An artificial intelligence-based battery prototype rapid design method and system

Abstract

The application relates to the technical field of battery prototype design, in particular to a battery prototype rapid design method and system based on artificial intelligence. The method comprises the following steps: obtaining an initial battery demand information set, guiding demand co-molding and potential parameter inference on customer demand through interactive questioning based on the initial battery demand information set, and obtaining a clear battery demand information set; obtaining a battery specification database, analyzing the thermal coupling relationship and aging curve characteristics of different battery specification combinations based on the battery specification database and in combination with the clear battery demand information set, and obtaining a candidate battery information set; and based on the candidate battery information set, performing thermal balance and life attenuation collaborative optimization, generating and outputting a battery assembly delivery scheme information set containing a battery manufacturing process and a battery physical object. The method realizes comprehensive optimization of battery core performance, greatly improves design efficiency and shortens the cycle, adapts to customized design requirements, and promotes the intelligent and standardized development of the battery design field.

Description

Technical Field

[0001] This application relates to the field of battery prototyping technology, and in particular to a rapid battery prototyping method and system based on artificial intelligence. Background Technology

[0002] Currently, there are significant challenges in rapidly obtaining customized battery prototypes for electronic products. Existing models rely on manual interaction and experience-based design, making it difficult for customers to translate vague application scenarios into precise technical parameters. This results in long design cycles and repeated modifications to the solutions. At the same time, existing design tools or online platforms are often disconnected from the back-end supply chain, and can only perform static matching based on a limited local module library. They cannot respond to market dynamics and diversified module supply in real time. From design confirmation to physical delivery, there is also a lengthy supplier coordination, production scheduling, and logistics process, making it difficult for the overall cycle to meet the development needs of rapid product iteration.

[0003] Therefore, the industry urgently needs a fundamental solution to address the efficiency bottlenecks on both the demand and supply sides. The core of this solution lies in how to build an intelligent collaborative platform that can proactively guide and accurately define customer needs at the demand input end, and deeply integrate real-time, cross-enterprise supply chain resources and production constraints at the solution generation end. This will ensure that every generated design solution is both technically feasible and immediately deliverable. Ultimately, by connecting the entire chain from intelligent design and supply chain collaboration to online delivery, the acquisition of battery prototypes will be transformed from the current long-cycle, high-cost model into a fast and deterministic online service. Summary of the Invention

[0004] This application provides a rapid design method and system for battery prototypes based on artificial intelligence to solve the above problems.

[0005] Firstly, this application provides a rapid battery prototype design method based on artificial intelligence. The method includes: acquiring an initial battery requirement information set; based on the initial battery requirement information set, guiding customer needs through interactive questioning and demand co-shaping and potential parameter inference to obtain a definite battery requirement information set; acquiring a battery specification database; based on the battery specification database and combined with the definite battery requirement information set, analyzing the thermal coupling relationship and aging curve characteristics of different battery specification combinations to obtain a candidate battery information set; and based on the candidate battery information set, performing thermal equalization and life decay co-optimization to generate and output a battery assembly delivery scheme information set containing the battery manufacturing process and the actual battery.

[0006] The above technical solutions enable intelligent design of the entire battery prototype design process, accurately uncover customers' real needs, and avoid design deviations from the source; scientifically analyze the characteristics of battery specification combinations to select reliable candidate solutions; and achieve optimal overall battery core performance through synergistic optimization of thermal equilibrium and life decay, thereby improving design efficiency, shortening the cycle, adapting to customized design requirements, and promoting the intelligent and standardized development of the battery design field.

[0007] Optionally, the step of guiding customer needs through interactive questioning and inferring potential parameters based on the initial battery demand information set to obtain a clear battery demand information set includes: the initial battery demand information set includes physical form requirements and application scenario requirements; based on the physical form requirements, analyzing the deterministic boundary conditions of the battery in terms of spatial constraints and interface configuration to obtain a physical constraint information set; based on the application scenario requirements, analyzing the dynamic load spectrum and working environment conditions related to the battery application scenario to obtain a scenario constraint information set; based on the physical constraint information set, combined with the scenario constraint information set, analyzing the performance specification gaps and design freedoms under the coupling of physical constraints and scenario constraints to obtain an interactive question information set for guiding demand clarification; based on the interactive question information set, conducting multiple rounds of question-and-answer interaction with the user, integrating user feedback, and inferring potential performance parameters including energy density, power characteristics, and cycle life expectations; integrating the physical constraint information set, the scenario constraint information set, and the potential performance parameters to construct the clear battery demand information set.

[0008] Optionally, the process of constructing the scenario constraint information set includes: based on the application scenario requirements, analyzing the driving factors that determine the battery's operating state in the application scenario to obtain operating condition driving information; based on the operating condition driving information, deducing the load intensity change sequence and duration distribution experienced by the battery during a complete task cycle to obtain dynamic load spectrum information characterizing the electrical stress profile; based on the application scenario requirements, analyzing the environmental factors and their changing patterns that affect the battery's structure in the physical space where the application scenario is located to obtain operating environment condition information including temperature and humidity spectrum and vibration spectrum; and integrating the dynamic load spectrum information and the operating environment condition information to construct the scenario constraint information set used to define the battery design input conditions.

[0009] Optionally, the process of constructing the interactive question information set includes: based on the physical constraint information set and combined with the scenario constraint information set, analyzing the upper limit of the dynamic load spectrum and the compatibility boundary of interface configuration and working environment conditions under physical space constraints to obtain constraint coupling limit information; based on the constraint coupling limit information, analyzing the quantitative demand gaps in energy density, power characteristics, and cycle life that are not clearly defined in the initial battery demand information set, identifying performance ambiguities that need to be further defined by the customer to obtain performance specification gap information; based on the performance specification gap information, analyzing the questioning direction and logic that can guide the customer to clarify ambiguities and supplement quantitative indicators, and integrating them to form the interactive question information set used to guide the clarification of requirements.

[0010] Optionally, the process of constructing the potential performance parameters includes: based on the interactive question information set, presenting guiding questions to the user in a logical order from macroscopic scenarios to microscopic parameters, and from qualitative descriptions to quantitative definitions, and collecting user feedback on each question to obtain initial question-and-answer records; based on the initial question-and-answer records, analyzing the ambiguity, contradictory needs, and missing parameters in the user's feedback on different questions, generating a set of follow-up questions to clarify contradictions, eliminate ambiguities, and supplement missing parameters, conducting a new round of interaction, and obtaining clarified and supplemented refined feedback information; based on the refined feedback information, analyzing the user's expression tendencies and priority hints regarding energy density, power characteristics, and cycle life, inferring the range of quantitative parameter values ​​that can simultaneously satisfy the user's expression tendencies and physical scenario constraints, and obtaining the potential performance parameters.

[0011] Optionally, the step of analyzing the thermal coupling relationship and aging curve characteristics of different battery specification combinations based on the battery specification database and the defined battery requirement information set to obtain a candidate battery information set includes: the battery specification database includes battery application adaptation information and battery replacement compatibility information; based on the battery application adaptation information and battery replacement compatibility information, combined with the defined battery requirement information set, analyzing the adaptability of each battery specification to physical constraints and scenario constraints, and the feasibility of replacement compatibility between specifications, to obtain a pool of combinable battery specifications; based on the pool of combinable battery specifications, combined with the dynamic load spectrum information and the working environment condition information, analyzing the heat generation, transfer, and mutual thermal influence laws of different battery specification combinations within a complete task cycle, to obtain thermal coupling relationship information of each combination; based on the thermal coupling relationship information, combined with the potential performance parameters, analyzing the performance degradation trend, service life change law, and matching characteristics with the potential performance parameters of each combination under thermal coupling, and screening out battery specification combinations with controllable thermal coupling risk and expected aging rate, to obtain a candidate battery information set.

[0012] Optionally, the construction process of the composable battery specification pool includes: based on the battery application adaptation information, combined with the physical constraint information set and the scenario constraint information set, analyzing the matching characteristics of each battery specification unit with space limitations, interface types, dynamic load spectrum and working environment conditions to obtain an adaptation specification unit set; based on the battery replacement compatibility information, combined with the adaptation specification unit set, analyzing the interchangeability of different specification units in electrical interfaces, communication protocols and structural dimensions, as well as the performance complementarity in energy characteristics and power characteristics when combined, to obtain a specification unit relationship information set with substitution and complementarity potential; based on the specification unit relationship information set, combined with the explicit battery requirement information set, analyzing the overall performance coverage of the potential performance parameter value range after performance superposition and redundant configuration through unit combination, as well as the comprehensive satisfaction of physical constraints and scenario constraints, and selecting specification unit combinations that can constitute the basis of an effective design scheme to obtain the composable battery specification pool.

