Signal light control method and system for mobile power charging device

Abstract

The present invention relates to the technical field of signal light control, and in particular to a signal light control method and system for a mobile power charging device. The method comprises the following steps: obtaining an internal structure diagram of a mobile power charging device; performing component visual recognition on the internal structure diagram of the mobile power charging device, and performing three-dimensional topological structure modeling to construct a three-dimensional topological model of the charging device; obtaining multi-dimensional working state parameters of the mobile power charging device; performing deep state feature learning on the multi-dimensional working state parameters to construct a working state map of the charging device; performing dynamic state mapping on the three-dimensional topological model of the charging device based on the working state map of the charging device to construct a dynamic operation twin topological model; performing dynamic operation evolution simulation on the dynamic operation twin topological model to obtain a dynamic state evolution rendering model. The present invention more intuitively and efficiently reflects the current operating state of the mobile power charging device by adjusting the dynamic display of the signal light in real time.

Description

Technical Field

[0001] The present invention relates to the technical field of signal light control, and in particular to a signal light control method and system of a mobile power charging device. Background Art

[0002] With the rapid development of electronic information technology, mobile power has become an important electronic device that is indispensable in people's daily life. As a key component of power management, the working state of the mobile power charging device directly affects the performance and service life of the mobile power. During long-term use, the mobile power charging device may have various hidden faults, such as battery capacity attenuation, controller abnormality, connection line damage, etc. Once these problems occur, they will have a serious impact on the charging performance. However, most of the mobile power charging devices on the market can only provide a unified signal light output, which is difficult to fully reflect the operation status of each component of the charging device and cannot timely discover hidden fault hazards. At the same time, it is difficult for users to accurately judge the use status of the charging device and cannot take effective preventive measures, thereby increasing the user's use risk. Therefore, it is urgently necessary to develop an intelligent mobile power charging device signal light control method, so that the working status of the mobile power charging device can be reflected in real time. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a signal light control method and system for a mobile power charging device to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides a signal light control method for a mobile power charging device, comprising the following steps:

[0005] Step S1: obtaining an internal structure diagram of a mobile power charging device; performing component visual recognition on the internal structure diagram of the mobile power charging device, and performing three-dimensional topological structure modeling to construct a three-dimensional topological model of the charging device;

[0006] Step S2: Acquire multi-dimensional working state parameters of the mobile power charging device; perform deep state feature learning on the multi-dimensional working state parameters to construct a working state map of the charging device;

[0007] Step S3: dynamically mapping the three-dimensional topological model of the charging device based on the working state map of the charging device to construct a dynamic operation twin topological model;

[0008] Step S4: simulate the dynamic operation evolution of the dynamic operation twin topology model, and perform component state evolution visualization rendering to obtain a dynamic state evolution rendering model;

[0009] Step S5: Calculate component load requirements and component failure probability based on the dynamic state evolution rendering model.

[0010] To obtain the predicted value of component load demand and the failure probability value of each component;

[0011] Step S6: Dynamically control the traffic light of the mobile power charging device according to the predicted value of the component load demand and the failure probability value of each component to construct a traffic light control strategy.

[0012] The present invention helps to understand the device composition and component functions by obtaining the internal structure diagram and performing visual identification of components, providing a basis for subsequent analysis. Constructing a three-dimensional topological model of the charging device can help visualize the device structure and help better understand the design and layout of the device. Deep state feature learning and working state map construction help to fully understand the working state of the charging device and provide detailed data support for subsequent analysis. Constructing a working state map of the charging device can help identify the relationship between different states of the device and provide a more accurate basis for traffic light control. Dynamic state mapping of the three-dimensional topological model based on the working state map helps to simulate the operation of the device under different working states and improve the pertinence of the control strategy. Constructing a dynamic operation twin topological model can achieve real-time monitoring and feedback, provide support for the flexibility and accuracy of the traffic light control strategy, and perform dynamic operation evolution simulation. Simulation and state visualization rendering can help simulate the changes of the device in actual operation, provide an intuitive reference for the design of traffic light control strategy, and obtain a dynamic state evolution rendering model, which can help visualize the operation of the device under different states, and provide support for fault prediction and control strategy optimization. Calculation of component load demand and fault probability based on the dynamic state evolution model can help predict the operating status of components and provide a basis for the formulation of traffic light control strategy. The predicted value of component load demand and fault probability can help to warn of potential faults in advance and ensure the stable operation of the device. Dynamic traffic light control based on load demand prediction value and fault probability value can help adjust the control strategy according to real-time situation and improve the safety and efficiency of charging device. Construction of traffic light control strategy can realize real-time monitoring and intelligent adjustment of charging device status, and improve the management level and operation quality of the device.

[0013] Preferably, step S1 comprises the following steps:

[0014] Step S11: obtaining an internal structure diagram of the mobile power charging device;

[0015] Step S12: visually identify components of the internal structure diagram of the mobile power charging device and mark all internal component nodes;

[0016] Step S13: Performing internal spatial distribution analysis on all internal component nodes to obtain component node spatial distribution data;

[0017] Step S14: performing spatial position positioning calculation on all internal component nodes to generate the spatial position coordinates of each component node;

[0018] Step S15: mining the inter-component topological structure association of the spatial position coordinates of each component node based on the component node spatial distribution data, and extracting component topological structure association data;

[0019] Step S16: Perform three-dimensional topological structure modeling on all internal component nodes according to the component topological structure association data to construct a three-dimensional topological model of the charging device.

[0020] The present invention provides a comprehensive understanding of the internal components of the mobile power charging device through the internal structure diagram, provides basic data for subsequent analysis and optimization, and helps to identify the position and function of each component through component visual identification and marking of internal component nodes, providing specific reference points for subsequent analysis and optimization. Analyzing the spatial distribution of component nodes helps to understand the relative position relationship between components, and provides data support for subsequent position positioning and topological structure association. Generating the spatial position coordinates of component nodes can accurately determine the specific position of each component in the charging device, and provide accurate spatial data for subsequent topological structure modeling. Extracting component topological structure association data can reveal the connection relationship and function between components, and provide important clues for establishing a three-dimensional topological model of the charging device. Constructing a three-dimensional topological model of the charging device helps to visualize the structure and association of the internal components of the charging device, and provides a visual reference for the design and optimization of functions such as signal light control.

[0021] Preferably, step S2 comprises the following steps:

[0022] Step S21: Acquire multi-dimensional working state parameters of the mobile power charging device;

[0023] Step S22: performing parameter standardization processing on the multi-dimensional working state parameter to obtain a standardized multi-dimensional working state parameter;

[0024] Step S23: performing time-series segmentation processing on the standardized multi-dimensional working state parameters to generate a multi-segment working state parameter sequence;

[0025] Step S24: Perform deep state feature learning on multiple working state parameter sequences to construct a working state map of the charging device.

[0026] The present invention helps to fully understand the operation of the mobile power charging device by acquiring multi-dimensional working state parameters, including key parameters such as battery state, charging state, and output power. The multi-dimensional parameter acquisition can provide a rich data source and provide sufficient information support for subsequent analysis and visualization. Standardization of the working state parameters helps to eliminate the dimensional differences between different parameters and ensure that the parameters have the same scale. The standardized parameters can better participate in subsequent calculations and analysis, and improve the accuracy and reliability of data processing. Time series segmentation processing can divide continuous working state parameters into multiple sections according to time, which helps to capture the changing trends of parameters in different time periods. Generating a multi-segment working state parameter sequence helps to analyze the working state of different time periods and provide a more detailed data basis for subsequent state feature learning. Through deep state feature learning, more advanced feature representations can be learned in the multi-segment working state parameter sequence, revealing the complex relationship between parameters. Constructing a working state map of the charging device helps to present the state of the multi-dimensional parameters in the form of a map, providing a dynamic visualization display of faults, health and load, and promoting an in-depth understanding and monitoring of the operating state of the mobile power charging device.

