Energy storage equipment structure design method and system based on digital twinning technology

Abstract

The invention discloses an energy storage equipment structure design method and system based on a digital twinborn technology. The method comprises the following steps: constructing a three-dimensional digital twinborn model of energy storage equipment; the heat dissipation performance of the energy storage equipment under different working conditions is simulated through a digital twin model, the temperature change, gas diffusion and pressure change of the energy storage equipment during thermal runaway are simulated, and the thermal runaway propagation state and the influence range thereof are evaluated; performing iterative optimization on the structural design of the energy storage equipment, simulating the advantages and disadvantages of result evaluation design, and automatically adjusting design parameters; the optimized design parameters are input into the digital twin model again for heat dissipation performance and thermal runaway simulation, whether the design meets the structural design requirement of the energy storage equipment or not is verified, and when the simulation result meets the structural design requirement of the energy storage equipment, a final design scheme is output. According to the method, the three-dimensional digital twinborn model is constructed, the heat dissipation performance and the thermal runaway condition are simulated, the AI algorithm is used for optimizing the structural design, and the defects of the traditional technology can be effectively overcome.

Description

Technical Field

[0001] This invention relates to the field of energy storage equipment design technology, and in particular to a structural design method and system for energy storage equipment based on digital twin technology. Background Technology

[0002] With the accelerating global energy transition, energy storage devices are playing an increasingly crucial role in the modern energy system. They are not only a core pillar for the effective integration of renewable energy sources (such as solar and wind power) into the power grid, but also play an irreplaceable role in scenarios such as power system frequency regulation, peak shaving and valley filling, and emergency backup. Energy storage devices can significantly improve energy efficiency, enhance grid stability, and provide a solid guarantee for the sustainable development of energy supply. According to the International Energy Agency (IEA), global installed energy storage capacity is expected to exceed 500 GW by 2030, highlighting the urgency and importance of energy storage technology in addressing the challenges of the energy transition.

[0003] Currently, the structural design and management of energy storage devices mainly rely on the following traditional technologies: Experience-based passive management: triggering alarms by setting fixed thresholds for parameters such as voltage and temperature. However, this method cannot predict the gradual aging of batteries, and the threshold setting depends on the engineer's experience, making it difficult to adapt to complex and changing dynamic operating conditions. Offline laboratory testing modeling: establishing empirical lifespan models (such as the Arrhenius equation and power-law model) through accelerated aging experiments. However, laboratory conditions differ significantly from actual operating environments, resulting in model extrapolation errors exceeding 30%. Simple balancing strategies: employing round-robin charging and discharging or static priority allocation. This strategy does not consider the differences in health status between batteries, leading to some batteries aging faster due to overload. These traditional technologies have revealed many shortcomings in practical applications. First, the lack of data dimensions is prominent; traditional voltage / temperature monitoring fails to capture the branch-level energy characteristics of battery clusters (such as ripple coefficient and harmonic distortion rate), resulting in a high rate of missed detection of early aging characteristics (up to 40%). Second, the analysis is time-consuming; weekly / monthly periodic testing cannot perceive changes in battery status in real time, making it difficult to adjust management strategies promptly. Furthermore, insufficient intelligent decision-making and static load allocation strategies exacerbate uneven losses among battery packs, shortening the overall system lifespan by approximately 30%. These issues not only affect the performance and lifespan of energy storage devices but also create potential safety hazards. Summary of the Invention

[0004] The main objective of this invention is to provide a structural design method for energy storage devices based on digital twin technology. By constructing a three-dimensional digital twin model, simulating heat dissipation performance and thermal runaway, optimizing the structural design using AI algorithms, and repeatedly verifying the design to ensure that it meets the requirements, this method can effectively solve the shortcomings of traditional technologies and promote the design and management technology of energy storage devices to a new level.

[0005] Another objective of this invention is to propose a structural design system for energy storage devices based on digital twin technology.

[0006] To achieve the above objectives, a first aspect of the present invention proposes a structural design method for energy storage devices based on digital twin technology, comprising: Utilizing computer-aided design technology to construct a three-dimensional digital twin model of energy storage equipment; The heat dissipation performance of energy storage devices under different operating conditions is simulated using digital twin models, including heat conduction, convection and radiation processes, and the temperature distribution and changes of battery modules are calculated. The temperature changes, gas diffusion, and pressure changes of an energy storage device during thermal runaway are simulated using a digital twin model to assess the propagation state of thermal runaway and its impact range. AI algorithms are used to iteratively optimize the structural design of energy storage devices, and the merits of the design are evaluated through simulation results, and the design parameters are automatically adjusted. The optimized design parameters are re-input into the digital twin model, and heat dissipation performance and thermal runaway simulations are performed again to verify whether the design meets the structural design requirements of the energy storage device. When the simulation results meet the structural design requirements of the energy storage device, the final design scheme, including the three-dimensional model, design parameters and performance evaluation report, is output.

[0007] In one embodiment of the present invention, the construction of a three-dimensional digital twin model of the energy storage device using computer-aided design technology includes: Standardized modeling is performed in advance based on detailed geometric information and material property information of battery modules, heat dissipation systems, shell structures, and internal connectors, using a classification and statistical approach. The model encapsulates multiple modular units of standardized modeling and maps and stores them with classification and statistical results; Using computer-aided design technology, various module unit packaging models are called according to design requirements, and modular arrangement is carried out according to design standards or design feedback to construct a three-dimensional digital twin model of the energy storage device.

