Active suppression method, system, and medium for ultra-thin battery thermal runaway behavior
By simulating production and conducting multi-scenario risk analysis, combined with traceability analysis and proactive adjustment, the production scheme for ultra-thin batteries was optimized, which solved the shortcomings in predicting and suppressing thermal runaway of ultra-thin batteries and improved production safety.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-10
- Publication Date
- 2026-03-31
AI Technical Summary
In existing technologies, it is difficult to effectively predict and suppress thermal runaway behavior in the production process of ultra-thin batteries. There is a lack of comprehensive analysis and dynamic adjustment methods, making it impossible to identify and prevent thermal runaway risks in a timely manner.
By simulating production and constructing multiple battery usage scenarios, thermal runaway risk analysis is conducted. Risk constraint sequences are introduced for source tracing analysis, source tracing factors are determined and actively adjusted, and production plans are optimized by combining multi-scenario risk optimization and multi-level optimization.
It effectively suppresses the thermal runaway behavior of ultra-thin batteries, improves production safety, and ensures the stability and safety of batteries under abnormal conditions.
Smart Images
Figure CN120974769B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of battery manufacturing technology, specifically to an active method, system, and medium for suppressing thermal runaway behavior in ultrathin batteries. Background Technology
[0002] Predicting and suppressing thermal runaway behavior during the production of ultra-thin batteries has always been a challenge in the battery manufacturing industry. Due to the structural and performance characteristics of ultra-thin batteries, they are easily affected by external factors during production and use, leading to thermal runaway. Traditional battery production processes struggle to effectively predict and identify thermal runaway risks using conventional methods. Thermal runaway often occurs under abnormal conditions such as high temperature, overcharging, and short circuits, making real-time detection and timely intervention impossible during production. Existing production solutions generally lack comprehensive analysis of battery thermal runaway behavior, effective thermal runaway risk prediction mechanisms, and dynamic adjustment methods, thus failing to effectively prevent and suppress potential thermal runaway behavior during production. Summary of the Invention
[0003] This application provides an active suppression method, system, and medium for thermal runaway behavior of ultrathin batteries, which addresses the technical problem of insufficient prediction and suppression of thermal runaway behavior of ultrathin batteries during the production process in the prior art.
[0004] In view of the above problems, this application provides an active method, system and medium for suppressing thermal runaway behavior of ultrathin batteries.
[0005] The first aspect of this application provides an active method for suppressing thermal runaway behavior in ultrathin batteries, the method comprising:
[0006] Simulated production is conducted based on an ultra-thin battery production plan to obtain a simulated ultra-thin battery. M battery usage scenarios are constructed, and thermal runaway behavior risk analysis is performed on the simulated ultra-thin battery based on these scenarios, establishing a thermal runaway risk sequence, where M is a positive integer greater than 1. A thermal runaway risk constraint sequence is introduced, and anomaly tracing analysis is performed on the ultra-thin battery production plan in conjunction with this sequence to determine thermal runaway production tracing factors. Active suppression and regulation are applied to the ultra-thin battery production plan based on these tracing factors, establishing a first space for battery production regulation. Thermal runaway risk optimization is performed on the first space for battery production regulation using a multi-scenario thermal runaway risk optimization mechanism, generating a second space for battery production regulation. Multi-level optimization is performed on the second space for battery production regulation using a battery production evaluation model to obtain an optimized battery production plan.
[0007] A second aspect of this application provides an active suppression system for thermal runaway behavior of ultrathin batteries, the system comprising:
[0008] The system comprises the following modules: a simulated production module for simulating production based on an ultra-thin battery production plan to obtain a simulated ultra-thin battery; a risk analysis module for constructing M battery usage scenarios and performing thermal runaway behavior risk analysis on the simulated ultra-thin battery based on these scenarios, establishing a thermal runaway risk sequence (M being a positive integer greater than 1); a source tracing analysis module for introducing a thermal runaway risk constraint sequence and performing anomaly source tracing analysis on the ultra-thin battery production plan based on this sequence to determine thermal runaway production source tracing factors; a suppression and regulation module for actively suppressing and regulating the ultra-thin battery production plan based on the thermal runaway production source tracing factors, establishing a first space for battery production regulation; a risk optimization module for optimizing the first space for battery production regulation based on a multi-scenario thermal runaway risk optimization mechanism, generating a second space for battery production regulation; and a multi-level optimization module for multi-level optimization of the second space for battery production regulation based on a battery production evaluation model to obtain an optimized battery production plan.
[0009] A third aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the active suppression method for thermal runaway behavior of an ultrathin battery provided in this application.
[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0011] This application simulates production based on an ultra-thin battery production plan to obtain a simulated ultra-thin battery; constructs M battery usage scenarios, and performs thermal runaway behavior risk analysis on the simulated ultra-thin battery based on the M battery usage scenarios to establish a thermal runaway risk sequence, where M is a positive integer greater than 1; introduces a thermal runaway risk constraint sequence, and combines the thermal runaway risk sequence to perform anomaly tracing analysis on the ultra-thin battery production plan to determine thermal runaway production tracing factors; actively suppresses and adjusts the ultra-thin battery production plan based on the thermal runaway production tracing factors to establish a first space for battery production adjustment; optimizes the first space for battery production adjustment based on a multi-scenario thermal runaway risk optimization mechanism to generate a second space for battery production adjustment; and performs multi-level optimization on the second space for battery production adjustment based on a battery production evaluation model to obtain an optimized battery production plan. This invention solves the technical problem of insufficient prediction and suppression of thermal runaway behavior in the production process of ultra-thin batteries in the prior art. By introducing multi-scenario thermal runaway risk analysis, tracing analysis, and active adjustment mechanisms, it achieves the technical effect of effectively suppressing thermal runaway behavior of ultra-thin batteries and improving production safety. Attached Figure Description
[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0013] Figure 1 A schematic flowchart of an active method for suppressing thermal runaway behavior of an ultrathin battery provided in an embodiment of this application;
[0014] Figure 2 This is a schematic diagram of the active suppression system for thermal runaway behavior of an ultrathin battery provided in an embodiment of this application.
