Box-type power supply storage and conversion cooperative control method and system based on digital twinning and AI

Abstract

The invention discloses a box-type power supply storage and conversion cooperative control method and system based on digital twinning and AI, and the method comprises the steps: detecting all parameters of a box-type power supply in real time through a power state monitoring module, and generating a high-fidelity digital twinning model through a digital twinning modeling module; the AI data processing module carries out deep analysis on model data and actual parameters and extracts features and laws, and then the energy storage management module generates optimized charging and discharging strategies. According to the method, the energy utilization efficiency is remarkably improved, unnecessary battery replacement operation is reduced through accurate monitoring and intelligent scheduling, and the battery replacement cost is reduced. Meanwhile, the optimized charging and discharging strategy prolongs the service life of the battery, and the long-term operation cost is further reduced. In addition, through real-time updating of the digital twinborn model and self-adaptive control of the AI, intelligence and adaptability of the system are enhanced, and the system can adapt to complex and changeable operation environments.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of box power supply management, specifically to a box power supply storage and replacement collaborative control method and system based on digital twinning and AI. BACKGROUND

[0002] With the continuous development of new energy technology, box power supply is increasingly widely used in various fields, such as electric vehicle charging, distributed energy storage, etc. In the use process of box power supply, energy storage management and replacement scheduling are two key links. Traditional box power supply management systems often lack real-time accurate monitoring of power supply status and efficient storage and replacement collaborative control, resulting in low energy utilization efficiency, high replacement cost, and poor user experience, etc. SUMMARY

[0003] In order to solve the problem that the existing box power supply management system lacks real-time accurate monitoring of power supply status and efficient storage and replacement collaborative control, the present application provides a box power supply storage and replacement collaborative control method and system based on digital twinning and AI. The specific technical scheme of the present application is as follows:

[0004] A box power supply storage and replacement collaborative control method based on digital twinning and AI, the control method comprising the following steps:

[0005] Detecting various parameters of the box power supply through the power supply status monitoring module, and then generating a digital twin model of the detected various parameters of the box power supply through the digital twin modeling module; performing data analysis on the data of the digital twin model and the various parameters of the box power supply through the AI data processing module, extracting features and rules in the data; generating charging and discharging strategies of the box power supply according to the various parameters of the box power supply and the features and rules extracted from the data through the energy storage management module.

[0006] Further, after generating the charging and discharging strategies of the box power supply, the energy storage management module obtains the user's replacement demand through the user interaction module; the replacement scheduling module simulates the replacement process according to the user's replacement demand, combined with the various parameters of the box power supply provided by the power supply status monitoring module and the digital twin model; the AI data processing module generates an optimal replacement scheduling scheme using AI algorithms according to the simulation results, wherein the replacement scheduling scheme includes replacement time, replacement location and selection of replacement equipment.

[0007] Further, the AI data processing module generates an optimal replacement scheduling scheme using AI algorithms according to the simulation results, comprising the following steps:

[0008] The AI data processing module takes the shortest replacement time and the lowest replacement cost as the objective function, and the location, state and traffic conditions of the replacement equipment as the constraint conditions, constructs the objective function of the replacement scheduling, and the objective function is represented as:

[0009] min(t travel +t swap +c cost )

[0010] wherein, t travel is the moving time of the load to reach the battery swap device, t swap is the battery swap operation time, c cost is the battery swap cost;

[0011] The AI data processing module solves the objective function by a genetic algorithm or an ant colony algorithm to obtain an optimal battery swap scheduling scheme; the AI data processing module transmits the optimal battery swap scheduling scheme to a target battery swap device that executes the optimal battery swap scheduling scheme, to guide the target battery swap device to perform battery swap on the box-type power supply of the load.

[0012] Further, the digital twin modeling module generates a digital twin model of the detected parameters of the box-type power supply, including the following steps:

[0013] The digital twin modeling module receives the parameters of the box-type power supply detected by the power state monitoring module, wherein the parameters of the box-type power supply include physical parameters and environmental parameters, the physical parameters include but are not limited to the voltage, current, battery temperature, battery internal resistance and battery capacity of the box-type power supply battery, and the environmental parameters include but are not limited to the environmental temperature, humidity and light intensity of the environment where the box-type power supply is located; the digital twin modeling module uses three-dimensional modeling and digital twin technology to construct a digital twin model of the box-type power supply according to the received physical parameters and environmental parameters, to realize real-time mapping and dynamic simulation of the physical entity of the box-type power supply; the digital twin modeling module receives the physical parameters and environmental parameters of the box-type power supply detected by the power state monitoring module every set time, and updates the digital twin model according to the received physical parameters and environmental parameters of the box-type power supply.

