte activity attenuation gradient of 0.08% / cycle in the cross-link tracking link, the preset range of the charge and discharge state latching mark is dynamically adjusted to 1.0 - 1.4 to generate a dynamic threshold interval; since the internal resistance-capacity attenuation coefficient of 1.5 exceeds the dynamic threshold interval of 1.4, reverse traceability processing is triggered. The relationship between the plate corrosion rate of 0.002 mm / cycle and the cumulative value of transportation shock is extracted from the cross-link tracking link, and the calculated traceability deviation value is 0.12; based on the deviation value and the historical trend of electrolyte activity attenuation, the warehousing safety verification mark is updated to an abnormal mark, and the transfer track code is synchronously updated.

[0076] Since there is a complex non-linear relationship between production parameters (such as electrolyte ratio, plate thickness) and usage status (such as charge and discharge cycle times, voltage attenuation rate) in the full-cycle management of batteries, and the existing technology lacks dynamic correlation analysis of these cross-link data, resulting in the inability to accurately predict the battery attenuation trend or locate the root cause of abnormalities. Based on this, in some embodiments, according to step 102, based on the electrolyte ratio parameter and plate thickness parameter in the batch data, the charge and discharge cycle times and voltage attenuation rate in the real-time status parameters are dynamically correlated to generate a cross-link tracking link indexed by the unique identification code of the single battery, including:

[0077] Step 201, calculate the initial capacity attenuation coefficient of the corresponding batch of batteries according to the sulfuric acid concentration gradient and additive proportion in the electrolyte ratio parameter, and fuse the initial capacity attenuation coefficient with the grid density distribution data in the plate thickness parameter to generate a batch attenuation reference value;

[0078] In this step, the sulfuric acid concentration gradient refers to the spatial distribution change of the sulfuric acid concentration in the electrolyte; the additive proportion is the content ratio of other chemical substances in the electrolyte except sulfuric acid; the initial capacity attenuation coefficient is the initial estimated value reflecting the attenuation of the battery capacity with the usage time; the grid density distribution data describes the density of the internal grid of the electrode plate and its spatial distribution; the batch attenuation reference value is a reference value generated based on production parameters and is used to quantify the initial state of battery attenuation.

[0079] In this embodiment, first, find the sulfuric acid concentration of the electrolyte and the content of the additive from the production data, and calculate an initial capacity attenuation coefficient to reflect the attenuation rate of the battery capacity; then, combine the thickness of the electrode plate and the density of the internal grid to adjust this initial capacity attenuation coefficient into a more accurate reference value, called the batch attenuation reference value, as the basis for subsequent calculations.

[0080] Step 202: Divide the number of charge-discharge cycles into segmented cumulative values according to the depth of discharge, extract the voltage offset amount matching the batch attenuation reference value based on the slope of the polarization voltage recovery curve at the end of each charge-discharge, and normalize the voltage offset amount according to the exponential growth trend of the segmented cumulative values to generate a normalized voltage offset amount.

[0081] In this step, the depth of discharge refers to the percentage of the battery discharge capacity in each charge-discharge cycle; the segmented cumulative value is the statistics of the number of charge-discharge cycles divided according to the depth of discharge; the slope of the polarization voltage recovery curve is the speed of voltage recovery after each charge-discharge; the voltage offset amount is the deviation between the actual voltage attenuation and the reference value; the normalization process is to adjust the voltage offset amount to a standard range for convenient subsequent calculations.

[0082] In this embodiment, first, divide the data into segments according to the number of charge-discharge times and the depth of each discharge during battery use; then, calculate a voltage offset amount through the speed of voltage recovery after each charge-discharge to reflect the deviation between the actual voltage attenuation and the reference value; finally, adjust this voltage offset amount into a standard value according to the exponential growth trend of the number of charge-discharge times for convenient subsequent calculations.

[0083] Step 203: Establish a dynamic compensation factor according to the non-linear correlation between the normalized voltage offset amount and the segmented cumulative values, perform iterative fitting on the dynamic compensation factor and the batch attenuation reference value according to the time series of production batches to generate a tracking link parameter set including the electrolyte activity attenuation gradient and the electrode plate corrosion rate, and based on the tracking link parameter set, establish a multi-dimensional mapping relationship using the unique identification code of the single battery, batch data, and real-time state parameters.

[0084] In this step, the dynamic compensation factor is a coefficient that is dynamically adjusted according to the voltage offset and the number of charge and discharge cycles, and is used to correct the predicted value of battery attenuation; iterative fitting is to make the predicted value closer and closer to the actual value through repeated calculations; the tracking link parameter set is a key parameter set that includes the attenuation gradient of electrolyte activity and the plate corrosion rate; the multi-dimensional mapping relationship is a data structure that associates production data, usage status, and recycling detection data through a unique identification code.

[0085] In this embodiment, first, based on the relationship between the standardized voltage offset and the number of charge and discharge cycles, a dynamically adjusted coefficient called the dynamic compensation factor is calculated; then, combined with the previous batch attenuation reference value, repeated calculations are performed to obtain the attenuation rate of electrolyte activity and the corrosion rate of the plates, generating a tracking link parameter set; finally, these parameters and production data and usage status data are associated through the unique "ID card" of the battery to form a multi-dimensional mapping relationship, which is convenient for subsequent problem finding and data analysis.

[0086] Step 204: Based on the multi-dimensional mapping relationship, associate and calibrate the attenuation gradient of the electrolyte activity with the charge and discharge status latch mark in the transfer trajectory code, and perform a reverse check on the plate corrosion rate and the residual plate thickness in the physical detection index to generate a check difference, and feedback the check difference into the multi-dimensional mapping relationship to generate a cross-link tracking link.

[0087] In this step, the reverse check is to find the deviation by comparing the residual plate thickness detected by recycling with the predicted value; the check difference refers to the difference between the predicted value and the measured value; the cross-link tracking link is to string production, usage, and recycling data into a line through a unique identification code to support anomaly tracing.

[0088] In this embodiment, first, associate the attenuation rate of the electrolyte activity with the charge and discharge status mark in the transfer trajectory code to calibrate the attenuation state of the battery; then, compare the residual plate thickness detected by recycling with the predicted value to calculate a deviation value; finally, feedback this deviation value into the multi-dimensional mapping relationship to dynamically adjust the tracking link parameters and generate a complete cross-link tracking link, which is convenient for finding the root cause of battery problems in the future.

[0089] For example, the unique identification code of a single battery cell is "BAT-2023-05A1". Its sulfuric acid concentration in the electrolyte is 36%, the additive proportion is 2%, the grid density of the electrode plate is 120 meshes, and the initial capacity attenuation coefficient is calculated to be 0.85. Combining with the electrode plate thickness parameter, the batch attenuation reference value 1.2 is generated; during the usage process, the cumulative charge and discharge cycles are 152 times, and the proportion of cycles with a discharge depth of 80% is 60%. The voltage attenuation rate drops from 3.65V to 3.52V, and the slope of the polarization voltage recovery curve drops from 1.2mV / s to 0.8mV / s. The extracted voltage offset is 0.15V and is normalized to 0.92; based on the non-linear relationship between the normalized voltage offset and the segmented cumulative value, a dynamic compensation factor 1.12 is generated. After iterative fitting with the batch attenuation reference value, the electrolyte activity attenuation gradient is 0.08% / cycle and the electrode plate corrosion rate is 0.002mm / cycle, and a tracking link parameter set is generated; through the unique identification code "BAT-2023-05A1", the tracking link parameter set is associated with production data and usage status data to form a multi-dimensional mapping relationship; the electrolyte activity attenuation gradient is calibrated with the charge and discharge status latching mark in the transfer trajectory code, and the electrode plate corrosion rate is inversely verified with the remaining thickness of the electrode plate detected during recycling (measured value 0.9mm). A calibration difference of 0.02mm is generated and fed back to the multi-dimensional mapping relationship, and finally a cross-link tracking link is generated to support subsequent abnormal traceability and dynamic threshold correction.