[0015] Figure labeling: Simulated production module 11, Risk analysis module 12, Source tracing analysis module 13, Suppression and regulation module 14, Risk optimization module 15, Multi-level optimization module 16. Detailed Implementation
[0016] This application provides an active suppression method, system, and medium for thermal runaway behavior of ultra-thin batteries. It addresses the technical problem of insufficient prediction and suppression of thermal runaway behavior of ultra-thin batteries during the production process in the prior art. By introducing multi-scenario thermal runaway risk analysis, source tracing and analysis, and active adjustment mechanisms, it achieves the technical effect of effectively suppressing thermal runaway behavior of ultra-thin batteries and improving production safety.
[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.
[0018] It should be noted that any variation of the terms "comprising" and "having" is intended to cover non-exclusive inclusion, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to such processes, methods, products, or devices.
[0019] Example 1, as Figure 1 As shown, this application provides an active method for suppressing thermal runaway behavior in ultrathin batteries, the method comprising:
[0020] Step S100: Conduct simulated production according to the ultra-thin battery production plan to obtain a simulated ultra-thin battery.
[0021] In this embodiment, based on the ultra-thin battery production plan, the battery's structure, materials, and manufacturing process are first modeled in detail using simulation technologies such as computer-aided design (CAD) and finite element analysis (FEA). The ultra-thin battery production plan includes battery design parameters, such as the selection of positive and negative electrode materials, the configuration of separator materials, electrolyte ratio, coating process, heat treatment conditions, and battery packaging method. Simulated production is then performed using these design parameters to generate a digital simulation battery model.
[0022] Furthermore, the method provided in the application embodiments for obtaining a simulated ultrathin battery further includes:
[0023] Simultaneously retrieve the simulated production monitoring data of the ultra-thin battery; evaluate the anomaly of the simulated production monitoring data according to the ultra-thin battery production plan to obtain the simulated production anomaly degree; if the simulated production anomaly degree is greater than or equal to the predetermined anomaly degree, generate a simulated production early warning signal.
[0024] In this embodiment, simulated production monitoring data of the ultra-thin battery is first retrieved synchronously. In the simulation system, a digital production model of the ultra-thin battery is generated using technologies such as computer-aided design (CAD) and finite element analysis (FEA). During the simulated production process, multiple key parameters of the battery, such as temperature, current, voltage, and pressure, are collected in real time using virtual sensors in the simulation environment. These data collectively constitute the simulated production monitoring data.
[0025] Next, anomaly evaluation is performed on the simulated production monitoring data based on the ultra-thin battery production plan. This process begins by acquiring the dataset for each monitoring parameter (such as temperature and voltage) during the production process. Then, the mean and standard deviation of each monitoring parameter are calculated. For each parameter, the deviation from the mean is calculated by subtracting the mean from the current data point value. The calculated mean is then divided by the corresponding standard deviation to obtain the anomaly degree of the corresponding monitoring parameter. This process is repeated to calculate the anomaly degree for multiple monitoring parameters. The calculated anomaly degrees are then linearly normalized to convert the anomaly degree of each monitoring parameter to a uniform scale. Finally, the normalized anomaly degrees are weighted according to preset weights to obtain the simulated production anomaly degree.
[0026] The simulated production anomaly level is compared with the predetermined anomaly level set by technical experts. When the simulated production anomaly level is greater than or equal to the predetermined anomaly level, a simulated production early warning signal is generated, and the simulated production is restarted.
[0027] Step S200: Construct M battery usage scenarios, and perform thermal runaway behavior risk analysis on the simulated ultrathin battery based on the M battery usage scenarios to establish a thermal runaway risk sequence, where M is a positive integer greater than 1.
[0028] In this embodiment, when constructing M battery usage scenarios, the battery usage record set is first retrieved based on the battery attributes of the ultra-thin battery production scheme. Scene feature identification is then performed based on the battery usage record set to obtain a group of battery usage scenarios. Next, the triggering degree is calculated for each scenario sample in the battery usage record set. By comparing the triggering degree with predetermined criteria, usage scenarios that meet the conditions are selected, thus determining the M battery usage scenarios.
[0029] Subsequently, thermal runaway behavior risk analysis was performed on the simulated ultrathin battery based on M battery usage scenarios. In this process, the m-th battery usage scenario was extracted from the M battery usage scenarios and used as the simulation input condition to simulate the thermal runaway behavior of the simulated ultrathin battery, obtaining battery simulation data under the m-th scenario. This simulation data was then input into multiple pre-built thermal runaway risk analysis models to obtain corresponding thermal runaway risk coefficients; the average of these coefficients was then calculated to obtain the thermal runaway risk coefficient for the m-th scenario, which was added to the thermal runaway risk sequence. By traversing all M usage scenarios, the thermal runaway risk sequence was obtained.
[0030] Furthermore, the method provided in the application embodiments, in constructing M battery usage scenarios, also includes:
[0031] Based on the ultra-thin battery attributes of the ultra-thin battery production scheme, usage records are retrieved to obtain a battery usage record set; based on the battery usage record set, scene features are identified to obtain a battery usage scene group; based on the battery usage record set, trigger degree is calculated for each usage scene sample in the battery usage scene group to obtain the trigger degree of each scene; based on the trigger degree of each scene, the battery usage scene group is selected to generate the M battery usage scenes with a trigger degree greater than or equal to a predetermined scene trigger degree.