[0008] In one embodiment of the present invention, simulating the heat dissipation performance of an energy storage device under different operating conditions using a digital twin model includes: Based on the designed three-dimensional digital twin model, and using the detailed geometric and material property information of each module unit, the heat dissipation performance of each module unit under rated operating conditions is simulated. The thermal simulation includes: Heat source simulation: Define the heat source distribution and power of the battery module in the digital twin model. Represented as:

[0009] in, For the designed battery discharge current, Battery voltage, This refers to the battery's internal resistance. For battery efficiency; Thermal conduction calculation: Using Fourier's law, the thermal conduction process and thermal conduction rate inside the battery module are calculated. Represented as:

[0010] in, The thermal conductivity of the material For temperature gradient; Convection heat transfer calculation: The convective heat transfer process between the battery module and the heat dissipation system is calculated using Newton's law of cooling, including the convective heat transfer rate. Represented as:

[0011] in, The convective heat transfer coefficient is... For heat exchange area, The surface temperature of the battery. The ambient temperature; Radiative heat transfer calculation: The radiative heat transfer process of the battery module is calculated using the Stefan-Boltzmann law, and the radiative heat transfer rate is calculated. Represented as:

[0012] in, Indicates surface emissivity, is the Stefan-Boltzmann constant.

[0013] In one embodiment of the present invention, the thermal runaway simulation process includes: Define the triggering conditions for thermal runaway, including battery temperature exceeding a critical value or a short circuit occurring inside the battery; The rate of temperature change of the battery module is calculated using a thermal runaway propagation model. The expression for the thermal runaway propagation model is as follows:

[0014] in, Indicates the rate of temperature change. Indicates temperature. This refers to the heat generated during thermal runaway. For the heat lost, For battery quality, Specific heat capacity of the material; Using Fick's law to simulate the gas diffusion process during thermal runaway, the gas diffusion flux is... Represented as:

[0015] in, The gas diffusion coefficient is... For the gas concentration gradient; Calculate the pressure change during thermal runaway using the ideal gas law. Represented as:

[0016] in, For the amount of gaseous substance, The gas constant is This represents the volume of the gas.

[0017] In one embodiment of the present invention, iterative optimization of the structural design of an energy storage device using an AI algorithm includes: The variable parameters for the structural design of the energy storage device are defined based on the detailed geometric and material properties of the battery module, heat dissipation system, shell structure, and internal connectors. These parameters include the layout, model, and material selection of the battery module, heat dissipation system, and shell structure. Define the performance metrics for the optimization target, including maximum temperature, thermal runaway propagation probability, and heat dissipation efficiency; Choose either a genetic algorithm or a particle swarm optimization algorithm to optimize the design parameters, and simultaneously construct a loss function to evaluate the quality of the design. Its expression is:

[0018] in, Represents the loss function. , as well as These are the dynamically adjusted weighting coefficients. The maximum temperature, For the target temperature, This represents the probability of thermal runaway propagation. For heat dissipation efficiency; The design parameters are adjusted iteratively through the algorithm to minimize the loss function until the design requirements are met.

[0019] In one embodiment of the present invention, design verification and iteration include: Define the conditions for design verification, including the maximum allowable temperature, the thermal runaway propagation probability threshold, and the heat dissipation efficiency target; The optimized design parameters were re-input into the digital twin model to simulate heat dissipation performance and thermal runaway, verifying whether the design met the verification conditions. If the verification results do not meet the design requirements, the design parameters are adjusted according to the optimization suggestions of the AI ​​algorithm, and the simulation verification is carried out again. When the verification results meet the design requirements, the optimization process is considered to have converged, and the final design scheme is output.

[0020] In one embodiment of the present invention, the design output includes the following: Output a three-dimensional digital twin model of the energy storage device, including detailed geometric information of the battery module, heat dissipation system, shell structure and internal connectors; Output optimized design parameters, including battery module layout, heat dissipation system dimensions, and housing material selection; Output a performance evaluation report, including detailed data on heat dissipation performance, thermal runaway propagation probability, and heat dissipation efficiency; Output a record of the optimization process, including design parameter adjustments and performance evaluation results for each iteration.

[0021] To achieve the above objectives, a second aspect of the present invention proposes a structural design system for energy storage devices based on digital twin technology, comprising: The model building module is used to construct a three-dimensional digital twin model of energy storage devices using computer-aided design technology; The performance simulation module is used to simulate the heat dissipation performance of energy storage devices under different operating conditions through a digital twin model, including heat conduction, convection and radiation processes, and to calculate the temperature distribution and changes of the battery module. The simulation evaluation module is used to simulate the temperature changes, gas diffusion, and pressure changes of energy storage devices when thermal runaway occurs through a digital twin model, and to evaluate the thermal runaway propagation state and its impact range. The iterative optimization module is used to iteratively optimize the structural design of energy storage devices using AI algorithms, evaluate the merits of the design through simulation results, and automatically adjust the design parameters. The simulation verification module is used to re-input the optimized design parameters into the digital twin model and perform heat dissipation performance and thermal runaway simulation again to verify whether the design meets the structural design requirements of the energy storage device. When the simulation results meet the structural design requirements of the energy storage device, the final design scheme including the three-dimensional model, design parameters and performance evaluation report is output.