[0090] Since in the full-cycle management of the battery, the relationship between the voltage attenuation rate and the number of charge and discharge cycles is complex and non-linear, it is difficult for the existing technology to accurately describe this dynamic change through a static model. At the same time, the synergistic action mechanism between the electrode plate corrosion rate and the electrolyte activity attenuation gradient has not been fully quantified, resulting in the inability to accurately locate the root cause during abnormal traceability. Based on this, as another embodiment, according to step 203, based on the non-linear correlation between the normalized voltage offset and the segmented cumulative value, a dynamic compensation factor is established. The dynamic compensation factor and the batch attenuation reference value are iteratively fitted according to the time series of production batches to generate a tracking link parameter set including the electrolyte activity attenuation gradient and the electrode plate corrosion rate. Based on the tracking link parameter set, a multi-dimensional mapping relationship is established using the unique identification code of the single battery cell, batch data, and real-time status parameters, including:

[0091] Step 301, based on the logarithmic growth trend of the normalized voltage offset and the segmented cumulative value, use the product coefficient of the increment of the segmented cumulative value and the change rate of the voltage offset within a sliding time window to construct the initial weight matrix of the dynamic compensation factor;

[0092] In this step, the sliding time window refers to a continuous time range used for dynamically analyzing data changes; the segmented cumulative value increment is the increase in the number of charge-discharge cycles within the time window; the voltage offset rate of change is the rate at which the voltage offset changes over time; the product coefficient is the product result of the segmented cumulative value increment and the voltage offset rate of change, used to reflect the dynamic relationship between the two; the initial weight matrix is a table containing multiple weight values for storing the initial calculation results of the dynamic compensation factor.

[0093] In this embodiment, first, a continuous time range is selected to count the increase in the number of charge-discharge cycles during this time, and at the same time, the rate of change of the voltage offset is calculated; then, these two values are multiplied to obtain a product coefficient to reflect the relationship between the number of charge-discharge cycles and the voltage offset; finally, an initial weight matrix is constructed using these product coefficients as the basis for the dynamic compensation factor.

[0094] Step 302: Align the initial weight matrix of the dynamic compensation factor with the batch decay reference value according to the time stamp of the production batch, and generate a dynamic decay compensation coefficient through the convolution operation between the fluctuation amplitude of the decay reference value within the sliding time window and the weight matrix.

[0095] In this step, the time stamp is the time mark of the production batch for aligning data of different batches; the fluctuation amplitude of the decay reference value is the change range of the batch decay reference value within the time window; the convolution operation is a mathematical calculation method for combining the weight matrix and the fluctuation amplitude of the decay reference value to generate a dynamic decay compensation coefficient.

[0096] In this embodiment, first, align the initial weight matrix with the time mark of the production batch to ensure consistent data time; then, calculate the change range of the batch decay reference value during this time; finally, use the convolution operation to combine the weight matrix and the fluctuation amplitude of the decay reference value to generate a dynamic decay compensation coefficient for adjusting the predicted value of battery decay.

[0097] Step 303: Establish a calculation model for the electrolyte activity decay gradient based on the spatial correlation between the dynamic decay compensation coefficient and the grid density distribution data in the plate thickness parameter. Use the calculation model of the electrolyte activity decay gradient to output the decay slope of the electrolyte activity decay with the number of charge-discharge cycles, and take the difference between the decay slope and the slope of the polarization voltage recovery curve as the initial estimate of the plate corrosion rate.

[0098] In this step, the spatial correlation is the distribution relationship of the plate thickness parameter at different positions; the calculation model is a mathematical tool used to describe the change of the electrolyte activity attenuation gradient with the number of charge-discharge cycles; the attenuation slope is the change rate of the electrolyte activity attenuation gradient; the slope of the polarization voltage recovery curve is the speed of voltage recovery after each charge-discharge; the initial estimated value of the plate corrosion rate is calculated through the difference between the attenuation slope and the slope of the polarization voltage recovery curve.

[0099] In this embodiment, first, according to the distribution relationship between the dynamic attenuation compensation coefficient and the plate thickness parameter, a calculation model is established to describe the change of the electrolyte activity attenuation gradient; then, this model is used to calculate the attenuation slope, and then compared with the slope of the polarization voltage recovery curve to obtain a difference as the initial estimated value of the plate corrosion rate.

[0100] Step 304: Based on the initial estimated value of the plate corrosion rate and the historical degradation trend of the residual plate thickness in the physical detection index, optimize the weight allocation of the dynamic attenuation compensation coefficient through the backpropagation algorithm, and generate a tracking link parameter set including the correction amount of the electrolyte activity attenuation gradient and the optimized value of the plate corrosion rate;

[0101] In this step, the backpropagation algorithm is an optimization method used to adjust the weight allocation of the dynamic attenuation compensation coefficient; the tracking link parameter set is a key parameter set including the correction amount of the electrolyte activity attenuation gradient and the optimized value of the plate corrosion rate.

[0102] In this embodiment, first, use the initial estimated value of the plate corrosion rate and the historical data of the residual plate thickness detected by recycling to optimize the weight allocation of the dynamic attenuation compensation coefficient through the backpropagation algorithm; then generate a tracking link parameter set, which includes the corrected electrolyte activity attenuation gradient and the optimized plate corrosion rate.

[0103] Step 305: Perform a time-axis superposition operation on the correction amount of the electrolyte activity attenuation gradient in the tracking link parameter set and the sulfuric acid concentration gradient in the batch data, and perform a spatial interpolation matching on the optimized value of the plate corrosion rate and the voltage attenuation rate in the real-time state parameter to generate a multi-dimensional mapping relationship;

[0104] In this step, the time-axis superposition operation is to combine the correction amount of the electrolyte activity attenuation gradient and the sulfuric acid concentration gradient in chronological order; the spatial interpolation matching is to match the optimized value of the plate corrosion rate and the voltage attenuation rate at different positions; the multi-dimensional mapping relationship is a data structure that associates production data, usage status, and recycling detection data through a unique identification code.

[0105] In this embodiment, first, the corrected electrolyte activity decay gradient and the sulfuric acid concentration gradient in the production data are combined in chronological order; then, the optimized plate corrosion rate and the voltage decay rate in the usage state are matched at different positions; finally, these data are associated with the unique identification code of the battery to generate a multi-dimensional mapping relationship, which facilitates subsequent problem finding and data analysis.