[0032] In this embodiment, when retrieving usage records based on the ultra-thin battery attributes of the ultra-thin battery production scheme, a database query method is used, employing conditional queries based on the ultra-thin battery attributes (such as SQL queries). During this process, by retrieving a database containing information such as battery model, battery capacity, and manufacturing process, all usage records meeting the ultra-thin battery attribute conditions are filtered out, thereby generating a battery usage record set. This battery usage record set contains historical usage data of the battery under different operating conditions and environments, such as charging cycles, depth of discharge, temperature, voltage, and load information.
[0033] Next, scene feature identification is performed based on the battery usage record set. In this process, clustering analysis methods (such as K-means clustering) are used to classify the data in the battery usage record set. By using the key features of each battery usage record (such as temperature, current, voltage, etc.) as input, the K-means algorithm is used to group the record set, generating battery usage scene clusters with similar features. The generated battery usage scene clusters contain multiple battery usage scene samples.
[0034] Subsequently, trigger intensity is calculated for each usage scenario sample within the battery usage scenario group based on the battery usage record set. Trigger intensity is calculated by statistically analyzing the frequency of each battery usage scenario sample within the battery usage record set. Specifically, a frequency statistics method is used to calculate the number of times each usage scenario appears in the record set. For example, if a battery usage scenario sample appears 300 times in 1000 records, then the trigger intensity for that scenario is 300 / 1000 = 0.3. This process yields the trigger intensity for each scenario.
[0035] Finally, based on the triggering intensity of each scenario, a group of battery usage scenarios is selected, generating M battery usage scenarios with a triggering intensity greater than or equal to a predetermined threshold. In this step, technical experts set a triggering intensity threshold and filter out scenario samples with a triggering intensity greater than or equal to that threshold. These filtered scenario samples are then used as battery usage scenarios. Through this process, M battery usage scenarios are obtained.
[0036] Furthermore, the method provided in the application embodiment, which analyzes the thermal runaway behavior risk of the simulated ultrathin battery based on the M battery usage scenarios and establishes a thermal runaway risk sequence, further includes:
[0037] The m-th battery usage scenario is extracted from the M battery usage scenarios, where m is a positive integer and 1 ≤ m ≤ M; thermal runaway behavior simulation is performed on the simulated ultrathin battery based on the m-th battery usage scenario to obtain the m-th scenario battery simulation data; the m-th scenario battery simulation data is input into multiple thermal runaway risk analysis models to obtain multiple thermal runaway risk coefficients; the mean of the multiple thermal runaway risk coefficients is calculated to generate the m-th scenario thermal runaway risk coefficient, and the m-th scenario thermal runaway risk coefficient is added to the thermal runaway risk sequence.
[0038] In this embodiment of the application, the m-th battery usage scenario is first randomly extracted from M battery usage scenarios, where m is a positive integer and 1≤m≤M.
[0039] Next, based on the m-th battery usage scenario, thermal runaway behavior simulation is performed on the ultra-thin battery. Thermal runaway behavior refers to problems such as overheating, expansion, or fire that may occur when a battery is subjected to abnormal operating conditions. In simulating thermal runaway behavior, a mathematical model of internal heat transfer is established using simulation software (such as COMSOL Multiphysics or ANSYS) to simulate the temperature changes of the battery in the m-th usage scenario and whether the battery will run away due to heat accumulation (e.g., overheating, expansion). This generates battery simulation data for the m-th scenario, including key thermal runaway parameters such as battery temperature, pressure, and current fluctuations.
[0040] Subsequently, the battery simulation data for scenario m is input into multiple thermal runaway risk analysis models. These models are pre-trained, and the training data includes fields of the same type as the battery simulation data (such as temperature, current, and voltage) and thermal runaway risk coefficients pre-labeled by technical experts. These models are then trained using machine learning algorithms such as Support Vector Machines (SVM), neural networks, or decision trees to obtain multiple thermal runaway risk analysis models. These trained models are then used to process the battery simulation data for scenario m, resulting in multiple thermal runaway risk coefficients.
[0041] Then, the average of multiple thermal runaway risk coefficients is calculated to determine the thermal runaway risk coefficient for scenario m, and the thermal runaway risk coefficient for scenario m is added to the thermal runaway risk sequence.
[0042] After calculating the thermal runaway risk coefficient for the m-th battery usage scenario, the aforementioned process is repeated, iterating through all M battery usage scenarios sequentially. In each iteration, the corresponding battery usage scenario is extracted, thermal runaway behavior is simulated, and corresponding battery simulation data is obtained. This simulation data is then input into multiple thermal runaway risk analysis models for evaluation, yielding the thermal runaway risk coefficient for that scenario. Finally, by processing all M battery usage scenarios, a thermal runaway risk sequence is obtained.
[0043] Step S300: Introduce a thermal runaway risk constraint sequence, and combine the thermal runaway risk sequence to perform anomaly tracing analysis on the ultrathin battery production scheme to determine the thermal runaway production tracing factor.
[0044] In this embodiment, thermal runaway risk constraints are first configured based on M battery usage scenarios to generate a thermal runaway risk constraint sequence. This sequence is used to limit the acceptable range of thermal runaway risk during battery production.
[0045] Next, anomaly detection is performed on the thermal runaway risk sequence using the thermal runaway risk constraint sequence to identify thermal runaway risk anomaly clusters. Then, based on the identified thermal runaway risk anomaly clusters, thermal runaway behavior simulation and recording are backtracked to generate a set of risk-abnormal thermal runaway behaviors. Finally, according to the ultra-thin battery production plan, the generated set of risk-abnormal thermal runaway behaviors is correlated and traced to determine the thermal runaway production traceability factors.