[0022] The beneficial effects of this invention are as follows: 1. This technical solution enables intelligent and efficient structural design of energy storage equipment, reduces the workload of designers, and improves design quality and equipment reliability.

[0023] 2. Modular and standardized modeling methods not only reduce the workload of designers, but also improve design quality and equipment reliability.

[0024] 3. By combining the simulation results of various thermodynamic equations, comprehensive guidance is provided for optimizing the heat dissipation design of energy storage devices, thereby achieving temperature stability of the devices under high load operation, extending battery life, and improving overall performance and reliability. Attached Figure Description

[0025] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 A flowchart illustrating a structural design method for an energy storage device based on digital twin technology, provided as an embodiment of the present invention; Figure 2 A detailed flowchart of a structural design method for energy storage devices based on digital twin technology provided in this embodiment of the invention; Figure 3 A flowchart illustrating the steps involved in generating a three-dimensional digital twin model, as provided in this embodiment of the invention. Figure 4 This is a schematic diagram of a structural design system for an energy storage device based on digital twin technology, provided as an embodiment of the present invention. Detailed Implementation

[0026] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] The following description, with reference to the accompanying drawings, illustrates a structural design method and system for energy storage devices based on digital twin technology, according to embodiments of the present invention.

[0029] This embodiment provides a structural design method for energy storage devices based on digital twin technology. For example... Figure 1 and Figure 2 As shown, the method includes the following steps: S1, using computer-aided design technology to construct a three-dimensional digital twin model of the energy storage device; S2 simulates the heat dissipation performance of energy storage devices under different operating conditions through a digital twin model, including heat conduction, convection and radiation processes, and calculates the temperature distribution and changes of the battery module. S3 uses a digital twin model to simulate temperature changes, gas diffusion, and pressure changes in energy storage devices during thermal runaway, and assesses the propagation state of thermal runaway and its impact range. S4 utilizes AI algorithms to iteratively optimize the structural design of energy storage devices, evaluates the merits of the design through simulation results, and automatically adjusts the design parameters. S5 re-inputs the optimized design parameters into the digital twin model and performs heat dissipation performance and thermal runaway simulations again to verify whether the design meets the structural design requirements of the energy storage device. When the simulation results meet the structural design requirements of the energy storage device, the final design scheme, including the three-dimensional model, design parameters, and performance evaluation report, is output.

[0030] Specifically, the working principle and beneficial effects of the above technical solution are as follows: By constructing a three-dimensional digital twin model (using computer-aided design technology to accurately reproduce the structural details of the energy storage device, including the geometry and material properties of components such as battery modules, heat dissipation systems, and casings), a digital mapping of the energy storage device structure is achieved, providing a high-precision virtual platform for subsequent simulation and optimization. By simulating heat dissipation performance (using thermodynamic models to calculate heat conduction, convection, and radiation processes; for example, under the condition of an ambient temperature of 30℃ and a battery charging and discharging power of 10kW, the simulation shows that the uniformity of the surface temperature distribution of the battery module is improved by 20%, and the temperature of the hot spot area is reduced by 15℃), potential heat dissipation bottlenecks can be identified in advance, and the layout of the heat dissipation system can be optimized, such as increasing the number of heat dissipation fins or adjusting the direction of the heat dissipation channels, thereby effectively improving the temperature stability of the energy storage device under high load operation. By simulating thermal runaway scenarios (setting extreme conditions such as internal battery short circuits and sudden temperature rises in a digital twin model, calculating the rate of temperature change, gas diffusion paths, and pressure accumulation trends; for example, simulations show that when the battery temperature exceeds 130°C, the gas diffusion rate increases threefold, and the pressure rises to a dangerous threshold within 5 seconds), the propagation path and impact range of thermal runaway are assessed. This provides a basis for designing safety protection measures, such as adding fireproof partitions or optimizing the exhaust system, thereby enhancing the safety of energy storage devices under extreme conditions. AI algorithms are used to optimize the structural design (with heat dissipation efficiency and thermal runaway risk as optimization targets, iterative adjustments to parameters such as battery layout and casing thickness are made through a genetic algorithm; after 50 generations of optimization, heat dissipation efficiency is improved by 18%, and the probability of thermal runaway propagation is reduced by 40%), automatically selecting the optimal design scheme and reducing the cost and time of manual trial and error. By re-simulating and validating the optimized design (re-inputting the adjusted parameters into the model and verifying under the same operating conditions; for example, in the optimized model, the maximum temperature of the battery module drops from 85℃ to 75℃, and the impact range of thermal runaway is reduced by 30%), the design is ensured to meet the structural requirements of the energy storage device. The final output is a complete solution including a detailed 3D model, optimized design parameters, and performance evaluation data. This achieves intelligent and efficient structural design of energy storage devices, reduces the workload of designers, and improves design quality and equipment reliability. This technical solution enables intelligent and efficient structural design of energy storage devices, reduces the workload of designers, and improves design quality and equipment reliability.