[0027] Preferably, the specific steps of step S24 are:

[0028] The multiple working state parameter sequences include real-time temperature parameters, charging power and charging load;

[0029] Performing temperature fluctuation analysis on real-time temperature parameters to generate charging device temperature fluctuation data;

[0030] Collect the temperature fluctuation data of the charging device at multiple time points to obtain the temperature fluctuation data at multiple time points;

[0031] Perform time series fitting on the temperature fluctuation data at multiple time points to construct a time series temperature fluctuation curve;

[0032] Calculate the cycle peak value of the charging power and extract the charging power peak value;

[0033] Performing peak cycle analysis on the charging power peak to generate a charging power peak cycle diagram;

[0034] Carry out load trend evolution of charging load and generate charging load trend characteristics;

[0035] According to the time series temperature fluctuation curve, the temperature-load correlation mining is carried out on the charging load trend characteristics to generate the temperature-load correlation law;

[0036] Deep state feature learning is performed on the temperature-load correlation law and the charging power peak cycle diagram to construct the charging device working state map.

[0037] The present invention generates temperature fluctuation data through temperature fluctuation analysis, provides detailed information for monitoring the temperature change of the charging device, calculates the periodic peak value of the charging power, reveals the maximum value of the charging power, helps to understand the energy transmission of the charging device, analyzes the evolution trend of the charging load, extracts the load characteristics, and provides a key reference for load management. Through multi-time point temperature fluctuation data collection and time series change fitting, a temperature fluctuation curve is constructed to reveal the temperature change trend and fluctuation. A periodic cycle analysis is performed on the power peak to generate a peak periodic cycle diagram, which helps to understand the fluctuation law of the charging power. The time series temperature fluctuation curve is used to associate and mine the charging load trend characteristics to generate a temperature-load association law and provide correlation information between temperature and load. In-depth state feature learning is performed in combination with the temperature-load association law and the charging power peak periodic cycle diagram to construct a charging device working state map, which provides a more in-depth analysis and visual display for fault detection, health monitoring and load management.

[0038] Preferably, step S3 specifically comprises the following steps:

[0039] Step S31: performing state parameter matching on the component node spatial distribution data based on the multi-dimensional working state parameters to obtain working state matching data of each component node;

[0040] Step S32: performing component node positioning integration on the charging device working state map according to the working state matching data of each component node to obtain a component positioning working state map;

[0041] Step S33: Based on the component positioning working state map, the three-dimensional topological model of the charging device is dynamically mapped to construct a dynamic operation twin topological model.

[0042] The present invention matches the multi-dimensional working status parameters with the spatial distribution data of the component nodes, so as to correspond the working status parameters with the specific component nodes, further refine the description of the working status, and obtain the working status matching data of each component node, which is helpful to understand the operating status of each node more accurately in the subsequent analysis. By integrating the working status matching data of each component node, the status information of each component node can be integrated into the working status map of the charging device to form a more complete component positioning working status map. The component positioning working status map provides an overall view of the status of different components of the charging device, which is helpful to comprehensively analyze the operating status of the charging device. Dynamic state mapping based on the component positioning working status map helps to map the working status information to the three-dimensional topological model of the charging device, realize the correspondence between the state information and the physical structure, and construct a dynamic operation twin topological model to realize real-time monitoring and simulation of the operating status of the charging device, and improve the accuracy and real-time performance of the dynamic visualization display of faults, health and load.

[0043] Preferably, the specific steps of step S4 are:

[0044] Step S41: defining a dynamic operation simulation time step; performing a dynamic operation evolution simulation on the dynamic operation twin topology model based on the dynamic operation simulation time step, and collecting dynamic evolution operation simulation data;

[0045] Step S42: performing multi-time point state feature analysis on the dynamic evolution operation simulation data, and extracting state evolution simulation data at multiple time points;

[0046] Step S43: performing component state evolution situation analysis on the state evolution simulation data at multiple time points to generate component state evolution situation characteristics at different time points;

[0047] Step S44: Perform component state evolution visualization rendering on the dynamically running twin topology model according to the component state evolution situation characteristics at different time points to obtain a dynamic state evolution rendering model.

[0048] The present invention helps to plan the time interval in the simulation process by defining the dynamic operation simulation time step, so that the simulation result is closer to the actual operation situation. By performing dynamic operation evolution simulation on the dynamic operation twin topology model and collecting dynamic evolution operation simulation data, simulation data and system state information at different time points can be obtained. Multi-time point state feature analysis on the dynamic evolution operation simulation data helps to identify the state change trend and key features of the system at different time points. Extracting state evolution simulation data at multiple time points can provide multi-dimensional state information for subsequent analysis and provide support for in-depth understanding of the system state. By performing component state evolution situation analysis on state evolution simulation data at multiple time points, the state evolution trend and characteristics of different components can be revealed. Generating component state evolution situation characteristics at different time points helps to fully understand the operation status of each component at different times, and provides important clues for fault diagnosis and prevention. Visual rendering of component state evolution of the dynamic operation twin topology model according to component state evolution situation characteristics at different time points can intuitively show the change process of the system state. Obtaining a dynamic state evolution rendering model helps to improve the dynamic visualization display of the mobile power charging device in terms of fault, health and load, and provide an intuitive reference for decision-making.

[0049] Preferably, the specific steps of step S5 are:

[0050] Step S51: performing component global operation state evaluation on the dynamic state evolution rendering model to obtain charging device operation state evaluation data;

[0051] Step S52: predicting short-term trend changes of the dynamic state evolution rendering model, thereby generating charging device short-term trend change prediction data;

[0052] Step S53: Calculate the component load demand based on the short-term trend change prediction data of the charging device, and extract the component load demand prediction value;

[0053] Step S54: identifying the state evolution of each component of the dynamic state evolution rendering model, and extracting the state evolution data of each component;

[0054] Step S55: Calculate the component failure probability of each component based on the component load demand prediction value, and generate a failure probability value of each component.

[0055] The present invention helps to comprehensively evaluate the overall operation of the charging device by evaluating the global operation status of the components of the dynamic state evolution rendering model. By obtaining the evaluation data of the operation status of the charging device, a quantitative evaluation of the overall performance of the system can be provided, providing a basis for operation optimization and troubleshooting. The short-term trend change prediction of the dynamic state evolution rendering model can help predict the state change trend of the charging device in the future. The generation of short-term trend change prediction data of the charging device helps to discover possible problems in advance and provide early warning for timely adjustment and maintenance. The component load demand calculation of the short-term trend change prediction data of the charging device helps to evaluate the load situation and demand of the system. Extracting the component load demand prediction value can help optimize the load distribution of the charging device and ensure the operation efficiency and stability of the system. The state evolution identification of each component of the dynamic state evolution rendering model helps to understand the state change of each component in detail. Extracting the state evolution data of each component can provide a detailed information basis for fault diagnosis and prevention. The component failure probability calculation of the state evolution data of each component based on the component load demand prediction value helps to evaluate the possibility of failure of each component. The generation of the failure probability value of each component can help to formulate targeted maintenance plans and preventive measures, thereby improving the reliability and stability of the charging device.