[0046] Furthermore, the method provided in the application embodiment introduces a thermal runaway risk constraint sequence, and combines the thermal runaway risk sequence to perform anomaly tracing analysis on the ultrathin battery production scheme to determine the thermal runaway production tracing factor, and also includes:
[0047] Based on the M battery usage scenarios, thermal runaway risk constraints are configured to generate a thermal runaway risk constraint sequence; anomaly detection is performed on the thermal runaway risk sequence based on the thermal runaway risk constraint sequence to determine thermal runaway risk anomaly clusters; thermal runaway behavior simulation and recording are backtracked based on the thermal runaway risk anomaly clusters to generate a risk anomaly thermal runaway behavior set; the risk anomaly thermal runaway behavior set is correlated and traced according to the ultra-thin battery production plan to generate the thermal runaway production traceability factor.
[0048] In this embodiment, thermal runaway risk constraints are first configured based on M battery usage scenarios. Specifically, technical experts set a range of thermal runaway risk coefficients for each battery usage scenario. This process generates a thermal runaway risk constraint sequence.
[0049] Next, anomaly detection is performed on the thermal runaway risk sequence based on the thermal runaway risk constraint sequence. During this process, the thermal runaway risk coefficient for each scenario in the thermal runaway risk sequence is compared with the corresponding interval in the thermal runaway risk constraint sequence. If the thermal runaway risk coefficient for a scenario is not within its preset thermal runaway risk coefficient interval, meaning the thermal runaway risk coefficient for that scenario exceeds the set safety range, the scenario is considered anomaly. This scenario is then considered anomaly and added to the thermal runaway risk anomaly cluster. Through this process, the thermal runaway risk anomaly cluster is determined, which includes all anomaly scenarios where the thermal runaway risk coefficient exceeds the preset interval.
[0050] Subsequently, thermal runaway behavior simulations and backtracking were performed based on the abnormal clusters of thermal runaway risks. The backtracking process was conducted using simulation-based backtracking, simulating thermal runaway behavior for all abnormal scenarios. Thermal analysis simulation tools (such as ANSYS or COMSOL Multiphysics) were used to simulate the battery's thermal behavior under abnormal operating conditions. This method captures temperature changes, current fluctuations, and other thermal response phenomena when the battery exceeds safety parameters. For example, if the battery temperature abnormally rises in a certain scenario, the simulation model will simulate the temperature rise process and record the battery's thermal response, ultimately forming a set of abnormal thermal runaway behaviors.
[0051] Finally, the set of abnormal thermal runaway behaviors was correlated and traced according to the ultra-thin battery production plan. This process first analyzed all recorded abnormal scenarios in the set of abnormal thermal runaway behaviors to determine the specific circumstances of each abnormal behavior, such as excessively high battery temperature under certain conditions or abnormalities occurring during charging. Next, these abnormal behaviors were compared with each step in the battery production plan. These steps included battery material selection, production processes, and equipment settings. By comparing the relationship between each stage of the production process and the abnormal behaviors, potential problems leading to thermal runaway were identified. For example, if the battery temperature is too high in a certain scenario, it may be due to incorrect temperature control system settings or a failure to follow standards in a certain stage of the production process, leading to excessive temperature and thus thermal runaway. Through this analysis, the root cause of the thermal runaway was ultimately identified; this identified root cause is the thermal runaway production traceability factor.
[0052] Step S400: Actively suppress and adjust the ultra-thin battery production scheme according to the thermal runaway production traceability factor to establish the first space for battery production adjustment.
[0053] In this embodiment, the ultra-thin battery production process is first actively suppressed and adjusted based on thermal runaway production traceability factors. During this process, based on the identified thermal runaway production traceability factors, potential thermal runaway hazards in battery production are analyzed, and corresponding adjustment measures are formulated for these hazards. For example, if a problem is found in the temperature control system settings, the temperature control equipment settings are adjusted; if the quality of raw materials does not meet requirements, the selection of raw materials or suppliers is adjusted to ensure compliance with battery production safety standards.
[0054] Next, multiple battery production adjustment schemes are generated based on these adjustments. These schemes vary according to different process requirements and adjustment strategies. Each adjustment scheme modifies a specific production stage, such as adjusting the current or voltage during charging or controlling the rate of temperature change, to ensure that the battery does not exceed safety thresholds during production. These adjustment schemes constitute the first space for battery production adjustment, which contains a variety of different production adjustment strategies.
[0055] Step S500: Optimize the thermal runaway risk of the first space for battery production adjustment according to the multi-scenario thermal runaway risk optimization mechanism to generate the second space for battery production adjustment.
[0056] In this embodiment, based on a multi-scenario thermal runaway risk optimization mechanism, each adjustment scheme in the first space of battery production adjustment is first simulated for production, generating simulated batteries for each scheme. Then, based on M battery usage scenarios, the thermal runaway behavior risk of each simulated battery is analyzed, and a corresponding thermal runaway risk sequence is established. Next, it is determined whether the thermal runaway risk sequence of each adjustment scheme meets the preset risk constraint criteria, and the adjustment schemes are screened based on the determination results, ultimately generating an optimized second space for battery production adjustment.
[0057] Furthermore, in the method provided in the application embodiments, the multi-scenario thermal runaway risk optimization mechanism includes:
[0058] Simulated production is performed for each battery production adjustment scheme within the first battery production adjustment space to obtain simulated batteries for each scheme; thermal runaway behavior risk analysis is performed on the simulated batteries for each scheme based on the M battery usage scenarios to establish a thermal runaway risk sequence for each scheme; it is determined whether the thermal runaway risk sequence for each scheme satisfies the thermal runaway risk constraint sequence to obtain the risk judgment result for each scheme; thermal runaway risk optimization is performed on the first battery production adjustment space based on the risk judgment result for each scheme to establish the second battery production adjustment space.