[0031] In one embodiment of the present invention, such as Figure 3 As shown, the construction of a three-dimensional digital twin model of an energy storage device using computer-aided design technology includes: Standardized modeling is performed in advance based on detailed geometric information and material property information of battery modules, heat dissipation systems, shell structures, and internal connectors, using a classification and statistical approach. The model encapsulates multiple modular units of standardized modeling and maps and stores them with classification and statistical results; Using computer-aided design technology, various module unit packaging models are called according to design requirements, and modular arrangement is carried out according to design standards or design feedback to construct a three-dimensional digital twin model of the energy storage device.

[0032] The working principle and beneficial effects of the above technical solution are as follows: By pre-classifying and statistically analyzing the detailed geometric and material properties of battery modules, heat dissipation systems, shell structures, and internal connectors, and conducting standardized modeling, the modeling accuracy and consistency of each module unit can be ensured, laying the foundation for subsequent model encapsulation and retrieval. For example, during the modeling process, the standard dimensions of the battery module can be set to 200mm × 150mm × 100mm, and the shell sample, shell thermal conductivity, interface positions, shell thickness to be 5mm, and the thermal conductivity of the heat dissipation system to be 200W / (m·K) can be defined, thereby achieving standardized design for each module. By encapsulating multiple standardized modeled module units and mapping and storing them with the classification and statistical results, an efficient and orderly model library can be established. For example, 100 different specifications of battery module models can be encapsulated as independent module units, and their geometric parameters, material properties, and performance indicators can be stored through database mapping, thereby achieving rapid retrieval and retrieval. This mapping storage method not only improves the efficiency of model management but also provides flexibility for subsequent modular arrangement. By utilizing computer-aided design (CAD) technology, various modular unit packaging models can be invoked according to design requirements, and modular arrangement can be performed based on design standards or design feedback, enabling the rapid construction of a 3D digital twin model of energy storage devices. For example, when designing an energy storage device, packaging models of 20 battery modules can be invoked based on power requirements, combined with packaging models of the heat dissipation system and shell structure, and laid out according to modular arrangement rules. This method allows for the rapid completion of modeling complex devices, while flexibly adjusting the layout and parameters of modules according to actual needs. This technical solution significantly improves the efficiency of constructing 3D digital twin models of energy storage devices and reduces the workload of repetitive modeling. Standardized modeling and packaging storage ensure high accuracy and consistency of the model, while modular arrangement provides flexible design adjustment capabilities, thereby achieving efficient and intelligent structural design of energy storage devices. This modular and standardized modeling method not only reduces the workload of designers but also improves design quality and equipment reliability.

[0033] In one specific embodiment, the heat dissipation performance simulation includes the following steps: Based on the designed three-dimensional digital twin model, and using the detailed geometric and material property information of each module unit, the heat dissipation performance of each module unit under rated operating conditions is simulated. The thermal simulation includes: Heat source simulation: Define the heat source distribution and power of the battery module in the digital twin model. Represented as:

[0034] in, For the designed battery discharge current, Battery voltage, This refers to the battery's internal resistance. For battery efficiency; Thermal conduction calculation: Using Fourier's law, the thermal conduction process and thermal conduction rate inside the battery module are calculated. Represented as:

[0035] in, The thermal conductivity of the material For temperature gradient; Convection heat transfer calculation: The convective heat transfer process between the battery module and the heat dissipation system is calculated using Newton's law of cooling, including the convective heat transfer rate. Represented as:

[0036] in, The convective heat transfer coefficient is... For heat exchange area, The surface temperature of the battery. The ambient temperature; Radiative heat transfer calculation: The radiative heat transfer process of the battery module is calculated using the Stefan-Boltzmann law, and the radiative heat transfer rate is calculated. Represented as:

[0037] in, Indicates surface emissivity, is the Stefan-Boltzmann constant.

[0038] The working principle and beneficial effects of the above technical solution are as follows: By simulating the heat source (defining the heat source distribution of the battery module in the digital twin model), the heat generation of the battery under rated operating conditions can be accurately quantified, providing accurate heat source data for subsequent heat dissipation analysis. For example, under a typical operating condition, the battery discharge current is 100A, the voltage is 3.6V, the internal resistance is 0.05Ω, and the efficiency is 90%. Substituting these values ​​into the formula, the heat source power is calculated to be P=304.44W, thus providing accurate heat source input for heat dissipation design. Through heat conduction calculations using Fourier's law, the heat conduction process inside the battery module can be simulated, calculating the temperature distribution and its changes within the module. For example, in the battery module, if the thermal conductivity of the material is 200 W / (m·K) and the temperature gradient is 0.05 K / m, then the heat conduction rate is... The negative sign indicates that the heat transfer direction is opposite to the temperature gradient direction, thus enabling accurate simulation of the heat transfer path and efficiency inside the battery module. Convective heat transfer calculations can evaluate the convective heat transfer efficiency between the battery module and the cooling system. For example, when the convective heat transfer coefficient is 10 W / (m²), the efficiency can be assessed. 2 K), with a heat exchange area of ​​0.1 m². 2 When the battery surface temperature is 40℃ and the ambient temperature is 25℃, the convective heat transfer rate is 1.5 W, providing a basis for optimizing the layout and parameters of the heat dissipation system. Radiation heat transfer can be calculated using the Stefan-Boltzmann law (for example, when the surface emissivity is 0.8, the Stefan-Boltzmann constant is 5.67 × 10⁻⁶). -8 W / (m 2 ·K 4 The heat exchange area is 0.1 m². 2 When the battery surface temperature is 313 K (40℃) and the ambient temperature is 298 K (25℃), the radiative heat transfer rate is 5.897 W, providing an important reference for evaluating the heat dissipation capacity of the battery module under high-temperature environments. This technical solution can comprehensively and accurately simulate the heat dissipation performance of energy storage devices under different operating conditions, providing a scientific basis for structural design. Heat source simulation ensures the accuracy of heat source data, heat conduction calculations reveal the heat transfer patterns within the module, convective heat transfer calculations evaluate the efficiency of the heat dissipation system, and radiative heat transfer calculations supplement the heat dissipation analysis under high-temperature environments. These simulation results work together to provide comprehensive guidance for optimizing the heat dissipation design of energy storage devices, thereby achieving temperature stability during high-load operation, extending battery life, and improving overall performance and reliability.