[0056] Preferably, the specific steps of step S6 are:

[0057] Dynamically control the signal light of the mobile power charging device according to the charging device operation status evaluation data, the component load demand prediction value and the failure probability value of each component to build a signal light control strategy;

[0058] The dynamic signal light control is specifically as follows: identifying the health status of the charging device operation status evaluation data, and when the charging device operation status evaluation data is greater than a preset charging device health status threshold, it is determined to be in a healthy state and a health status signal is generated; based on the health status signal, the mobile power charging device is subjected to a green signal light that is always on;

[0059] Perform load demand shortage analysis on the component load demand forecast value to generate load demand shortage data; generate a demand shortage signal based on the load demand shortage data, and perform a yellow signal light slow flashing process on the mobile power charging device according to the demand shortage signal;

[0060] The fault probability value of each component is identified by using a preset fault probability threshold, and when there is a component whose fault probability value is greater than or equal to the preset fault probability threshold, a fault alarm signal is generated; based on the fault alarm signal, the red signal light of the mobile power charging device is flashed rapidly.

[0061] The present invention can timely capture the health status of the charging device by performing health status identification on the charging device operation status evaluation data. After the health status signal is generated, the green signal light is always on, which helps to convey the information of the normal operation of the charging device to the operator, and improves the visual display effect of the operation status. By analyzing the component load demand prediction value, the load demand situation of the system can be accurately evaluated, and the load demand shortage situation can be discovered in time. After the demand shortage signal is generated, the slow flashing of the yellow signal light helps to remind the operator that the system has a load demand shortage, prompting timely adjustment or processing, and enhancing the effect of dynamic display of the load. The fault probability value of the component is identified through a preset fault probability threshold, so that components that may have faults can be quickly discovered. After the fault alarm signal is generated, the fast flashing of the red signal light helps to urgently warn the operator of the existing fault situation, improves the effect of dynamic display of the fault, and prompts rapid processing and maintenance.

[0062] In this specification, a signal light control system of a mobile power charging device is provided, which is used to execute the signal light control method of the mobile power charging device as described above, including:

[0063] A three-dimensional topology module is used to obtain the internal structure diagram of the mobile power charging device; perform component visual recognition on the internal structure diagram of the mobile power charging device, perform three-dimensional topological structure modeling, and construct a three-dimensional topological model of the charging device;

[0064] A state map module is used to obtain multi-dimensional working state parameters of a mobile power charging device; perform deep state feature learning on the multi-dimensional working state parameters to construct a working state map of the charging device;

[0065] A dynamic state mapping module is used to dynamically map the three-dimensional topological model of the charging device based on the working state map of the charging device, and to construct a dynamic operation twin topological model;

[0066] The dynamic operation evolution module is used to simulate the dynamic operation evolution of the dynamic operation twin topology model and perform visual rendering of the component state evolution to obtain a dynamic state evolution rendering model;

[0067] A state prediction module is used to calculate component load demand and component failure probability based on a dynamic state evolution rendering model to obtain component load demand prediction values ​​and failure probability values ​​of each component;

[0068] The signal light control module is used to dynamically control the signal lights of the mobile power charging device according to the predicted value of component load demand and the failure probability value of each component, so as to construct a signal light control strategy.

[0069] By acquiring the internal structure diagram of the mobile power charging device, the present invention can deeply understand the component layout and connection method of the charging device, and provide basic data for subsequent analysis. Through component visual recognition and three-dimensional topological structure modeling, a real three-dimensional topological model of the charging device can be constructed, which is helpful to visualize the internal structure of the charging device. Acquiring multi-dimensional working state parameters of the mobile power charging device can fully understand the operating state of the charging device and provide detailed data for subsequent analysis. Through deep state feature learning and construction of working state maps, a comprehensive working state map of the charging device can be formed to provide rich state information for subsequent analysis. Dynamic state mapping of the three-dimensional topological model based on the working state map of the charging device can combine static structural information with dynamic working states to achieve comprehensive dynamic model construction. Construction of a dynamic operation twin topological model is helpful to monitor the operating state changes of the charging device in real time, and provide an accurate basis for subsequent analysis and control. Dynamic operation evolution simulation and component state evolution visualization rendering can intuitively display the component operation status of the charging device under different working conditions. Generating a dynamic state evolution rendering model is helpful for real-time monitoring and analysis of the operating status of the charging device, and provides visualization support for fault diagnosis and prevention. Calculation of component load demand and component failure probability based on the dynamic state evolution rendering model can predict the load demand of the charging device and the possibility of component failure. Generating component load demand prediction values ​​and failure probability values ​​of each component can help to formulate reasonable maintenance plans and preventive measures, improve the reliability and stability of the charging device, and dynamically control the signal lights of the mobile power charging device according to the component load demand prediction values ​​and component failure probability values. The signal light display can be adjusted according to the real-time status, and the dynamic visualization display effect of faults, health and load can be improved. The construction of a signal light control strategy is helpful to timely reflect the state changes of the charging device, provide intuitive information feedback to operators, and promote timely processing and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 A schematic flow chart of the steps of a signal light control method of a mobile power charging device of the present invention;

[0071] Figure 2 Detailed implementation flow chart of step S1;

[0072] Figure 3 Detailed implementation flow chart of step S2;

[0073] Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0074] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0075] The present application example provides a signal light control method and system for a mobile power charging device. The execution subject of the signal light control method and system for a mobile power charging device includes but is not limited to: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0076] See also Figures 1 to 4 The present invention provides a signal light control method for a mobile power charging device, the signal light control method for a mobile power charging device comprising the following steps:

[0077] Step S1: obtaining an internal structure diagram of a mobile power charging device; performing component visual recognition on the internal structure diagram of the mobile power charging device, and performing three-dimensional topological structure modeling to construct a three-dimensional topological model of the charging device;

[0078] Step S2: Acquire multi-dimensional working state parameters of the mobile power charging device; perform deep state feature learning on the multi-dimensional working state parameters to construct a working state map of the charging device;

[0079] Step S3: dynamically mapping the three-dimensional topological model of the charging device based on the working state map of the charging device to construct a dynamic operation twin topological model;

[0080] Step S4: simulate the dynamic operation evolution of the dynamic operation twin topology model, and perform component state evolution visualization rendering to obtain a dynamic state evolution rendering model;

[0081] Step S5: Calculate component load requirements and component failure probability based on the dynamic state evolution rendering model.

[0082] To obtain the predicted value of component load demand and the failure probability value of each component;

[0083] Step S6: Dynamically control the traffic light of the mobile power charging device according to the predicted value of the component load demand and the failure probability value of each component to construct a traffic light control strategy.

