Lithium battery equipment temperature equalization and energy consumption optimization system and method based on digital twinning

Abstract

The invention discloses a lithium battery equipment temperature equalization and energy consumption optimization system and method based on digital twinning. Constructing a digital twinborn model of the lithium battery equipment, and realizing fusion interaction of multi-physical parameter data; establishing a balanced energy-saving control model between the temperature field of the internal space of the cavity and the temperature control parameters through an ANFIS technology; the turbulent flow wind speed optimization module is used for cooperatively regulating and controlling the rotating speed of a fan and the temperature of a cavity by adopting a double-closed-loop feedback control strategy; an equipment health state evaluation model is constructed based on a deep learning algorithm, and fault early warning and optimization suggestion automatic generation are realized; a mixed reality technology is innovatively introduced in a human-computer interaction level, a multi-mode interaction mode is provided, and the ability of an operator to understand and control the running state of equipment is improved in combination with a mixed reality display function. According to the invention, real-time monitoring and optimal control of the running state of the lithium battery equipment are realized, the balance of the temperature field and the energy efficiency level of the system are remarkably improved, and important technical support is provided for green intelligent manufacturing.

Description

Technical Field

[0001] The present invention relates to temperature control technology in the field of lithium-ion battery (lithium electricity) manufacturing, and in particular to a temperature balancing and energy consumption optimization system and method for lithium battery equipment based on digital twins. Background Art

[0002] In the manufacturing process of lithium battery equipment, temperature control is one of the key factors affecting battery performance and life.

[0003] Although the traditional temperature control system can manage the temperature of the equipment to a certain extent, there are still many technical problems that need to be solved:

[0004] First, due to the heat conduction characteristics and structural design limitations of traditional temperature control systems, the temperature distribution in each area of the cavity is often not uniform, resulting in poor product consistency between batches;

[0005] Secondly, the existing temperature control system has high energy consumption, which not only increases the operating costs of enterprises, but also goes against the current development concept of green manufacturing;

[0006] In addition, the traditional temperature control system has a slow response speed, making it difficult to achieve real-time optimization and control of the equipment's operating status. At the same time, the working mechanism of lithium battery equipment is relatively complex, and the data information transmitted by the host computer lacks intuitiveness and cannot effectively reflect the actual working status of the equipment, making it difficult for workers to monitor and observe the equipment's operation in real time during actual operation.

[0007] Therefore, how to improve the temperature balance and energy efficiency of lithium battery equipment and realize real-time and intuitive monitoring of equipment operating conditions has become a technical problem that needs to be solved urgently in the industry. Summary of the invention

[0008] The purpose of the present invention is to overcome the shortcomings and deficiencies of the above-mentioned prior art and provide a temperature balancing and energy consumption optimization system and method for lithium battery equipment based on digital twins. The present invention achieves precise control of the internal temperature field and energy consumption optimization of lithium battery equipment by constructing a digital twin model of lithium battery equipment and combining modules such as ANFIS control, spoiler wind speed optimization, intelligent predictive maintenance and mixed reality interaction.

[0009] The present invention is achieved through the following technical solutions:

[0010] A temperature balancing and energy consumption optimization system for lithium battery equipment based on digital twins, including the following modules:

[0011] Digital Twin Module for:

[0012] Based on multi-physics field coupling analysis technology, a high-precision digital model of lithium battery equipment is constructed, which can simultaneously simulate the changes of physical parameters such as temperature field, pressure field and flow rate field;

[0013] Utilize historical operation data to learn and optimize the digital twin model, improving the model's prediction accuracy and robustness;

[0014] Implement bidirectional mapping between the actual physical space and the virtual digital space, including real-time data acquisition and feedback mechanisms, ensuring that the virtual model can accurately reflect the state of physical devices and reverse-optimize the operation of actual devices according to the adjustment results in the virtual space;

[0015] ANFIS control module, for:

[0016] Adopt the adaptive network fuzzy inference algorithm, combined with the dynamic parameter adaptive adjustment mechanism, which can automatically adjust the membership function parameters and inference rules in the fuzzy rule base according to real-time working condition data;

[0017] Achieve fine control of the device temperature to ensure temperature balance of the lithium battery device under different working conditions;

[0018] Integrate energy consumption prediction and optimization strategies, and dynamically adjust the temperature control strategy to achieve the lowest energy consumption operation on the premise of ensuring temperature balance;

[0019] Turbulent flow wind speed optimization module, for:

[0020] Simulate the influence of different wind speeds on heat flow, and select the optimal wind speed parameters based on the optimization algorithm to minimize the temperature difference inside the device and improve temperature balance;

[0021] Utilize the double closed-loop control mechanism of fan speed and cavity temperature to achieve real-time adjustment of fan speed and cavity temperature, ensuring the stable operation of the system under dynamic working conditions;

[0022] Intelligent predictive maintenance module, for:

[0023] Equipment health status assessment: Evaluate the health status of key components of the lithium battery equipment through deep learning algorithms to identify potential performance degradation or anomalies;

[0024] Fault risk prediction: Based on digital twin model simulation and historical operation data, predict the potential fault risks of the equipment under different working conditions and provide early warning information;

[0025] Maintenance recommendation generation: Automatically generate maintenance recommendations and optimized operation strategies according to the equipment health status and fault risk analysis results to extend the equipment life and improve production efficiency;

[0026] Intelligent diagnosis and early warning: Real-time monitor the equipment operation status, conduct intelligent diagnosis in combination with the digital twin model, provide fault location and repair suggestions, and issue early warnings before potential problems occur;

[0027] The mixed reality interaction module is used for:

[0028] Providing multi-modal human-computer interaction methods, including gesture recognition, voice control, and tactile feedback, etc., supporting operators to monitor equipment and adjust parameters in a more natural way, and improving the efficiency of human-computer interaction;

[0029] The adaptive mixed reality display function based on deep learning can automatically identify the key parts of the lithium battery equipment and label relevant information in real time, helping operators intuitively understand the equipment status;

[0030] Providing an immersive visual interface, supporting users to perform remote or on-site equipment operation, parameter setting, and fault diagnosis through mixed reality technology.