[0014] Further, the AI data processing module performs data analysis on the data of the digital twin model and the parameters of the box-type power supply, including the following steps:

[0015] The AI data processing module obtains the parameters of the box-type power supply from the power state detection module, and obtains the real-time mapping and dynamic simulation data from the digital twin model; the AI data processing module performs cleaning, noise reduction and normalization processing on the obtained data to remove noise and outliers in the data, and converts the processed data into a set analysis format; the AI data processing module uses artificial intelligence algorithms to analyze and mine the data in the converted format, to extract features and rules in the data; wherein the artificial intelligence algorithms include but are not limited to machine learning algorithms or deep learning algorithms; the AI data processing module learns from historical data to establish a power state prediction model to predict the remaining capacity and life parameters of the power supply.

[0016] Further, the AI data processing module establishes a power state prediction model, including the following steps:

[0017] The AI data processing module establishes a power state prediction model using a prediction model construction algorithm, wherein the prediction model construction algorithm includes but is not limited to support vector machine (SVM) or long short-term memory network (LSTM); the AI data processing module receives the voltage V, current I and battery temperature T of the time series t of the box power supply, and generates a prediction model of the battery remaining capacity S, and the prediction model is expressed as:

[0018] S = f(V t ,I t ,T t ,…,V t-n ,I t-n ,T t-n )

[0019] Wherein, f is a prediction function, and n is the size of the time window.

[0020] Further, the energy storage management module generates a charging strategy for the box power supply according to the parameters of the box power supply and the characteristics and rules extracted from the data, including the following steps:

[0021] The energy storage management module dynamically adjusts the charging current of the battery of the box power supply according to the remaining capacity and temperature of the battery of the box power supply, and the adjustment formula of the charging current I c is:

[0022]

[0023] Wherein, I max is the maximum charging current, C r is the battery remaining capacity, and C max is the rated capacity of the battery.

[0024] Further, the energy storage management module generates a discharging strategy for the box power supply according to the parameters of the box power supply and the characteristics and rules extracted from the data, including the following steps:

[0025] The energy storage management module adjusts the discharge amount and discharge current according to the demand of the load connected with the box power supply and the state of the battery of the box power supply.

[0026] Further, when the energy storage management module charges or discharges the box power supply, the power state monitoring module detects the parameters of the box power supply in charging or discharging; the power state monitoring module judges whether the state of the box power supply is normal according to the parameters of the box power supply, and sends an alarm signal to the user when an abnormal state is detected, wherein the abnormal state includes but is not limited to battery overheating, overcharging or overdischarging.

[0027] A box-type power supply storage and replacement collaborative control system based on digital twinning and AI, which executes the box-type power supply storage and replacement collaborative control method based on digital twinning and AI described above, the control system comprises a digital twinning modeling module, an AI data processing module, a power state monitoring module, an energy storage management module, a power replacement scheduling module, a communication module, a user interaction module and a safety protection module; the power state monitoring module is used for detecting various parameters of the box-type power supply; the digital twinning modeling module is used for constructing a digital twinning model of the box-type power supply according to the various parameters of the box-type power supply; the AI data processing module is used for extracting features and rules of data from the data of the digital twinning model and the various parameters of the box-type power supply; the energy storage management module is used for managing the power replacement process of the box-type power supply based on the digital twinning model and the AI algorithm; the power replacement scheduling module is used for generating an optimal power replacement scheduling scheme according to the simulation results of the digital twinning model; the communication module is used for communication between the modules in the system and between the system and external devices; the user interaction module is used for providing an interface for the user to interact with the system; and the safety protection module is used for safety protection of the box-type power supply system, which includes physical safety protection and information safety protection.

[0028] The box-type power supply storage and replacement collaborative control method based on digital twinning and AI of the present application solves the problems existing in the prior art through innovative technical means, achieves significant technical effects, and the specific effects are as follows:

[0029] Precise monitoring and real-time feedback: the power state monitoring module monitors the various parameters of the box-type power supply in real time, which can accurately grasp the current state of the power supply. This real-time monitoring capability enables the system to timely adjust the charging and discharging strategies, avoiding the energy waste caused by delayed monitoring in traditional systems.

[0030] Intelligent data analysis and strategy generation: the AI data processing module deeply analyzes the data of the digital twinning model and the actual parameters of the box-type power supply, extracts the features and rules in the data. Based on these features and rules, the energy storage management module can generate more optimized charging and discharging strategies to maximize energy utilization efficiency. For example, when the load is low, the system can intelligently adjust the charging power to avoid overcharging; when the load is high, the discharging strategy is optimized to meet the demand while prolonging the battery life.

