Mechanical arm cleaning robot system based on zero-code digital twinning

Abstract

The application provides a mechanical arm cleaning robot system and design method based on zero code digital twinning, and relates to the technical field of cleaning robot design. The method comprises the following steps: establishing a three-dimensional digital twinning model of a locomotive object scene based on a locomotive body cleaning scene; collecting a mechanical arm digital twinning model of a cleaning mechanical arm, performing digital twinning driving, and forming mechanical arm basic driving data; obtaining locomotive body recognition classification data, and forming mechanical arm optimized cleaning scheme data; obtaining locomotive cleaning image data, and establishing a cleaning effect evaluation model; performing locomotive cleaning operation based on the mechanical arm optimized cleaning scheme data, and forming real-time monitoring and maintenance analysis result data; and performing intelligent operation analysis according to the real-time monitoring and maintenance analysis result data, and forming intelligent operation analysis result data. The method improves the intelligentization, self-adaptation and collaboration of the cleaning robot, improves the quality and efficiency of the cleaning service, and provides technical support for the innovative development of the cleaning industry.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cleaning robot design, in particular to a mechanical arm cleaning robot system based on zero-code digital twinning. BACKGROUND

[0002] With the development of industrialization and urbanization, the cleaning work of large facilities such as high-rise buildings, airplanes and ships is increasing, but the traditional manual cleaning method has problems such as low efficiency, high cost and poor safety, which limits the quality and scale of cleaning services. According to statistics, the global cleaning service market reached 1.74 trillion US dollars in 2020, and is expected to grow to 2.41 trillion US dollars in 2027, with a compound annual growth rate of 4.8%. However, the cleaning industry still faces technical bottlenecks and development challenges, such as the complexity of the surface shape and structure of the cleaning object, the variability of the environmental conditions of the cleaning object, the difference in cleaning requirements and standards of the cleaning object, and the complexity of the collaborative tasks of the cleaning object and the cleaning tool. Therefore, it is of great engineering significance and social value to develop an intelligent, efficient and safe cleaning robot system.

[0003] Locomotives are widely used transportation tools, and the cleaning work of their bodies and parts is an important link to ensure the running performance and safety of locomotives. However, the current cleaning work of locomotives mainly relies on manual or cleaning robots based on tracks, vehicles, drones, etc. These methods have some shortcomings, such as insufficient adaptability to the complex shape and structure of the locomotive body and parts, weak positioning and recognition ability of the locomotive body and parts, difficulty in achieving precise and flexible cleaning actions, low adjustment ability of cleaning parameters, poor evaluation ability of cleaning effect, low utilization efficiency of cleaning resources, low adaptability to cleaning environment, poor cleaning safety and reliability, etc.

[0004] Therefore, it is urgent to design a mechanical arm cleaning robot system based on zero-code digital twinning technology, which realizes real-time digital twinning driving of the locomotive body and parts, improves the intelligent, adaptive and collaborative ability of the cleaning robot, and improves the quality and efficiency of cleaning services, providing technical support for the innovative development of the cleaning industry. SUMMARY

[0005] The purpose of the present application is to provide a mechanical arm cleaning robot system based on zero-code digital twinning, which realizes real-time digital twinning driving of the locomotive body and parts, improves the intelligent, adaptive and collaborative ability of the cleaning robot, and improves the quality and efficiency of cleaning services, providing technical support for the innovative development of the cleaning industry.

[0006] In a first aspect, the present application provides a mechanical arm cleaning robot design method based on zero-code digital twinning, comprising: based on a locomotive body cleaning scene, establishing a three-dimensional digital twinning model of a locomotive object scene for a cleaning object through a zero-code platform; collecting a mechanical arm digital twinning model of a cleaning mechanical arm, and combining the three-dimensional data twinning model of the locomotive object scene to perform digital twinning driving to form mechanical arm basic driving data; obtaining locomotive body recognition classification data, and combining the mechanical arm basic driving data to perform cleaning strategy and scheme generation optimization analysis to form mechanical arm optimized cleaning scheme data; obtaining locomotive cleaning image data, and performing cleaning effect evaluation analysis to establish a cleaning effect evaluation model; based on the mechanical arm optimized cleaning scheme data, performing locomotive cleaning operation, collecting real-time cleaning data for operation monitoring and maintenance analysis to form real-time monitoring and maintenance analysis result data; and performing intelligent operation analysis according to the real-time monitoring and maintenance analysis result data to form intelligent operation analysis result data.

[0007] In the present application, the method improves the intelligentization, self-adaptation and collaboration of the cleaning robot by realizing real-time digital twinning driving of the locomotive body and parts, improves the quality and efficiency of cleaning services, and provides technical support for the innovative development of the cleaning industry.

[0008] As a possible implementation manner, based on a locomotive body cleaning scene, a three-dimensional digital twinning model of a locomotive cleaning scene for a cleaning object is established through a zero-code platform, comprising: based on a locomotive body cleaning scene, a digital twinning model of main equipment in the scene is established through a zero-code platform to form a locomotive cleaning scene three-dimensional digital twinning model matching the real cleaning scene; real-time data of the locomotive body and parts are collected, and data twinning models of different locomotive bodies and parts are established using the zero-code platform to form a locomotive body three-dimensional data twinning model.