[0106] For example, the unique identification code of a certain single battery is "BAT-2023-05A1", its electrolyte sulfuric acid concentration is 36%, and the grid density of the plate is 120 meshes. First, according to the sulfuric acid concentration and plate thickness parameters, the initial capacity decay coefficient is calculated to be 0.85, and the batch decay reference value 1.2 is generated in combination with the grid density distribution data of the plate. During the usage process, the battery has been charged and discharged 152 times in total, among which the proportion of cycles with a discharge depth of 80% is 60%, the voltage decay rate drops from 3.65V to 3.52V, and the slope of the polarization voltage recovery curve drops from 1.2mV / s to 0.8mV / s. Based on these data, the voltage offset is extracted as 0.15V and normalized to 0.92 through an exponential growth trend. Next, based on the logarithmic growth trend of the normalized voltage offset and the segmented cumulative value, the product coefficient of the increment of the segmented cumulative value within the sliding time window and the change rate of the voltage offset is used to construct the initial weight matrix of the dynamic compensation factor. Align the initial weight matrix with the time stamp of the production batch of the batch decay reference value, and generate the dynamic decay compensation coefficient 1.12 through convolution operation. Then, according to the distribution relationship between the dynamic decay compensation coefficient and the plate thickness parameters, a calculation model of the electrolyte activity decay gradient is established, and the electrolyte activity decay gradient is obtained as 0.08% / cycle. The difference between the decay slope and the slope of the polarization voltage recovery curve is used as the initial estimated value of the plate corrosion rate, which is 0.002mm / cycle. Subsequently, based on the initial estimated value of the plate corrosion rate and the historical data of the residual thickness of the recycled detected plates, the weight distribution of the dynamic decay compensation coefficient is optimized through the backpropagation algorithm to generate a set of tracking link parameters, which includes the corrected electrolyte activity decay gradient of 0.07% / cycle and the optimized plate corrosion rate of 0.0018mm / cycle. Finally, the corrected electrolyte activity decay gradient is subjected to a time-axis superposition operation with the sulfuric acid concentration gradient in the batch data, and the optimized plate corrosion rate is subjected to spatial interpolation matching with the voltage decay rate in the real-time state parameters to generate a multi-dimensional mapping relationship. This mapping relationship supports subsequent anomaly tracing and dynamic threshold correction, providing data support for the full-cycle management of the battery.

[0107] Since during the transportation and storage of the battery, the vibration and shock of the transportation vehicle and the temperature and humidity fluctuations in the storage environment have a significant impact on the battery performance, but the existing technology lacks the ability to quantitatively analyze these external factors and dynamically monitor them, resulting in the inability to accurately evaluate their contribution to battery attenuation. Based on this, in some embodiments, as described in step 103, according to the geographical location switching timing in the path node data and the temperature and humidity fluctuation range in the environmental monitoring data, a transfer trajectory code bound to the unique identification code of the single battery is generated, including:

[0108] Step 401, based on the transportation vehicle type and residence duration of adjacent nodes in the geographical location switching timing, calculate a path switching frequency factor, and use the path switching frequency factor to generate a geographical location compression code according to the inverse proportional relationship between the impact coefficient corresponding to the transportation vehicle type and the residence duration, where the geographical location compression code contains the spatio-temporal distribution characteristics of the cumulative value of transportation shocks;

[0109] In this step, the path switching frequency factor is a coefficient reflecting the switching frequency of adjacent nodes in the transportation path; the impact coefficient is a quantitative value of the vibration and shock of different transportation vehicles on the battery; the geographical location compression code is a data coding form used to record the spatio-temporal characteristics of geographical location switching in the transportation path; the cumulative value of transportation shocks is the sum of vibration and shock during transportation.

[0110] In this embodiment, first, according to the switching time and residence duration of adjacent nodes in the transportation path, calculate a path switching frequency factor to reflect the complexity of the transportation path; then, combine the impact coefficient corresponding to the type of transportation vehicle (such as a truck, a ship) to generate a geographical location compression code, which contains the cumulative value of vibration and shock during transportation.

[0111] Step 402, extract the continuous over-standard duration and the peak value of the fluctuation amplitude exceeding the preset storage safety threshold within the temperature and humidity fluctuation range, calculate a temperature and humidity impact factor, and use the temperature and humidity impact factor to generate an initial assignment of the storage safety verification mark through the product of the continuous over-standard duration and the peak value of the fluctuation amplitude;

[0112] In this step, the temperature and humidity fluctuation range is the change range of temperature and humidity in the storage environment; the continuous over-standard duration is the continuous time when the temperature and humidity exceed the safety threshold; the peak value of the fluctuation amplitude is the maximum value of temperature and humidity fluctuation; the temperature and humidity impact factor is a quantitative value reflecting the impact of the storage environment on the battery performance; the storage safety verification mark is an identification field used to record the storage environment risk.

[0113] In this embodiment, first, find the time and peak values of temperature and humidity exceeding the safety thresholds from the warehousing environment data, and calculate a temperature and humidity impact factor to reflect the potential risk of the warehousing environment on the battery; then, use this impact factor to generate an initial assignment of the warehousing safety verification mark as the basis for subsequent risk judgment.

[0114] Step 403: Perform a spatio-temporal superposition operation on the cumulative value of transportation shock in the geographical location compression encoding and the temperature and humidity impact factor to generate a mixed trajectory feature vector, where the activation condition threshold of the charge and discharge status latch mark associated with the unique identification code of the single battery is embedded in the mixed trajectory feature vector;

[0115] In this step, the mixed trajectory feature vector is a data vector generated by combining the cumulative value of transportation shock and the temperature and humidity impact factor; the activation condition threshold is the condition value for triggering the charge and discharge status latch mark.

[0116] In this embodiment, first, combine the cumulative value of transportation shock and the temperature and humidity impact factor to generate a mixed trajectory feature vector; then, bind this vector to the unique identification code of the battery and embed the activation condition threshold of the charge and discharge status latch mark in the vector to facilitate subsequent judgment of whether the battery status is abnormal.

[0117] Step 404: Calculate a trajectory anomaly coefficient based on the mutation gradient of the cumulative value of transportation shock between adjacent nodes and the temporal continuity of the duration of continuous exceeding the standard within the temperature and humidity fluctuation range;

[0118] In this step, the mutation gradient is the change speed of the cumulative value of transportation shock between adjacent nodes; the temporal continuity is the distribution characteristic of the temperature and humidity exceeding the standard events in time; the trajectory anomaly coefficient is a comprehensive index reflecting the impact of transportation and warehousing links on the battery performance.

[0119] In this embodiment, first, calculate the change speed of the cumulative value of transportation shock between adjacent nodes, and then combine the time distribution of the temperature and humidity exceeding the standard events to calculate a trajectory anomaly coefficient to comprehensively evaluate the impact of transportation and warehousing links on the battery.

[0120] Step 405: Compare the trajectory anomaly coefficient with the activation condition threshold of the charge and discharge status latch mark to generate multi-dimensional verification data, and synchronously write the initial assignment of the warehousing safety verification mark, the temperature and humidity impact factor, and the multi-dimensional verification data into the dynamic verification field to generate a transfer trajectory code bound to the unique identification code of the single battery;

[0121] In this step, the multi-dimensional verification data is a multi-dimensional data set including transportation shock, warehousing environment, and charge and discharge status; the dynamic verification field is the part of the transfer trajectory code used to store verification data.

[0122] In this embodiment, first, the trajectory anomaly coefficient is compared with the activation condition threshold of the charge-discharge status latch flag to generate multi-dimensional verification data. Then, the initial assignment of the warehousing safety verification flag, the temperature and humidity impact factor, and the multi-dimensional verification data are written into the dynamic verification field together to generate a transfer trajectory code bound to the unique battery identification code, facilitating subsequent risk monitoring and anomaly traceability.