[0039] In one embodiment of the present invention, the thermal runaway simulation process includes the following steps: Define the triggering conditions for thermal runaway, including battery temperature exceeding a critical value or a short circuit occurring inside the battery; The rate of temperature change of the battery module is calculated using a thermal runaway propagation model. The expression for the thermal runaway propagation model is as follows:

[0040] in, Indicates the rate of temperature change. Indicates temperature. This refers to the heat generated during thermal runaway. For the heat lost, For battery quality, Specific heat capacity of the material; Using Fick's law to simulate the gas diffusion process during thermal runaway, the gas diffusion flux is... Represented as:

[0041] in, The gas diffusion coefficient is... For the gas concentration gradient; Calculate the pressure change during thermal runaway using the ideal gas law. Represented as:

[0042] in, For the amount of gaseous substance, The gas constant is This represents the volume of the gas.

[0043] The working principle and beneficial effects of the above technical solution are as follows: By defining the triggering conditions for thermal runaway (including battery temperature exceeding a critical value, such as 150℃, or a short circuit occurring inside the battery), potential dangerous situations can be identified in a timely manner, providing a clear starting point for subsequent simulations. For example, in the experiment, when the battery temperature reaches 150℃, the thermal runaway simulation is triggered, thereby starting to monitor temperature changes and gas diffusion. The thermal runaway propagation model is used to calculate the temperature change rate of the battery module, and the temperature change trend is obtained through parameter calculation. For example, when the battery module generates 10,000 joules of heat and dissipates 2,000 joules of heat during thermal runaway, the battery mass is 1 kg, and the material specific heat capacity is 800 joules per kilogram of Kelvin, the temperature change rate is (10,000-2,000) / (1×800) = 10 Kelvin per second, which indicates that the battery temperature rises by 10℃ per second, thus enabling the prediction of the propagation speed and impact range of thermal runaway. Fick's law is used to simulate the gas diffusion process during thermal runaway, and the gas diffusion flux is calculated using the gas diffusion coefficient and concentration gradient. For example, during battery thermal runaway, the gas diffusion coefficient is 0.1 m² / s, the concentration gradient is 10 mol / m³ / m, and the gas diffusion flux is -0.1 × 10 = -1 mol / m² / s. The negative sign indicates that the gas diffusion direction is opposite to the concentration gradient direction, thus enabling the prediction of gas diffusion paths and rates, providing a basis for designing effective gas emission systems. The ideal gas law is used to calculate the pressure change during thermal runaway, and the pressure is calculated using the amount of gas, gas constant, and temperature. For example, in a thermal runaway process, the amount of gaseous substance is 0.1 moles, the gas constant is 8.314 joules per mole per Kelvin, the temperature is 500 Kelvin, the gas volume is 0.01 cubic meters, and the pressure is (0.1 × 8.314 × 500) / 0.01 = 4157 Pascals. This indicates that under thermal runaway conditions, the internal pressure of the battery will increase significantly, thus enabling the assessment of the impact of pressure on the device structure and providing a reference for designing pressure release mechanisms. This technical solution can comprehensively simulate temperature changes, gas diffusion, and pressure changes during thermal runaway, providing a scientific basis for the safe design of energy storage devices. Defining the thermal runaway triggering conditions ensures the timeliness and accuracy of the simulation; the thermal runaway propagation model reveals the temperature change patterns; the gas diffusion simulation assesses the gas diffusion path and rate; and the pressure change calculation supplements the analysis of the impact of pressure on the device structure. These simulation results work together to provide comprehensive guidance for optimizing the safe design of energy storage devices, thereby effectively preventing thermal runaway accidents and ensuring the safety of equipment and personnel.