[0084] The present invention helps to understand the device composition and component functions by obtaining the internal structure diagram and performing visual identification of components, providing a basis for subsequent analysis. Constructing a three-dimensional topological model of the charging device can help visualize the device structure and help better understand the design and layout of the device. Deep state feature learning and working state map construction help to fully understand the working state of the charging device and provide detailed data support for subsequent analysis. Constructing a working state map of the charging device can help identify the relationship between different states of the device and provide a more accurate basis for traffic light control. Dynamic state mapping of the three-dimensional topological model based on the working state map helps to simulate the operation of the device under different working states and improve the pertinence of the control strategy. Constructing a dynamic operation twin topological model can achieve real-time monitoring and feedback, provide support for the flexibility and accuracy of the traffic light control strategy, and perform dynamic operation evolution simulation. Simulation and state visualization rendering can help simulate the changes of the device in actual operation, provide an intuitive reference for the design of traffic light control strategy, and obtain a dynamic state evolution rendering model, which can help visualize the operation of the device under different states, and provide support for fault prediction and control strategy optimization. Calculation of component load demand and fault probability based on the dynamic state evolution model can help predict the operating status of components and provide a basis for the formulation of traffic light control strategy. The predicted value of component load demand and fault probability can help to warn of potential faults in advance and ensure the stable operation of the device. Dynamic traffic light control based on load demand prediction value and fault probability value can help adjust the control strategy according to real-time situation and improve the safety and efficiency of charging device. Construction of traffic light control strategy can realize real-time monitoring and intelligent adjustment of charging device status, and improve the management level and operation quality of the device.

[0085] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a signal light control method of a mobile power charging device of the present invention. In this example, the steps of the method include:

[0086] Step S1: obtaining an internal structure diagram of a mobile power charging device; performing component visual recognition on the internal structure diagram of the mobile power charging device, and performing three-dimensional topological structure modeling to construct a three-dimensional topological model of the charging device;

[0087] In this embodiment, the internal structure images of the mobile power charging device are obtained based on the original design drawings. These images can clearly show the shape, size and layout of each component inside the charging device. Computer vision technology, such as deep learning target detection algorithm, is used to automatically identify each component in the structure diagram. Through the trained neural network model, key components such as the battery, controller, and connecting wires in the image are accurately extracted. Computer-aided design (CAD) technology is used to construct a three-dimensional geometric model of the charging device based on the component information obtained in the previous step. In the three-dimensional model, the shape, size, position relationship of each component, and the connection topological relationship between them are accurately expressed to generate a complete charging device. A three-dimensional topological model is established to provide a basis for subsequent status monitoring and fault analysis. By comparing the actual charging device with the three-dimensional model, the geometric accuracy and topological structure of the model are continuously optimized. The three-dimensional model is superimposed and compared with the actual device using technologies such as augmented reality (AR), and errors in the model are discovered and corrected to ensure that the three-dimensional topological model can highly restore the actual internal structure and component layout of the charging device. The optimized three-dimensional topological model data is stored in a standard CAD data format (such as STEP, IGES, etc.), and a model database is established to effectively manage the three-dimensional topological models of charging devices of different models. It supports functions such as query, comparison, and version control of model data to meet the needs of subsequent diagnostic analysis.

[0088] Step S2: Acquire multi-dimensional working state parameters of the mobile power charging device; perform deep state feature learning on the multi-dimensional working state parameters to construct a working state map of the charging device;

[0089] In this embodiment, various sensors are deployed inside the charging device to collect multi-dimensional working status data such as voltage, current, temperature, vibration, etc. in real time. These real-time collected status parameter data are transmitted to the data center for processing and analysis through wired or wireless means. The collected original status parameter data are pre-processed by cleaning, normalization and other operations to remove noise and abnormal values. In combination with the physical structure and working mechanism of the charging device, key features that have an important impact on status identification are extracted, including characteristic indicators of various aspects such as electrical characteristics, thermal characteristics, and mechanical characteristics of each component. A deep neural network model, such as a long short-term memory (LSTM) network, is used to perform end-to-end learning on the pre-processed multi-dimensional status features, and the network model is trained so that it can be used as a charging device. It can automatically extract high-order implicit features of the working state of the charging device. Through this deep feature learning, it can effectively capture the complex correlations between state parameters, and map the state feature vectors extracted by the deep learning model into a two-dimensional or three-dimensional visualization space to form a two-dimensional or three-dimensional state map that reflects the working state of the charging device. In this map, similar state points represent similar working states, and state points that are far apart represent large differences in working states. As the charging device generates more data in actual use, the state map model is continuously updated and optimized, and the existing model is quickly adapted to the new model of charging device using technologies such as transfer learning, to ensure that the state map can continue to accurately reflect the changing laws of the working state of the charging device.

[0090] Step S3: dynamically mapping the three-dimensional topological model of the charging device based on the working state map of the charging device to construct a dynamic operation twin topological model;

[0091] In this embodiment, the constructed working state map of the charging device is associated with the established three-dimensional topological model. Through the correspondence between the state feature vector and each component in the three-dimensional model, a mapping relationship between the two is established. The multi-dimensional working state data of the charging device is collected in real time and mapped to the state map. According to the correspondence between the state map and the three-dimensional model, the state of each component in the three-dimensional topological model is dynamically updated, so that the three-dimensional model can reflect the changes in the operating state of the charging device in actual use in real time. The updated three-dimensional topological model forms a digital twin relationship with the actual charging device, and the operating state data of the charging device is synchronized in real time to ensure that the digital model is kept consistent with the actual equipment. Maintain a high degree of consistency. The digital twin model can be used to realize virtual monitoring of the status of the charging device and fault prediction. The digital twin model can be used to carry out virtual tests and fault simulations of the charging device, analyze the status changes of each component in the three-dimensional model, and discover possible hidden dangers and failure risks. This provides a basis for the preventive maintenance of the charging device and allows for the formulation of more accurate maintenance plans. As the charging device generates more data in actual use, the digital twin model is continuously updated and optimized. Using technologies such as machine learning, the deviation between the digital model and the actual equipment is automatically discovered and continuously corrected to ensure that the digital twin model can highly simulate the dynamic operating status of the charging device under various working conditions.

[0092] Step S4: simulate the dynamic operation evolution of the dynamic operation twin topology model, and perform component state evolution visualization rendering to obtain a dynamic state evolution rendering model;

[0093] In this embodiment, a digital twin model is used to simulate the dynamic operation process of the charging device under various working conditions. Through simulation means, the working state changes of the internal components of the charging device are dynamically predicted and deduced to obtain the overall operating state of the charging device and the evolution of the state of each component over time. According to the working mechanism and failure mode of the charging device, the visualization indicators of the key component states are determined, such as the battery capacity attenuation degree, the controller temperature rise amplitude, the connection line loss and other state parameters, and intuitive visualization codes are designed for these indicators, such as color, transparency, size and other visual mappings. The component state evolution data obtained in step 1 is mapped to the three-dimensional topological model constructed in step S3, and real-time rendering technology is used, such as the Three.js library based on WebGL. , dynamically update the visual attributes of each component in the three-dimensional model, realize the dynamic visualization of the status of the internal components of the charging device over time, develop a Web-based visualization application, integrate the dynamic state rendering function of step 3, support users to interactively switch observation angles and time nodes, view the status changes of the internal components of the charging device, and provide auxiliary analysis tools such as status indicator trend charts and fault probability curves to facilitate users to conduct in-depth diagnosis. According to user feedback and actual application needs, continuously optimize the performance and interactive experience of the dynamic state rendering model, use virtual reality (VR), augmented reality (AR) and other technologies to further enhance the immersion of dynamic state rendering, embed the visualization model into the remote operation and maintenance system of the mobile power supply, and provide users with intuitive diagnostic tools.

[0094] Step S5: Calculate component load requirements and component failure probability based on the dynamic state evolution rendering model.