[0031] The digital twin module is implemented in the following ways:

[0032] Data collection and processing: Obtaining multi-dimensional parameters such as temperature, humidity, and pressure during the operation of the lithium battery equipment;

[0033] Equal-proportion modeling: Constructing a virtual lithium battery model with the same size as the actual lithium battery equipment for visualizing the cavity temperature distribution;

[0034] Dynamic data correction: Dynamically correcting the operation data based on sensor feedback and storing it in the twin database;

[0035] Learning and optimization: Using historical operation data to train and optimize the model and adjust parameters to improve the prediction accuracy;

[0036] Bidirectional mapping and feedback: Realizing the real-time synchronization between the actual physical equipment status and the virtual digital model status;

[0037] The digital twin module realizes the support for the following modules:

[0038] Providing the ANFIS control module with real-time updated equipment status information as the basic data for optimizing the temperature control strategy;

[0039] Providing the turbulent flow wind speed optimization module with a heat flow distribution simulation environment and experimental data to assist in optimizing the wind speed distribution and energy consumption efficiency;

[0040] Providing the intelligent predictive maintenance module with the operation status data of the lithium battery equipment to support the prediction and diagnosis of potential fault risks;

[0041] Providing the mixed reality interaction module with real-time model updates and mixed reality display functions to help operators intuitively understand the equipment status.

[0042] The ANFIS control module is implemented in the following ways:

[0043] Fuzzy rule base establishment: Based on the knowledge and historical data in the field of lithium battery temperature control, construct a fuzzy rule base applicable to the temperature control of lithium battery equipment;

[0044] Dynamic parameter adjustment: Through an adaptive network mechanism, optimize the membership function parameters and inference rules in real time to cope with changes in working conditions;

[0045] Temperature control strategy generation: Generate accurate temperature control instructions according to the optimized fuzzy rules and current working condition data;

[0046] Energy consumption prediction and optimization: Combine the energy consumption model and optimization algorithm to dynamically adjust the temperature control strategy to ensure the lowest energy consumption under the premise of meeting the temperature requirements.

[0047] The ANFIS control module provides support for the following modules:

[0048] Data interaction with the digital twin module: Receive real-time device status information from the digital twin module and provide it with optimized control instructions and energy consumption data;

[0049] Support for the spoiler wind speed optimization module: By sharing the temperature control strategy and energy consumption prediction results, collaboratively optimize the wind speed field distribution to maximize the comprehensive energy efficiency;

[0050] Support for the intelligent predictive maintenance module: Provide operation data related to temperature control to support the assessment of the device health status and the prediction of potential failure risks;

[0051] Support for the mixed reality interaction module: Output user-friendly control interface information, enhance the operator's monitoring ability of the device status, and improve the human-machine collaboration efficiency through multi-modal interaction methods.

[0052] The spoiler wind speed optimization module is implemented in the following ways:

[0053] Dual closed-loop control design: Establish a dual closed-loop feedback control system for the fan speed and the cavity temperature, and precisely control the fan speed and the hot air flow through the speed loop and the temperature loop respectively;

[0054] Wind speed field simulation: Use the fluid mechanics model to simulate the heat flow at different wind speeds, analyze its influence on the internal temperature distribution of the device, and provide data support for optimization;

[0055] Application of optimization algorithm: Based on the temperature distribution objective function (such as the temperature difference minimization function, the energy consumption minimization function), calculate and select the optimal fan speed and duct parameters through the optimization algorithm;

[0056] Temperature field homogenization strategy: Dynamically adjust the wind speed distribution according to the simulation results to ensure that the temperature deviation in the key areas inside the device is within the allowable range.

[0057] The spoiler wind speed optimization module supports the following modules:

[0058] Data interaction with the digital twin model: Obtain real-time working condition data through the digital twin model, and continuously optimize the wind speed control strategy based on historical operation data;

[0059] Support for the dynamic adjustment of the ANFIS control module: Provide real-time temperature and wind speed feedback for the ANFIS fuzzy inference system to help it dynamically adjust the membership function parameters and inference rules, further improving the temperature control accuracy and energy consumption efficiency;

[0060] Support for the intelligent predictive maintenance module: Feedback problems such as parameter anomalies encountered during the execution of the actuator to further improve the prediction accuracy;

[0061] Data interconnection with the mixed reality interaction module: Display the optimized wind speed distribution and temperature field status to the operator through the mixed reality interface.