[0059] In this embodiment, simulated production is first performed according to each battery production adjustment scheme in the first space of battery production adjustment. By simulating each battery production adjustment scheme, a corresponding simulated battery is generated, and simulated batteries for each scheme are obtained.
[0060] Next, based on M battery usage scenarios, the thermal runaway behavior risk of each simulated battery is analyzed. Similar to the previous process of analyzing the thermal runaway behavior risk of simulated ultra-thin batteries, each usage scenario is extracted sequentially and applied to the simulated battery to simulate thermal runaway behavior. Through simulation analysis, the thermal response of the simulated battery under different scenarios is analyzed, and the thermal runaway risk coefficient for each scenario is calculated. The analysis results of multiple scenarios are summarized into a thermal runaway risk sequence for each adjustment scheme. Through this process, a thermal runaway risk sequence for each scheme is established.
[0061] Next, it is determined whether the thermal runaway risk sequence of each scheme meets the thermal runaway risk constraint sequence. This involves comparing each scheme's thermal runaway risk sequence with the thermal runaway risk constraint sequence to check if the scheme's risk is within a safe range. If the thermal runaway risk coefficient of a scheme exceeds the set safe range, the scheme is deemed to have potential risk and does not meet safety requirements, and is marked as "unqualified." If the risks of all scenarios are within the safe range, the scheme is deemed to meet the requirements and is marked as "qualified." Through this process, the risk assessment results for each scheme are obtained.
[0062] Finally, based on the risk assessment results of each scheme, thermal runaway risk optimization is performed on the first space of battery production regulation. That is, only the battery production regulation schemes marked as qualified in the first space of battery production regulation are retained, and the battery production regulation schemes marked as unqualified are eliminated, thus establishing an optimized second space of battery production regulation.
[0063] Step S600: Based on the battery production evaluation model, perform multi-level optimization on the second space of battery production adjustment to obtain an optimized battery production scheme.
[0064] In this embodiment, based on a pre-constructed battery production evaluation model, the second space for battery production regulation is first evaluated and optimized to generate a third space for battery production regulation. Then, based on the multi-dimensional indicators in the battery production evaluation model (such as battery basic performance, battery production safety, and battery thermal safety), weights are allocated to generate a comprehensive battery quality evaluation model. Using this comprehensive quality evaluation model, the third space for battery production regulation is evaluated and optimized to generate a fourth space for battery production regulation that satisfies the constraints of the comprehensive battery quality evaluation. Finally, energy consumption minimization is optimized based on the fourth space for battery production regulation to ultimately generate an optimized battery production scheme.
[0065] Furthermore, the method provided in the application embodiments, which involves multi-level optimization of the second space for battery production adjustment based on a battery production evaluation model to obtain an optimized battery production scheme, further includes:
[0066] The battery production evaluation model is used to evaluate and optimize the second space of battery production regulation, establishing a third space for battery production regulation. Weights are allocated based on the multi-dimensional indicators of battery production evaluation in the battery production evaluation model to generate a comprehensive battery quality evaluation model. These multi-dimensional indicators include basic battery performance, battery production safety, and battery thermal safety. The comprehensive quality evaluation model is then used to optimize the third space of battery production regulation, establishing a fourth space that satisfies the constraints of the comprehensive battery quality evaluation. Finally, the fourth space of battery production regulation is used to minimize energy consumption, generating the optimized battery production scheme.
[0067] In this embodiment, when evaluating and optimizing the second space of battery production adjustment according to the battery production evaluation model, the multi-dimensional indicators of battery production evaluation are first traversed, and battery production evaluation constraints are set by technical experts. The multi-dimensional indicators of battery production evaluation include battery basic performance, battery production safety, and battery thermal safety. The battery production evaluation constraints are pre-set safety coefficients for battery basic performance, battery production safety, and battery thermal safety. Then, a first battery production adjustment scheme is randomly extracted from the second space of battery production adjustment and input into the battery production evaluation model for evaluation. Through the model's calculation, a first battery production evaluation result is obtained, including battery basic performance coefficient, battery production safety coefficient, and battery thermal safety coefficient. If the first battery production evaluation result meets the preset battery production evaluation constraints, the adjustment scheme is added to the third space of battery production adjustment. By repeating the aforementioned steps, the third space of battery production adjustment is obtained.
[0068] Next, weights are allocated based on the multi-dimensional indicators of battery production evaluation in the battery production evaluation model, specifically, pre-set weights are assigned to battery basic performance, battery production safety, and battery thermal safety. This weighted allocation of the multi-dimensional indicators generates a comprehensive battery quality evaluation model. This model is used to calculate the weighted coefficients of battery basic performance, battery production safety, and battery thermal safety to obtain the comprehensive battery quality evaluation coefficient.
[0069] Subsequently, a comprehensive quality evaluation and optimization process is performed on the third space of battery production regulation based on the battery comprehensive quality evaluation model. In this process, the battery's basic performance coefficient, battery production safety coefficient, and battery thermal safety coefficient corresponding to each scheme in the third space of battery production regulation are input into the battery comprehensive quality evaluation model for calculation, resulting in the corresponding battery comprehensive quality evaluation coefficient. The calculated battery comprehensive quality evaluation coefficient is then compared with the battery comprehensive quality evaluation constraints, which are pre-set battery comprehensive quality evaluation thresholds. When the battery comprehensive quality evaluation coefficient is greater than or equal to the battery comprehensive quality evaluation threshold, the corresponding scheme is considered to meet the battery comprehensive quality evaluation constraints, and the scheme is added to the fourth space of battery production regulation.