[0123] For example, the unique identification code of a single battery is "BAT-2023-05A1", its transportation route is "City S → City W → City C", and the transportation vehicle is a truck (code TRK-009). It stays in City S for 2 hours and in City W for 5 hours. According to the type of transportation vehicle and the staying duration, the path switching frequency factor is calculated to be 1.2, and combined with the impact coefficient corresponding to the truck, a geographical location compression code is generated, which includes a transportation impact cumulative value of 0.85. In the warehousing link, this battery is stored in Warehouse No. WH-07. The environmental monitoring data shows that the temperature has exceeded 35°C (threshold 30°C) for 3 consecutive days, the humidity peak has reached 85% (threshold 80%), the duration of continuous exceeding the standard is 72 hours, and the peak value of the fluctuation range is 10°C. Based on these data, the temperature and humidity impact factor is calculated to be 0.75, and the initial assignment of the warehousing safety verification flag is generated. Next, the transportation impact cumulative value of 0.85 and the temperature and humidity impact factor of 0.75 are subjected to a spatio-temporal superposition operation to generate a mixed trajectory feature vector, and the activation condition threshold of 1.5 of the charge-discharge status latch flag associated with the battery unique identification code is embedded in the vector. Then, according to the mutation gradient of the transportation impact cumulative value between adjacent nodes and the temporal continuity of the temperature and humidity exceeding the standard events, the trajectory anomaly coefficient is calculated to be 1.8. The trajectory anomaly coefficient of 1.8 is compared with the activation condition threshold of 1.5 of the charge-discharge status latch flag to generate multi-dimensional verification data. Finally, the initial assignment of the warehousing safety verification flag, the temperature and humidity impact factor, and the multi-dimensional verification data are synchronously written into the dynamic verification field to generate a transfer trajectory code bound to "BAT-2023-05A1". This code supports subsequent risk monitoring and anomaly traceability, providing data support for the full-cycle management of the battery.

[0124] Since the duration and fluctuation range of the temperature and humidity exceeding the standard events in the warehousing link have timeliness and spatial distribution characteristics on the performance of the battery, and the existing technology lacks dynamic quantitative analysis of these characteristics, resulting in insufficient accuracy of the warehousing environment risk assessment. Based on this, as another embodiment, according to step 402, the duration of continuous exceeding the standard and the peak value of the fluctuation range exceeding the preset warehousing safety threshold within the temperature and humidity fluctuation range are extracted, the temperature and humidity impact factor is calculated, and the initial assignment of the warehousing safety verification flag is generated by multiplying the temperature and humidity impact factor by the duration of continuous exceeding the standard and the peak value of the fluctuation range, including:

[0125] Step 501: Based on the monitoring time points within the temperature and humidity fluctuation range that continuously exceed the preset warehousing safety threshold, extract the time intervals and over-standard durations between adjacent over-standard events, and calculate the time decay coefficient of the over-standard events.

[0126] In this step, the monitoring time point is the specific time when the temperature and humidity exceed the preset safety threshold; adjacent over-standard events are continuously occurring temperature and humidity over-standard events; the time interval is the time difference between adjacent over-standard events; the over-standard duration is the duration of a single over-standard event; and the time decay coefficient is a coefficient reflecting the timeliness impact of over-standard events.

[0127] In this embodiment, first, find the time points in the temperature and humidity monitoring data that continuously exceed the safety threshold, and calculate the time intervals between adjacent over-standard events and the duration of each over-standard; then, calculate a time decay coefficient based on these data to reflect the timeliness of the impact of over-standard events on the battery.

[0128] Step 502: Extract the maximum value of the peak of the fluctuation amplitude and the fluctuation slope between adjacent peaks, and combine with the time decay coefficient to calculate the dynamic weighting factor.

[0129] In this step, the peak of the fluctuation amplitude is the maximum value of the temperature and humidity fluctuation; the fluctuation slope is the change speed between adjacent peaks; and the dynamic weighting factor is a weight value generated by combining the time decay coefficient and the fluctuation slope, used to quantify the comprehensive impact of over-standard events.

[0130] In this embodiment, first, find the maximum value of the temperature and humidity fluctuation and the change speed between adjacent peaks; then, combine with the previously calculated time decay coefficient to calculate a dynamic weighting factor to comprehensively reflect the impact of over-standard events on the battery.

[0131] Step 503: Perform segmented decay compensation on the over-standard duration according to the time decay coefficient to generate the compensated over-standard duration, and perform amplitude normalization processing on the peak of the fluctuation amplitude according to the dynamic weighting factor to generate the normalized peak of the fluctuation.

[0132] In this step, the segmented decay compensation is to adjust the over-standard duration according to the time decay coefficient; the compensated over-standard duration is the adjusted over-standard duration; the amplitude normalization processing is to adjust the peak of the fluctuation amplitude to the standard range according to the dynamic weighting factor; and the normalized peak of the fluctuation is the adjusted value of the fluctuation amplitude.

[0133] In this embodiment, first, adjust the over-standard duration with the time decay coefficient to generate the compensated over-standard duration; then, adjust the peak of the fluctuation amplitude with the dynamic weighting factor to generate the normalized peak of the fluctuation for convenient subsequent calculation.

[0134] Step 504: Generate a temperature and humidity impact factor based on the product relationship between the compensated over-standard duration and the normalized fluctuation peak value, and linearly superimpose the temperature and humidity impact factor and the dynamic weighting factor to generate an initial assignment of the warehousing safety verification mark;

[0135] In this step, the temperature and humidity impact factor is a quantitative value reflecting the impact of the warehousing environment on battery performance; linear superposition is to combine the temperature and humidity impact factor and the dynamic weighting factor in proportion; the warehousing safety verification mark is an identification field used to record the risks of the warehousing environment.

[0136] In this embodiment, first multiply the compensated over-standard duration by the normalized fluctuation peak value to generate a temperature and humidity impact factor; then, combine this impact factor and the dynamic weighting factor in proportion to generate an initial assignment of the warehousing safety verification mark as the basis for subsequent risk judgment.

[0137] For example, the unique identification code of a single battery is "BAT-2023-05A1", which is stored in Warehouse No. WH-07 during the warehousing process. Environmental monitoring data shows that the temperature and humidity have exceeded the safety threshold for 3 consecutive days, where the temperature exceeds 35°C (threshold 30°C) and the humidity peak reaches 85% (threshold 80%). First, extract the time interval between adjacent over-standard events as 24 hours, the over-standard duration as 72 hours, and calculate the time decay coefficient as 0.8; then, extract the maximum value of the fluctuation amplitude peak as 10°C and the fluctuation slope between adjacent peaks as 0.5, and calculate the dynamic weighting factor as 0.6 in combination with the time decay coefficient; next, segmentally decay and compensate the over-standard duration according to the time decay coefficient to generate a compensated over-standard duration of 57.6 hours, and normalize the amplitude of the fluctuation amplitude peak according to the dynamic weighting factor to generate a normalized fluctuation peak value of 6°C; finally, generate a temperature and humidity impact factor of 345.6 based on the product relationship between the compensated over-standard duration of 57.6 hours and the normalized fluctuation peak value of 6°C, and linearly superimpose it with the dynamic weighting factor of 0.6 to generate an initial assignment of the warehousing safety verification mark of 207.36. This initial assignment is used for the generation of subsequent transfer track encoding and risk monitoring.