[0031] Optimized power replacement scheduling: through digital twinning modeling and AI data analysis, the system can predict the remaining power and usage state of the box-type power supply, and plan the power replacement time in advance. This precise scheduling capability reduces unnecessary power replacement operations and lowers the power replacement frequency, thereby significantly reducing the power replacement cost. BRIEF DESCRIPTION OF DRAWINGS

[0032] Fig. 1A flowchart of a box-type power supply storage and replacement collaborative control method based on digital twinning and AI in an embodiment of the present application;

[0033] Fig. 2 A signal transmission schematic diagram of a box-type power supply storage and replacement collaborative control system based on digital twinning and AI in an embodiment of the present application;

[0034] Fig. 3 A working principle diagram of an AI data processing module in an embodiment of the present application;

[0035] Fig. 4 A working principle diagram of a replacement scheduling module in an embodiment of the present application. DETAILED DESCRIPTION

[0036] Embodiments of the present application will be described in detail below, with examples shown in the accompanying drawings, wherein the same or similar reference numbers represent the same or similar elements or elements having the same or similar functions throughout.

[0037] In the description of the present application, it should be noted that for orientation words, such as the terms "center", "transverse", "longitudinal", "length", "width", "thickness", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. indicate the orientation and positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and cannot be understood as limiting the specific protection scope of the present application.

[0038] In addition, if the terms "first", "second" are used for description purposes only, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features. Therefore, the "first" and "second" features defined can explicitly or implicitly include one or more of the features, and in the description of the present application, the meaning of "at least" is one or more, unless otherwise explicitly specified and limited.

[0039] In the present application, unless otherwise explicitly specified and limited, if the terms "assembly", "connection", "connection" are used, they should be broadly understood, for example, they can be fixedly connected, or can be detachably connected, or integrally connected; can be mechanically connected; can be directly connected, or connected through an intermediate medium; can be connected internally between two elements. For those skilled in the art, the specific meaning of the above-mentioned terms in the present application can be understood according to the specific circumstances.

[0040] In the application, unless otherwise specified and limited, "above" or "below" the second feature can include direct contact between the first and second features, or contact between the first and second features through another feature between them. Furthermore, "above," "below," and "over" the second feature includes the first feature being directly above or diagonally above the second feature, or simply indicating that the first feature is at a higher horizontal level than the second feature. "Above," "below," and "below" the second feature includes the first feature being directly below or diagonally below the second feature, or simply indicating that the first feature is at a lower horizontal level than the second feature.

[0041] The following description, in conjunction with the accompanying drawings, further illustrates specific embodiments of this application, making the technical solution and its beneficial effects clearer and more explicit. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, but should not be construed as limiting it.

[0042] like Figs. 1 to 4 As shown, a collaborative control method for a box-type power supply storage and swapping system based on digital twins and AI is proposed. This control method includes the following steps:

[0043] The power status monitoring module detects various parameters of the box-type power supply, and then the digital twin modeling module generates a digital twin model of the detected parameters. The AI ​​data processing module analyzes the data from the digital twin model and the box-type power supply parameters to extract features and patterns. Finally, the energy storage management module generates charging and discharging strategies for the box-type power supply based on its parameters and the extracted features and patterns.

[0044] In one embodiment, after generating the charging and discharging strategies for the power supply, the energy storage management module obtains the user's battery swapping needs through the user interaction module. The battery swapping scheduling module simulates the battery swapping process based on the user's needs, combined with various parameters of the box-type power supply provided by the power status monitoring module and a digital twin model. The AI ​​data processing module uses AI algorithms to generate the optimal battery swapping scheduling scheme based on the simulation results. This scheme includes the selection of battery swapping time, location, and equipment. The battery swapping equipment is the device that provides or releases power to the box-type power supply, and the location is the location of the swapping equipment and the current location of the box-type power supply.

[0045] A digital twin is a virtual digital model that accurately reflects and simulates the physical properties, behavior, and performance of a physical entity (such as a device, system, or process) using real-time data and advanced modeling techniques. A digital twin can not only simulate the current state of a physical entity but also predict its future behavior and optimize its performance through feedback mechanisms.

[0046] Building a digital twin model usually includes the following steps:

[0047] Data collection: Sensor data: Collect real-time operation data such as temperature, pressure, current, voltage, etc. through sensors installed on physical entities. Historical data: Collect historical operation data of physical entities for model training and verification. Environmental data: Collect data related to the operating environment of physical entities, such as weather conditions, load changes, etc.

[0048] Physical modeling: Geometric modeling: Build a geometric model of the physical entity, including its shape, size and structure. Physical property modeling: Define the physical properties of the physical entity, such as material characteristics, thermal conductivity, electrical conductivity, etc. Behavior modeling: Establish a behavior model of the physical entity to describe its dynamic behavior and response characteristics.

[0049] Data fusion and processing: Data cleaning: Remove noise and outliers in collected data. Data fusion: Fuse multi-source data to form a complete data set. Data standardization: Convert data to a unified format and unit for subsequent processing.