[0095] To obtain the predicted value of component load demand and the failure probability value of each component;

[0096] In this embodiment, the constructed dynamic state rendering model is used to monitor the operating state of each component inside the charging device in real time, and real-time working data of multiple dimensions such as voltage, current, temperature, vibration, etc. are obtained as the basis for subsequent analysis. The time series analysis and machine learning methods are used to model and predict the obtained component working state data, predict the power demand of each component (such as battery, controller, sensor, etc.) within a certain period of time in the future, and obtain the load demand prediction value of each component as a reference for dynamic traffic light control. The Bayesian network, neural network and other machine learning models are used to perform fault prediction analysis on the component working state data. According to the health status indicators of the components, such as battery capacity, insulation performance, vibration level, etc., the probability of failure of each component within a certain period of time in the future is calculated, and the failure probability value of each component is obtained, which provides a basis for subsequent fault warning. As the charging device generates more dynamic working state data in actual use, the above prediction model is continuously updated and optimized, and the existing prediction model is quickly applied to the new model of charging device by using technologies such as transfer learning, to ensure the accuracy of load demand prediction and fault probability calculation, and meet actual application needs.

[0097] Step S6: Dynamically control the traffic light of the mobile power charging device according to the predicted value of the component load demand and the failure probability value of each component to construct a traffic light control strategy.

[0098] In this embodiment, in combination with the working mechanism and failure mode of the charging device, signal light display rules for different states are formulated. For example, when the load of a key component is too high or the failure probability is high, the corresponding warning light is turned on. When all components are working normally, the signal light of the normal working state is displayed. The obtained component load demand prediction value and failure probability value are used as input parameters for signal light control. An algorithm model is designed to fuse and analyze these two types of data to obtain a comprehensive component working status indicator. According to the fused component working status indicator, the display status of the charging device signal light is adjusted in real time. When the status indicator of a component exceeds the normal range, the corresponding warning light is turned on to alert the user. When the status indicators of all components are within the normal range, the signal light of the normal working state is displayed.

[0099] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0100] Step S11: obtaining an internal structure diagram of the mobile power charging device;

[0101] Step S12: visually identify components of the internal structure diagram of the mobile power charging device and mark all internal component nodes;

[0102] Step S13: Performing internal spatial distribution analysis on all internal component nodes to obtain component node spatial distribution data;

[0103] Step S14: performing spatial position positioning calculation on all internal component nodes to generate the spatial position coordinates of each component node;

[0104] Step S15: mining the inter-component topological structure association of the spatial position coordinates of each component node based on the component node spatial distribution data, and extracting component topological structure association data;

[0105] Step S16: Perform three-dimensional topological structure modeling on all internal component nodes according to the component topological structure association data to construct a three-dimensional topological model of the charging device.

[0106] In this embodiment, the internal structure diagram of the mobile power charging device can be searched and obtained, which can usually be obtained through design documents, information provided by the manufacturer or disassembling the physical object. Ensure that the format of the internal structure diagram is suitable for subsequent processing. Common formats include CAD files (such as DWG or DXF), PDF files or high-resolution pictures. If the drawing is in picture format, use image processing software (such as Photoshop, GIMP) for preprocessing to ensure that the image clarity and contrast are appropriate for subsequent recognition. Use computer vision and image processing technology, select appropriate tools and libraries (such as OpenCV, TensorFlow, PyTorch) to perform component recognition. If the internal components have special shapes or signs, training may be required. A deep learning model (such as a convolutional neural network) is used to identify these components. A labeled data set is prepared for training. The processed internal structure diagram is input into the recognition model for component recognition. The recognition results include the category and position of each component. All identified component nodes are marked in the diagram, and the component type and corresponding position coordinates are recorded. The spatial distribution characteristics of the component nodes are defined, including the relative position, density, and layout between nodes. The marked component node information is sorted to form a node data set, including the type, position coordinates, and relationship of each node in the diagram. Appropriate analysis methods are selected, such as: Cluster analysis: Use K-Means, DBSCAN and other methods to analyze the clustering characteristics of nodes. Heat map analysis: Generate component nodes. Heat map, showing the distribution density of nodes, performing spatial distribution analysis on the sorted node data, obtaining the spatial distribution data of component nodes, forming a visual result (such as a heat map), determining a suitable coordinate system, usually using a three-dimensional coordinate system (X, Y, Z) to represent the position of component nodes, selecting a method for spatial positioning, common methods include: geometric calculation: performing geometric coordinate calculations based on the position of the component in the diagram, image processing technology: using edge detection, contour recognition and other methods to determine the precise position of the component, calculating the spatial position coordinates of each component node based on the markings and relative positions of the components in the internal structure diagram, saving the calculated spatial position coordinates of each component node in the data table to form a component coordinate data set, defining The topological relationship between components, including the connection, dependency and interaction between components, select the appropriate topological structure mining method, such as: Graph theory method: regard the components as nodes in the graph, use graph theory algorithms (such as Dijkstra algorithm) to calculate the connection relationship between nodes, association rule mining: use Apriori or FP-Growth algorithm to mine the association relationship between components, analyze the spatial position coordinates and spatial distribution data of component nodes, mine the topological structure association data between components, organize and save the extracted topological structure association data for subsequent modeling, select appropriate 3D modeling tools or software, such as Blender, SketchUp, AutoCAD or 3DCAD software, and make a modeling plan.Including the modeling method, material properties and connection method of each component, according to the topological structure association data and the spatial position coordinates of the component nodes, build the 3D model of each component one by one, and connect them according to the topological relationship, adjust the details of the model, such as the size, shape and material of the component, verify the generated 3D model to ensure that it is consistent with the actual internal structure, and make necessary optimizations, and save the final 3D topological model in a standard format (such as STL, OBJ or FBX) for subsequent use and display.

[0107] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0108] Step S21: Acquire multi-dimensional working state parameters of the mobile power charging device;

[0109] Step S22: performing parameter standardization processing on the multi-dimensional working state parameter to obtain a standardized multi-dimensional working state parameter;

[0110] Step S23: performing time-series segmentation processing on the standardized multi-dimensional working state parameters to generate a multi-segment working state parameter sequence;

[0111] Step S24: Perform deep state feature learning on multiple working state parameter sequences to construct a working state map of the charging device.

[0112] In this embodiment, the multi-dimensional working state parameters that need to be obtained are clearly defined, including: real-time temperature parameters: monitoring the temperature of the battery and the charging device, charging power: real-time recording of the charging power, charging load: monitoring the current charging load state, using sensors and data acquisition devices (such as Arduino, RaspberryPi) to monitor and record the above parameters in real time, ensuring that the sensors have sufficient accuracy and response speed to obtain accurate data, and storing the collected multi-dimensional working state parameters in real time to a database (such as MySQL, MongoDB) or a data stream platform (such as ApacheKafka) to ensure the continuous availability and integrity of the data, and selecting a suitable standardization method, for example: Z-score standardization: suitable for processing parameters with different means and variances, Min-Max standardization: suitable for scaling parameters to a uniform range (such as [0, 1]), determining the rules for time series segmentation, which can be segmented based on time windows (such as every 10 minutes) or state changes (such as charging state conversion), and segmenting the standardized working state parameters according to the defined rules: using the sliding window method to extract The working state parameter sequence in each time period, each parameter sequence should include real-time temperature, charging power and charging load, forming multiple working state parameter sequences, and selecting appropriate deep learning methods for state feature learning. Commonly used models include: Long Short-Term Memory Network (LSTM): suitable for processing time series data and can capture long-term dependencies, Convolutional Neural Network (CNN): used to extract local features in time series data, organize multiple working state parameter sequences into training sets, including input features (real-time temperature, charging power, charging load) and target outputs (can be state categories or other indicators), ensure that the data format is suitable for input into the deep learning model, perform data division (training set, validation set, test set), use the organized data to train the selected deep learning model, set appropriate hyperparameters (such as learning rate, batch size, number of training rounds), and monitor the model training process. After the model training is completed, use the trained model to predict the working state parameters, extract state features, build a working state map of the charging device, visualize the state map, and display the feature distribution and change trend under different working states.