[0138] In the battery recycling process, abnormal changes in the ratio of internal resistance to remaining capacity may be caused by factors in multiple links such as production, transportation, and warehousing. The prior art lacks the ability to dynamically trace these cross-link impacts, resulting in low efficiency in locating the root cause of abnormalities. Based on this, in some embodiments, according to step 104, when the ratio of internal resistance to remaining capacity in the physical detection index exceeds the preset range corresponding to the charge and discharge status latch mark in the transfer track encoding, trigger reverse traceability processing based on the cross-link tracking link, and update the warehousing safety verification mark in the transfer track encoding to an abnormal identification, including:

[0139] Step 601: Calculate the internal resistance capacity attenuation coefficient based on the logarithmic attenuation characteristic of the ratio of the internal resistance value to the remaining capacity, and dynamically adjust the preset range boundary value corresponding to the charge-discharge state latch flag according to the historical change trend of the electrolyte activity attenuation gradient in the cross-link tracking link to generate a dynamic threshold interval;

[0140] In this step, the internal resistance capacity attenuation coefficient is a quantitative index reflecting the attenuation speed of the ratio of the internal resistance value to the remaining capacity; the logarithmic attenuation characteristic is the mathematical characteristic of the ratio of the internal resistance value to the remaining capacity changing with time; the dynamic threshold interval is the abnormal judgment range dynamically adjusted according to the historical data of the electrolyte activity attenuation gradient.

[0141] In this embodiment, first, calculate an internal resistance capacity attenuation coefficient according to the change rule of the ratio of the internal resistance value to the remaining capacity to reflect the attenuation speed of the battery health state; then, combine the historical data of the electrolyte activity attenuation gradient in the cross-link tracking link to dynamically adjust the preset range boundary value of the charge-discharge state latch flag to generate a dynamic threshold interval for judging whether the battery state is abnormal.

[0142] Step 602: When the internal resistance capacity attenuation coefficient exceeds the dynamic threshold interval, trigger reverse traceability processing, extract the spatio-temporal correlation characteristics of the cumulative value of the plate corrosion rate and the cumulative value of the transportation shock in the transfer track code in the cross-link tracking link, and generate a traceability deviation value;

[0143] In this step, reverse traceability processing is to analyze the influence of production, transportation, storage and other links on battery performance from the recycling link in reverse; the cumulative value of the plate corrosion rate is the sum of the plate corrosion rate accumulated over time; the spatio-temporal correlation characteristic is the distribution relationship of the cumulative value of the transportation shock in time and space; the traceability deviation value is a quantitative index reflecting the difference between the abnormal root cause and the actual detection value.

[0144] In this embodiment, when the internal resistance capacity attenuation coefficient exceeds the dynamic threshold interval, trigger reverse traceability processing; extract the cumulative value of the plate corrosion rate from the cross-link tracking link, and combine the cumulative value of the transportation shock in the transfer track code to analyze their distribution relationship in time and space to generate a traceability deviation value to reflect the difference between the abnormal root cause and the actual detection value.

[0145] Step 603: Calculate the parameter traceability weight distribution coefficient according to the matching degree between the traceability deviation value and the historical change trend of the electrolyte activity attenuation gradient, and based on the parameter traceability weight distribution coefficient, perform reverse interpolation operations on the grid density distribution data of the plate thickness parameters and the sulfuric acid concentration gradient of the electrolyte ratio parameters in the cross-link tracking link to generate a dynamic traceability matrix;

[0146] In this step, the parameter traceability weight distribution coefficient is a quantitative value reflecting the contribution weights of different links to the abnormal root cause; the reverse interpolation operation is to inversely calculate the plate thickness parameter and the electrolyte concentration gradient according to the weight distribution coefficient; the dynamic traceability matrix is a data set containing the predicted value of the residual plate thickness and the corrected value of the electrolyte concentration.

[0147] In this embodiment, first, according to the historical change trend of the traceability deviation value and the electrolyte activity attenuation gradient, a parameter traceability weight distribution coefficient is calculated to reflect the contribution weights of different links to the abnormal root cause; then, this weight distribution coefficient is used to perform a reverse interpolation operation on the plate thickness parameter and the electrolyte concentration gradient to generate a dynamic traceability matrix, which contains the predicted value of the residual plate thickness and the corrected value of the electrolyte concentration.

[0148] Step 604: Perform a difference check on the predicted value of the residual plate thickness in the dynamic traceability matrix and the measured value of the residual plate thickness in the physical detection index to generate a check error factor, and linearly superimpose the check error factor with the initial assignment of the warehousing safety check mark to update the warehousing safety check mark as an abnormal identifier.

[0149] In this step, the difference check is to compare the predicted value of the residual plate thickness with the measured value; the check error factor is the difference between the predicted value and the measured value; the abnormal identifier is an identification field used to mark that there is a risk in the warehousing environment.

[0150] In this embodiment, first, the predicted value of the residual plate thickness in the dynamic traceability matrix is compared with the measured value of the recovery detection to calculate a check error factor; then, this error factor is combined with the initial assignment of the warehousing safety check mark to update the warehousing safety check mark as an abnormal identifier, indicating that there is a risk in the warehousing environment.

[0151] For example, the unique identification code of a certain single battery is "BAT-2023-05A1". During the recycling process, the internal resistance value is detected to increase from the initial 12 mΩ to 28 mΩ, and the remaining capacity is 62% of the nominal value. The internal resistance capacity attenuation coefficient is calculated to be 1.5. According to the historical data of the electrolyte activity attenuation gradient of 0.08% / cycle in the cross-link tracking link, the preset range boundary value of the charge and discharge state latch mark is dynamically adjusted to generate a dynamic threshold interval of 1.0 - 1.4. Since the internal resistance capacity attenuation coefficient of 1.5 exceeds the dynamic threshold interval of 1.4, reverse traceability processing is triggered. The cumulative value of the plate corrosion rate of 0.002 mm / cycle and the cumulative value of the transportation impact of 0.85 in the transfer trajectory code are extracted from the cross-link tracking link to generate a traceability deviation value of 0.12. According to the historical change trends of the traceability deviation value and the electrolyte activity attenuation gradient, the parameter traceability weight distribution coefficient of 0.8 is calculated, and based on this coefficient, inverse interpolation operations are performed on the grid density distribution data of the plate thickness parameters and the sulfuric acid concentration gradient of the electrolyte ratio parameters in the cross-link tracking link to generate a dynamic traceability matrix. The difference between the predicted value of the remaining plate thickness of 0.9 mm in the dynamic traceability matrix and the measured value of 0.88 mm detected during recycling is verified to generate a verification error factor of 0.02 mm, and it is linearly superimposed with the initial assignment of 207.36 of the warehousing safety verification mark to update the warehousing safety verification mark to an abnormal identification, indicating that there is a risk in the warehousing environment. This result supports the risk warning and abnormal traceability of subsequent full-cycle management.