[0044] In one embodiment of the present invention, the process of iteratively optimizing the structural design of an energy storage device using an AI algorithm includes: The variable parameters for the structural design of the energy storage device are defined based on the detailed geometric and material properties of the battery module, heat dissipation system, shell structure, and internal connectors. These parameters include the layout, model, and material selection of the battery module, heat dissipation system, and shell structure. Define the performance metrics for the optimization target, including maximum temperature, thermal runaway propagation probability, and heat dissipation efficiency; Choose algorithms such as genetic algorithms or particle swarm optimization to optimize the design parameters, and construct a loss function to evaluate the quality of the design. Its expression is:

[0045] in, Represents the loss function. , as well as These are the dynamically adjusted weighting coefficients. The maximum temperature, For the target temperature, This represents the probability of thermal runaway propagation. For heat dissipation efficiency; The design parameters are adjusted iteratively through the algorithm to minimize the loss function until the design requirements are met.

[0046] In one embodiment of the present invention, design verification and iteration includes the following steps: Define the conditions for design verification, including the maximum allowable temperature, the thermal runaway propagation probability threshold, and the heat dissipation efficiency target; The optimized design parameters were re-input into the digital twin model to simulate heat dissipation performance and thermal runaway, verifying whether the design met the verification conditions. If the verification results do not meet the design requirements, the design parameters are adjusted according to the optimization suggestions of the AI ​​algorithm, and the simulation verification is carried out again. When the verification results meet the design requirements, the optimization process is considered to have converged, and the final design scheme is output.

[0047] The working principle and beneficial effects of the above technical solution are as follows: By defining variable parameters for the structural design of energy storage devices (covering the layout, model, and material selection of battery modules, heat dissipation systems, and shell structures), a basic framework for AI algorithm optimization is provided. For example, optional parameters for battery module layout include the number of parallel connections and the number of series layers; variable parameters for the heat dissipation system include the thickness of the heat sink and the width of the heat dissipation channels; and shell material selection parameters include materials with different thermal conductivity, such as aluminum alloy and magnesium alloy. This diversity of parameters provides ample room for adjustment in subsequent optimization. By setting performance indicators for the optimization targets (including maximum temperature, thermal runaway propagation probability, and heat dissipation efficiency), the optimization direction of the AI ​​algorithm is clarified. For example, the maximum temperature target is set to not exceed 60℃, the thermal runaway propagation probability target is set to be less than 5%, and the heat dissipation efficiency target is set to be greater than 70%. These specific indicators provide clear measurement standards for algorithm optimization. Genetic algorithms or particle swarm optimization algorithms are selected to optimize the design parameters, and a loss function is constructed to evaluate the design's quality. The loss function dynamically adjusts the weight coefficients, comprehensively considering the impact of maximum temperature, thermal runaway propagation probability, and heat dissipation efficiency. For example, in a certain optimization iteration, if the maximum temperature is 55℃ (target 60℃), the thermal runaway propagation probability is 3% (target 5%), and the heat dissipation efficiency is 65% (target 70%), then the loss function value might be 0.25 (calculated based on the weights and deviations of each parameter). Through iterative algorithm adjustments, the parameters are gradually reduced until the design requirements are met. During design verification and iteration, clear verification conditions are defined, providing a basis for judging whether the design is qualified. The optimized parameters are re-input into the digital twin model for simulation verification. If the results are unsatisfactory, such as a maximum temperature reaching 62℃ in a simulation, exceeding the allowable range, the parameters are readjusted and verified again based on AI algorithm suggestions, such as increasing the number of heat sinks or replacing materials with higher thermal conductivity. When the simulation results show that the maximum temperature has decreased to 58℃, the thermal runaway propagation probability has decreased to 4%, and the heat dissipation efficiency has increased to 72%, the verification results meet the requirements, the optimization process converges, and the final design scheme is output. Through this technical solution, the AI ​​algorithm can systematically optimize the structural design of energy storage devices. Defining variable parameters and performance metrics provides clear inputs and objectives for optimization. Genetic algorithms or particle swarm optimization algorithms search for the optimal solution through continuous iteration, while the loss function quantifies the quality of the design. The design verification and iterative process ensures the reliability of the optimization results. This approach, combining AI algorithms and digital twin technology, not only improves the efficiency and quality of energy storage device structural design but also significantly reduces the workload of designers, providing technical support for the high-performance and high-safety design of energy storage devices.

[0048] In one embodiment of the present invention, the design output includes the following: Output a three-dimensional digital twin model of the energy storage device, including detailed geometric information of the battery module, heat dissipation system, shell structure and internal connectors; Output optimized design parameters, including battery module layout, heat dissipation system dimensions, and housing material selection; Output a performance evaluation report, including detailed data on heat dissipation performance, thermal runaway propagation probability, and heat dissipation efficiency; Output a record of the optimization process, including design parameter adjustments and performance evaluation results for each iteration.