[0113] In this embodiment, the specific steps of step S24 are:

[0114] The multiple working state parameter sequences include real-time temperature parameters, charging power and charging load;

[0115] Performing temperature fluctuation analysis on real-time temperature parameters to generate charging device temperature fluctuation data;

[0116] Collect the temperature fluctuation data of the charging device at multiple time points to obtain the temperature fluctuation data at multiple time points;

[0117] Perform time series fitting on the temperature fluctuation data at multiple time points to construct a time series temperature fluctuation curve;

[0118] Calculate the cycle peak value of the charging power and extract the charging power peak value;

[0119] Performing peak cycle analysis on the charging power peak to generate a charging power peak cycle diagram;

[0120] Carry out load trend evolution of charging load and generate charging load trend characteristics;

[0121] According to the time series temperature fluctuation curve, the temperature-load correlation mining is carried out on the charging load trend characteristics to generate the temperature-load correlation law;

[0122] Deep state feature learning is performed on the temperature-load correlation law and the charging power peak cycle diagram to construct the charging device working state map.

[0123] In this embodiment, a temperature sensor is used to monitor the temperature of the charging device in real time, and the temperature data is recorded regularly. The standard deviation and mean of the temperature are calculated to analyze the volatility of the temperature. The temperature fluctuation data is collected at different time points to form a time series. Polynomial fitting or other regression methods (such as curve_fit of the SciPy library) are used to construct a time series temperature fluctuation curve. Charging power data is obtained regularly and stored in an array. charging_power_data=[random.uniform(0, 100)for_inrange(100)]#Simulate power data;

[0124] #Calculate peak value;

[0125] peaks=[xforxincharging_power_dataifx>threshold]#custom threshold;

[0126] Calculate the periodic variation of charging power using Fourier transform or periodogram analysis methods.

[0127] fromscipy.fftimportfft;

[0128] power_fft=fft(charging_power_data);

[0129] Record charging load data in real time and generate trend characteristics.

[0130] load_data = [random.uniform(0, 50) for_inrange(100)] #Simulate load data;

[0131] Use correlation coefficients or regression analysis to explore the relationship between temperature and load.

[0132] correlation=np.corrcoef(temperature_data, load_data)[0, 1];

[0133] print(f"Temperature-LoadCorrelation:{correlation}");

[0134] Use a deep learning framework (such as TensorFlow or PyTorch) to build a model, input temperature fluctuation and charging power peak data, and learn status features.

[0135] importtensorflowastf;

[0136] model = tf.keras.Sequential([

[0137] tf.keras.layers.Dense(64, activation='relu', input_shape=(2,)), # Input temperature and power;

[0138] tf.keras.layers.Dense(1)#output state features; ]);

[0140] model.compile(optimizer='adam', loss='mean_squared_error');

[0141] model.fit(X_train, y_train, epochs=100);

[0142] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0143] Step S31: performing state parameter matching on the component node spatial distribution data based on the multi-dimensional working state parameters to obtain working state matching data of each component node;

[0144] Step S32: performing component node positioning integration on the charging device working state map according to the working state matching data of each component node to obtain a component positioning working state map;

[0145] Step S33: Based on the component positioning working state map, the three-dimensional topological model of the charging device is dynamically mapped to construct a dynamic operation twin topological model.

[0146] In this embodiment, the spatial distribution information of all component nodes is collected, including the spatial position of each node, historical working state parameters (such as temperature, charging power and load), etc., to ensure that the multi-dimensional working state parameters (such as temperature, charging power, charging load, etc.) collected in real time have been standardized and organized into a structured format, and a similarity calculation method (such as Euclidean distance, cosine similarity) is used to evaluate the degree of matching between the working state of the component node and the multi-dimensional working state parameters. For each component node, the spatial distribution data is matched with the real-time working state parameters, and the matching results are recorded to generate working state matching data for each component node, including matching scores and corresponding state parameters. The working state map of the charging device is collected to ensure that it contains all component nodes and their mutual relationships. An integrated learning or weighted average method is used to locate and integrate the working state map according to the working state matching data of each component node. For each component node, its matching The score is combined with the node position in the working status map to determine the final positioning of the component. Combined with multi-dimensional status parameters, the component node position in the working status map is updated, and the integrated component positioning data and the updated working status map are saved as new data sets to ensure the integrity and accuracy of the information. Ensure that the three-dimensional topological model of the charging device has been constructed, including all components and their connection relationships. Select a suitable dynamic state mapping algorithm, such as a graph-based mapping algorithm or a deep learning method (such as a neural network in the figure), map the node status in the component positioning working status map to the three-dimensional topological model, update the status of each component in real time, and use real-time data to dynamically adjust the topological model to ensure that the model reflects the current working status. Integrate the results of dynamic mapping to form a dynamic operation twin topological model of the charging device, and use visualization tools (such as PowerBI, Tableau) to display the dynamic operation model, allowing real-time monitoring and analysis.

[0147] In this embodiment, step S4 includes the following steps:

[0148] Step S41: defining a dynamic operation simulation time step; performing a dynamic operation evolution simulation on the dynamic operation twin topology model based on the dynamic operation simulation time step, and collecting dynamic evolution operation simulation data;

[0149] Step S42: performing multi-time point state feature analysis on the dynamic evolution operation simulation data, and extracting state evolution simulation data at multiple time points;

[0150] Step S43: performing component state evolution situation analysis on the state evolution simulation data at multiple time points to generate component state evolution situation characteristics at different time points;

[0151] Step S44: Perform component state evolution visualization rendering on the dynamically running twin topology model according to the component state evolution situation characteristics at different time points to obtain a dynamic state evolution rendering model.

[0152] In this embodiment, according to the working characteristics of the charging device and the data collection frequency, a suitable dynamic operation simulation time step (such as per second, per minute, etc.) is defined, and a suitable dynamic simulation algorithm is selected. For example, based on discrete event simulation (DES) or system dynamics model (SDM), the set time step is used to perform evolution simulation on the dynamic operation twin topology model. In each time step, the component status (such as temperature, power, load) in the model is updated and the changes are recorded. At the end of each time step, dynamic evolution operation simulation data is collected, including the state parameters of each component. The collected dynamic evolution operation simulation data is sorted in chronological order to form a time series data set. Statistical analysis methods (such as mean, standard deviation, maximum value, minimum value, etc.) are used to extract state features of multiple time points, and the integrated time series data is analyzed to extract state evolution simulation data at each time point. , and record important features (such as peak values, fluctuation ranges, etc.), select appropriate analysis methods, such as trend analysis, rate of change analysis, or machine learning-based models (such as decision trees or random forests) to analyze the evolution of component states, analyze the extracted state evolution simulation data at multiple time points, identify the state evolution characteristics of each component, record the state change trends and characteristics at different time points, select appropriate visualization tools and technologies, such as Unity, Blender, or WebGL, for dynamic state visualization rendering, and visualize the dynamic running twin topology model according to the component state evolution characteristics at different time points to achieve dynamic effects and display the changes in state over time, including changes in key parameters such as temperature, power, and load. Generate a dynamic state evolution rendering model and display it, so that users can monitor and analyze the working status of the charging device in real time.