[0013] Optionally, the process of constructing the thermal coupling relationship information includes: based on the combinatorial battery specification cells and combined with the dynamic load spectrum information, analyzing the heat generation rate and heat accumulation characteristics of each specification cell under different load intensities and durations to obtain heat generation characteristic information; based on the heat generation characteristic information and combined with the working environment condition information, analyzing the paths and efficiency of heat conduction through material contact surfaces and convection through internal space fluids within the assembly composed of each specification cell, as well as the heat dissipation bottlenecks in heat exchange between the assembly shell and the external environment to obtain heat transfer path information for each assembly; based on the heat transfer path information, analyzing the pattern of temperature field superposition between adjacent cells and the inability to dissipate heat in time due to differences in the spatial arrangement and heat generation sequence of different specification cells, resulting in the formation of local hot spots, and the impact on cell performance and safety to obtain temperature field superposition effect information; integrating the temperature field superposition effect information and the working environment condition information to construct the thermal coupling relationship information used to characterize the thermal behavior and thermal risk of each battery specification assembly in the working scenario.

[0014] Optionally, the step of performing coordinated optimization of thermal equilibrium and lifespan degradation based on the candidate battery information set to generate and output a battery assembly delivery scheme information set containing the battery manufacturing process and the actual battery, includes: based on the candidate battery information set and combined with the thermal coupling relationship information, analyzing the quantitative mapping law between the temperature field superposition effect and the performance aging rate under the driving of the dynamic load spectrum information for different specification combinations, and obtaining the thermal aging evolution characteristics of each combination; based on the thermal aging evolution characteristics, analyzing measures to adjust the arrangement topology between cells and introduce functional thermal management interfaces to reconstruct the heat transfer path within the combinatorial battery specification pool, thereby simultaneously optimizing the temperature rise of key parts and the overall aging rate, and obtaining a thermal-lifespan coordinated control scheme set; based on the thermal-lifespan coordinated control scheme set and combined with the potential performance parameters, evaluating and screening the coordinated schemes that can simultaneously meet the lifespan expectations and control the thermal coupling risk within the allowable range of the temperature field superposition effect, binding them with the suitable battery specification combinations, performing supply chain coordinated orchestration, and generating and outputting the battery assembly delivery scheme information set.

[0015] Secondly, this application provides an artificial intelligence-based rapid battery prototyping system, comprising: a battery requirement module, used to acquire an initial battery requirement information set, and based on the initial battery requirement information set, guide customer needs through interactive questioning to co-shape requirements and infer potential parameters to obtain a definite battery requirement information set; a specification combination module, used to acquire a battery specification database, and based on the battery specification database and the definite battery requirement information set, analyze the thermal coupling relationship and aging curve characteristics of different battery specification combinations to obtain a candidate battery information set; and a solution collaboration module, used to perform thermal equalization and life decay collaborative optimization based on the candidate battery information set, and generate and output a battery assembly delivery solution information set containing the battery manufacturing process and the actual battery. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram illustrating an application scenario provided in one embodiment of this application;

[0018] Figure 2 A flowchart illustrating a rapid battery prototyping method based on artificial intelligence, provided as an embodiment of this application; Figure 3This is a schematic diagram of a rapid prototyping system for batteries based on artificial intelligence, provided as an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, 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 some, not all, of the embodiments of this application. 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.

[0020] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0021] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0022] In the existing battery design process, the battery industry urgently needs to break through the efficiency bottlenecks on both the supply and demand sides. Currently, the acquisition cycle of battery prototypes is long and the cost is high. It is necessary to build an intelligent collaborative platform to connect the entire process and achieve fast and deterministic online delivery services.

[0023] Based on this, this application provides a rapid design method and system for battery prototypes based on artificial intelligence. Existing battery designs are prone to problems such as demand deviation, blind selection of solutions, performance imbalance, and lengthy cycles. By utilizing an intelligent collaborative platform that integrates "online battery design + delivery platform + supply chain integration", the intelligent full-process design can accurately break through these problems, collaboratively optimize core performance, improve efficiency and adapt to customization, and promote the intelligent standard upgrade of the industry.

[0024] Figure 1 This application provides an illustration of an application scenario: in the application of an intelligent collaborative platform for "online battery design + delivery platform + supply chain integration", the method provided in this application is used to accurately identify the real needs of customers, and achieve the best overall performance of the battery core through the synergistic optimization of thermal balance and life decay, adapting to customized design requirements and promoting the intelligent and standardized development of the battery design field.

[0025] Specifically, the method provided in this application can be applied to any server. The server interacts with an online battery design platform and battery industry standard data to obtain an initial battery requirement information set provided by the online battery design platform and a battery specification database provided by the battery industry standard data. A dual-objective optimization model is then constructed to adjust design parameters, generating and outputting a battery assembly delivery plan information set. The customer selects the desired battery assembly delivery plan on the online platform, then fills in the required quantity of the physical battery assembly and the physical delivery information. The online platform automatically generates a price. After the customer confirms and pays online, the online platform sends the battery assembly delivery plan information set to the factory, which manufactures the physical battery according to the information set. Once completed, the battery is delivered to the customer via logistics. Compared to the current industry standard of 2-3 months for battery physical delivery, this method can reduce the battery assembly delivery cycle to within 15 days. Simultaneously, it scientifically analyzes the characteristics of battery specification combinations, generates and outputs a battery assembly delivery plan information set to the customer, providing a complete and accurate standardized design basis for battery prototype R&D and production.

[0026] For specific implementation details, please refer to the following examples.

[0027] Figure 2 This is a flowchart illustrating a rapid battery prototyping method based on artificial intelligence, provided as an embodiment of this application. The method of this embodiment can be applied to servers in the above-described scenarios. Figure 2 As shown, the method includes: S201. Obtain an initial battery demand information set. Based on the initial battery demand information set, guide customer demand through interactive questioning, co-shape demand, and infer potential parameters to obtain a clear battery demand information set.

[0028] The initial battery requirement information set can be a collection of battery-related requirements initially raised by battery customers, without systematic organization and in-depth analysis, with the online battery design platform as the data source. Demand co-shaping can be a process of jointly organizing, clarifying, and refining battery requirements based on the customer's initial needs through interactive questioning and multiple rounds of communication. Potential parameter inference can be achieved by combining information such as the customer's industry attributes, usage scenarios, and operating conditions.

[0029] A defined battery demand information set can be a set of battery demand information that is clearly oriented, has well-defined parameters, and is complete and comprehensive, formed after completing demand co-shaping and potential parameter inference of the initial battery demand information set.

[0030] Specifically, in the process of demand mining for customized battery prototype design, by acquiring initial requirements and conducting demand co-shaping and potential parameter inference through interactive questioning, vague and scattered original requirements are transformed into a clear set of battery demand information. This accurately anchors the customer's real needs from the source, solving the problem of shallow demand mining and disconnection from actual use needs in existing designs. It provides accurate and comprehensive demand basis for subsequent design stages and avoids design rework due to demand deviations.

[0031] S202. Obtain the battery specification database. Based on the battery specification database and the clearly defined battery requirement information set, analyze the thermal coupling relationship and aging curve characteristics of different battery specification combinations to obtain the candidate battery information set.

[0032] A battery specification database can be a specialized database storing various basic battery specifications, performance indicators, applicable scenarios, and measured data, using battery industry standards as its data source. A battery specification combination can be an overall battery design scheme formed by combining battery cells of different basic specifications from the database according to certain rules. Thermal coupling relationships can be the correlations between battery cells in different battery specification combinations, including heat transfer, heat superposition, and the interaction of thermal effects. Aging curve characteristics can be the characteristics of how battery performance degrades with usage time and number of uses during cyclic charging and discharging and operation under different conditions. A candidate battery information set can be a collection of information on various battery specification combinations that meet the customer's basic needs, along with their corresponding thermal coupling, aging curve, and other performance characteristics, after analyzing the battery specification database in conjunction with a defined battery requirement information set.

[0033] Specifically, in the specification screening process of battery prototype design, by accessing the battery specification database and combining it with a clear requirement analysis of the thermal coupling relationship and aging curve characteristics of different specification combinations, a candidate battery information set is obtained through scientific screening. This replaces the existing simple parameter matching based on manual experience, solves the problem of one-sided specification screening, avoids design risks such as thermal runaway and excessively rapid lifespan degradation, and provides a reliable and suitable basic solution for subsequent optimization stages.

[0034] S203. Based on the candidate battery information set, perform coordinated optimization of thermal equilibrium and life decay, and generate and output a battery assembly delivery scheme information set that includes the battery manufacturing process and the actual battery.

[0035] Thermal equalization is a battery performance optimization goal that aims to achieve uniform heat distribution among battery cells during use by adjusting the structure and parameters of the battery specification combination, thus avoiding localized overheating. Lifespan degradation refers to the gradual decline in battery performance during use due to factors such as charge-discharge cycles and changes in operating conditions. Co-optimization of thermal equalization and lifespan degradation involves simultaneously optimizing both thermal equalization effectiveness and lifespan degradation rate as core optimization objectives, achieving optimal overall battery thermal and lifespan performance through multi-dimensional adjustments to design parameters. The battery manufacturing process refers to the complete process chain information from raw material selection to finished battery production. The physical battery refers to the physical entity and final deliverable that embodies the thermal equalization design and lifespan degradation optimization goals. The battery assembly delivery solution information set is a complete delivery solution information set generated after co-optimization of thermal equalization and lifespan degradation, including the final specifications of the battery prototype, design parameters, performance indicators, applicable operating conditions, and optimization instructions.