[0049] The working principle and beneficial effects of the above technical solution are as follows: By outputting a three-dimensional digital twin model of the energy storage device (covering detailed geometric information of battery modules, heat dissipation systems, shell structures, and internal connectors), designers are provided with an intuitive and accurate virtual prototype. For example, the model details the dimensions of the battery module (200mm × 150mm × 100mm), the thickness of the heat sink in the heat dissipation system (5mm), the thickness of the aluminum alloy shell (3mm), and the layout of the internal connectors, enabling designers to fully understand the structural details of the equipment and identify potential design problems in advance. The output of optimized design parameters (including the layout of the battery modules, the dimensions of the heat dissipation system, and the selection of shell materials) provides specific guidance for actual production. For example, the optimized parameters show that a 3×2×4 matrix layout of the battery modules achieves optimal space utilization and heat dissipation; adjusting the width of the heat dissipation channels in the heat dissipation system to 8mm can improve heat dissipation efficiency by 20%; and choosing aluminum alloy as the shell material can reduce the weight of the equipment while ensuring structural strength. These optimized adjustments provide a basis for efficient production and performance assurance of the equipment. The output performance evaluation report (including detailed data on heat dissipation performance, thermal runaway propagation probability, and heat dissipation efficiency) enables designers to quantitatively evaluate the merits of their designs. For example, the report indicates that under operating conditions of 35°C ambient temperature and 12kW battery charging / discharging power, the maximum temperature of the device is 58°C, the thermal runaway propagation probability is reduced to 3%, and the heat dissipation efficiency reaches 75%. These specific data indicators provide strong evidence for the reliability of the design. The output optimization process record (including design parameter adjustments and performance evaluation results for each iteration) provides valuable experience for continuous design improvement and future similar projects. For example, the record shows that in the 5th iteration, by increasing the number of heat sinks and adjusting their layout, the device's heat dissipation efficiency improved by 15%, while in the 8th iteration, the optimized shell material selection reduced the device weight by 10% while maintaining structural strength. These records help designers review the optimization path, avoid repeated trial and error, and improve the design efficiency of future projects. This technical solution achieves comprehensive digitization and visualization of the energy storage device design process. The 3D digital twin model provides an intuitive design reference, the optimized design parameters ensure the accuracy of production guidance, the performance evaluation report quantifies the strengths and weaknesses of the design, and the optimization process record accumulates valuable design experience. This comprehensive design output method not only improves the accuracy and efficiency of the design but also provides strong support for the high-performance and high-safety design of energy storage devices, while reducing design costs and time investment.

[0050] In summary, this invention effectively addresses the shortcomings of traditional technologies by constructing a three-dimensional digital twin model, simulating heat dissipation performance and thermal runaway, and utilizing AI algorithms to optimize structural design.

[0051] This invention also provides a structural design system 10 for energy storage devices based on digital twin technology, such as... Figure 4 As shown, the system 10 includes: Model building module 100 is used to build a three-dimensional digital twin model of the energy storage device using computer-aided design technology; The performance simulation module 200 is used to simulate the heat dissipation performance of energy storage devices under different operating conditions through a digital twin model, including heat conduction, convection and radiation processes, and to calculate the temperature distribution and changes of the battery module. The simulation evaluation module 300 is used to simulate the temperature changes, gas diffusion and pressure changes of an energy storage device when thermal runaway occurs through a digital twin model, and to evaluate the thermal runaway propagation state and its impact range. The iterative optimization module 400 is used to iteratively optimize the structural design of energy storage devices using AI algorithms, evaluate the merits of the design through simulation results, and automatically adjust the design parameters. The simulation verification module 500 is used to re-input the optimized design parameters into the digital twin model and perform heat dissipation performance and thermal runaway simulation again to verify whether the design meets the structural design requirements of the energy storage device. When the simulation results meet the structural design requirements of the energy storage device, the final design scheme including the three-dimensional model, design parameters and performance evaluation report is output.

[0052] An embodiment of the present invention provides a structural design system for energy storage devices based on digital twin technology. By constructing a three-dimensional digital twin model, simulating heat dissipation performance and thermal runaway, and optimizing the structural design using AI algorithms, it can effectively address the shortcomings of traditional technologies.

[0053] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0054] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0055] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

Claims

1. A method for structural design of energy storage equipment based on digital twin technology, characterized in that, Comprise: Constructing a three-dimensional digital twin model of the energy storage device using computer-aided design technology; Simulating the heat dissipation performance of the energy storage device under different working conditions through the digital twin model, including heat conduction, convection, and radiation processes, and calculating the temperature distribution and its changes of the battery module; Simulating the temperature changes, gas diffusion, and pressure changes of the energy storage device when thermal runaway occurs through the digital twin model, and evaluating the thermal runaway propagation state and its impact range; Iteratively optimizing the structural design of the energy storage device using AI algorithms, evaluating the design through simulation results, and automatically adjusting design parameters; Re-inputting the optimized design parameters into the digital twin model to simulate the heat dissipation performance and thermal runaway again, verifying whether the design meets the structural design requirements of the energy storage device, and outputting the final design scheme including the three-dimensional model, design parameters, and performance evaluation report when the simulation results meet the structural design requirements of the energy storage device.

2. The method of claim 1, wherein the method is characterized by: The construction of a three-dimensional digital twin model of the energy storage device using computer-aided design technology comprises: Pre-classifying and statistically standardizing the modeling work according to the detailed geometric information, material attribute information of the battery module, heat dissipation system, shell structure, and internal connecting parts; Model encapsulation of the standardized modeling of multiple module units, and mapping storage with the classification statistics results; Using computer-aided design technology, calling the encapsulated models of multiple module units according to design requirements, and arranging them modularly according to design standards or design feedback to construct a three-dimensional digital twin model of the energy storage device.