[0050] Model construction and verification: Model construction: Use physical models and data-driven methods to build digital twin models. Finite element analysis (FEA), computational fluid dynamics (CFD), etc. physical modeling methods can be used in combination with machine learning and deep learning algorithms. Model verification: Compare the model with the actual operation data of the physical entity to verify the accuracy and reliability of the model.

[0051] As one of the embodiments, the AI data processing module generates the optimal battery replacement scheduling scheme according to the simulation results using AI algorithms, including the following steps:

[0052] The AI data processing module takes the shortest battery replacement time and the lowest battery replacement cost as the objective function, where the battery replacement time is the time for the battery box to complete charging or discharging, and the battery replacement cost is the distance between the battery box and the battery replacement device, which is the travel distance. The location, state (whether the battery replacement device is working) and traffic conditions (according to the map display, the current traffic conditions of the battery box moving to the location of the battery replacement device) of the battery replacement device are used as constraint conditions to construct the objective function of the battery replacement scheduling, which is represented as:

[0053] min(t travel +t swap +c cost )

[0054] Where t travel is the moving time of the load to the battery replacement device, t swap is the battery replacement operation time, and c cost is the battery replacement cost.

[0055] The AI data processing module solves the objective function by a genetic algorithm or an ant colony algorithm to obtain an optimal battery replacement scheduling scheme. The AI data processing module transmits the optimal battery replacement scheduling scheme to a target battery replacement device that executes the optimal battery replacement scheduling scheme to guide the target battery replacement device to replace the battery of the box-type power supply of the load. The genetic algorithm (GA) is a search and optimization technique based on the principles of natural selection and genetics. It simulates the biological evolution process and gradually improves the quality of candidate solutions through selection, crossover (recombination), and mutation operations. The ant colony algorithm (ACO) is an optimization algorithm that simulates the foraging behavior of ants. Ants release pheromones to mark paths during foraging, and other ants choose paths based on the concentration of pheromones to find the shortest path.

[0056] As one of the embodiments, the digital twin modeling module generates a digital twin model of the detected parameters of the box-type power supply, including the following steps:

[0057] The digital twin modeling module receives the parameters of the box-type power supply detected by the power state monitoring module, wherein the parameters of the box-type power supply include physical parameters and environmental parameters, the physical parameters include but are not limited to the voltage, current, battery temperature, battery resistance, and battery capacity of the box-type power supply battery, and the environmental parameters include but are not limited to the environmental temperature, humidity, and light intensity of the environment in which the box-type power supply is located. The digital twin modeling module uses three-dimensional modeling and digital twin technology to construct a digital twin model of the box-type power supply according to the received physical parameters and environmental parameters, and to realize real-time mapping and dynamic simulation of the physical entity of the box-type power supply. The digital twin modeling module receives the physical parameters and environmental parameters of the box-type power supply detected by the power state monitoring module every set time, and updates the digital twin model according to the received physical parameters and environmental parameters of the box-type power supply, to realize real-time updating and optimization of the digital twin model, and to ensure the consistency of the model and the physical entity. The set time can be 5 minutes, 10 minutes, 15 minutes, or 20 minutes, etc.

[0058] As one of the embodiments, the AI data processing module performs data analysis on the data of the digital twin model and the parameters of the box-type power supply, including the following steps:

[0059] The AI data processing module obtains various parameters of the box-type power supply from the power state detection module and obtains real-time mapping and dynamic simulation data from the digital twin model. The AI data processing module cleans, denoises, and normalizes the obtained data to remove noise and outliers in the data, and converts the processed data into a set analysis format. The AI data processing module analyzes and mines the data in the converted format using artificial intelligence algorithms, extracting features and patterns from the data. The artificial intelligence algorithms include but are not limited to machine learning algorithms or deep learning algorithms. The AI data processing module learns from historical data to establish a power state prediction model to predict the remaining capacity and life parameters of the power supply.

[0060] Machine learning is a branch of artificial intelligence that enables computer systems to automatically learn and improve from data without explicit programming. Major algorithm categories include supervised learning, linear regression, logistic regression, support vector machines (SVM), decision trees, random forests, unsupervised learning, K-means clustering, hierarchical clustering, reinforcement learning, Q-learning, and deep Q-networks (DQN).

[0061] Deep learning is a subfield of machine learning, based on deep structure of artificial neural network, through multi-level neural network to automatically learn the feature representation of data. Main algorithm categories: feedforward neural networks (FNN), multilayer perceptron (MLP), convolutional neural networks (CNN), recurrent neural networks (RNN), long short-term memory (LSTM), gated recurrent unit (GRU), generative adversarial networks (GAN) and DCGAN (Deep Convolutional GAN), steps: use convolutional layer and deconvolutional layer in generator and discriminator, generate high-quality image data.