[0036] Specifically, in the process of optimizing and outputting the battery prototype design scheme, thermal equilibrium and life decay are optimized in a coordinated manner through the candidate information set. A dual-objective optimization model is constructed to adjust the design parameters, and a battery assembly delivery scheme information set is generated and output. This solves the drawbacks of the existing single optimization design, avoids the mutual constraints between thermal equilibrium and life performance, and achieves the comprehensive optimization of the battery's core performance. It provides a complete and accurate standardized design basis for the research and development and production of battery prototypes.

[0037] The method provided in this embodiment enables intelligent design of the entire battery prototype design process, accurately uncovers the real needs of customers, and avoids design deviations from the source; it scientifically analyzes the characteristics of battery specification combinations and selects reliable candidate solutions; and it achieves the best overall performance of the battery core through the synergistic optimization of thermal equilibrium and life decay. The current battery physical delivery cycle takes 2-3 months, while this solution can compress the cycle to less than 15 days. This not only greatly improves design efficiency and significantly shortens the R&D cycle, but also accurately adapts to customized design needs and promotes the intelligent and standardized development of the battery design field.

[0038] In some embodiments, the initial battery requirement information set includes physical form factor requirements and application scenario requirements. Based on the physical form factor requirements, the deterministic boundary conditions of the battery in terms of spatial constraints and interface configuration are analyzed to obtain a physical constraint information set. Based on the application scenario requirements, the dynamic load spectrum and operating environment conditions related to the battery application scenario are analyzed to obtain a scenario constraint information set. Based on the physical constraint information set and combined with the scenario constraint information set, the performance specification gaps and design degrees of freedom existing under the coupling of physical constraints and scenario constraints are analyzed to obtain an interactive question information set to guide the clarification of requirements. Based on the interactive question information set, multiple rounds of question-and-answer interaction are conducted with the user, user feedback is integrated, and potential performance parameters including energy density, power characteristics, and cycle life expectations are inferred. The physical constraint information set, the scenario constraint information set, and the potential performance parameters are integrated to construct a clear battery requirement information set.

[0039] The physical constraint information set can be a set of deterministic boundary conditions regarding battery space constraints and interface configurations, derived from the analysis of battery physical form requirements. The scenario constraint information set can be integrated from dynamic load spectrum information and operating environment condition information corresponding to the battery application scenario, defining the battery's operating conditions and environmental input conditions. Performance specification gaps can be the absence of clearly defined quantitative performance indicators such as energy density, power characteristics, and cycle life in the initial battery requirements, under the coupling of physical and scenario constraints. Design freedom can be the range of adjustable battery performance parameters and specifications within the constraints of both physical and scenario. The interactive question information set can be a set of questions and logic used to guide customers to clarify ambiguous performance aspects. Potential performance parameters can be inferred from user feedback, including the expected range of quantitative parameter values ​​for energy density, power characteristics, and cycle life, satisfying both physical and scenario constraints.

[0040] Specifically, in the existing battery design process, the initial requirements provided by customers (such as "small size and long range") are often vague and inherently contradictory. Designing directly based on such requirements can easily lead to repeated modifications or even make the solution unfeasible. Through systematic constraint analysis and proactive interaction, the qualitative and vague requirements of customers can be transformed into clear design inputs that are consistent and quantifiable, thereby reducing design iterations from the source.

[0041] In the specific analysis process: First, the "physical shape requirements" are analyzed. For example, if the customer inputs "must be installed in the L-shaped space reserved in the chassis, with dimensions not exceeding 1200mm x 800mm x 150mm, using an XT90 interface," this is analyzed into a deterministic set of physical constraint information, including specific boundary dimensions and a list of interface models. Next, the "application scenario requirements" are analyzed, such as "used for logistics forklifts, two shifts per day, each shift working continuously for 4 hours, including frequent starts and stops and short-term lifting of heavy objects." Based on this, a typical work cycle is deduced: the power requirements and durations of the forklift in unloaded movement, loaded movement, lifting, and idling states are analyzed to generate dynamic load spectrum information characterizing current changes; simultaneously... By querying typical environmental data from logistics warehouses, information on working environment conditions including daytime temperature fluctuations and slight ground vibrations is generated. This information is then integrated into a scenario constraint information set. Coupled analysis is then performed: the actual usable volume of the L-shaped space after meeting heat dissipation spacing is calculated. This is compared with the energy and power requirements estimated from the dynamic load spectrum. It is found that if conventional battery cells are used, the energy density needs to exceed a certain threshold (e.g., 180Wh / L) to meet the required range, and the interface needs to withstand the estimated peak current. These quantitative requirements, which cannot be directly determined from the initial requirements, are identified as performance specification gaps. Based on this, an interactive question information set is generated, such as: "To meet 8 hours of daily battery life, we estimate that approximately XX energy is needed." kWh. Considering your space constraints, this requires a higher cell energy density, which may increase costs. What is the approximate cost range per kWh that you can accept? Or, "Load analysis shows a short-term high current demand, which will affect battery life. Do you prioritize peak power or cycle life?" Through multiple rounds of such interactions, user feedback on the weighting of cost, life, and power is collected, ultimately leading to the inference of quantified potential performance parameters, such as "energy density must be ≥200Wh / L, peak power capability must be ≥5C, and cycle life target >2000 cycles (capacity decay to 80%)". Finally, physical constraints, scenario constraints, and potential performance parameters are integrated to form a clear set of battery requirement information that can be used for subsequent specification matching.

[0042] In alternative or modified implementations: physical constraint analysis can be combined with 3D CAD models for more accurate spatial and thermal simulations, rather than just geometric calculations; scene constraint generation can access IoT data from actual devices, automatically generating more representative load and environment spectra through data mining; the interactive interface can be a graphical configuration wizard, a natural language chatbot, or a VR / AR-based immersive experience to suit different user preferences; and the inference of potential performance parameters can employ more complex multi-objective optimization models to find Pareto optimal solutions for users to choose from within a fuzzy preference range, rather than a single value range.

[0043] In some embodiments, based on application scenario requirements, the driving factors that determine the battery's operating state in the application scenario are analyzed to obtain operating condition driving information; based on the operating condition driving information, the load intensity change sequence and duration distribution experienced by the battery during a complete task cycle are deduced to obtain dynamic load spectrum information characterizing the electrical stress profile; based on application scenario requirements, the environmental factors and their changing patterns that affect the battery structure in the physical space where the application scenario is located are analyzed to obtain operating environment condition information including temperature and humidity spectrum and vibration spectrum; the dynamic load spectrum information and operating environment condition information are integrated to construct a scenario constraint information set for defining the battery design input conditions.

[0044] Operating condition information can be a set of core influencing factors that directly determine the battery's charging, discharging, start-up, and shutdown states in the battery application scenario. Dynamic load spectrum information can be a sequence of load intensity changes and duration distribution that characterizes the battery's electrical stress profile within a complete task cycle. Operating environment condition information can include temperature and humidity spectra and vibration spectra, representing the variation patterns and characteristics of ambient temperature, humidity, and vibration intensity in the physical space where the battery application scenario is located.

[0045] Specifically, existing battery designs only take into account the application scenario type in a general way, without measuring the electrical and environmental stresses on the battery under the chemical conditions. This can easily lead to a mismatch between the design and the actual use scenario, resulting in problems such as excessively rapid battery life degradation and substandard performance. By accurately disassembling the scenario constraints, we can provide battery designs with input conditions that fit the actual situation.

[0046] In the specific analysis process: First, the user-input "application scenario requirements" (e.g., "warehouse logistics AGV, load capacity 500kg, daily operation 12 hours, including sloping sections") are analyzed. Based on this, the driving factors that determine the battery's operating state are analyzed. For example, "motor start / stop," "load change," and "overcoming slope" are identified as core driving factors. Next, the dynamic load spectrum is deduced: Based on the typical task cycle of the AGV (e.g., picking up goods - driving - unloading - returning), combined with motor parameters, vehicle dynamics model, and route information (including slope), the timing curve of the battery output current within a complete cycle is calculated through simulation, quantifying the high-current pulse (e.g., 150A) during the acceleration phase. The system analyzes the distribution of base current (e.g., 30A) and duration during 10-second continuous operation and uniform speed operation. Simultaneously, it analyzes the working environment conditions: based on the "warehousing environment" requirements, it queries historical environmental databases or sets standards to obtain typical temperature and humidity spectra (e.g., working temperature 5-35°C, daily temperature difference approximately 10°C; humidity 40%-70%). Based on the type of AGV's road surface (e.g., epoxy flooring, slow-moving strip), it defines the corresponding vibration spectrum (e.g., main vibration frequency 5-50Hz, corresponding to bumpy driving). Finally, it integrates the dynamic load spectrum information (current-time curve) and the working environment condition information (temperature and humidity spectrum, vibration spectrum description file) to form a structured set of scenario constraint information.

[0047] In alternative or modified implementations: For the generation of dynamic load spectra, if it does not rely on accurate physical model simulation, a matching method based on a typical working condition mode library can be adopted: The system has built-in load templates such as "AGV standard cycle" and "UAV hovering-maneuvering cycle". After the user selects or fine-tunes the parameters (such as maximum current multiple, cycle ratio), the load spectrum is quickly generated. For working environment conditions, if the user cannot provide detailed data, a preset standard environment spectrum (such as industrial-grade temperature cycle spectrum, random vibration spectrum) bound to the keywords of "application scenario requirements" (such as "outdoor communication base station", "underwater robot") can be called as the default input.