[0062] The intelligent predictive maintenance module is implemented in the following ways:

[0063] Use deep learning algorithms to analyze the historical operation data and real-time data of the equipment, identify the changing trends of the equipment health status, establish a health status assessment model, and predict the performance degradation of the equipment under different working conditions;

[0064] Combine the simulation results of the digital twin model to predict the possibility and time point of potential faults, accurately locate the fault location through the intelligent diagnosis function, and provide repair suggestions;

[0065] According to the equipment health status and fault risk analysis results, formulate personalized maintenance plans and optimized operation strategies, automatically generate maintenance reports, and guide the operator to perform equipment maintenance;

[0066] Through the mixed reality interaction module, present the predictive maintenance information to the operator in an intuitive way, support the operator to confirm and adjust the maintenance suggestions, and optimize the model parameters according to the actual maintenance effect.

[0067] The intelligent predictive maintenance module supports the following modules:

[0068] Data interaction with the digital twin module: Further improve the accuracy of the digital twin model by real-time updating the equipment operation data and health status information, and enhance the two-way mapping ability between the virtual space and the physical space;

[0069] Support for the ANFIS control module: Dynamically adjust the temperature control strategy based on the equipment health status assessment results, optimize energy consumption while ensuring the balanced distribution of the temperature field, and improve the efficiency and stability of the lithium battery equipment manufacturing process;

[0070] Support for the Turbulent Flow Wind Speed Optimization Module: Through the predictive maintenance function, detect and solve abnormal problems of parameters such as fan speed and cavity temperature in advance, ensure the stable operation of the turbulent flow wind speed control system, and further optimize the accuracy of hot air flow and the uniformity of temperature field distribution;

[0071] Support for the Mixed Reality Interaction Module: Provide visual information on the real-time device health status and maintenance suggestions for operators, improve the human-machine interaction efficiency, and mark the information of key parts through the mixed reality function to help operators more intuitively understand and control the device status.

[0072] The mixed reality interaction module is implemented in the following ways:

[0073] Data Acquisition and Processing: Obtain device operation data and environmental information through sensors and cameras, and combine deep learning algorithms to identify and mark key parts;

[0074] Model Training and Deployment: Train the mixed reality display model based on historical data to achieve the automatic identification and information marking function of key parts of the device;

[0075] Hardware Integration and Testing: Integrate the mixed reality interaction module with the control system, sensors, and actuators of the lithium battery device, and optimize the human-machine interaction experience through actual operation tests;

[0076] The mixed reality interaction module supports the following modules:

[0077] Work collaboratively with the digital twin module, receive real-time simulation data and visualize it to help operators more intuitively understand the device status;

[0078] Support the parameter adjustment function of the ANFIS control module, dynamically adjust the temperature control strategy through voice or gesture commands, and improve the system operation efficiency;

[0079] Accept the optimized wind speed distribution and temperature field status of this module and display them to operators to achieve support for the turbulent flow wind speed optimization module;

[0080] Link with the intelligent predictive maintenance module, display the predictive maintenance suggestions to operators in the form of mixed reality, and provide an interactive interface for confirmation and execution.

[0081] Compared with the prior art, the present invention has the following advantages and effects:

[0082] The present invention realizes the balanced distribution of the temperature field of lithium battery equipment and a significant improvement in energy efficiency level by constructing a high-precision digital twin model and combining ANFIS control technology and a spoiler air velocity optimization algorithm. Meanwhile, the application of intelligent predictive maintenance technology and mixed reality technology provides operators with the ability to perceive the equipment status in all dimensions, further improving the intelligence level of information processing and the accuracy of on-site operations.

[0083] (1) Enhanced information processing ability and visualization level

[0084] The digital twin system significantly improves the intelligence level of information processing. It can update the virtual digital space in real time based on the status of the actual physical equipment. This not only enhances the effect of online monitoring but also provides a visualization platform for the optimization and decision-making in the production process of lithium battery equipment.

[0085] (2) Achieved adaptive regulation of temperature balance and energy conservation

[0086] An adaptive control mechanism based on ANFIS is introduced into the digital twin system, which can dynamically adjust process variables according to real-time working conditions. By establishing a double closed-loop control model for the spoiler fan speed and the cavity temperature, this system has better performance compared with traditional PID and fuzzy control. These improvements highlight the effectiveness of the proposed method in achieving precise temperature control and significant energy conservation.

[0087] (3) Achieved the integration of virtual digital space and actual physical space

[0088] The present invention establishes a two-way mapping and synchronous feedback mechanism between the virtual digital space and the real physical space in the production process of lithium battery equipment. By using mixed reality technology, real-time data on the internal state of the equipment, the cavity temperature, and heat transfer parameters are visualized and monitored in the interactive environment. This enables workers to continuously understand the equipment status and ensures the safe and reliable operation of the production process of lithium battery equipment.

[0089] In summary, the digital twin system proposed based on the adaptive neuro-fuzzy inference system (ANFIS) and AR technology provides a systematic solution for achieving precise temperature control and significant energy conservation in the production of lithium battery equipment. The present invention not only deepens the control and utilization of thermal management but also paves the way for future research on optimizing energy utilization and improving production efficiency in the lithium battery industry. Brief Description of the Drawings

[0090] Figure 1 It is a schematic diagram of the data flow of the digital twin module; it describes the data transmission and processing process from the actual physical space to the virtual digital space.

[0091] Figure 2It is the structure diagram of the ANFIS control network, which shows the components of the ANFIS network and its working principle, including the fuzzy rule base, inference engine, etc.