[0062] As one of the embodiments, the AI data processing module establishes a power state prediction model, including the following steps:

[0063] The AI data processing module uses a prediction model construction algorithm to establish a power state prediction model, wherein the prediction model construction algorithm includes but is not limited to support vector machine SVM or long short-term memory network LSTM. The AI data processing module receives the voltage V, current I and battery temperature T of the time series t of the box power supply, generates a prediction model of the battery remaining capacity S, and the prediction model is expressed as:

[0064] S = f(V t ,I t ,T t ,…,V t-n ,I t-n ,T t-n )

[0065] Wherein, f is a prediction function, and n is the size of the time window.

[0066] Of course, the user can also generate other prediction models according to actual needs, such as battery charging time, battery service life, battery charging temperature or battery charging current change prediction model.

[0067] As one of the embodiments, the energy storage management module generates a charging strategy for the box power supply according to the parameters of the box power supply and the characteristics and rules extracted from the data, including the following steps:

[0068] The energy storage management module dynamically adjusts the charging current of the battery of the box-type power supply according to the remaining capacity and temperature of the battery of the box-type power supply. When the remaining capacity of the battery is low, a larger charging current is used for fast charging; when the battery is close to full, a smaller charging current is used for trickle charging to protect the battery. The adjustment formula of the charging current I c is:

[0069]

[0070] wherein I max is the maximum charging current, C r is the remaining capacity of the battery, and C max is the rated capacity of the battery.

[0071] As one of the embodiments, the energy storage management module generates a discharging strategy for the box-type power supply according to the parameters of the box-type power supply and the characteristics and rules in the extracted data, including the following steps:

[0072] The energy storage management module adjusts the discharging amount and discharging current according to the demand of the load connected to the box-type power supply and the state of the battery of the box-type power supply. For example, when the box-type power supply needs to release the remaining capacity of the battery from 90% to 50%, the minimum amount of electricity required for the subsequent trip of the load needs to be considered. Assuming it is 60%, the battery swapping device will only release the remaining capacity of the box-type power supply to 60% or 65%. The load is an electric ship or an electric vehicle powered by the box-type power supply.

[0073] As one of the embodiments, when the energy storage management module charges or discharges the box-type power supply, the power state monitoring module detects the parameters of the box-type power supply during charging or discharging. The power state monitoring module determines whether the state of the box-type power supply is normal according to the parameters of the box-type power supply. When an abnormal state is detected, an alarm signal is sent to the user, wherein the abnormal state includes but is not limited to battery overheating, overcharging or overdischarging.

[0074] A box-type power supply storage and replacement collaborative control system based on digital twinning and AI, which executes the above-mentioned box-type power supply storage and replacement collaborative control method based on digital twinning and AI. The control system includes a digital twinning modeling module, an AI data processing module, a power state monitoring module, an energy storage management module, a battery swapping scheduling module, a communication module, a user interaction module and a safety protection module. The power state monitoring module is used to detect the parameters of the box-type power supply. In actual application, various sensors such as voltage sensors, current sensors and temperature sensors are installed on the box-type power supply to collect physical parameters and environmental parameters of the power supply in real time.

[0075] The state parameters in the power state monitoring module include but are not limited to battery voltage, current, temperature, internal resistance, and remaining capacity. The monitored data is transmitted in real time to the digital twin modeling module and the AI data processing module, providing real-time data support for the update of the digital twin model and the analysis of the AI algorithm. At the same time, the module can also provide real-time warning for the power state. When an abnormal state is detected, including but not limited to battery overheating, overcharging, and overdischarging, an alarm signal is sent in time. The power state monitoring module monitors the power state in real time and sends a warning when an abnormality is detected. The energy storage management module formulates charging and discharging strategies based on the monitoring results and prediction models, such as automatically starting the charging program when the battery remaining capacity is below 20%, and dynamically adjusting the charging current according to the battery temperature. The battery replacement scheduling module receives the battery replacement demand submitted by the user through the mobile phone APP, combines the current power state and traffic information, and uses genetic algorithm to generate the optimal battery replacement route and time to schedule the battery replacement equipment to the designated location for battery replacement operation.

[0076] The communication module ensures real-time data transmission between modules. Users can view the power state, charging progress, and battery replacement scheduling information in real time through the mobile phone APP and make relevant settings. The security protection module monitors the system in real time to prevent illegal intrusion and data leakage.