3. The method of claim 1, wherein the method is characterized by: Simulating the heat dissipation performance of the energy storage device under different working conditions through the digital twin model comprises: Based on the designed three-dimensional digital twin model, simulating the heat dissipation performance of each module unit under the rated working state based on the detailed geometric information and material attribute information of each module unit, wherein the thermal simulation content includes: Heat source simulation: Define the heat source distribution of the battery module in the digital twin model, heat source power is represented as: wherein, is the battery discharge current, is the battery voltage, is the battery internal resistance, is the battery efficiency; Heat conduction calculation: The heat conduction process inside the battery module is calculated using the Fourier law, the heat conduction rate is represented as: wherein, is the thermal conductivity of the material, is the temperature gradient; Convection heat transfer calculation: the convection heat transfer process between the battery module and the heat dissipation system is calculated using Newton's cooling law, the convection heat transfer rate is represented as: wherein, is the convective heat transfer coefficient, is the heat transfer area, is the battery surface temperature, is the ambient temperature; Radiation heat transfer calculation: The radiation heat transfer process of the battery module is calculated using the Stefan-Boltzmann law, and the radiation heat transfer rate is represented as: wherein denotes the surface emissivity, is the Stefan-Boltzmann constant.

4. The method of claim 1, wherein the method is characterized by: The thermal runaway simulation process comprises: Defining the trigger conditions of thermal runaway, including the battery temperature exceeding the critical value or the short circuit occurring inside the battery; Calculating the temperature change rate of the battery module using the thermal runaway propagation model, and the expression of the thermal runaway propagation model is: wherein, represents the rate of temperature change, represents the temperature, is the heat generated during thermal runaway, is the heat dissipated, is the battery mass, is the specific heat capacity of the material; The diffusion process of the gas in the thermal runaway process is simulated by using Fick's law, and the gas diffusion flux is represented as: wherein, D is the gas diffusion coefficient, C is the gas concentration gradient; The pressure change during the thermal runaway process is calculated using the ideal gas law, and the pressure is expressed as: wherein, is the amount of gas substance, is the gas constant, is the gas volume.

5. The method of claim 1, wherein the method is characterized by: Iterative optimization of the structural design of the energy storage device using AI algorithms comprises: Defining the variable parameters of the energy storage device structure design according to the detailed geometric information and material attribute information of the battery module, heat dissipation system, shell structure, and internal connecting parts, including the layout mode, model, and material selection of the battery module, heat dissipation system, and shell structure; Defining the performance indicators of the optimization target, including the maximum temperature, thermal runaway propagation probability, and heat dissipation efficiency; Selecting genetic algorithm or particle swarm optimization algorithm to optimize the design parameters, while constructing a loss function to evaluate the design, and the expression is: wherein, represents a loss function, , and are dynamically adjusted weight coefficients, is a maximum temperature, is a target temperature, is a thermal runaway propagation probability, is a heat dissipation efficiency; Adjusting the design parameters through algorithm iteration to minimize the loss function until the design requirements are met.

6. The method of claim 1, wherein the method is characterized by: Design verification and iteration comprises: Defining the conditions for design verification, including the maximum allowed temperature, thermal runaway propagation probability threshold, and heat dissipation efficiency target; Re-inputting the optimized design parameters into the digital twin model to simulate the heat dissipation performance and thermal runaway, verifying whether the design meets the verification conditions; If the verification result does not meet the design requirements, adjust the design parameters according to the optimization suggestions of the AI algorithm, and re-simulate and verify; When the verification result meets the design requirements, determine that the optimization process converges, and output the final design scheme.

7. The method of claim 1, wherein the method is characterized by: The design output includes the following: Output the three-dimensional digital twin model of the energy storage device, including detailed geometric information of the battery module, heat dissipation system, shell structure and internal connecting parts; Output the optimized design parameters, including the layout of the battery module, the size of the heat dissipation system and the selection of the shell material; Output the performance evaluation report, including detailed data of heat dissipation performance, thermal runaway propagation probability and heat dissipation efficiency; Output the record of the optimization process, including the adjustment of design parameters and performance evaluation results of each iteration.

8. A digital twin technology-based energy storage device structure design system, characterized by, Including: Model construction module, for constructing the three-dimensional digital twin model of the energy storage device using computer-aided design technology; Performance simulation module, for simulating the heat dissipation performance of the energy storage device under different working conditions through the digital twin model, including heat conduction, convection and radiation processes, calculating the temperature distribution and its change of the battery module; Simulation evaluation module, for simulating the temperature change, gas diffusion and pressure change of the energy storage device when thermal runaway occurs through the digital twin model, evaluating the thermal runaway propagation state and its influence range; Iterative optimization module, for iterative optimization of the structure design of the energy storage device using AI algorithm, evaluating the pros and cons of the design through simulation results, and automatically adjusting the design parameters; Simulation verification module, for re-inputting the optimized design parameters into the digital twin model, simulating the heat dissipation performance and thermal runaway again, verifying whether the design meets the structural design requirements of the energy storage device, and outputting the final design scheme including the three-dimensional model, design parameters and performance evaluation report when the simulation result meets the structural design requirements of the energy storage device.

Images