[0092] Figure 3 It is the schematic diagram of the spoiler wind speed optimization process, which shows the whole process of dynamically adjusting the rotation speed of the spoiler fan to regulate the wind speed change by combining real-time data, ensuring temperature balance.

[0093] Figure 4 It is the schematic diagram of the intelligent predictive maintenance module, which shows the whole process of intelligent predictive maintenance of equipment, automatic generation of fault warning and optimization suggestions.

[0094] Figure 5 It is the real-time communication and visualization interaction process between the server side and the client side, which shows the whole communication process of transmitting the data obtained from the device side and performing mixed reality visualization display. Specific implementation manners

[0095] The present invention will be further described in detail below in conjunction with specific embodiments.

[0096] Figures 1 to 5 As shown, the present invention discloses a lithium battery equipment temperature balance and energy consumption optimization system based on digital twin, which is specifically as follows:

[0097] Step S1: Specific implementation of the digital twin module, as Figure 1 shown.

[0098] Step S11: Data acquisition and processing

[0099] Install temperature, humidity and pressure sensors in the key production areas of lithium battery equipment (such as battery electrode manufacturing, electrolyte injection and formation stages). The selection of these positions is based on the factors that have the greatest impact on the equipment performance. Use median filtering and moving average filters to remove noise data. For outliers, use statistical methods (such as 3σ criterion or IQR method) to detect and eliminate them. Use an analog-to-digital converter to convert analog signals into digital signals, and perform unified data formatting processing through software to ensure the compatibility of all sensor data. Scale each parameter to the range of 0-1 or a specific interval to eliminate the dimension difference and facilitate subsequent data analysis and model training. Set a sampling rate of 10Hz to ensure that the collected data can reflect the dynamic changes of the equipment. At the same time, optimize the data transmission protocol to reduce latency and ensure real-time performance.

[0100] Step S12: Bidirectional mapping mechanism

[0101] Transmit sensor data to the digital twin platform in real time through industrial communication protocols (such as Modbus, Profinet, etc.). Use Modbus TCP for data transmission and configure the RTU mode to adapt to different sensor types. Profinet IO is used for integrated device configuration to ensure efficient data exchange. Based on detailed physical model analysis, establish the mapping relationship between each sensor parameter and the virtual model attributes, and establish the data correspondence between the virtual model and the actual device. For example, temperature changes affect the color and material of the 3D model, ensuring that the virtual model can truly reflect the state of the production equipment.

[0102] Step S13: Dynamic data correction

[0103] Apply machine learning algorithms (such as random forest) to predict sensor drift, and automatically adjust the correction value through a feedback mechanism. Use a time series database to store historical data, and combine weighted average and Kalman filtering to optimize the current state estimation to ensure the accuracy of the model.

[0104] Step S14: Isometric modeling technology

[0105] Use CAD software to generate a high-precision model and convert it into a format suitable for a rendering engine (such as Unity) to achieve a realistic virtual environment. Implement data-driven dynamic updates to ensure that the virtual model is synchronized with the actual device state. Use the subscription mode to receive sensor data changes and trigger model updates. Use Unreal Engine for high-quality rendering, process lighting, material, and shadow effects to enhance visual realism. Integrate mixed reality devices such as HoloLens and use SLAM technology to achieve precise alignment between the virtual model and the actual device, providing an immersive interactive experience.

[0106] Step S2: Specific implementation of the ANFIS control module, such as Figure 2 as shown.

[0107] Step S21: Multi-dimensional working condition data analysis

[0108] Integrate multi-dimensional real-time data from the digital twin module, including parameters such as temperature, humidity, and pressure. At the same time, combine the historical operation data of the production equipment, such as past temperature control records and equipment status logs. Ensure that the data format of all data sources is consistent and perform data conversion or standardization. First, perform descriptive statistics to calculate basic statistics such as the mean, standard deviation, maximum value, and minimum value of each parameter to understand the data distribution. Next, perform correlation analysis, using the Pearson correlation coefficient or the Spearman rank correlation coefficient to evaluate the degree of association between different parameters and identify factors that have a significant impact on temperature control. Then use the principal component analysis method to perform dimensionality reduction, extract the main influencing factors, and reduce redundant data. For missing data points, you can choose interpolation methods (such as linear interpolation, polynomial interpolation) or delete samples with missing values. Use box plots, Z-score methods, etc. to identify abnormal data points and decide whether to remove or adjust these data. Finally, establish a structured database to store the integrated multi-dimensional operating data and historical operation data to ensure data integrity and traceability.

[0109] Step S22: Online learning mechanism

[0110] First, construct the ANFIS model, whose network structure consists of five layers: Input Layer: Receive multi-dimensional working condition data as input. Fuzzification layer: Convert crisp (precise) input into the membership of fuzzy sets, usually using membership functions such as triangles, trapezoids, etc. Rule Base Layer: Contains multiple fuzzy logic rules, each of which corresponds to specific input conditions and output results. For example, "If the temperature is high and the humidity is low, the cooling system is partially turned on." Inference and Activation Layer: Apply fuzzy logic reasoning to calculate the activation degree of each rule and weight the conclusions. Defuzzification Layer: Convert fuzzy output into precise control instructions, such as using the center of gravity method, average method, etc.

[0111] Next, the ANFIS model is trained online using real-time data streams, and model parameters are adjusted using methods such as least squares support vector machine (LSSVR) or particle swarm optimization (PSO). The membership parameters and weight coefficients of fuzzy rules are updated regularly to ensure that the model can adapt to dynamically changing working conditions.