[0070] Finally, energy consumption minimization optimization is performed based on the fourth space of battery production regulation to generate an optimized battery production scheme. In this process, energy consumption calculations are performed for each regulation scheme in the fourth space. Simulation is used to evaluate the energy consumption of each regulation scheme in the actual production process, particularly the electricity and other energy consumed during production (such as battery temperature control, cooling systems, and battery charging rates). The simulation calculates the total energy consumption of each scheme by setting production process parameters, equipment power consumption, and environmental factors. Then, the energy consumption of all regulation schemes is compared, and the scheme with the lowest energy consumption is selected as the optimized battery production scheme.
[0071] Furthermore, in the method provided in the application embodiments, the evaluation and optimization of the second space for battery production adjustment based on the battery production evaluation model to establish a third space for battery production adjustment further includes:
[0072] The battery production evaluation multivariate indicators are traversed, and battery production evaluation constraints are set; a battery production adjustment first scheme is extracted according to the battery production adjustment second space; the battery production adjustment first scheme is input into the battery production evaluation model to obtain a battery production evaluation first result; if the battery production evaluation first result satisfies the battery production evaluation constraints, the battery production adjustment first scheme is added to the battery production adjustment third space.
[0073] In this embodiment, the multi-dimensional indicators for battery production evaluation are first traversed, and battery production evaluation constraints are set. The battery production evaluation constraints include preset thresholds for basic battery performance, preset thresholds for battery production safety, and preset thresholds for battery thermal safety, which are preset by technical experts.
[0074] Next, the second space for battery production adjustment is randomly extracted to obtain the first scheme for battery production adjustment.
[0075] The first battery production adjustment scheme is then input into the battery production evaluation model. This model is pre-trained. During training, a supervised learning algorithm is used to map the input data (i.e., the parameters of the battery production adjustment scheme) to the output data (i.e., battery performance indicators, such as the battery basic performance coefficient, battery production safety coefficient, and battery thermal safety coefficient). The model's weights are continuously adjusted through backpropagation and optimization algorithms (such as gradient descent) to enable the model to accurately predict battery performance under different schemes. The battery production evaluation model is then used to process the first battery production adjustment scheme to obtain the first battery production evaluation result, which includes the battery basic performance coefficient, battery production safety coefficient, and battery thermal safety coefficient corresponding to the first battery production adjustment scheme.
[0076] Subsequently, the first result of battery production evaluation is compared with the battery production evaluation constraints. When the battery basic performance coefficient, battery production safety coefficient and battery thermal safety coefficient in the first result of battery production evaluation are all greater than or equal to the preset thresholds for battery basic performance, battery production safety and battery thermal safety in the battery production evaluation constraints, the first result of battery production evaluation is considered to meet the battery production evaluation constraints, and the first battery production adjustment scheme is added to the third space of battery production adjustment.
[0077] Through the aforementioned steps, each scheme in the second space of battery production adjustment is evaluated to generate the third space of battery production adjustment.
[0078] In summary, the embodiments of this application have at least the following technical effects:
[0079] This application simulates production based on an ultra-thin battery production plan to obtain a simulated ultra-thin battery; constructs M battery usage scenarios, and performs thermal runaway behavior risk analysis on the simulated ultra-thin battery based on the M battery usage scenarios to establish a thermal runaway risk sequence, where M is a positive integer greater than 1; introduces a thermal runaway risk constraint sequence, and combines the thermal runaway risk sequence to perform anomaly tracing analysis on the ultra-thin battery production plan to determine thermal runaway production tracing factors; actively suppresses and adjusts the ultra-thin battery production plan based on the thermal runaway production tracing factors to establish a first space for battery production adjustment; optimizes the first space for battery production adjustment based on a multi-scenario thermal runaway risk optimization mechanism to generate a second space for battery production adjustment; and performs multi-level optimization on the second space for battery production adjustment based on a battery production evaluation model to obtain an optimized battery production plan. This invention solves the technical problem of insufficient prediction and suppression of thermal runaway behavior in the production process of ultra-thin batteries in the prior art. By introducing multi-scenario thermal runaway risk analysis, tracing analysis, and active adjustment mechanisms, it achieves the technical effect of effectively suppressing thermal runaway behavior of ultra-thin batteries and improving production safety.
[0080] Example 2, based on the same inventive concept as the active suppression method for thermal runaway behavior of ultrathin batteries in the foregoing examples, such as... Figure 2 As shown, this application provides an active suppression system for thermal runaway behavior of ultrathin batteries. The system and method embodiments in this application are based on the same inventive concept. The system includes:
[0081] The simulation production module 11 is used to simulate production according to the ultra-thin battery production plan to obtain a simulated ultra-thin battery; the risk analysis module 12 is used to construct M battery usage scenarios and perform thermal runaway behavior risk analysis on the simulated ultra-thin battery according to the M battery usage scenarios to establish a thermal runaway risk sequence, where M is a positive integer greater than 1; the source tracing analysis module 13 is used to introduce a thermal runaway risk constraint sequence and perform anomaly source tracing analysis on the ultra-thin battery production plan in combination with the thermal runaway risk sequence to determine the thermal runaway production source tracing factor; the suppression and regulation module 14 is used to actively suppress and regulate the ultra-thin battery production plan according to the thermal runaway production source tracing factor to establish a battery production regulation first space; the risk optimization module 15 is used to perform thermal runaway risk optimization on the battery production regulation first space according to the multi-scenario thermal runaway risk optimization mechanism to generate a battery production regulation second space; the multi-level optimization module 16 is used to perform multi-level optimization on the battery production regulation second space according to the battery production evaluation model to obtain a battery production optimization plan.