[0152] During the reverse traceability process, the spatial distribution characteristics of the plate thickness parameters and the electrolyte concentration gradient are crucial for locating the root cause of anomalies. However, the existing technology lacks the ability to perform dynamic interpolation and coupling analysis on these parameters, resulting in insufficient accuracy of the traceability results. Based on this, as another embodiment, according to step 603, based on the matching degree between the traceability deviation value and the historical change trend of the electrolyte activity attenuation gradient, the parameter traceability weight distribution coefficient is calculated. Based on the parameter traceability weight distribution coefficient, inverse interpolation operations are performed on the grid density distribution data of the plate thickness parameters and the sulfuric acid concentration gradient of the electrolyte ratio parameters in the cross-link tracking link to generate a dynamic traceability matrix, including:

[0153] Step 701: Extract the attenuation slope and fluctuation period within a continuous time window in the historical change trend of the electrolyte activity attenuation gradient, calculate the trend matching degree, and calculate the parameter traceability weight distribution coefficient according to the time attenuation coefficient of the spatio-temporal correlation characteristics between the trend matching degree and the cumulative value of the transportation impact;

[0154] In this step, the attenuation slope is the rate of change of the electrolyte activity attenuation gradient over time; the fluctuation period is the periodic characteristic of the change in the attenuation slope; the trend matching degree is a quantitative index reflecting the consistency between the current attenuation trend and the historical trend; the time attenuation coefficient is the coefficient by which the cumulative value of the transportation shock decays over time; the parameter traceability weight distribution coefficient is a quantitative value reflecting the contribution weights of different links to the abnormal root cause.

[0155] In this embodiment, first, the attenuation slope and the fluctuation period are found from the historical data of the electrolyte activity attenuation gradient, and a trend matching degree is calculated to reflect the consistency between the current attenuation trend and the historical trend. Then, in combination with the time attenuation coefficient of the cumulative value of the transportation shock, a parameter traceability weight distribution coefficient is calculated to reflect the contribution weights of different links to the abnormal root cause.

[0156] Step 702: Perform spatial interpolation on the grid density distribution data of the plate thickness parameter according to the parameter traceability weight distribution coefficient to generate an initial distribution matrix of the predicted value of the residual plate thickness, and perform time-axis reverse compensation on the sulfuric acid concentration gradient according to the historical change trend of the electrolyte activity attenuation gradient to generate a compensated sulfuric acid concentration distribution matrix.

[0157] In this step, spatial interpolation is to perform interpolation calculation on the plate thickness parameter at different positions according to the parameter traceability weight distribution coefficient; the initial distribution matrix is the initial data set of the predicted value of the residual plate thickness; time-axis reverse compensation is to perform reverse adjustment on the sulfuric acid concentration gradient according to the historical trend of the electrolyte activity attenuation gradient; the compensated sulfuric acid concentration distribution matrix is the adjusted sulfuric acid concentration data set.

[0158] In this embodiment, first, perform interpolation calculation on the plate thickness parameter at different positions with the parameter traceability weight distribution coefficient to generate an initial distribution matrix of the predicted value of the residual plate thickness. Then, according to the historical trend of the electrolyte activity attenuation gradient, perform reverse adjustment on the sulfuric acid concentration gradient to generate a compensated sulfuric acid concentration distribution matrix.

[0159] Step 703: Adjust the grid density weights in the initial distribution matrix of the predicted value of the residual plate thickness according to the mutation gradient of the cumulative value of the transportation shock and the spatial correlation between the compensated sulfuric acid concentration distribution matrix to generate a dynamically adjusted predicted matrix of the residual plate thickness.

[0160] In this step, the mutation gradient is the rate of change of the cumulative value of the transportation shock between adjacent nodes; the spatial correlation is the relationship between the compensated sulfuric acid concentration distribution matrix and the predicted value of the residual plate thickness at different positions; the grid density weight is the weight value of the plate thickness parameter at different positions; the dynamically adjusted predicted matrix of the residual plate thickness is the adjusted data set of the residual plate thickness.

[0161] In this embodiment, first, the change rate of the accumulated transportation shock value between adjacent nodes is calculated, and then, in combination with the spatial distribution characteristics of the compensated sulfuric acid concentration distribution matrix, the grid density weights in the initial distribution matrix of the predicted value of the residual plate thickness are adjusted to generate a dynamically adjusted predicted matrix of the residual plate thickness.

[0162] Step 704: Perform a spatio-temporal coupling operation on the dynamically adjusted predicted matrix of the residual plate thickness and the compensated sulfuric acid concentration distribution matrix to generate a dynamic traceability matrix.

[0163] In this step, the spatio-temporal coupling operation combines the dynamically adjusted predicted matrix of the residual plate thickness and the compensated sulfuric acid concentration distribution matrix in terms of time and space; the dynamic traceability matrix is a data set containing the predicted value of the residual plate thickness and the corrected value of the sulfuric acid concentration.

[0164] In this embodiment, first, the dynamically adjusted predicted matrix of the residual plate thickness and the compensated sulfuric acid concentration distribution matrix are combined in terms of time and space to generate a dynamic traceability matrix, which contains the predicted value of the residual plate thickness and the corrected value of the sulfuric acid concentration and is used for subsequent anomaly traceability and risk warning.

[0165] For example, the unique identification code of a single battery is "BAT-2023-05A1". In the reverse traceability process, first, the attenuation slope of 0.08% / cycle and the fluctuation period of 30 days are extracted from the historical data of the electrolyte activity attenuation gradient, and the trend matching degree is calculated to be 0.9; combined with the time attenuation coefficient of 0.8 of the accumulated transportation shock value, the parameter traceability weight distribution coefficient of 0.72 is calculated. Then, this weight distribution coefficient is used for spatial interpolation of the grid density distribution data of the plate thickness parameters to generate the initial distribution matrix of the predicted value of the residual plate thickness; at the same time, according to the historical trend of the electrolyte activity attenuation gradient, the sulfuric acid concentration gradient is compensated in the reverse direction of the time axis to generate the compensated sulfuric acid concentration distribution matrix. Next, according to the mutation gradient of 0.5 of the accumulated transportation shock value and the spatial correlation of the compensated sulfuric acid concentration distribution matrix, the grid density weights in the initial distribution matrix of the predicted value of the residual plate thickness are adjusted to generate a dynamically adjusted predicted matrix of the residual plate thickness. Finally, a spatio-temporal coupling operation is performed on the dynamically adjusted predicted matrix of the residual plate thickness and the compensated sulfuric acid concentration distribution matrix to generate a dynamic traceability matrix, which contains the predicted value of the residual plate thickness of 0.9 mm and the corrected value of the sulfuric acid concentration of 36.5%. This dynamic traceability matrix supports subsequent anomaly traceability and risk warning and provides data support for the full-cycle management of the battery.

[0166] Figure 2 FIG. [ID] is a schematic structural diagram of a full-cycle management system for battery transfer provided by an embodiment of the present application. As Figure 2 shown, the system includes:

[0167] An acquisition module 21, configured to acquire batch data of a storage battery in the production link, environmental monitoring data in the warehousing link, path node data in the transportation link, real-time status parameters in the usage link, and physical detection indexes in the recycling link;

[0168] An association module 22, configured to dynamically associate the charge-discharge cycle times and voltage attenuation rate in the real-time status parameters based on the electrolyte ratio parameter and plate thickness parameter in the batch data, and generate a cross-link tracking link indexed by the unique identification code of a single storage battery;

[0169] A generation module 23, configured to generate a transfer trajectory code bound to the unique identification code of a single storage battery according to the geographical location switching time sequence in the path node data and the temperature and humidity fluctuation range in the environmental monitoring data;

[0170] A trigger module 24, configured to trigger reverse traceability processing based on the cross-link tracking link and update the warehousing safety verification mark in the transfer trajectory code to an abnormal mark when the ratio of the internal resistance value to the remaining capacity in the physical detection indexes exceeds a preset range corresponding to the charge-discharge status latch mark in the transfer trajectory code.