[0048] In some embodiments, based on the physical constraint information set and combined with the scenario constraint information set, the upper limit of the dynamic load spectrum, the compatibility boundary of interface configuration and working environment conditions of the physical space constraints are analyzed to obtain constraint coupling limit information; based on the constraint coupling limit information, the quantitative demand gaps of energy density, power characteristics and cycle life that are not clearly defined in the initial battery demand information set are analyzed to identify performance ambiguities that need to be further defined by the customer to obtain performance specification gap information; based on the performance specification gap information, the questioning direction and logic that can guide the customer to clarify ambiguities and supplement quantitative indicators are analyzed and integrated to form an interactive questioning information set for guiding the clarification of requirements.

[0049] Constraint coupling information can be design boundary conditions formed by the interaction of physical constraints and scenario constraints, representing the dual limitations of physical space and interface configuration on the battery's dynamic load-bearing capacity and environmental adaptability. Performance specification gap information can be quantitative missing items in energy density, power characteristics, and cycle life that are not clearly defined in the initial requirements, as well as a set of performance ambiguities that need to be defined by the customer. The questioning direction and logic can be a questioning design principle based on performance specification gaps, guiding the customer to clarify their requirements from scenario requirements to parameter quantification, and from macro to micro, ensuring the relevance and progression of the questions.

[0050] Specifically, in existing battery designs, selection is often based directly on vague initial requirements, which can easily lead to conflicts between physical constraints and scenario requirements, as well as performance parameter mismatches, resulting in design rework. Clearly defining the constraint coupling boundaries and providing targeted guidance to customers to complete the parameters are the core prerequisites for avoiding design deviations.

[0051] In the specific analysis process: First, constraint coupling analysis is performed. For example, the customer inputs "for drones, battery compartment size is 1005020mm" (physical constraint) and "requires continuous flight for 30 minutes" (scenario constraint). Combining the thermal resistance parameters of a typical battery module under this size with the dynamic load spectrum under drone flight conditions, it is calculated that the theoretical temperature rise of this space under continuous discharge may exceed a certain safety threshold. This is the "constraint coupling limit information". Next, gap identification is performed. Based on this temperature rise limit, it is deduced that if the flight time is met, quantitative requirements are put forward for the energy density and heat dissipation efficiency of the battery. However, these values ​​were not clearly stated in the customer's initial requirements. Thus, "energy density must not be less than XXX Wh / L" and "maximum allowable operating temperature" are identified as "performance specification gap information". Finally, based on these gaps, decision tree logic is used to generate questions, such as "To control the temperature rise, do you prioritize using battery cells with higher energy density but slightly higher cost, or are you willing to accept a slightly larger size to enhance heat dissipation?", thus forming a guiding "interactive question information set".

[0052] In alternative or modified implementations: the logic for generating questions can be replaced with case-based reasoning (CBR): retrieve successful cases similar to the current "constraint coupling restriction information" from the historical project library, extract the key issues and options clarified with the client at that time, and form the current question set after adaptation. Another modification is to introduce a multi-round game model, treat the system as an agent trying to maximize the success rate of the solution, and model the questioning process as a process of obtaining the client's preference distribution by minimizing information entropy, thereby dynamically adjusting the order and depth of questions.

[0053] In some embodiments, based on an interactive question information set, guiding questions are presented to the user sequentially in a logical order from macroscopic scenarios to microscopic parameters, and from qualitative descriptions to quantitative definitions. User feedback on each question is collected to obtain an initial question-and-answer record. Based on this record, the ambiguity, contradictory needs, and missing parameters in the user's feedback are analyzed. A set of follow-up questions is generated to clarify contradictions, eliminate ambiguities, and supplement deficiencies, leading to a new round of interaction and obtaining refined feedback information that has been clarified and supplemented. Based on this refined feedback information, the user's tendency and priority in expressing energy density, power characteristics, and cycle life are analyzed to infer the range of quantitative parameter values ​​that can simultaneously satisfy both the user's expression tendencies and physical scenario constraints, thus obtaining potential performance parameters.

[0054] The initial Q&A record can be a collection of users' original feedback on each question after asking questions according to a macro-to-micro, qualitative-to-quantitative logic. Detailed feedback information can be a collection of precise user needs feedback obtained by analyzing the initial Q&A record for ambiguity, contradictions, and omissions, followed by clarification and supplementation through follow-up questions. The logical order can be a question arrangement rule that first explores the macro-level scenario of battery applications, then delves into specific performance parameters, first clarifying the direction of needs through qualitative questions, and then determining parameter values ​​through quantitative questions.

[0055] Specifically, directly collecting customer requirements in existing battery designs can easily lead to problems such as ambiguous parameters and conflicting requirements, resulting in a large deviation between the design and actual needs. Furthermore, illogical questions increase communication costs and make it impossible to efficiently deduce performance parameters that conform to physical constraints, thus restricting the efficiency and accuracy of battery design.

[0056] In the specific analysis process: a multi-round closed-loop interaction protocol is executed. In the first round, the system calls the "interactive question information set" and presents questions in a preset logical order through a web interface in the form of a dynamic form or chat window. For example, first select "application scenario (e.g., outdoor mobile robot)" from the drop-down menu, and then automatically pop up related sub-questions based on the selected scenario, such as "peak power demand (kW) within a typical task cycle". Each time the user answers a question, the answer is recorded in real time to the "initial question and answer record" JSON object. Subsequently, the system starts the contradiction and ambiguity analysis module: this module is based on a rule engine and compares the logical consistency of different answers in the record. For example, if the user selects "cost-sensitive project" in the previous question, but fills in "cycle life requirement > 5000 times (usually corresponding to high-cost cells)" in the next question, it is marked as "potential contradiction"; if the user answers "the higher the better" for "energy density", it is marked as "ambiguous expression". Based on the analysis results, the system dynamically generates a "set of follow-up questions," such as a pop-up clarification dialog box: "You mentioned that 'cost sensitivity' and 'long cycle life' may conflict. Which has a higher priority? Or what is the acceptable lifespan range?" After the user provides supplementary answers, "refined feedback information" is generated. Finally, the parameter inference module works: it first identifies the priority ranking from the "refined feedback information" through text analysis (such as keyword extraction and sentiment analysis) (for example, if the user repeatedly emphasizes "range," it implies that energy density has the highest priority); then, combined with the known "set of physical constraint information" (such as maximum allowable volume), it calls the built-in battery performance parameter association database (which stores empirical mapping relationships such as "under volume X, using Y-type cells, the typical energy density range is AB"), and calculates the recommended range of quantitative parameters that can meet all constraints and expression tendencies through a multi-objective trade-off algorithm (such as: recommended energy density >240Wh / kg, peak power must meet ≥5kW, and cycle life can be guaranteed >2000 times), outputting "potential performance parameters."

[0057] In alternative or modified implementations: the interactive interface can be implemented without being limited to web forms. It can be integrated with a voice assistant for question-and-answer interaction and converted into structured text records by a speech recognition module. The rule engine used to analyze "vague expressions and contradictory needs" can be replaced by a trained natural language processing (NLP) model. This model directly performs intent recognition and contradiction detection on the dialogue text. In addition to rule-based database mapping, the parameter inference process can also use a constraint solver to model the physical relationships between user constraints, physical constraints, and performance parameters (such as the inverse relationship between energy density and power density) as a system of inequality equations and automatically solve for feasible parameter solution space.

[0058] In some embodiments, the battery specification database includes battery application adaptation information and battery replacement compatibility information. Based on the battery application adaptation information and battery replacement compatibility information, combined with a set of explicit battery requirements, the compatibility of each battery specification with physical constraints and scenario constraints, as well as the feasibility of replacement compatibility between specifications, are analyzed to obtain a pool of combinable battery specifications. Based on the pool of combinable battery specifications, combined with dynamic load spectrum information and working environment condition information, the heat generation, transfer, and mutual thermal influence of different battery specification combinations during a complete task cycle are analyzed to obtain thermal coupling relationship information for each combination. Based on the thermal coupling relationship information, combined with potential performance parameters, the performance degradation trend, service life change law, and matching characteristics with potential performance parameters of each combination under thermal coupling are analyzed to screen out battery specification combinations with controllable thermal coupling risk and aging rate that meets expectations, thus obtaining a candidate battery information set.

[0059] A pool of composable battery specifications can be a set of battery specification units selected from a battery specification database that simultaneously meets the constraints of a clearly defined battery requirement information set and has the potential for substitution compatibility and performance complementarity among specifications. Thermal coupling relationship information can be a comprehensive set of information characterizing the patterns of heat generation, transfer, and temperature field superposition between units in different battery specification combinations under working scenarios, as well as thermal risks.

[0060] The aging curve characteristics can be seen as the performance of a battery specification combination decreases with the usage period under thermal coupling, and it is the core basis for judging whether the battery life meets the requirements.