[0077] The digital twin modeling module is used to construct a digital twin model of the box-type power supply based on various parameters of the box-type power supply. The digital twin modeling module collects physical parameters of the box-type power supply through a sensor network, including but not limited to voltage, current, temperature, battery capacity, and environmental parameters, including but not limited to temperature, humidity, and light intensity. Using three-dimensional modeling software and digital twin technology, a virtual model of the box-type power supply is constructed based on the collected parameters, realizing real-time mapping and dynamic simulation of the physical entity of the box-type power supply. The module can also update and optimize the digital twin model in real time to ensure consistency between the model and the physical entity.

[0078] The AI data processing module is used to extract features and rules from the data of the digital twin model and various parameters of the box-type power supply. The AI data processing module includes a data acquisition unit, a data preprocessing unit, and a data analysis unit. The data acquisition unit in the AI data processing module is used to collect data from the sensor network, digital twin model, and other external data sources. The data preprocessing unit cleans, denoises, and normalizes the collected data, removing noise and outliers, and converting the data into a format suitable for analysis. The data analysis unit uses artificial intelligence algorithms, including but not limited to machine learning algorithms or deep learning algorithms, to analyze and mine the preprocessed data, extract features and rules from the data, and provide support for subsequent decision-making. Through learning from historical data, a power state prediction model is established to predict the remaining capacity and life parameters of the power supply.

[0079] The energy storage management module is used to manage the battery replacement process of the box-type power supply based on the digital twin model and AI algorithm. The energy storage management module formulates reasonable charging and discharging strategies according to the real-time data provided by the power supply state monitoring module and the analysis results of the AI data processing module, realizes efficient utilization and life extension of the battery; in the charging process, the charging current and voltage are dynamically adjusted according to the remaining capacity and temperature parameters of the battery, to avoid overcharging and undercharging; in the discharging process, the power is reasonably distributed according to the load demand and battery state, to ensure stable operation of the system.

[0080] The battery replacement scheduling module is used to generate the optimal battery replacement scheduling scheme according to the simulation results of the digital twin model. The battery replacement scheduling module obtains the user's battery replacement demand through the user interaction module, combines the power supply state information provided by the power supply state monitoring module and the simulation results of the digital twin model on the battery replacement process, and generates the optimal battery replacement scheduling scheme using AI algorithm; the battery replacement scheduling scheme includes battery replacement time, battery replacement location, and selection of battery replacement equipment; to maximize the battery replacement efficiency and minimize the battery replacement cost; at the same time, the battery replacement scheduling module can also interact with the external traffic network and energy supply network to ensure the smooth progress of the battery replacement process

[0081] The communication module is used for communication between the modules in the system and between the system and external devices. The communication module uses multiple communication protocols, including but not limited to Bluetooth, Wi-Fi, 4G / 5G, to ensure real-time data transmission and reliable interaction; it can transmit the virtual model data generated by the digital twin modeling module, the analysis results of the AI data processing module, and the real-time data of the power supply state monitoring module to other modules and external devices, while receiving instructions and data from external devices, to realize remote monitoring and management of the system.

[0082] The user interaction module is used to provide an interface for users to interact with the system. In the user interaction module, users can real-time understand the state information of the box-type power supply, submit battery replacement demand, and set personalized management strategies; at the same time, the user interaction module can also push the system's warning information and battery replacement reminders to the user, to improve user experience. The human-computer interaction module provides an intuitive and convenient operation interface for the operator, including a target display interface, a parameter setting interface, and a warning information interface.

[0083] The security protection module is used for the security protection of the box-type power supply system, and the security protection includes physical security protection and information security protection. The physical security protection in the security protection module is realized by installing an access control system, a monitoring camera, and fire and explosion prevention equipment; the information security protection is realized by using encryption technology, authentication technology, and access control technology to ensure the safe transmission and storage of system data and prevent data from being stolen, tampered with, and damaged.

[0084] The box-type power supply storage and replacement collaborative control method based on digital twinning and AI of the application solves the problems in the prior art through innovative technical means, achieves significant technical effects, and specifically as follows:

[0085] Precise monitoring and real-time feedback: the power state monitoring module monitors the parameters of the box-type power supply in real time, and can accurately grasp the current state of the power supply. This real-time monitoring capability enables the system to timely adjust the charging and discharging strategies, avoiding the energy waste caused by untimely monitoring in traditional systems.

[0086] Intelligent data analysis and strategy generation: the AI data processing module deeply analyzes the data of the digital twinning model and the actual parameters of the box-type power supply, extracts the features and rules in the data. Based on these features and rules, the energy storage management module can generate more optimized charging and discharging strategies to maximize energy utilization efficiency. For example, when the load is low, the system can intelligently adjust the charging power to avoid overcharging. When the load is high, the discharging strategy is optimized to meet the demand while prolonging the battery life.

[0087] Optimized replacement scheduling: through the digital twinning model and AI data analysis, the system can predict the remaining power and usage state of the box-type power supply, and plan the replacement time in advance. This precise scheduling capability reduces unnecessary replacement operations and reduces the replacement frequency, thereby significantly reducing the replacement cost.