[0112] Finally, design appropriate training step size and learning rate to prevent the model from overfitting or underfitting. Hyperparameters can be adjusted through methods such as cross-validation. Ensure that the online learning mechanism can run stably under real-time data flow and has good convergence speed and noise resistance.

[0113] Step S23: Fuzzy rule inference

[0114] First, design the fuzzy sets and membership functions. According to the temperature control requirements of the lithium battery equipment, define appropriate fuzzy sets, such as "low temperature", "medium temperature", and "high temperature". Design the corresponding membership functions, which can be triangular, trapezoidal, or other custom functions to ensure a reasonable description of the input data. Next, design the rule base. Based on domain knowledge and historical data analysis, formulate a series of fuzzy logic rules. For example: If the temperature is higher than the set value and the humidity is lower than a certain threshold, then increase the opening degree of the cooling system. If the temperature is close to the set value but the humidity is high, then reduce the power output of the heating system. Ensure that the rule base covers all possible working conditions, and the rules are mutually exclusive and complete. Finally, generate inference and control instructions. Input the current working condition data, after fuzzy processing, apply the fuzzy logic rules for inference, calculate the activation degree of each rule and the comprehensive output. Convert the fuzzy output into specific control commands (such as percentage opening degree, specific power value, etc.) and send them to the actuator.

[0115] Step S24: Historical data analysis and optimization

[0116] First, establish a historical data warehouse. Using database technology, record various parameters and control decisions during each production process, including input data, fuzzy inference results, control instruction outputs, and actual equipment responses. Ensure the efficiency and security of data storage to support long-term preservation and fast query. Next, conduct data analysis and optimization. Use algorithms such as random forest, gradient boosting trees (such as XGBoost, LightGBM) to analyze the influence degree of each factor on temperature control in historical data. According to the data analysis results, adjust the fuzzy logic rules, such as adding or modifying certain rules to improve control accuracy. Use optimization methods such as genetic algorithm (GA), simulated annealing (SA) to adjust the membership functions and weight coefficients of the ANFIS model to improve the overall performance. Finally, design a feedback mechanism. Establish a feedback loop, regularly review historical data and control effects, and evaluate the effectiveness of the current model. Make necessary model updates or parameter adjustments according to the evaluation results to ensure the continuous optimization of the ANFIS control system.

[0117] Step S3: Specific implementation of the spoiler wind speed optimization module, such as Figure 3 shown.

[0118] Step S31: Dual closed-loop control system design

[0119] First, design the control system architecture. The outer-loop controller is responsible for receiving the target temperature input and calculating the temperature deviation based on the actual temperature sensor data. The inner-loop controller is responsible for adjusting the motor speed according to the speed deviation. By adjusting the duty cycle of the PWM (Pulse Width Modulation) signal, the speed of the fan motor is controlled. The actuator includes the fan motor and the inverter module. Then, design the ANFIS controller. Introduce the ANFIS controller into the outer-loop controller to dynamically adjust the fuzzy rules according to the temperature deviation and optimize the fan control strategy. The inner-loop controller also uses the ANFIS controller to achieve precise adjustment of the motor speed. The speed of the fan motor is controlled by the PWM (Pulse Width Modulation) signal output by the inverter. The duty cycle of the PWM determines the average voltage and speed of the motor. The larger the duty cycle (i.e., the larger the pulse width), the higher the motor speed; conversely, the lower the speed. Finally, integrate the double closed-loop control system into the lithium battery device and verify the temperature control accuracy, response speed, and stability of the system through experiments.

[0120] Step S32: Wind speed field simulation and optimization

[0121] First, establish the flow field model. Use CFD software (such as ANSYS Fluent, COMSOL Multiphysics) to establish a three-dimensional flow field model inside the device. Consider the device geometry, fan layout, duct design, and heat source distribution in the model. Then, perform mesh generation and solution. Perform mesh generation according to the device geometry to ensure that the mesh in the key areas (such as near the heat source) is fine enough to capture the flow and heat transfer characteristics. Set the boundary conditions (such as inlet velocity, outlet pressure, wall temperature, etc.) and run the numerical simulation. Then, analyze the air flow distribution and heat transfer. Analyze the flow path of the air flow inside the device, focusing on the temperature field and velocity field near the heat source. Optimize the fan layout through the simulation results to ensure uniform air flow distribution and reduce local high-temperature areas. Adjust the duct structure (such as channel width, elbow angle, etc.) to improve the air flow efficiency and cooling effect. Verify through simulation whether the optimized duct design can significantly reduce the temperature fluctuation inside the device. Finally, install the optimized fan layout and duct design in the actual device and conduct experimental tests to verify the effectiveness of the CFD simulation results.

[0122] Step S33: Optimal parameter selection

[0123] Dynamically adjust the fan speed according to the temperature distribution and air flow velocity inside the device. Increase the air volume in high-temperature areas and decrease the air volume in low-temperature areas to improve the cooling efficiency. The dynamic adjustment is achieved through an ANFIS controller. Use intelligent optimization algorithms such as genetic algorithm (GA) or particle swarm optimization (PSO) to adjust the system parameters online or offline. Online optimization can adjust the parameters in real time according to the temperature deviation and fan speed feedback, which is suitable for complex and changeable working conditions. Offline optimization can calculate the optimal parameter combination offline based on experimental or simulation data and apply it to the actual system. Conduct stability tests on the optimized control system to ensure its robustness under different loads and environmental conditions. Finally, verify the temperature control accuracy, energy consumption efficiency, and long-term operation reliability of the system.