[0171] Figure 2 The described storage battery transfer full-cycle management system can execute Figure 1 The storage battery transfer full-cycle management method described in the illustrated embodiment, and its implementation principle and technical effects will not be elaborated further. For the storage battery transfer full-cycle management system in the above embodiment, the specific manners in which each module and unit perform operations have been described in detail in the embodiment related to the method, and will not be elaborated here.

[0172] In a possible design, Figure 2 The storage battery transfer full-cycle management system in the illustrated embodiment can be implemented as a computing device, as Figure 3 shown, and this computing device can include a storage component 31 and a processing component 32;

[0173] The storage component 31 stores one or more computer instructions, and among them, the one or more computer instructions are called and executed by the processing component 32.

[0174] The processing component 32 is used to obtain batch data of the battery during the production link, environmental monitoring data during the storage link, path node data during the transportation link, real-time status parameters during the usage link, and physical detection indicators during the recycling link; based on the electrolyte ratio parameter and plate thickness parameter in the batch data, dynamically associate the charge and discharge cycle times and voltage attenuation rate in the real-time status parameters, and generate a cross-link tracking link indexed by the unique identification code of the single battery; generate a transfer trajectory code bound to the unique identification code of the single battery according to the geographical location switching time sequence in the path node data and the temperature and humidity fluctuation range in the environmental monitoring data; when the ratio of the internal resistance value to the remaining capacity in the physical detection indicators exceeds the preset range corresponding to the charge and discharge status latch mark in the transfer trajectory code, trigger reverse traceability processing based on the cross-link tracking link, and update the storage safety verification mark in the transfer trajectory code to an abnormal mark.

[0175] Among them, the processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0176] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0177] Of course, the computing device may also necessarily include other components, such as input / output interfaces, display components, communication components, etc.

[0178] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above peripheral interface module may be an output device, an input device, etc.

[0179] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0180] Among them, the computing device may be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device may refer to a cloud server, and the above processing component, storage component, etc. may be basic server resources leased or purchased from a cloud computing platform.

[0181] The embodiments of the present application also provide a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above-mentioned Figure 1 a method for managing the entire life cycle of battery transfer shown in the embodiments.

[0182] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0183] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0184] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0185] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present application.

Claims

1. A battery circulation full cycle management method, characterized in that: include: Obtaining batch data of batteries in the production link, environmental monitoring data in the storage link, path node data in the transportation link, real-time status parameters in the use link, and physical detection indicators in the recycling link; Based on the electrolyte ratio parameters and the plate thickness parameters in the batch data, the number of charge and discharge cycles and the voltage decay rate in the real-time status parameters are dynamically associated to generate a cross-link tracking link indexed by the unique identification code of the single battery; Generate a flow track code bound to a unique identification code of a single battery according to the geographical location switching timing in the path node data and the temperature and humidity fluctuation range in the environmental monitoring data; When the ratio of the internal resistance value to the remaining capacity in the physical detection indicator exceeds the preset range corresponding to the charge and discharge status latch mark in the circulation track code, the reverse traceability processing based on the cross-link tracking link is triggered, and the warehouse safety verification mark in the circulation track code is updated to an abnormal mark.

2. The method according to claim 1, characterized in that Based on the electrolyte ratio parameters and the plate thickness parameters in the batch data, the number of charge and discharge cycles and the voltage decay rate in the real-time status parameters are dynamically associated to generate a cross-link tracking link indexed by the unique identification code of the single battery, including: According to the sulfuric acid concentration gradient and the proportion of additives in the electrolyte ratio parameters, the initial capacity attenuation coefficient of the corresponding batch of batteries is calculated, and the initial capacity attenuation coefficient is merged with the grid density distribution data in the plate thickness parameters to generate a batch attenuation reference value; The number of charge and discharge cycles is divided into segmented cumulative values ​​according to the discharge depth, and based on the slope of the polarization voltage recovery curve of the voltage decay rate at the end of each charge and discharge, a voltage offset matching the batch decay reference value is extracted, and the voltage offset is normalized according to the exponential growth trend of the segmented cumulative value to generate a normalized voltage offset; According to the nonlinear correlation between the normalized voltage offset and the segmented cumulative value, a dynamic compensation factor is established, and the dynamic compensation factor and the batch attenuation reference value are iteratively fitted according to the time series of the production batch to generate a tracking link parameter set including the electrolyte activity attenuation gradient and the plate corrosion rate. Based on the tracking link parameter set, a multi-dimensional mapping relationship is established using the single battery unique identification code and batch data and real-time status parameters; Based on the multi-dimensional mapping relationship, the electrolyte activity attenuation gradient is associated and calibrated with the charge and discharge state latch mark in the flow trajectory code, and the plate corrosion rate is reversely checked with the plate residual thickness in the physical detection index to generate a verification difference, which is then fed back into the multi-dimensional mapping relationship to generate a cross-link tracking link.

3. The method according to claim 2, characterized in that According to the nonlinear correlation between the normalized voltage offset and the segmented cumulative value, a dynamic compensation factor is established, and the dynamic compensation factor and the batch attenuation reference value are iteratively fitted according to the time series of the production batch to generate a tracking link parameter set including the electrolyte activity attenuation gradient and the plate corrosion rate. Based on the tracking link parameter set, a multi-dimensional mapping relationship is established using the single battery unique identification code and batch data and real-time status parameters, including: Based on the logarithmic growth trend of the normalized voltage offset and the segmented cumulative value, an initial weight matrix of the dynamic compensation factor is constructed by adopting the product coefficient of the segmented cumulative value increment and the voltage offset change rate within the sliding time window; Aligning the initial weight matrix of the dynamic compensation factor with the batch attenuation reference value according to the timestamp of the production batch, and generating a dynamic attenuation compensation coefficient by performing a convolution operation on the attenuation reference value fluctuation amplitude within the sliding time window and the weight matrix; According to the spatial correlation between the dynamic attenuation compensation coefficient and the grid density distribution data in the plate thickness parameter, a calculation model for the electrolyte activity attenuation gradient is established, and the calculation model for the electrolyte activity attenuation gradient is used to output the attenuation slope of the electrolyte activity attenuation gradient as the number of charge and discharge cycles changes, and the difference between the attenuation slope and the slope of the polarization voltage recovery curve is used as the initial estimate of the plate corrosion rate; Based on the initial estimated value of the electrode plate corrosion rate and the historical degradation trend of the electrode plate residual thickness in the physical detection index, the weight distribution of the dynamic attenuation compensation coefficient is optimized by a back propagation algorithm to generate a tracking link parameter set including an electrolyte activity attenuation gradient correction amount and an electrode plate corrosion rate optimization value; The electrolyte activity attenuation gradient correction value in the tracking link parameter set is superimposed on the sulfuric acid concentration gradient in the batch data on the time axis, and the plate corrosion rate optimization value is spatially interpolated and matched with the voltage attenuation rate in the real-time state parameter to generate a multi-dimensional mapping relationship.