[0088] Prolonging battery life: optimized charging and discharging strategies can effectively reduce the number of charging and discharging times and deep charging and discharging of the battery, prolonging the service life of the battery. The prolongation of the battery life not only reduces the frequency of battery replacement, but also reduces the performance degradation caused by battery aging, further reducing long-term operating costs.

[0089] Real-time monitoring and early warning: the power state monitoring module can monitor the state of the box-type power supply in real time and issue an early warning in a timely manner when an anomaly is detected. This real-time monitoring and early warning function improves the reliability and safety of the system, and users can always know the power state to avoid inconvenience caused by sudden failures.

[0090] Efficient scheduling and fast response: Through AI-driven storage and exchange collaborative control, the system can quickly respond to users' electricity demand and optimize the exchange and charging process. For example, in the electric vehicle charging scenario, the system can quickly schedule appropriate power sources for charging according to the vehicle's power demand and the current status of the box power supply, reducing user waiting time.

[0091] Application of digital twin technology: The digital twin model can accurately simulate the running state of the box power supply, providing a virtual "digital twin" for the system. Through this digital twin, the system can test and optimize various strategies in a virtual environment, thereby achieving more efficient control in actual operation.

[0092] AI-driven adaptive control: The AI data processing module can automatically adjust the control strategy according to real-time data, enabling the system to adapt to different operating environments and load changes. This adaptive control capability improves the flexibility and robustness of the system, enabling it to operate stably in complex and variable scenarios.

[0093] In summary, the application combines digital twin technology and AI algorithms to achieve precise monitoring, intelligent analysis, and optimized control of the box power supply, significantly improving energy utilization efficiency, reducing exchange costs, enhancing user experience, and enhancing the intelligence and adaptability of the system.

[0094] In the description of the specification, the description of the terms "in combination with an embodiment", "preferably", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in combination with the embodiment or example are included in at least one embodiment or example of the present application, and the illustrative description of the above terms in the specification does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. The connection described in the description of the specification has obvious effects and practical effects.

[0095] Through the above description of structure and principle, those skilled in the art should understand that the present application is not limited to the above specific embodiments, and improvements and alternatives using techniques known in the art on the basis of the present application all fall within the scope of the present application, which should be defined by the claims.

Claims

1. A method for coordinated control of box-type power supply storage and switching based on digital twin and AI, characterized in that, The control method includes the following steps: The power status monitoring module detects various parameters of the box-type power supply, and then the digital twin modeling module generates a digital twin model of the detected parameters of the box-type power supply. The AI ​​data processing module analyzes the data of the digital twin model and various parameters of the box power supply to extract features and patterns from the data. The energy storage management module generates charging and discharging strategies for the box-type power supply based on its various parameters and the features and patterns extracted from the data.

2. The box-type power supply storage and switching collaborative control method based on digital twin and AI according to claim 1, characterized in that, After generating the charging and discharging strategies for the upward power source, the energy storage management module obtains the user's battery swapping needs through the user interaction module. The battery swapping scheduling module simulates the battery swapping process based on the user's battery swapping needs and the various parameters of the box-type power supply and the digital twin model provided by the power status monitoring module. The AI ​​data processing module uses AI algorithms to generate the optimal battery swapping scheduling plan based on the simulation results. The battery swapping scheduling plan includes the selection of battery swapping time, battery swapping location, and battery swapping equipment.

3. The box-type power supply storage and switching collaborative control method based on digital twin and AI according to claim 2, characterized in that, The AI ​​data processing module uses AI algorithms to generate the optimal battery swapping scheduling scheme based on the simulation results, including the following steps: The AI ​​data processing module uses the shortest battery swapping time and lowest battery swapping cost as objective functions, and the location, status, and traffic conditions of the battery swapping equipment as constraints, to construct an objective function for battery swapping scheduling. The objective function is expressed as follows: min(t travel +t swap +c cost ) Among them, t travel t is the time it takes for the load to travel to the battery swapping equipment. swap For battery swapping operation time, c cost For the cost of battery swapping; The AI ​​data processing module solves the objective function using a genetic algorithm or an ant colony algorithm to obtain the optimal battery swapping scheduling scheme. The AI ​​data processing module will obtain the optimal battery swapping scheduling plan and transmit it to the target battery swapping equipment that executes the optimal battery swapping scheduling plan, so as to guide the target battery swapping equipment to swap the load's box-type power supply.