[0082] Furthermore, the system is also used to implement the following functions:
[0083] Based on the ultra-thin battery attributes of the ultra-thin battery production scheme, usage records are retrieved to obtain a battery usage record set; based on the battery usage record set, scene features are identified to obtain a battery usage scene group; based on the battery usage record set, trigger degree is calculated for each usage scene sample in the battery usage scene group to obtain the trigger degree of each scene; based on the trigger degree of each scene, the battery usage scene group is selected to generate the M battery usage scenes with a trigger degree greater than or equal to a predetermined scene trigger degree.
[0084] Furthermore, the system is also used to implement the following functions:
[0085] The m-th battery usage scenario is extracted from the M battery usage scenarios, where m is a positive integer and 1 ≤ m ≤ M; thermal runaway behavior simulation is performed on the simulated ultrathin battery based on the m-th battery usage scenario to obtain the m-th scenario battery simulation data; the m-th scenario battery simulation data is input into multiple thermal runaway risk analysis models to obtain multiple thermal runaway risk coefficients; the mean of the multiple thermal runaway risk coefficients is calculated to generate the m-th scenario thermal runaway risk coefficient, and the m-th scenario thermal runaway risk coefficient is added to the thermal runaway risk sequence.
[0086] Furthermore, the system is also used to implement the following functions:
[0087] Based on the M battery usage scenarios, thermal runaway risk constraints are configured to generate a thermal runaway risk constraint sequence; anomaly detection is performed on the thermal runaway risk sequence based on the thermal runaway risk constraint sequence to determine thermal runaway risk anomaly clusters; thermal runaway behavior simulation and recording are backtracked based on the thermal runaway risk anomaly clusters to generate a risk anomaly thermal runaway behavior set; the risk anomaly thermal runaway behavior set is correlated and traced according to the ultra-thin battery production plan to generate the thermal runaway production traceability factor.
[0088] Furthermore, the system is also used to implement the following functions:
[0089] Simulated production is performed for each battery production adjustment scheme within the first battery production adjustment space to obtain simulated batteries for each scheme; thermal runaway behavior risk analysis is performed on the simulated batteries for each scheme based on the M battery usage scenarios to establish a thermal runaway risk sequence for each scheme; it is determined whether the thermal runaway risk sequence for each scheme satisfies the thermal runaway risk constraint sequence to obtain the risk judgment result for each scheme; thermal runaway risk optimization is performed on the first battery production adjustment space based on the risk judgment result for each scheme to establish the second battery production adjustment space.
[0090] Furthermore, the system is also used to implement the following functions:
[0091] The battery production evaluation model is used to evaluate and optimize the second space of battery production regulation, establishing a third space for battery production regulation. Weights are allocated based on the multi-dimensional indicators of battery production evaluation in the battery production evaluation model to generate a comprehensive battery quality evaluation model. These multi-dimensional indicators include basic battery performance, battery production safety, and battery thermal safety. The comprehensive quality evaluation model is then used to optimize the third space of battery production regulation, establishing a fourth space that satisfies the constraints of the comprehensive battery quality evaluation. Finally, the fourth space of battery production regulation is used to minimize energy consumption, generating the optimized battery production scheme.
[0092] Furthermore, the system is also used to implement the following functions:
[0093] The battery production evaluation multivariate indicators are traversed, and battery production evaluation constraints are set; a battery production adjustment first scheme is extracted according to the battery production adjustment second space; the battery production adjustment first scheme is input into the battery production evaluation model to obtain a battery production evaluation first result; if the battery production evaluation first result satisfies the battery production evaluation constraints, the battery production adjustment first scheme is added to the battery production adjustment third space.
[0094] Furthermore, the system is also used to implement the following functions:
[0095] Simultaneously retrieve the simulated production monitoring data of the ultra-thin battery; evaluate the anomaly of the simulated production monitoring data according to the ultra-thin battery production plan to obtain the simulated production anomaly degree; if the simulated production anomaly degree is greater than or equal to the predetermined anomaly degree, generate a simulated production early warning signal.
[0096] Example 3: Based on the active suppression method for thermal runaway behavior of ultrathin batteries in the foregoing examples, and using the same inventive concept, this application also provides a computer-readable storage medium storing a computer program that, when executed, implements the steps of any of the methods described in Example 1 above.
[0097] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.
[0098] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.
[0099] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.