4. The method according to claim 1, characterized in that: According to the geographical location switching timing in the path node data and the temperature and humidity fluctuation range in the environmental monitoring data, a flow trajectory code bound to the unique identification code of the single battery is generated, including: Based on the transportation tool type and the stay time of the adjacent nodes in the geographic location switching sequence, a path switching frequency factor is calculated, and the path switching frequency factor is used to generate a geographic location compression code according to the inverse proportional relationship between the impact coefficient corresponding to the transportation tool type and the stay time, wherein the geographic location compression code includes the spatiotemporal distribution characteristics of the transportation impact cumulative value; Extract the continuous exceeding time and fluctuation amplitude peak value of the temperature and humidity fluctuation range that exceeds the preset storage safety threshold, calculate the temperature and humidity influence factor, and use the temperature and humidity influence factor to generate the initial assignment of the storage safety verification mark through the product of the continuous exceeding time and the fluctuation amplitude peak value; Performing a spatiotemporal superposition operation on the transport impact cumulative value in the geographic location compression code and the temperature and humidity influencing factor to generate a hybrid trajectory feature vector, wherein the hybrid trajectory feature vector is embedded with an activation condition threshold of a charge and discharge state latch mark associated with the unique identification code of the single battery; The trajectory anomaly coefficient is calculated according to the sudden change gradient of the transport impact cumulative value between adjacent nodes and the temporal continuity of the duration of continuous exceeding of the standard within the temperature and humidity fluctuation range; The trajectory anomaly coefficient is compared with the activation condition threshold of the charge and discharge status latch mark to generate multi-dimensional verification data, and the initial assignment of the warehouse safety verification mark, the temperature and humidity influencing factor and the multi-dimensional verification data are synchronously written into the dynamic verification field to generate a circulation trajectory code bound to the unique identification code of the single battery.

5. The method according to claim 4, characterized in that Extract the continuous exceeding time and fluctuation amplitude peak value of the temperature and humidity fluctuation range that exceeds the preset storage safety threshold, calculate the temperature and humidity influence factor, and use the temperature and humidity influence factor to generate the initial assignment of the storage safety verification mark by multiplying the continuous exceeding time and the fluctuation amplitude peak value, including: Based on the monitoring time points at which the temperature and humidity continuously exceed the preset storage safety threshold within the temperature and humidity fluctuation range, the time intervals between adjacent exceeding events and the duration of exceeding the standard are extracted, and the time attenuation coefficient of the exceeding event is calculated; Extracting the maximum value of the fluctuation amplitude peak value and the fluctuation slope between adjacent peak values, and combining the time attenuation coefficient to calculate the dynamic weighting factor; Performing segmented attenuation compensation on the duration of exceeding the standard according to the time attenuation coefficient to generate the duration of exceeding the standard after compensation, and performing amplitude normalization processing on the peak value of the fluctuation amplitude according to the dynamic weighting factor to generate the normalized fluctuation peak value; According to the product relationship between the excess time after compensation and the normalized fluctuation peak value, the temperature and humidity influence factor is generated, and the temperature and humidity influence factor is linearly superimposed with the dynamic weighting factor to generate the initial assignment of the warehouse safety verification mark.

6. The method according to claim 1, characterized in that When the ratio of the internal resistance value to the remaining capacity in the physical detection index exceeds the preset range corresponding to the charge and discharge state latch mark in the circulation track code, the reverse tracing process based on the cross-link tracking link is triggered, and the storage safety verification mark in the circulation track code is updated to an abnormal mark, including: Based on the logarithmic attenuation characteristic of the ratio of the internal resistance value to the remaining capacity, the internal resistance capacity attenuation coefficient is calculated, and according to the historical change trend of the electrolyte activity attenuation gradient in the cross-link tracking link, the preset range boundary value corresponding to the charge and discharge state latch mark is dynamically adjusted to generate a dynamic threshold interval; When the internal resistance capacity attenuation coefficient exceeds the dynamic threshold range, the reverse tracing process is triggered to extract the temporal and spatial correlation characteristics of the cumulative value of the plate corrosion rate in the cross-link tracking link and the cumulative value of the transport impact in the flow trajectory code, and generate a tracing deviation value; According to the matching degree between the traceability deviation value and the historical change trend of the electrolyte activity attenuation gradient, the parameter traceability weight distribution coefficient is calculated, and based on the parameter traceability weight distribution coefficient, the grid density distribution data of the plate thickness parameter in the cross-link tracking link and the sulfuric acid concentration gradient of the electrolyte ratio parameter are reversely interpolated to generate a dynamic traceability matrix; The predicted value of the residual thickness of the plate in the dynamic traceability matrix is ​​difference-checked with the actual value of the residual thickness of the plate in the physical detection index to generate a verification error factor, and the verification error factor is linearly superimposed with the initial assignment of the warehouse safety verification mark to update the warehouse safety verification mark to an abnormal mark.

7. The method according to claim 6, characterized in that According to the matching degree between the traceability deviation value and the historical change trend of the electrolyte activity attenuation gradient, the parameter traceability weight distribution coefficient is calculated. Based on the parameter traceability weight distribution coefficient, the grid density distribution data of the plate thickness parameter in the cross-link tracking link and the sulfuric acid concentration gradient of the electrolyte ratio parameter are reversely interpolated to generate a dynamic traceability matrix, including: Extract the attenuation slope and fluctuation period in the continuous time window of the historical change trend of the electrolyte activity attenuation gradient, calculate the trend matching degree, and calculate the parameter tracing weight distribution coefficient according to the time attenuation coefficient of the temporal and spatial correlation characteristics of the trend matching degree and the transport impact cumulative value; The grid density distribution data of the plate thickness parameter is spatially interpolated according to the parameter traceability weight distribution coefficient to generate an initial distribution matrix of the predicted value of the plate residual thickness, and the sulfuric acid concentration gradient is reversely compensated on the time axis according to the historical change trend of the electrolyte activity attenuation gradient to generate a compensated sulfuric acid concentration distribution matrix; According to the spatial correlation between the mutation gradient of the transport impact cumulative value and the compensated sulfuric acid concentration distribution matrix, the grid density weight in the initial distribution matrix of the electrode plate residual thickness prediction value is adjusted to generate a dynamically adjusted electrode plate residual thickness prediction matrix; The dynamically adjusted plate residual thickness prediction matrix and the compensated sulfuric acid concentration distribution matrix are subjected to spatiotemporal coupling operation to generate a dynamic traceability matrix.

8. A battery circulation full cycle management system, characterized in that: include: The acquisition module is used to obtain the batch data of the battery in the production link, the environmental monitoring data in the storage link, the path node data in the transportation link, the real-time status parameters in the use link, and the physical detection indicators in the recycling link; An association module, for dynamically associating the number of charge and discharge cycles and the voltage decay rate in the real-time state parameters based on the electrolyte ratio parameters and the plate thickness parameters in the batch data, and generating a cross-link tracking link indexed by the unique identification code of the single battery; A generation module, used to generate a flow trajectory code bound to a unique identification code of a single battery according to the geographical location switching timing in the path node data and the temperature and humidity fluctuation range in the environmental monitoring data; A trigger module is used to trigger reverse tracing processing based on the cross-link tracking link when the ratio of the internal resistance value to the remaining capacity in the physical detection indicator exceeds a preset range corresponding to the charge and discharge status latch mark in the circulation trajectory code, and update the warehouse safety verification mark in the circulation trajectory code to an abnormal mark.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a battery circulation full-cycle management method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a battery circulation full-cycle management method as described in any one of claims 1 to 7 is implemented.

Images