[0124] Step S4: Specific implementation of the intelligent predictive maintenance module, such as Figure 4 shown.

[0125] Step S41: Establish a health status assessment model

[0126] Use recurrent neural network (RNN) and its variants (such as LSTM or GRU) to capture the time dependence of the device operating state. For supervised learning tasks, adopt multi-classification models (such as fully connected neural network, support vector machine, etc.) to classify the health status. Extract meaningful features (such as statistical features like mean, variance, peak value, kurtosis, skewness, etc.) from the time series data, and combine frequency domain analysis (such as Fourier transform) to extract frequency features for model input. Use historical operation data to conduct supervised training on the deep learning model, and evaluate the generalization performance of the model through cross-validation (K-fold cross-validation or holdout method). Adopt an early stopping mechanism to prevent overfitting. Establish a prediction model for the device health state index (SOH, State of Health) to quantify the degree of device degradation. Use classification tasks to divide the device state into three levels: "normal", "warning", and "fault". Use the trained deep learning model to conduct rolling prediction on real-time data, identify the change trend of the device health state, and generate a degradation curve in combination with the simulation results of the digital twin model.

[0127] Step S42: Predict the possibility and time point of potential faults

[0128] Input the health status assessment results predicted by the deep learning algorithm into the digital twin model to simulate the operating status of the device under different working conditions. Combine historical fault data and real-time data to analyze the probability distribution of potential faults. Use a regression model or a time series prediction model to predict the fault occurrence time and output the confidence interval. Based on the simulation results of the digital twin model, combined with sensor data and health status assessment results, use fault tree analysis (FTA) or Bayesian network (BN) to accurately locate the fault position. Fault components can be identified by analyzing information such as vibration signals and temperature distributions. Automatic repair strategies are generated according to the fault type and severity. For example, for the problem of overheating battery, it is recommended to adjust the cooling system parameters or replace the defective battery module; for mechanical component wear, it is recommended to lubricate or replace the components.

[0129] Step S43: Develop a personalized maintenance plan and optimize the operation strategy

[0130] Based on the health status assessment model and the fault risk prediction results, dynamically adjust the maintenance cycle. For example, implement preventive maintenance for high-risk components; extend the maintenance interval for low-risk components. Combine the simulation results of the digital twin model to optimize the operating parameters of the device (such as temperature, pressure, rotation speed, etc.) to reduce the probability of faults. For example, adjust the motor speed to reduce the impact of vibration on the battery module. The maintenance report includes the health status assessment results of the device, fault risk warning information, maintenance suggestions (including specific operation steps, required tools and spare parts list), and suggestions for optimizing operating parameters. Feed back the actual maintenance effect into the system to update the parameters of the deep learning model and the digital twin model to optimize the prediction accuracy.

[0131] Step S5: The specific implementation of the mixed reality interaction module, such as Figure 5 shown.

[0132] Step S51: Design of the virtual-real combined interface

[0133] Select a head-mounted display (HMD) that supports high-precision positioning and a large field of view, such as Microsoft HoloLens, Meta Quest Pro, etc. Ensure that the hardware device has good environmental light adaptability and low-latency characteristics to improve the user experience of workers. Bind the key parameters of the device (such as temperature sensors, humidity sensors, etc.) to the digital twin model to ensure the synchronization of virtual and real data. Use a mixed reality library (such as Unity Mixed Reality Foundation, Vuforia) to achieve precise positioning of the device in the real environment. Through feature matching and SLAM technology, ensure that the virtual model can be accurately superimposed on the field of view of the actual production device. Design the user interface in the mixed reality framework to ensure that key information (such as alarms, operation guides) can be presented quickly.

[0134] Step S52: Real-time data visualization

[0135] Use industrial communication protocols (such as Modbus, OPC UA, MQTT) to achieve real-time data interaction between devices and the mixed reality system. Develop lightweight data transmission middleware to ensure low latency and high reliability, enabling real-time data updates in the mixed reality system and ensuring that users see the latest status. Display the change trends of key parameters in the mixed reality interface in the form of 2D charts (such as line charts, bar charts) or 3D views. Use color coding to distinguish normal, warning, and dangerous states to ensure intuitive understanding. When the operating parameters of the device exceed the preset range, the system triggers visual and auditory alarms in the mixed reality interface (such as a flashing red area, voice prompt). Automatically pop up solution suggestions to help operators quickly locate problems. At the same time, set up gesture interaction and voice control in the program to allow users to confirm or cancel the alarm through gestures or voice. Provide a historical data query function to facilitate the analysis of the change trends of the device operating status.

[0136] Step S53: Operation guidance and training

[0137] Convert the operation process of the production equipment into a mixed reality guidance program to support users to complete the operation step by step. Integrate voice commentary and text prompts to ensure that the training content is easy to understand. Real-time display the operation steps and key precautions in the mixed reality interface. Provide operators with a virtual training environment to simulate various production scenarios in the mixed reality to help them master the equipment operation process and emergency handling methods. Provide real-time operation guides. When operators encounter problems during actual operation, the system can

[0138] The implementation manners of the present invention are not limited by the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications made without departing from the spirit and principle of the present invention shall be equivalent replacement manners and are all included in the protection scope of the present invention.