[0061] Specifically, existing battery designs rely solely on proprietary modules, resulting in limited combination options and a lack of quantitative analysis of the thermal coupling and aging characteristics of specification combinations. This can easily lead to issues such as thermal runaway and underperformance in finished products. By integrating full-specification data analysis across the supply chain, we can provide a scientific basis for selecting candidate solutions for the design.

[0062] In the specific analysis process: First, based on each candidate specification unit in the combinatorial battery specification pool (such as a certain model of cell A, cell B, and a certain model of BMS board), its respective heat generation parameters (such as the internal resistance-heat generation lookup table at different rates) and physical size model are retrieved from the background database. Then, combined with the dynamic load spectrum information corresponding to the user scenario (e.g., "discharge at 2C for the first 10 minutes, then rest for the next 5 minutes"), a computational fluid dynamics (CFD) simulation engine or a simplified lumped parameter thermal model is used to perform a transient thermal simulation of a complete task cycle for each possible unit combination and its preset geometric arrangement. The simulation will output the temperature change curve of key points in the combination over time and analyze the heat transfer path, thereby quantifying the "thermal coupling relationship information," such as "electricity..." "When the load peaks, the surface temperature of cell A reaches a maximum of 65°C, causing the temperature of the adjacent BMS chip area to rise to 58°C." Then, this temperature history is used as input to call the built-in aging model library (e.g., an electrochemical aging model based on the Arrhenius equation) to predict the capacity decay curve (aging curve characteristics) of each key unit (such as cell A) in the combination under this thermal environment. Finally, the predicted end of life (e.g., the number of cycles at which the capacity decays to 80%) is compared with the expected cycle life in the user's potential performance parameters, and it is checked whether the temperature of any node in the entire simulation process exceeds the safety threshold (e.g., the maximum operating temperature of the cell, the junction temperature of electronic components). Only those combinations whose predicted life meets the expectations and whose temperature risk is controllable throughout the process will be screened into the candidate battery information set.

[0063] In alternative or modified implementations: If the platform's computing power is limited or the requirement for rapid response is extremely high, a simplified strategy can be adopted. For example, instead of performing full-cycle transient CFD simulation, a rule-based rapid assessment matrix for thermal coupling risk can be established. This involves pre-developing a temperature rise coefficient table for typical proximity relationships (e.g., "side-by-side" or "5mm stacking spacing") between different types of specification units (e.g., "high-power soft-pack cells," "cylindrical cells," "aluminum substrate PCBs") through experiments or high-fidelity simulations. During analysis, the additional temperature rise in key areas is quickly estimated by looking up the table based on the actual arrangement of the combination, and then combined with the unit's basic heat generation to assess thermal risk. For aging analysis, a large-scale regression model based on historical similar scenarios can be used instead. The load spectrum characteristics and average operating temperature are input, and the lifetime prediction range is directly output instead of detailed curves.

[0064] In some embodiments, based on battery application adaptation information, combined with physical constraint information set and scenario constraint information set, the matching characteristics of each battery specification unit with space limitations, interface type, dynamic load spectrum and working environment conditions are analyzed to obtain an adaptation specification unit set; based on battery replacement compatibility information, combined with the adaptation specification unit set, the interchangeability of different specification units in electrical interface, communication protocol and structural size, as well as the performance complementarity in energy characteristics and power characteristics when combined, are analyzed to obtain a specification unit relationship information set with substitution and complementarity potential; based on the specification unit relationship information set, combined with the explicit battery requirement information set, the overall performance coverage of the potential performance parameter value range after performance superposition and redundant configuration through unit combination, as well as the comprehensive satisfaction of physical constraints and scenario constraints, are analyzed to screen specification unit combinations that can form the basis of effective design schemes, and a composable battery specification pool is obtained.

[0065] Battery application compatibility information can be basic data stored in the platform's battery specification database. The compatible specification unit set can be a collection of individual battery specification units selected from the battery specification database that match the physical and scenario constraints of the customer's clearly defined battery needs. Battery replacement compatibility information can be data on the interchangeability and performance complementarity between different battery specification units recorded in the database. The specification unit relationship information set can be a dataset characterizing the feasibility of substitution and performance complementarity between compatible specification units, clarifying the interchange conditions of different units and the performance superposition effect after combination. Performance superposition refers to the synergistic effect of the overall energy, power, and other performance indicators after combining multiple battery specification units, achieving the combined effect of the individual unit indicators and meeting the customer's potential performance parameter requirements. Redundancy configuration can be the configuration of spare specification units added in the unit combination to improve the reliability of the battery assembly. Coverage completeness refers to the degree to which the overall performance of the combined battery specification units meets the customer's potential performance parameter value range.

[0066] Specifically, existing battery designs rely solely on the company's own modules, resulting in a limited number of combination options that cannot meet the diverse performance and constraint requirements of customers. Furthermore, they do not consider the compatibility and complementarity between cells, which can easily lead to substandard performance and unmet constraints after combination. By integrating supply chain data to screen effective combinations, the design limitations of the company's own modules can be overcome, significantly increasing the range of battery assembly options. At the same time, compatible and complementary cell combinations can be accurately selected to ensure that the combined performance meets customer needs.

[0067] In the specific analysis process: First, based on the user-defined "physical constraint information set" (e.g., battery compartment internal dimensions of 1005020mm, interface of XT60) and "scenario constraint information set" (e.g., operating temperature -20℃~60℃), the system retrieves "battery application compatibility information" from all suppliers in the supply chain collaboration database. The built-in rule engine executes a series of filtering queries, such as: SELECT * FROM component_table WHERE length<= 100 AND width<=50 AND height<=20 AND connector_type = 'XT60' AND min_operating_temp<= -20 AND max_operating_temp>=60. The preliminary result set obtained through this query is the "adaptation specification unit set". Next, based on the "battery replacement compatibility information", the relationships between units within this set are analyzed. The system creates a feature vector for each unit in the set, containing fields such as electrical interface protocol, mechanical installation dimensions, and communication bus type. By comparing the feature vectors of different units, the similarity is calculated (e.g., using a cosine similarity algorithm). If the similarity between two cell units in terms of installation size, tab position, and voltage platform exceeds a preset threshold (e.g., 85%), they are determined to be "interchangeable" and this relationship is recorded. At the same time, the system runs a performance matching algorithm: for example, if it identifies that the user's potential performance parameters require both "high energy density" and "high power", the system will actively search in the adaptation set and mark the cells labeled as "high energy type" and "high power type" cells as "parallel complementary" in the relationship information set. Finally, the system performs combination and coverage evaluation. It uses a graph traversal algorithm, with the units in the "adapted specification unit set" as nodes and the interchangeable and complementary relationships in the "specification unit relationship information set" as edges, to explore all possible combination paths. For each explored combination path (i.e., a candidate combination of specification cells), the system will simulate and calculate its overall performance (e.g., total capacity = cell A capacity + cell B capacity, maximum current = sum of parallel branch currents), and check whether the overall performance range fully covers the value range defined by the user's "potential performance parameters," while also verifying whether all physical and scenario constraints are met. Combinations that pass this evaluation will be formally included in the "combinable battery specification pool."

[0068] In alternative or modified implementations: the rule engine can be replaced with a machine learning-based classification model. This model, trained on historical successful and failed adaptation data, directly predicts the compatibility probability of a new specification unit with a given set of constraints, thereby generating a "fit specification unit set". For compatibility analysis, knowledge graph technology can be used to construct a "specification unit relationship information set", treating units as entities and "replaceable", "required matching", "performance complementary", etc., as relationship edges. Graph query languages ​​(such as Cypher) can be used to efficiently discover multi-hop compatible combination chains. In addition, for coverage evaluation, a more refined electrochemical simulation model can be introduced in the performance simulation calculation stage to predict the actual output voltage and temperature rise of the combined battery pack under dynamic load spectrum, rather than simply superimposing parameters, thereby making the selected specification pool more manufacturable.

[0069] In some embodiments, based on the composable battery specification cells and combined with dynamic load spectrum information, the heat generation rate and heat accumulation characteristics of each specification cell under different load intensities and durations are analyzed to obtain heat generation characteristic information. Based on the heat generation characteristic information and combined with working environment condition information, the paths and efficiencies of heat conduction through material contact surfaces and convection through internal space fluids within the assembly composed of each specification cell are analyzed, as well as the heat dissipation bottlenecks in heat exchange between the assembly shell and the external environment, to obtain heat transfer path information for each assembly. Based on the heat transfer path information, the patterns of temperature field superposition between adjacent cells and the inability to dissipate heat in time due to differences in the spatial arrangement and heat generation sequence of different specification cells are analyzed, as well as the impact on cell performance and safety, to obtain temperature field superposition effect information. Integrating the temperature field superposition effect information and working environment condition information, a thermal coupling relationship information is constructed to characterize the thermal behavior and thermal risk of each battery specification assembly under working scenarios.

[0070] Heat generation characteristics information can be specific data on the heat generation rate and heat accumulation of each battery cell under different load intensities and durations, reflecting the heat generation patterns of the cells themselves. Heat transfer path information can be the conduction and convection paths of heat within the battery assembly, as well as data related to heat dissipation bottlenecks in heat exchange between the assembly and the external environment, including dimensions such as contact conduction, fluid convection, and shell heat dissipation. Temperature field superposition effect information can be the pattern of local hotspots formed by the superposition of temperature fields of adjacent cells due to differences in the spatial arrangement and heat generation sequence of battery cells, and the impact of this effect on cell performance and safety.