4. The box-type power supply storage and switching collaborative control method based on digital twin and AI according to claim 3, characterized in that, The digital twin modeling module generates a digital twin model from the detected parameters of the box-type power supply, including the following steps: The digital twin modeling module receives various parameters of the box power supply detected by the power status monitoring module. These parameters include physical parameters and environmental parameters. The physical parameters include, but are not limited to, the voltage, current, temperature, internal resistance, and capacity of the box power supply battery. The environmental parameters include, but are not limited to, the ambient temperature, humidity, and light intensity of the environment in which the box power supply is located. The digital twin modeling module utilizes 3D modeling and digital twin technology to construct a digital twin model of the box-type power supply based on the received physical and environmental parameters, enabling real-time mapping and dynamic simulation of the physical entity of the box-type power supply. The digital twin modeling module receives the physical and environmental parameters of the box-type power supply detected by the power status check module at set intervals, and updates the digital twin model based on the received physical and environmental parameters of the box-type power supply.

5. The box-type power supply storage and switching collaborative control method based on digital twin and AI according to claim 4, characterized in that, The AI ​​data processing module performs data analysis on the digital twin model data and various parameters of the box-type power supply, including the following steps: The AI ​​data processing module obtains various parameters of the box-type power supply from the power status detection module, and obtains real-time mapping and dynamic simulation data from the digital twin model; The AI ​​data processing module cleans, denoises, and normalizes the acquired data to remove noise and outliers, and converts the processed data into a set analysis format. The AI ​​data processing module uses artificial intelligence algorithms to analyze and mine the converted data, extracting features and patterns from the data; among them, artificial intelligence algorithms include, but are not limited to, machine learning algorithms or deep learning algorithms; The AI ​​data processing module learns from historical data to build a power state prediction model, predicting the remaining capacity and lifespan parameters of the power supply.

6. The box-type power supply storage and switching collaborative control method based on digital twin and AI according to claim 5, characterized in that, The AI ​​data processing module establishes a power state prediction model, including the following steps: The AI ​​data processing module uses a predictive model building algorithm to establish a power state prediction model. The predictive model building algorithm includes, but is not limited to, support vector machine (SVM) or long short-term memory network (LSTM). The AI ​​data processing module receives the voltage V, current I, and battery temperature T of the box-type power supply based on the time series t, and generates a prediction model for the remaining battery capacity S. This prediction model is expressed as follows: S=f(V t ,I t ,T t ,…,V t-n ,I t-n ,T t-n ) Where f is the prediction function and n is the time window size.

7. The box-type power supply and energy storage cooperative control method based on digital twin and AI according to claim 6, characterized in that, The energy storage management module generates a charging strategy for the box-type power supply based on its various parameters and the features and patterns extracted from the data. This strategy includes the following steps: The energy storage management module dynamically adjusts the charging current of the battery in the box-type power supply based on the remaining capacity and temperature of the battery. The charging current I... c The adjustment formula is: Among them, I max For the maximum charging current, C r For the remaining battery capacity, C max This refers to the battery's rated capacity.

8. The box-type power supply storage and switching collaborative control method based on digital twin and AI according to claim 7, characterized in that, The energy storage management module generates a discharge strategy for the box-type power supply based on various parameters and features and patterns extracted from the data, including the following steps: The energy storage management module adjusts the discharge amount and discharge current based on the load requirements connected to the box power supply and the battery status of the box power supply.

9. The box-type power supply storage and switching collaborative control method based on digital twin and AI according to claim 8, characterized in that, When the energy storage management module charges or discharges the box-type power supply, the power status monitoring module detects various parameters of the box-type power supply during charging or discharging. The power status monitoring module determines whether the power supply is in normal condition based on various parameters of the box power supply. When an abnormal condition is detected, an alarm signal is issued to the user. Abnormal conditions include, but are not limited to, battery overheating, overcharging, or over-discharging.

10. A box-type power storage and switching collaborative control system based on digital twin and AI, characterized in that, The control system implements the box-type power storage and swapping collaborative control method based on digital twin and AI as described in any one of claims 1 to 9. The control system includes a digital twin modeling module, an AI data processing module, a power status monitoring module, an energy storage management module, a battery swapping scheduling module, a communication module, a user interaction module, and a safety protection module. The power status monitoring module is used to detect various parameters of the box-type power supply; The digital twin modeling module is used to construct a digital twin model of the box-type power supply based on various parameters of the box-type power supply. The AI ​​data processing module is used to extract the features and patterns of the data from the digital twin model and various parameters of the box power supply. The energy storage management module is used to manage the battery swapping process of the box-type power supply based on a digital twin model and AI algorithms. The battery swapping scheduling module is used to generate the optimal battery swapping scheduling scheme based on the simulation results of the digital twin model. The communication module is used for communication between modules within the system and between the system and external devices; The user interaction module is used to provide users with an interface for interacting with the system; The security protection module is used to provide security protection for the box-type power supply system, including physical security protection and information security protection.

Images