Claims
1. A method of active suppression of thermal runaway behavior of an ultrathin battery, characterized in that, The method comprises the following steps: According to the ultra-thin battery production scheme, simulate production to obtain a simulated ultra-thin battery; Construct M battery use scenarios, and analyze the thermal runaway behavior risk of the simulated ultra-thin battery according to the M battery use scenarios to establish a thermal runaway risk sequence, M being a positive integer greater than 1; Introduce a thermal runaway risk constraint sequence, and combine the thermal runaway risk sequence to analyze the abnormal source of the ultra-thin battery production scheme, and determine the thermal runaway production traceability factor; According to the thermal runaway production traceability factor, actively inhibit and adjust the ultra-thin battery production scheme to establish a battery production adjustment first space; According to the multi-scenario thermal runaway risk optimization mechanism, the battery production adjustment first space is subjected to thermal runaway risk optimization to generate a battery production adjustment second space; According to the battery production evaluation model, the battery production adjustment second space is subjected to multi-level optimization to obtain a battery production optimization scheme; According to the M battery use scenarios, the thermal runaway behavior risk of the simulated ultra-thin battery is analyzed to establish a thermal runaway risk sequence, which comprises: According to the M battery use scenarios, the mth battery use scenario is extracted, m being a positive integer, 1≤m≤M; According to the mth battery use scenario, the thermal runaway behavior of the simulated ultra-thin battery is simulated to obtain mth scenario battery simulation data; The mth scenario battery simulation data is input into a plurality of thermal runaway risk analysis models to obtain a plurality of thermal runaway risk coefficients; The mean value of the plurality of thermal runaway risk coefficients is calculated to generate the mth scenario thermal runaway risk coefficient, and the mth scenario thermal runaway risk coefficient is added to the thermal runaway risk sequence; The multi-scenario thermal runaway risk optimization mechanism comprises: According to each battery production adjustment scheme in the battery production adjustment first space, simulate production to obtain simulated batteries of each scheme; According to the M battery use scenarios, the thermal runaway behavior risk of the simulated batteries of each scheme is analyzed to establish a thermal runaway risk sequence of each scheme; Determine whether the thermal runaway risk sequence of each scheme satisfies the thermal runaway risk constraint sequence to obtain a risk judgment result of each scheme; According to the risk judgment result of each scheme, the battery production adjustment first space is subjected to thermal runaway risk optimization to establish the battery production adjustment second space; According to the battery production evaluation model, the battery production adjustment second space is subjected to multi-level optimization to obtain a battery production optimization scheme, which comprises: According to the battery production evaluation model, the battery production adjustment second space is evaluated and optimized to establish a battery production adjustment third space; According to the battery production evaluation multi-index of the battery production evaluation model, weight distribution is performed to generate a battery comprehensive quality evaluation model, the battery production evaluation multi-index comprising battery basic performance, battery production safety, and battery thermal safety; According to the battery comprehensive quality evaluation model, the battery production adjustment third space is subjected to comprehensive quality evaluation optimization to establish a battery production adjustment fourth space that satisfies the battery comprehensive quality evaluation constraint; According to the battery production adjustment fourth space, energy consumption minimization optimization is performed to generate the battery production optimization scheme.
2. The method of claim 1, wherein the battery is a thin battery. The M battery use scenarios are constructed, which comprises: According to the use record search of the ultra-thin battery attribute of the ultra-thin battery production scheme, a battery use record set is obtained; According to the battery use record set, scene feature recognition is performed to obtain a battery use scene group; According to the battery use record set, trigger degree calculation is performed on each use scene sample in the battery use scene group to obtain scene trigger degrees; According to the scene trigger degrees, the battery use scene group is selected to generate the M battery use scenes with a scene trigger degree greater than or equal to a predetermined scene trigger degree.
3. The method of claim 1, wherein the battery is a thin battery. A thermal runaway risk constraint sequence is introduced, and abnormality backtracking analysis is performed on the ultra-thin battery production scheme combined with the thermal runaway risk sequence to determine a thermal runaway production backtracking factor, including: According to the M battery use scenes, a thermal runaway risk constraint configuration is performed to generate the thermal runaway risk constraint sequence; According to the thermal runaway risk constraint sequence, abnormality detection is performed on the thermal runaway risk sequence to determine a thermal runaway risk abnormality cluster; According to the thermal runaway risk abnormality cluster, a risk abnormality thermal runaway behavior set is generated through thermal runaway behavior simulation record backtracking; According to the ultra-thin battery production scheme, the risk abnormality thermal runaway behavior set is associated and tracked to generate the thermal runaway production backtracking factor.
4. The method of claim 1, wherein the battery is a thin battery. According to the battery production evaluation model, the battery production adjustment second space is evaluated and optimized to establish a battery production adjustment third space, including: The battery production evaluation multi-element index is traversed, and a battery production evaluation constraint is set; According to the battery production adjustment second space, a battery production adjustment first scheme is extracted; The battery production adjustment first scheme is input into the battery production evaluation model to obtain a battery production evaluation first result; If the battery production evaluation first result meets the battery production evaluation constraint, the battery production adjustment first scheme is added to the battery production adjustment third space.
5. The method of claim 1, wherein the battery is a thin battery. A simulated ultra-thin battery is obtained, including: The simulation production monitoring data of the simulated ultra-thin battery is synchronously called; According to the ultra-thin battery production scheme, abnormality evaluation is performed on the simulation production monitoring data to obtain a simulation production abnormality degree; If the simulation production abnormality degree is greater than or equal to a predetermined abnormality degree, a simulation production early warning signal is generated.
6. An active suppression system of the thermal runaway behavior of ultra-thin batteries, characterized by, The system is used to perform the active inhibition method of the ultra-thin battery thermal runaway behavior, and the system includes: A simulation production module is configured to perform simulation production according to an ultra-thin battery production scheme to obtain a simulated ultra-thin battery; A risk analysis module is configured to construct M battery use scenes and perform thermal runaway behavior risk analysis on the simulated ultra-thin battery according to the M battery use scenes to establish a thermal runaway risk sequence, where M is a positive integer greater than 1; A backtracking analysis module is configured to introduce a thermal runaway risk constraint sequence and perform abnormality backtracking analysis on the ultra-thin battery production scheme combined with the thermal runaway risk sequence to determine a thermal runaway production backtracking factor; An inhibition adjustment module is configured to perform active inhibition adjustment on the ultra-thin battery production scheme according to the thermal runaway production backtracking factor to establish a battery production adjustment first space. The risk optimization module is configured to perform thermal runaway risk optimization on the first space of the battery production adjustment according to a multi-scenario thermal runaway risk optimization mechanism, and generate a second space of the battery production adjustment; The multi-level optimization module is configured to perform multi-level optimization on the second space of the battery production adjustment according to a battery production evaluation model, and obtain an optimized scheme of the battery production.
7. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the active inhibition method of the thermal runaway behavior of the ultra-thin battery according to any one of claims 1-5.
Citation Information
Patent Citations
Tracing management method and system for lithium ion battery production
CN118014165A
Lithium battery manufacturing parameter optimization method and electronic equipment
CN118228487A