[0153] In this embodiment, step S5 includes the following steps:

[0154] Step S51: performing component global operation state evaluation on the dynamic state evolution rendering model to obtain charging device operation state evaluation data;

[0155] Step S52: predicting short-term trend changes of the dynamic state evolution rendering model, thereby generating charging device short-term trend change prediction data;

[0156] Step S53: Calculate the component load demand based on the short-term trend change prediction data of the charging device, and extract the component load demand prediction value;

[0157] Step S54: identifying the state evolution of each component of the dynamic state evolution rendering model, and extracting the state evolution data of each component;

[0158] Step S55: Calculate the component failure probability of each component based on the component load demand prediction value, and generate a failure probability value of each component.

[0159] In this embodiment, the state parameters of each component in the dynamic state evolution rendering model are collected, including temperature, power, load, etc., and the indicators for global operation state evaluation are defined, such as component working efficiency, overall energy consumption, temperature fluctuation range, and charging efficiency. The state of each component is comprehensively evaluated using the analytic hierarchy process (AHP), fuzzy logic, or weighted scoring method. The operation state evaluation data of the charging device is recorded, and a corresponding report is generated to facilitate subsequent analysis. The state data in the dynamic state evolution rendering model is sorted to form a time series data set for prediction. A short-term trend prediction model is selected, such as a time series prediction model (such as ARIMA, SARIMA), a machine learning model (such as a support vector machine, a random forest), and the selected model is used to predict the short-term trend and generate the short-term trend change prediction data of the charging device. The short-term trend change prediction data is stored as structured data to facilitate subsequent analysis and selection of appropriate load demand calculation methods, which may include: load demand estimation based on prediction models, load distribution algorithms (such as optimization models), calculating the load demand of each component according to the short-term trend change prediction data, extracting the component load demand prediction value, recording the expected load of each component in the short term, and saving the calculated component load demand prediction value to the database for subsequent use, extracting the state data of each component from the dynamic state evolution rendering model, including historical state and real-time state, analyzing the state of each component one by one, identifying its state evolution data, and recording the state changes of each component, calculating the failure probability value of each component based on the component load demand prediction value and state evolution data, recording the failure probability value, and determining its state within an acceptable range.

[0160] In this embodiment, step S6 includes the following steps:

[0161] Dynamically control the signal light of the mobile power charging device according to the charging device operation status evaluation data, the component load demand prediction value and the failure probability value of each component to build a signal light control strategy;

[0162] The dynamic signal light control is specifically as follows: identifying the health status of the charging device operation status evaluation data, and when the charging device operation status evaluation data is greater than a preset charging device health status threshold, it is determined to be in a healthy state and a health status signal is generated; based on the health status signal, the mobile power charging device is subjected to a green signal light that is always on;

[0163] Perform load demand shortage analysis on the component load demand forecast value to generate load demand shortage data; generate a demand shortage signal based on the load demand shortage data, and perform a yellow signal light slow flashing process on the mobile power charging device according to the demand shortage signal;

[0164] The fault probability value of each component is identified by using a preset fault probability threshold, and when there is a component whose fault probability value is greater than or equal to the preset fault probability threshold, a fault alarm signal is generated; based on the fault alarm signal, the red signal light of the mobile power charging device is flashed rapidly.

[0165] In this embodiment, various operating parameters of the charging device, such as voltage, current, temperature, vibration, etc., are collected in real time, and a charging device health status assessment model based on machine learning is established. These parameters are analyzed and modeled, and the assessment results are compared with the preset health status threshold to determine whether the charging device is currently in a healthy state. If the health status is good, a "healthy state" signal is generated as a basis for subsequent signal light control. The power demand data of various components of the charging device, including batteries, controllers, sensors, etc., are collected. Time series analysis and gray prediction methods are used to predict the load demand of each component within a certain period of time in the future. According to the prediction results, it is analyzed whether there is a shortage of load demand for each component. If there is a shortage of load demand, a "demand shortage" signal is generated. The operating status parameters of each key component, such as battery attenuation and fan wear, are monitored in real time through sensors. A component failure prediction model based on a Bayesian network is established to predict each component. The failure probability of each component in a certain period of time in the future is compared with the preset failure probability threshold. Once the failure probability of a component exceeds the threshold, a "fault alarm" signal is generated. According to the generated "healthy status", "demand shortage" and "fault alarm" signals, a traffic light control strategy is constructed: if the charging device is in a healthy state, the green signal light is always on; if there is a component load demand shortage, the yellow signal light is slowly flashing; if there is a risk of component failure, the red signal light is quickly flashing. The above traffic light control strategy is executed in real time through a distributed intelligent control unit, and the operation data is uploaded to the cloud in real time for remote diagnosis and fault prediction. Reinforcement learning technology is used to continuously optimize the parameters and rules of the traffic light control strategy. According to user feedback, equipment status and other factors, the threshold and time of the traffic light switching are adjusted to maximize the overall user experience of the charging device while ensuring safety and reliability.

[0166] A three-dimensional topology module is used to obtain the internal structure diagram of the mobile power charging device; perform component visual recognition on the internal structure diagram of the mobile power charging device, perform three-dimensional topological structure modeling, and construct a three-dimensional topological model of the charging device;

[0167] A state map module is used to obtain multi-dimensional working state parameters of a mobile power charging device; perform deep state feature learning on the multi-dimensional working state parameters to construct a working state map of the charging device;

[0168] A dynamic state mapping module is used to dynamically map the three-dimensional topological model of the charging device based on the working state map of the charging device, and to construct a dynamic operation twin topological model;

[0169] The dynamic operation evolution module is used to simulate the dynamic operation evolution of the dynamic operation twin topology model and perform visual rendering of the component state evolution to obtain a dynamic state evolution rendering model;

[0170] A state prediction module is used to calculate component load demand and component failure probability based on a dynamic state evolution rendering model to obtain component load demand prediction values ​​and failure probability values ​​of each component;

[0171] The signal light control module is used to dynamically control the signal lights of the mobile power charging device according to the predicted value of component load demand and the failure probability value of each component, so as to construct a signal light control strategy.

[0172] By acquiring the internal structure diagram of the mobile power charging device, the present invention can deeply understand the component layout and connection method of the charging device, and provide basic data for subsequent analysis. Through component visual recognition and three-dimensional topological structure modeling, a real three-dimensional topological model of the charging device can be constructed, which is helpful to visualize the internal structure of the charging device. Acquiring multi-dimensional working state parameters of the mobile power charging device can fully understand the operating state of the charging device and provide detailed data for subsequent analysis. Through deep state feature learning and construction of working state maps, a comprehensive working state map of the charging device can be formed to provide rich state information for subsequent analysis. Dynamic state mapping of the three-dimensional topological model based on the working state map of the charging device can combine static structural information with dynamic working states to achieve comprehensive dynamic model construction. Construction of a dynamic operation twin topological model is helpful to monitor the operating state changes of the charging device in real time, and provide an accurate basis for subsequent analysis and control. Dynamic operation evolution simulation and component state evolution visualization rendering can intuitively display the component operation status of the charging device under different working conditions. Generating a dynamic state evolution rendering model is helpful for real-time monitoring and analysis of the operating status of the charging device, and provides visualization support for fault diagnosis and prevention. Calculation of component load demand and component failure probability based on the dynamic state evolution rendering model can predict the load demand of the charging device and the possibility of component failure. Generating component load demand prediction values ​​and failure probability values ​​of each component can help to formulate reasonable maintenance plans and preventive measures, improve the reliability and stability of the charging device, and dynamically control the signal lights of the mobile power charging device according to the component load demand prediction values ​​and component failure probability values. The signal light display can be adjusted according to the real-time status, and the dynamic visualization display effect of faults, health and load can be improved. The construction of a signal light control strategy is helpful to timely reflect the state changes of the charging device, provide intuitive information feedback to operators, and promote timely processing and maintenance.