Claims

1. A temperature equalization and energy consumption optimization system for lithium battery equipment based on digital twin, characterized in that, It includes the following modules: The digital twin module is used for: Based on the multi-physical-field coupling analysis technology, construct a high-precision digital model of the lithium battery equipment, which can simultaneously simulate the changes of physical parameters such as temperature field, pressure field and flow velocity field; Use historical operation data to learn and optimize the digital twin model to improve the model prediction accuracy and robustness; Realize the bidirectional mapping between the actual physical space and the virtual digital space, including the real-time data acquisition and feedback mechanism, so that the virtual model can accurately reflect the state of the physical equipment, and reverse-optimize the actual equipment operation according to the adjustment results in the virtual space; The ANFIS control module is used for: Adopt the adaptive network fuzzy inference algorithm, combined with the dynamic parameter adaptive adjustment mechanism, which can automatically adjust the membership function parameters and inference rules in the fuzzy rule base according to the real-time working condition data; Realize the fine control of the equipment temperature, so that the temperature of the lithium battery equipment is balanced under different working conditions; Integrate the energy consumption prediction and optimization strategy, and dynamically adjust the temperature control strategy to achieve the lowest energy consumption operation on the premise of ensuring temperature balance; The turbulence wind speed optimization module is used for: Simulate the influence of different wind speeds on the heat flow, and select the optimal wind speed parameters based on the optimization algorithm to minimize the temperature difference inside the equipment and improve the temperature balance; Use the double closed-loop control mechanism of the fan speed and the cavity temperature to realize the real-time adjustment of the fan speed and the cavity temperature, so that the system can operate stably under dynamic working conditions; The intelligent prediction and maintenance module is used for: Equipment health status assessment: Through deep learning algorithms, assess the health status of key components of lithium battery equipment and identify potential performance degradation or abnormal conditions; Fault risk prediction: Based on digital twin model simulation and historical operation data, predict the potential fault risks of the equipment under different working conditions and provide early warning information; Maintenance suggestion generation: According to the equipment health status and fault risk analysis results, automatically generate maintenance suggestions and optimized operation strategies to extend the equipment life and improve production efficiency; Intelligent diagnosis and early warning: Real-time monitor the equipment operation status, combine with the digital twin model for intelligent diagnosis, provide fault location and repair suggestions, and issue early warnings before potential problems occur; The mixed reality interaction module is used for: Provide multi-modal human-computer interaction methods, support operators to monitor the equipment and adjust parameters in a natural way, and improve the human-computer interaction efficiency; The adaptive mixed reality display function based on deep learning can automatically identify the key parts of the lithium battery equipment and mark relevant information in real time to help operators intuitively understand the equipment status; Provide an immersive visualization interface, support users to perform remote or on-site equipment operation, parameter setting and fault diagnosis through mixed reality technology.

2. The implementation method of the digital twin-based lithium battery equipment temperature equalization and energy consumption optimization system according to claim 1, characterized in that, The digital twin module is implemented in the following ways: Data acquisition and processing: Obtain multi-dimensional parameters during the operation of the lithium battery equipment; Equal-proportion modeling: Construct a virtual lithium battery model with the same size as the actual lithium battery equipment for visualizing the cavity temperature distribution; Dynamic data correction: Dynamically correct the operation data based on sensor feedback and store it in the twin database; Learning optimization: Use historical operation data to train, optimize and adjust the parameters of the model to improve the prediction accuracy; Bidirectional Mapping and Feedback: Achieve real-time synchronization between the states of actual physical devices and virtual digital models.

3. The implementation method of the lithium battery equipment temperature balance and energy consumption optimization system based on digital twin according to claim 2, characterized in that, The digital twin module provides support for the following modules: Provide the ANFIS control module with real-time updated device status information as the basic data for optimizing temperature control strategies; Provide the turbulent flow wind speed optimization module with a heat flow distribution simulation environment and experimental data to assist in optimizing the wind speed distribution and energy consumption efficiency; Provide the intelligent predictive maintenance module with the operating status data of lithium battery equipment to support the prediction and diagnosis of potential failure risks; Provide the mixed reality interaction module with real-time model updates and mixed reality display functions to help operators intuitively understand the device status.

4. The implementation method of the lithium battery equipment temperature balance and energy consumption optimization system based on digital twin according to claim 2, characterized in that, The ANFIS control module is implemented in the following ways: Fuzzy rule base establishment: Based on the knowledge of lithium battery temperature control and historical data, construct a fuzzy rule base applicable to the temperature control of lithium battery equipment; Dynamic parameter adjustment: Through the adaptive network mechanism, optimize the membership function parameters and inference rules in real time to cope with changes in working conditions; Temperature control strategy generation: Generate accurate temperature control instructions according to the optimized fuzzy rules and current working condition data; Energy consumption prediction and optimization: Combine the energy consumption model and optimization algorithm to dynamically adjust the temperature control strategy to ensure the lowest energy consumption under the premise of meeting the temperature requirements.