[0071] Specifically, existing battery designs only criticize the thermal characteristics of individual cells without analyzing the thermal coupling relationship of the entire assembly. This can easily lead to accelerated battery aging and reduced safety due to localized hot spots. By analyzing the thermal behavior of the entire assembly from all dimensions, we can provide accurate thermal data support for subsequent thermal-life optimization. At the same time, by integrating the supply chain to achieve data sharing, we can improve the efficiency and accuracy of upstream and downstream collaborative design.

[0072] In the specific analysis process, the system constructs thermal coupling relationship information as follows: First, based on the technical parameter manual of each battery specification unit (such as a certain model 21700 cell) in the combinatorial battery specification pool, its internal resistance-temperature curve and heating coefficient under unit current are extracted. Combined with the dynamic load spectrum information derived from the user scenario (for example, a large current pulse of 100A lasting 2 minutes during the drone's climb phase), the built-in electrothermal coupling calculation engine is invoked to calculate in real time the instantaneous heat generation power of the cell in each time slice of this load spectrum (formula: P_heat=I). 2 The total heat generated in the work cycle is obtained by integrating *R(T) and generating the heat generation characteristics of the unit. Then, based on the three-dimensional digital model of the candidate scheme (automatically generated by the size, shape and preset arrangement of the specification unit), the thermal simulation mesh is automatically divided using the finite element analysis (FEA) method. Properties such as thermal conductivity and specific heat capacity are assigned to different materials (e.g., cell casing, aluminum foil, insulating film, cooling plate). Boundary conditions are set according to the working environment conditions (e.g., ambient temperature 40°C). The simulation engine calculates the complete process of heat transfer from the inside of each heat generation unit to the surroundings through contact conduction and natural air convection (or forced air cooling / liquid cooling channels), and outputs the results. Temperature cloud maps and heat flux density maps are used to quantitatively obtain information on heat transfer paths and thermal resistance values ​​along each path. Finally, the simulation results are analyzed to identify "hot spots" where the local temperature is significantly higher than the regional average due to the spatial aggregation of multiple heat-generating units (such as multiple cells side by side) and poor heat dissipation paths. For example, the simulation shows that during peak load periods, the temperature of the middle cell is 15°C higher than that of the edge cells, and this temperature difference is not effectively reduced during load breaks. The uneven spatial temperature distribution and its dynamic changes over time are combined with the location of hot spots, the magnitude of temperature rise, and the duration of the temperature difference to quantify the temperature field superposition effect information. All of the above information is structured and integrated to form the thermal coupling relationship information of the candidate scheme.

[0073] In alternative or modified implementations: the implementation methods of the above process can be adjusted as follows: 1. For scenarios sensitive to computing resources or requiring rapid screening, a reduced-order model (ROM) can be used instead of a complete FEA simulation. For example, a neural network model can be pre-trained through a large number of simulations, with the input being the specification unit parameters, arrangement matrix, and load spectrum feature vector, directly outputting the predicted highest temperature and maximum temperature difference. 2. Heat transfer path analysis can be simplified to a lumped-parameter thermal network method, abstracting each battery cell as a thermal capacity node, and the contact thermal resistance and convection thermal resistance between cells as the thermal resistance of the connection node. The temperature distribution can be quickly estimated by solving the thermal network equation. 3. In addition to absolute temperature, the evaluation of temperature field superposition effect information can also introduce the "heat accumulation factor" index, which is the ratio of heat generation power per unit volume to local heat dissipation capacity, to identify potential risk areas earlier.

[0074] In some embodiments, based on candidate battery information sets and combined with thermal coupling relationship information, the quantitative mapping law between the temperature field superposition effect and performance aging rate under the dynamic load spectrum information is analyzed for different specification combinations, and the thermal aging evolution characteristics of each combination are obtained. Based on the thermal aging evolution characteristics, measures to simultaneously optimize the temperature rise of key parts and the overall aging rate by adjusting the arrangement topology between cells and introducing functional thermal management interfaces to reconstruct the heat transfer path within the combinatorial battery specification pool are analyzed, and a set of thermal-life synergistic control schemes is obtained. Based on the set of thermal-life synergistic control schemes and combined with potential performance parameters, synergistic schemes that can simultaneously meet life expectations and control thermal coupling risks within the allowable range of temperature field superposition effects are evaluated and screened. These schemes are then bound to the appropriate battery specification combinations, and supply chain collaborative orchestration is performed to generate and output a set of battery assembly delivery scheme information containing battery manufacturing processes and physical batteries.

[0075] Thermally induced aging evolution characteristics can be seen as a quantitative mapping law between the superposition effect of temperature field and the performance aging rate under the dynamic load spectrum driving battery specification combination, reflecting the dynamic process of battery performance degradation and lifespan changes under thermal coupling. Arrangement topology can be the spatial arrangement of battery specification cells in the battery assembly, including cell spacing, placement orientation, and combination structure. Functional thermal management interface can be an interface structure / material added to optimize battery heat transfer. Thermal-life synergistic control scheme set can be a collection of feasible measures to simultaneously optimize the temperature rise of key components and the overall aging rate by adjusting the battery cell arrangement topology and introducing a functional thermal management interface. Supply chain collaborative orchestration can be the platform's real-time coordination and synchronization of inventory, production capacity, and logistics data of suppliers of battery cells, thermal management components, etc., in the supply chain, ensuring the availability of materials and rapid delivery of battery prototype design schemes.

[0076] Specifically, existing battery designs only optimize thermal equalization or lifespan degradation individually, which can easily lead to issues such as controllable thermal coupling risks but unsatisfactory lifespan, or lifespan meeting requirements but localized excessive temperature rise. Furthermore, without considering the actual supply chain materials, design solutions are prone to failure due to material shortages, significantly extending the battery prototype delivery cycle. This solution achieves simultaneous optimization of battery thermal equalization and lifespan degradation, effectively controlling thermal coupling risks and ensuring battery lifespan meets expectations. Simultaneously, by combining supply chain collaboration and API integration, the design solution is matched with actual materials, significantly shortening the design and delivery cycle of battery prototypes.

[0077] In the specific analysis process: First, for each battery specification combination in the "candidate battery information set", its corresponding "thermal coupling relationship information" is retrieved. This information includes the heat generation data of each cell under different loads, the heat conduction path efficiency within the combination, and the predicted temperature field distribution (which may include hot spot locations and temperature rise data). The system has a built-in or connected "temperature rise-aging correlation database", which establishes capacity decay rate and internal resistance growth curves for different cell chemical systems at different temperatures and different SoCs (state of charge) through historical tests or authoritative models (such as the Arrhenius equation combined with an electrochemical degradation model). Next, the system performs numerical simulation or rapid calculation: "Dynamic load spectrum information" (such as a current-time series representing a typical operating cycle) is applied to the thermal model of the battery pack to simulate the temperature change curves of each cell within the battery pack over a complete task cycle or even multiple cycles. Then, based on the temperature history of each cell, the "temperature rise-aging correlation database" is queried to map the predicted capacity decay or internal resistance increase of each cell. Subsequently, through weighted calculation (e.g., based on capacity or series relationship), the overall performance retention rate of the entire battery pack at the expected end of its life (e.g., after 500 cycles) is calculated. This process quantifies the "thermal aging evolution characteristics" of the pack. Following this, the optimization engine is activated: targeting the identified main hot spots and aging weaknesses, the engine, under the constraints of the "combinable battery specification pool" (ensuring unchanged electrical connections and basic dimensions), optimizes the battery pack accordingly. The engine attempts limited spatial arrangement adjustments (e.g., moving the hottest battery cell from the center to a position closer to the heat sink, or inserting a low-heating battery cell between two high-heating cells as a thermal buffer). Simultaneously, the engine selects suitable materials from the preset "thermal interface material library" (such as silicone pads with different thermal conductivity, graphene heat sinks), and calculates the improvement effect on hot spot temperature drop and overall temperature uniformity after adding or thickening the material at key contact surfaces (such as between the battery cell and the casing, and between battery cells). Each adjustment and material configuration attempt triggers a round of rapid simplified thermal simulation and aging effect reassessment. Finally, all adjustment schemes that can significantly reduce the maximum temperature (e.g., by more than 5°C) and improve the overall lifespan decay rate to meet the expected lifespan range in the "potential performance parameters" are summarized into a "thermal-lifespan synergistic control scheme set".

[0078] In alternative or modified implementations: the construction of the aforementioned "temperature rise-aging correlation database" can be based on accelerated aging test data of specific cell models at multiple constant temperatures provided by supply chain partners, using interpolation and extrapolation to approximate the aging under variable temperature conditions. Furthermore, the generation of the "thermal-life synergistic control scheme" can be achieved through a pre-defined rule base, rather than relying on an automated optimization engine. For example, the rule base might specify that "when the predicted maximum temperature exceeds T_max, a heat dissipation pad with a thermal conductivity greater than K must be added at the corresponding location" or "when any two cells..." When the predicted temperature difference of a battery cell exceeds ΔT, it is recommended to insert another battery cell of the same model in between to balance the heat flow. Based on the simulation results matching rules, a list of recommended measures is automatically generated. Another variation is that for particularly complex or demanding designs, the system may not directly output the final optimization solution, but instead generate a detailed "Thermal-Life Co-design Analysis Report". The report highlights the hot spot locations, the predicted lifespan shortcomings, and provides a comparison of the advantages and disadvantages of multiple control measures (such as increased cost, weight changes, and size fine-tuning). Engineers make the final selection and confirmation, and then bind them to generate the final delivery solution, which is then given to the customer.