[0173] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0174] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A signal light control method for a mobile power charging device, characterized in that: The following steps are involved: Step S1: obtaining an internal structure diagram of a mobile power charging device; visually identifying components of the internal structure diagram of the mobile power charging device, and performing three-dimensional topological structure modeling to construct a three-dimensional topological model of the charging device; the specific steps of step S1 are: Step S11: obtaining an internal structure diagram of the mobile power charging device; Step S12: visually identify components of the internal structure diagram of the mobile power charging device and mark all internal component nodes; Step S13: Performing internal spatial distribution analysis on all internal component nodes to obtain component node spatial distribution data; Step S14: performing spatial position positioning calculation on all internal component nodes to generate the spatial position coordinates of each component node; Step S15: mining the inter-component topological structure association of the spatial position coordinates of each component node based on the component node spatial distribution data, and extracting component topological structure association data; Step S16: performing three-dimensional topological structure modeling on all internal component nodes according to the component topological structure association data to construct a three-dimensional topological model of the charging device; Step S2: obtaining multi-dimensional working state parameters of the mobile power charging device; performing deep state feature learning on the multi-dimensional working state parameters to construct a working state map of the charging device; the specific steps of step S2 are: Step S21: Acquire multi-dimensional working state parameters of the mobile power charging device; Step S22: performing parameter standardization processing on the multi-dimensional working state parameter to obtain a standardized multi-dimensional working state parameter; Step S23: performing time-series segmentation processing on the standardized multi-dimensional working state parameters to generate a multi-segment working state parameter sequence; Step S24: Perform deep state feature learning on multiple working state parameter sequences to construct a working state map of the charging device; the specific steps of step S24 are: The multiple working state parameter sequences include real-time temperature parameters, charging power and charging load; Performing temperature fluctuation analysis on real-time temperature parameters to generate charging device temperature fluctuation data; Collect the temperature fluctuation data of the charging device at multiple time points to obtain the temperature fluctuation data at multiple time points; Perform time series fitting on the temperature fluctuation data at multiple time points to construct a time series temperature fluctuation curve; Calculate the cycle peak value of the charging power and extract the charging power peak value; Performing peak cycle analysis on the charging power peak to generate a charging power peak cycle diagram; Carry out load trend evolution of charging load and generate charging load trend characteristics; According to the time series temperature fluctuation curve, the temperature-load correlation mining is carried out on the charging load trend characteristics to generate the temperature-load correlation law; Conduct deep state feature learning on the temperature-load correlation law and charging power peak cycle diagram to construct the charging device working state map; Step S3: dynamically mapping the three-dimensional topological model of the charging device based on the working state map of the charging device to construct a dynamic operation twin topological model; Step S4: simulate the dynamic operation evolution of the dynamic operation twin topology model, and perform component state evolution visualization rendering to obtain a dynamic state evolution rendering model; Step S5: Calculate component load requirements and component failure probabilities based on the dynamic state evolution rendering model. To obtain the predicted value of component load demand and the failure probability value of each component; Step S6: Dynamically control the traffic light of the mobile power charging device according to the predicted value of the component load demand and the failure probability value of each component to construct a traffic light control strategy.

2. The signal light control method of the mobile power charging device according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: performing state parameter matching on the component node spatial distribution data based on the multi-dimensional working state parameters to obtain working state matching data of each component node; Step S32: performing component node positioning integration on the charging device working state map according to the working state matching data of each component node to obtain a component positioning working state map; Step S33: Based on the component positioning working state map, the three-dimensional topological model of the charging device is dynamically mapped to construct a dynamic operation twin topological model.

3. The signal light control method of the mobile power charging device according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: defining a dynamic operation simulation time step; performing a dynamic operation evolution simulation on the dynamic operation twin topology model based on the dynamic operation simulation time step, and collecting dynamic evolution operation simulation data; Step S42: performing multi-time point state feature analysis on the dynamic evolution operation simulation data, and extracting state evolution simulation data at multiple time points; Step S43: performing component state evolution situation analysis on the state evolution simulation data at multiple time points to generate component state evolution situation characteristics at different time points; Step S44: Perform component state evolution visualization rendering on the dynamically running twin topology model according to the component state evolution situation characteristics at different time points to obtain a dynamic state evolution rendering model.

4. The signal light control method of the mobile power charging device according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: performing component global operation state evaluation on the dynamic state evolution rendering model to obtain charging device operation state evaluation data; Step S52: predicting short-term trend changes of the dynamic state evolution rendering model, thereby generating charging device short-term trend change prediction data; Step S53: Calculate the component load demand based on the short-term trend change prediction data of the charging device, and extract the component load demand prediction value; Step S54: identifying the state evolution of each component of the dynamic state evolution rendering model, and extracting the state evolution data of each component; Step S55: Calculate the component failure probability of each component based on the component load demand prediction value, and generate a failure probability value of each component.

5. The signal light control method of the mobile power charging device according to claim 1, characterized in that: The specific steps of step S6 are: Dynamically control the signal light of the mobile power charging device according to the charging device operation status evaluation data, the component load demand prediction value and the failure probability value of each component to build a signal light control strategy; The dynamic signal light control is specifically as follows: identifying the health state of the charging device operation state evaluation data, and when the charging device operation state evaluation data is greater than a preset charging device health state threshold, determining that it is in a healthy state, and generating a health state signal; Based on the health status signal, the green signal light of the mobile power charging device is always on; Perform load demand shortage analysis on the component load demand forecast value to generate load demand shortage data; generate a demand shortage signal based on the load demand shortage data, and perform a yellow signal light slow flashing process on the mobile power charging device according to the demand shortage signal; Using a preset fault probability threshold to identify the fault probability value of each component, when there is a component whose fault probability value is greater than or equal to the preset fault probability threshold, a fault alarm signal is generated; Based on the fault alarm signal, the red signal light of the mobile power charging device flashes rapidly.

6. A signal light control system for a mobile power charging device, characterized in that: The signal light control method for executing the mobile power charging device according to claim 1 comprises: A three-dimensional topology module is used to obtain the internal structure diagram of the mobile power charging device; perform component visual recognition on the internal structure diagram of the mobile power charging device, perform three-dimensional topological structure modeling, and construct a three-dimensional topological model of the charging device; A state map module is used to obtain multi-dimensional working state parameters of a mobile power charging device; perform deep state feature learning on the multi-dimensional working state parameters to construct a working state map of the charging device; A dynamic state mapping module is used to dynamically map the three-dimensional topological model of the charging device based on the working state map of the charging device, and to construct a dynamic operation twin topological model; The dynamic operation evolution module is used to simulate the dynamic operation evolution of the dynamic operation twin topology model and perform visual rendering of the component state evolution to obtain a dynamic state evolution rendering model; A state prediction module is used to calculate component load demand and component failure probability based on a dynamic state evolution rendering model to obtain component load demand prediction values ​​and failure probability values ​​of each component; The signal light control module is used to dynamically control the signal lights of the mobile power charging device according to the predicted value of component load demand and the failure probability value of each component, so as to construct a signal light control strategy.

Images