5. The implementation method of the lithium battery equipment temperature balance and energy consumption optimization system based on digital twin according to claim 4, characterized in that, The ANFIS control module provides support for the following modules: Data interaction with the digital twin module: Receive real-time device status information from the digital twin module and provide it with optimized control instructions and energy consumption data; Support for the turbulent flow wind speed optimization module: Through sharing temperature control strategies and energy consumption prediction results, cooperate to optimize the wind speed field distribution to maximize the comprehensive energy efficiency; Support for the intelligent predictive maintenance module: Provide operation data related to temperature control to support the assessment of equipment health status and the prediction of potential failure risks; Support for the mixed reality interaction module: Output user-friendly control interface information, enhance the operator's monitoring ability of the device status, and improve the human-machine collaboration efficiency through multi-modal interaction methods.

6. The implementation method of the lithium battery device temperature balancing and energy consumption optimization system based on digital twin according to claim 2, wherein, The turbulent flow wind speed optimization module is implemented in the following ways: Dual closed-loop control design: Establish a dual closed-loop feedback control system for the fan speed and the cavity temperature, and respectively achieve precise control of the fan speed and the hot air flow through the speed loop and the temperature loop; Wind speed field simulation: Use the fluid mechanics model to simulate the heat flow at different wind speeds, analyze its impact on the internal temperature distribution of the device, and provide data support for optimization; Application of optimization algorithms: Based on the temperature distribution objective function, calculate and select the optimal fan speed and duct parameters through optimization algorithms; Temperature field homogenization strategy: Dynamically adjust the wind speed distribution according to the simulation results to ensure that the temperature deviation in the key areas inside the device is within the allowable range.

7. The implementation method of the lithium battery equipment temperature balance and energy consumption optimization system based on digital twin according to claim 6, characterized in that, The turbulent flow wind speed optimization module provides support for the following modules: Data interaction with the digital twin model: Obtain real-time working condition data through the digital twin model and continuously optimize the wind speed control strategy based on historical operation data; Support for the dynamic adjustment of the ANFIS control module: Provide real-time temperature and wind speed feedback for the ANFIS fuzzy inference system to help it dynamically adjust the membership function parameters and inference rules, and improve the temperature control accuracy and energy consumption efficiency; Support for the intelligent predictive maintenance module: Feedback problems such as parameter anomalies encountered during the execution of the actuator to improve the prediction accuracy. Data intercommunication with the mixed reality interaction module: Display the optimized wind speed distribution and temperature field status to the operator through the mixed reality interface.

8. The implementation method of the lithium battery device temperature balance and energy consumption optimization system based on digital twin according to claim 2, wherein, The intelligent predictive maintenance module is implemented in the following ways: Use deep learning algorithms to analyze the historical operation data and real-time data of the equipment, identify the change trend of the equipment health status, establish a health status evaluation model, and predict the performance degradation of the equipment under different working conditions. Combine the simulation results of the digital twin model to predict the possibility and time point of potential failures, accurately locate the fault position through the intelligent diagnosis function, and provide repair suggestions. According to the equipment health status and fault risk analysis results, formulate personalized maintenance plans and optimized operation strategies, automatically generate maintenance reports, and guide the operator to perform equipment maintenance. Through the mixed reality interaction module, present the predictive maintenance information to the operator in an intuitive way, support the operator to confirm and adjust the maintenance suggestions, and optimize the model parameters according to the actual maintenance effect.

9. The implementation method of the lithium battery equipment temperature balance and energy consumption optimization system based on digital twin according to claim 8, characterized in that, The intelligent predictive maintenance module supports the following modules: Data interaction with the digital twin module: Improve the accuracy of the digital twin model by real-time updating the equipment operation data and health status information, and enhance the bidirectional mapping ability between the virtual space and the physical space. Support for the ANFIS control module: Based on the equipment health status evaluation results, dynamically adjust the temperature control strategy, optimize energy consumption while ensuring the balanced distribution of the temperature field, and improve the efficiency and stability of the lithium battery equipment manufacturing process. Support for the spoiler wind speed optimization module: Through the predictive maintenance function, detect and solve parameter anomalies in advance, ensure the stable operation of the spoiler wind speed control system, and optimize the accuracy of the hot air flow and the uniformity of the temperature field distribution. Support for the mixed reality interaction module: Provide the operator with visual information on the real-time equipment health status and maintenance suggestions, improve the human-machine interaction efficiency, and mark the key part information through the mixed reality function to help the operator more intuitively understand and control the equipment status.

10. The implementation method of the lithium battery equipment temperature balance and energy consumption optimization system based on digital twin according to claim 2, characterized in that, The mixed reality interaction module is implemented in the following ways: Data collection and processing: Obtain the equipment operation data and environmental information through sensors and cameras, and combine deep learning algorithms to identify and label the key parts. Model training and deployment: Train the mixed reality display model based on historical data to achieve the automatic identification and information annotation functions of the key parts of the equipment. Hardware integration and testing: Integrate the mixed reality interaction module with the control system, sensors and actuators of the lithium battery equipment, and optimize the human-machine interaction experience through actual operation testing. The mixed reality interaction module supports the following modules: Work in collaboration with the digital twin module, receive real-time simulation data and visualize it to help the operator more intuitively understand the equipment status. It supports the parameter adjustment function of the ANFIS control module, dynamically adjusts the temperature control strategy through voice or gesture commands, and improves the system operation efficiency; accepts the wind speed distribution and temperature field status optimized by the module, and displays them to the operator to support the spoiler wind speed optimization module; it works with the intelligent predictive maintenance module to display predictive maintenance suggestions to the operator in the form of mixed reality, and provides an interactive interface for confirmation and execution.

Images