[0079] Figure 3 A schematic diagram of a rapid battery prototyping system based on artificial intelligence is provided as an embodiment of this application, as shown below. Figure 3 As shown, the battery prototyping rapid design system 300 based on artificial intelligence in this embodiment includes: a battery requirement module 301, a specification combination module 302, and a solution collaboration module 303.

[0080] The battery demand module 301 is used to acquire an initial battery demand information set. Based on the initial battery demand information set, it guides customer demand co-shaping and potential parameter inference through interactive questioning to obtain a clear battery demand information set. The specification combination module 302 is used to acquire a battery specification database. Based on the battery specification database and the clear battery demand information set, it analyzes the thermal coupling relationship and aging curve characteristics of different battery specification combinations to obtain a candidate battery information set. The solution collaboration module 303 is used to perform thermal equalization and life decay collaborative optimization based on the candidate battery information set, and generate and output a battery assembly delivery solution information set that includes the battery manufacturing process and the actual battery.

[0081] Optionally, when the battery demand module 301 guides customer demand co-shaping and potential parameter inference through interactive questioning based on the initial battery demand information set to obtain a clear battery demand information set, it is specifically used for: the initial battery demand information set including physical form requirements and application scenario requirements; based on the physical form requirements, analyzing the deterministic boundary conditions of the battery in terms of spatial constraints and interface configuration to obtain a physical constraint information set; based on the application scenario requirements, analyzing the dynamic load spectrum and working environment conditions related to the battery application scenario to obtain a scenario constraint information set; based on the physical constraint information set, combined with the scenario constraint information set, analyzing the performance specification gaps and design freedoms existing under the coupling of physical constraints and scenario constraints to obtain an interactive question information set for guiding demand clarification; based on the interactive question information set, conducting multiple rounds of question-and-answer interaction with the user, integrating user feedback, and inferring potential performance parameters including energy density, power characteristics, and cycle life expectations; integrating the physical constraint information set, the scenario constraint information set, and the potential performance parameters to construct the clear battery demand information set.

[0082] Optionally, the battery requirement module 301, during the construction process of the scenario constraint information set, is specifically used for: analyzing the driving factors that determine the battery's working state in the application scenario based on the application scenario requirements, and obtaining operating condition driving information; based on the operating condition driving information, deducing the load intensity change sequence and duration distribution experienced by the battery within a complete task cycle, and obtaining dynamic load spectrum information characterizing the electrical stress profile; based on the application scenario requirements, analyzing the environmental factors and change patterns that affect the battery structure in the physical space where the application scenario is located, and obtaining operating environment condition information including temperature and humidity spectrum and vibration spectrum; integrating the dynamic load spectrum information and the operating environment condition information to construct the scenario constraint information set used to define the battery design input conditions.

[0083] Optionally, during the construction of the interactive question information set, the battery demand module 301 is specifically used to: based on the physical constraint information set and combined with the scenario constraint information set, analyze the upper limit of the dynamic load spectrum, the compatibility boundary of interface configuration and working environment conditions of physical space constraints, and obtain constraint coupling restriction information; based on the constraint coupling restriction information, analyze the quantitative demand gaps of energy density, power characteristics and cycle life that are not clearly defined in the initial battery demand information set, identify the performance ambiguities that need to be further defined by the customer, and obtain performance specification gap information; based on the performance specification gap information, analyze the questioning direction and logic that can guide the customer to clarify ambiguities and supplement quantitative indicators, and integrate them to form the interactive question information set used to guide the clarification of requirements.

[0084] Optionally, during the construction of the potential performance parameters, the battery demand module 301 is specifically used for: based on the interactive question information set, presenting guiding questions to the user in a logical order from macroscopic scenarios to microscopic parameters and from qualitative descriptions to quantitative definitions, and collecting user feedback on each question to obtain initial question-and-answer records; based on the initial question-and-answer records, analyzing the ambiguity, contradictions in demand, and missing parameters in the user's feedback on different questions, generating a set of follow-up questions to clarify contradictions, eliminate ambiguities, and supplement missing parameters, conducting a new round of interaction, and obtaining refined feedback information that has been clarified and supplemented; based on the refined feedback information, analyzing the user's expression tendencies and priority hints regarding energy density, power characteristics, and cycle life, inferring the range of quantitative parameter values ​​that can simultaneously satisfy the user's expression tendencies and physical scenario constraints, and obtaining the potential performance parameters.

[0085] Optionally, when the specification combination module 302 analyzes the thermal coupling relationship and aging curve characteristics of different battery specification combinations based on the battery specification database and the explicit battery requirement information set to obtain a candidate battery information set, it is specifically used for: the battery specification database including battery application adaptation information and battery replacement compatibility information; based on the battery application adaptation information and battery replacement compatibility information, combined with the explicit battery requirement information set, analyzing the adaptability of each battery specification to physical constraints and scenario constraints, and the feasibility of replacement compatibility between specifications, to obtain a pool of combinable battery specifications; based on the pool of combinable battery specifications, combined with the dynamic load spectrum information and the working environment condition information, analyzing the heat generation, transfer, and mutual thermal influence laws of different battery specification combinations within a complete task cycle, to obtain thermal coupling relationship information of each combination; based on the thermal coupling relationship information, combined with the potential performance parameters, analyzing the performance degradation trend, service life change law, and matching characteristics with the potential performance parameters of each combination under thermal coupling, screening out battery specification combinations with controllable thermal coupling risk and aging rate that meet expectations, to obtain a candidate battery information set.

[0086] Optionally, during the construction process of the composable battery specification pool, the specification combination module 302 is specifically used for: based on the battery application adaptation information, combined with the physical constraint information set and the scenario constraint information set, analyzing the matching characteristics of each battery specification unit with space limitations, interface types, dynamic load spectrum and working environment conditions to obtain an adaptation specification unit set; based on the battery replacement compatibility information, combined with the adaptation specification unit set, analyzing the interchangeability of different specification units in electrical interfaces, communication protocols and structural dimensions, as well as the performance complementarity in energy characteristics and power characteristics when combined, to obtain a specification unit relationship information set with substitution and complementarity potential; based on the specification unit relationship information set, combined with the explicit battery requirement information set, analyzing the overall performance coverage of the potential performance parameter value range after performance superposition and redundant configuration through unit combination, as well as the comprehensive satisfaction of physical constraints and scenario constraints, and selecting specification unit combinations that can constitute the basis of an effective design scheme to obtain the composable battery specification pool.

[0087] Optionally, the specification combination module 302, during the construction of the thermal coupling relationship information, is specifically used for: based on the combinable battery specification pool and combined with the dynamic load spectrum information, analyzing the heat generation rate and heat accumulation characteristics of each specification unit under different load intensities and durations to obtain heat generation characteristic information; based on the heat generation characteristic information and combined with the working environment condition information, analyzing the path and efficiency of heat conduction through material contact surfaces and convection through internal space fluids within the assembly composed of each specification unit, as well as the heat dissipation bottlenecks in heat exchange between the assembly shell and the external environment, to obtain heat transfer path information for each assembly; based on the heat transfer path information, analyzing the pattern of temperature field superposition between adjacent units and the inability to dissipate heat in time due to differences in the spatial arrangement and heat generation sequence of different specification units, resulting in the formation of local hot spots, and the impact on unit performance and safety, to obtain temperature field superposition effect information; integrating the temperature field superposition effect information and the working environment condition information to construct the thermal coupling relationship information used to characterize the thermal behavior and thermal risk of each battery specification combination in the working scenario.

[0088] Optionally, when the scheme coordination module 303 performs thermal equilibrium and life decay co-optimization based on the candidate battery information set to generate and output a battery assembly delivery scheme information set, it is specifically used to: based on the candidate battery information set and combined with the thermal coupling relationship information, analyze the quantitative mapping law between the temperature field superposition effect and performance aging rate under the dynamic load spectrum information driving different specification combinations, and obtain the thermal aging evolution characteristics of each combination; based on the thermal aging evolution characteristics, analyze the measures to adjust the arrangement topology between cells and introduce functional thermal management interfaces to reconstruct the heat transfer path within the combinable battery specification pool, thereby simultaneously optimizing the temperature rise of key parts and the overall aging rate, and obtain a thermal-life co-regulation scheme set; based on the thermal-life co-regulation scheme set and combined with the potential performance parameters, evaluate and screen out the co-regulation schemes that can simultaneously meet the life expectation and control the thermal coupling risk within the allowable range of the temperature field superposition effect, bind them with the adapted battery specification combinations, perform supply chain co-arrangement, and generate and output the battery assembly delivery scheme information set containing the battery manufacturing process and the actual battery.

[0089] The system in this embodiment can be used to execute the methods of any of the above embodiments, and its implementation principle and technical effect are similar, so they will not be described again here.

Claims

1. A rapid battery prototyping method based on artificial intelligence, characterized in that, include: Obtain an initial battery demand information set; based on the initial battery demand information set, guide customer demand co-shaping and potential parameter inference through interactive questioning to obtain a clear battery demand information set. Obtain a battery specification database. Based on the battery specification database and the specified battery requirement information set, analyze the thermal coupling relationship and aging curve characteristics of different battery specification combinations to obtain a candidate battery information set. Based on the candidate battery information set, thermal equalization and lifespan degradation are jointly optimized to generate and output a battery assembly delivery plan information set that includes the battery manufacturing process and the actual battery.

2. The method according to claim 1, characterized in that, Based on the initial battery demand information set, the process involves guiding customer needs through interactive questioning, shaping demand co-engineering, and inferring potential parameters to obtain a clear battery demand information set, including: The initial battery requirement information set includes physical shape requirements and application scenario requirements; Based on the physical shape requirements, the deterministic boundary conditions of the battery in terms of spatial constraints and interface configuration are analyzed to obtain a set of physical constraint information. Based on the application scenario requirements, the dynamic load spectrum and working environment conditions related to the battery application scenario are analyzed to obtain the scenario constraint information set. Based on the physical constraint information set and the scenario constraint information set, the performance specification gap and design freedom under the coupling of physical constraints and scenario constraints are analyzed to obtain an interactive question information set to guide the clarification of requirements. Based on the interactive question information set, multiple rounds of question-and-answer interaction are conducted with the user, and user feedback is integrated to infer potential performance parameters including energy density, power characteristics and cycle life expectations. The physical constraint information set, the scenario constraint information set, and the potential performance parameters are integrated to construct the explicit battery requirement information set.

3. The method according to claim 2, characterized in that, The process of constructing the scenario constraint information set includes: Based on the application scenario requirements, the driving factors that determine the battery's operating state in the application scenario are analyzed to obtain operating condition driving information. Based on the aforementioned operating condition driving information, the load intensity change sequence and duration distribution experienced by the battery during the complete task cycle are deduced to obtain dynamic load spectrum information characterizing the electrical stress profile. Based on the application scenario requirements, the environmental factors and their variation patterns that affect the battery structure in the physical space of the application scenario are analyzed, and working environment condition information including temperature and humidity spectrum and vibration spectrum is obtained. By integrating the dynamic load spectrum information and the working environment condition information, a set of scenario constraint information is constructed to define the input conditions for battery design.

4. The method according to claim 3, characterized in that, The process of constructing the interactive question information set includes: Based on the physical constraint information set and the scenario constraint information set, the upper limit of the physical space constraints on the dynamic load spectrum, the compatibility boundary of interface configuration and working environment conditions are analyzed to obtain constraint coupling limit information. Based on the constraint coupling limit information, the quantitative demand gaps of energy density, power characteristics and cycle life that are not clearly defined in the initial battery demand information set are analyzed, and performance ambiguities that need to be further defined by customers are identified to obtain performance specification gap information. Based on the performance specification gap information, the analysis guides customers to clarify ambiguous items and supplement quantitative indicators through questioning directions and logic, and integrates them to form the interactive question information set used to guide the clarification of needs.

5. The method according to claim 4, characterized in that, The process of constructing the potential performance parameters includes: Based on the interactive question information set, guiding questions are presented to the user in a logical order from macro-level scenarios to micro-level parameters and from qualitative descriptions to quantitative definitions. The user's feedback on each question is collected to obtain the initial question and answer record. Based on the initial question and answer records, the system analyzes the ambiguity, contradictions in needs, and missing parameters in the user's feedback on different questions, generates a set of follow-up questions to clarify contradictions, eliminate ambiguities, and supplement missing information, conducts a new round of interaction, and obtains detailed feedback information that has been clarified and supplemented. Based on the refined feedback information, the user's expression tendencies and priority hints regarding energy density, power characteristics, and cycle life are analyzed to infer the range of quantification parameter values ​​that can simultaneously satisfy the user's expression tendencies and physical scenario constraints, thus obtaining the potential performance parameters.

6. The method according to claim 5, characterized in that, Based on the battery specification database and the defined battery requirement information set, the thermal coupling relationship and aging curve characteristics of different battery specification combinations are analyzed to obtain a candidate battery information set, including: The battery specification database includes battery application adaptation information and battery replacement compatibility information. Based on the battery application adaptation information and battery replacement compatibility information, combined with the explicit battery demand information set, the compatibility of each battery specification with physical constraints and scenario constraints, as well as the feasibility of replacement compatibility between specifications, are analyzed to obtain a pool of combinable battery specifications. Based on the aforementioned combinable battery specification pool, combined with the dynamic load spectrum information and the working environment condition information, the heat generation, transfer and mutual thermal influence of different battery specification combinations during the complete task cycle are analyzed to obtain the thermal coupling relationship information of each combination. Based on the thermal coupling relationship information and the potential performance parameters, the performance degradation trend, service life change law and matching characteristics with the potential performance parameters of each combination under thermal coupling are analyzed. Battery specification combinations with controllable thermal coupling risk and aging rate that meet expectations are selected to obtain a candidate battery information set.

7. The method according to claim 6, characterized in that, The construction process of the composable battery specification cell includes: Based on the battery application adaptation information, combined with the physical constraint information set and the scenario constraint information set, the matching characteristics of each battery specification unit with space limitations, interface type, dynamic load spectrum and working environment conditions are analyzed to obtain the adaptation specification unit set. Based on the battery replacement compatibility information, combined with the set of adaptable specification units, the interchangeability of different specification units in terms of electrical interface, communication protocol and structural size is analyzed, as well as the performance complementarity in energy characteristics and power characteristics when combined, to obtain a set of specification unit relationship information with replacement and complementarity potential. Based on the specification unit relationship information set and the explicit battery requirement information set, the overall performance is analyzed to achieve performance superposition and redundant configuration through unit combination. The analysis also considers the completeness of the coverage of potential performance parameter value range and the comprehensive satisfaction of physical and scenario constraints. Specification unit combinations that can form the basis of effective design schemes are selected to obtain the composable battery specification pool.

8. The method according to claim 7, characterized in that, The process of constructing the thermal coupling relationship information includes: Based on the aforementioned combinable battery specification cells and combined with the dynamic load spectrum information, the heat generation rate and heat accumulation characteristics of each specification cell under different load intensities and durations are analyzed to obtain heat generation characteristic information. Based on the heat generation characteristics information and the working environment conditions information, the heat transfer path and efficiency of heat in the assembly composed of each specification unit are analyzed through the material contact surface and through the internal space fluid, as well as the heat dissipation bottleneck of heat exchange between the assembly shell and the external environment, so as to obtain the heat transfer path information of each assembly. Based on the heat transfer path information, the study analyzes the pattern of local hot spots formed by the superposition of temperature fields between adjacent units and the inability of heat to dissipate in time due to the spatial arrangement and heat generation time difference of different specification units, as well as the impact on unit performance and safety, and obtains information on temperature field superposition effect. By integrating the temperature field superposition effect information and the working environment condition information, thermal coupling relationship information is constructed to characterize the thermal behavior and thermal risk of each battery specification combination under working scenarios.

9. The method according to claim 8, characterized in that, The step of performing coordinated optimization of thermal equalization and lifespan degradation based on the candidate battery information set, generating and outputting a battery assembly delivery plan information set containing the battery manufacturing process and the physical battery, includes: Based on the candidate battery information set and the thermal coupling relationship information, the quantitative mapping law between the temperature field superposition effect and the performance aging rate under the dynamic load spectrum information is analyzed for different specification combinations, and the thermal aging evolution characteristics of each combination are obtained. Based on the aforementioned thermal aging evolution characteristics, this paper analyzes measures to adjust the cell arrangement topology and introduce functional thermal management interfaces to reconstruct the heat transfer path within the composable battery specification cell, thereby simultaneously optimizing the temperature rise of key components and the overall aging rate, and obtains a set of thermal-life synergistic regulation schemes. Based on the aforementioned thermal-life synergistic control scheme set, and combined with the aforementioned potential performance parameters, a synergistic scheme that can simultaneously meet life expectations and control thermal coupling risks within the allowable range of the superposition effect of the temperature field is evaluated and screened. This scheme is then bound to the appropriate battery specification combination, and supply chain collaborative orchestration is performed to generate and output the battery assembly delivery scheme information set.

10. A rapid prototyping system for batteries based on artificial intelligence, characterized in that, The method applied to any one of claims 1-9 includes: The battery demand module is used to obtain an initial battery demand information set. Based on the initial battery demand information set, it guides customer demand co-shaping and infers potential parameters through interactive questioning to obtain a clear battery demand information set. The specification combination module is used to obtain a battery specification database, and based on the battery specification database and the explicit battery requirement information set, analyze the thermal coupling relationship and aging curve characteristics of different battery specification combinations to obtain a candidate battery information set. The solution collaboration module is used to perform thermal equalization and lifespan degradation collaborative optimization based on the candidate battery information set, and generate and output a battery assembly delivery solution information set that includes the battery manufacturing process and the actual battery.

Images