[0009] In the present application, the locomotive body cleaning scene is a specific application scene, and a self-developed zero-code platform is used to quickly build a digital twinning model of the locomotive body and the locomotive cleaning scene, and main equipment in the scene, such as a cleaning disc with a member, a dry ice tank, an ice maker, an AGV trolley, an AGV parking space, and an AGV charging pile. Through the zero-code digital twinning development platform, the digital twinning application can be quickly built and delivered through dragging and dropping without writing any code, greatly reducing the development threshold and difficulty.

[0010] As a possible implementation manner, a mechanical arm digital twin model of the cleaning mechanical arm is collected, and a locomotive object three-dimensional data twin model is combined to perform digital twin driving to form mechanical arm basic driving data, including: combining plug-in technology, Internet of Things technology and big data technology, determining basic driving information of the cleaning robot according to the locomotive cleaning scene three-dimensional data twin model and the locomotive body three-dimensional data twin model, and forming the mechanical arm basic driving data.

[0011] In the present application, based on the digital twin model, the plug-in technology, the Internet of Things technology and the big data technology are used to realize the real-time digital twin driving of the mechanical arm of the cleaning robot and the cooperative control with the AGV trolley, and the real-time cleaning operation and feedback of the locomotive body are realized. Through rich industry templates and resources, the basic parameters of the digital twin model can be set according to the actual parameters and model of the locomotive cleaning mechanical arm, such as joint sensitivity, joint activity range, upper limit of linear velocity and acceleration of each joint, motion data compensation, etc., to realize the digital twin driving of the locomotive cleaning mechanical arm.

[0012] As a possible implementation manner, locomotive body recognition and classification data are obtained, and cleaning strategy and scheme generation optimization analysis is performed in combination with the mechanical arm basic driving data to form mechanical arm optimized cleaning scheme data, including: obtaining image data of different locomotive bodies and parts, and performing feature extraction and classification to form locomotive body classification and recognition data; collecting cleaning action control data, and combining the locomotive body classification and recognition data and the mechanical arm basic driving data to generate a strategy scheme based on model training, and obtaining cleaning effect data in the model training process, using the cleaning effect data as the direction guide for model training, optimizing the strategy scheme, and forming the mechanical arm optimized cleaning scheme data.

[0013] In the present application, based on the digital twin model, the machine learning technology is used to realize intelligent recognition and classification of locomotive bodies and parts, and according to different vehicle types, vehicle numbers, vehicle lengths, vehicle widths, vehicle heights, vehicle ages, vehicle conditions, etc., corresponding cleaning strategies and schemes are generated and optimized.

[0014] As a possible implementation manner, image data of different locomotive bodies and parts are obtained, and feature extraction and classification are performed to form locomotive body classification and recognition data, including: using a transfer learning method, selecting a pre-trained ResNet-50 model as a basic network, and fine-tuning and training according to a specific data set, wherein: in the model training process, the feature extraction capability of the ResNet-50 is preserved by freezing part of the layers, and the model is fine-tuned on the unfrozen layers to make the model better adapt to the locomotive recognition requirements; the training uses a labeled data set to adjust the model parameters using a loss function and an optimization algorithm to improve the recognition accuracy, and the generalization ability of the model is ensured through cross-validation and test set evaluation.

[0015] In the present application, the intelligent recognition and classification scheme constructs a convolutional neural network (CNN) model through deep learning technology for feature extraction and classification of locomotive body and component images. The transfer learning method is adopted, and the pre-trained ResNet-50 model is selected as the base network, and fine-tuning and training are performed according to the specific data set. The data set contains images and labels of various types of locomotive bodies and components, including high-speed trains, bullet trains, ordinary trains, and components such as locomotive heads, carriages, wheels, and windows. During model training, the feature extraction capability of ResNet-50 is preserved by freezing part of its layers, and fine-tuning is performed on the unfrozen layers to make the model better adapt to the locomotive recognition requirements. The training uses the labeled data set, and the loss function and optimization algorithm are used to adjust the model parameters to improve the recognition accuracy. Cross-validation and test set evaluation are used to ensure the generalization ability of the model. Through the digital twin development tool of the self-developed zero-code platform, the model is quickly deployed to the intelligent recognition system to realize real-time image acquisition and processing. The model performs feature extraction and classification on the collected images and outputs the corresponding labels to help maintenance personnel identify different types of locomotive bodies and components. At the same time, the system continuously accumulates data through the feedback mechanism, continuously optimizes the model performance, and can realize fault recognition and automatic warning functions, such as triggering a warning and maintenance task when identifying body damage or component wear, improving the intelligent and automated level of locomotive maintenance.

[0016] As a possible implementation, the generation of the strategy scheme generation adopts the following way: a strategy-based method is adopted, and the Actor-Critic algorithm is used as the learning framework to learn and update according to the environment and reward function, wherein: the environment includes the state of the locomotive body and components and the state of the cleaning robot; in the process of determining the cleaning strategy, the cleaning efficiency, cleaning quality and cleaning cost are comprehensively considered, and the reward function guides the model to generate high-quality cleaning strategies.

[0017] In the present application, a deep reinforcement learning (DRL) model is constructed using reinforcement learning techniques to generate and optimize cleaning strategies and solutions for locomotive bodies and components. A policy-based approach is adopted, using the Actor-Critic algorithm as the learning framework, and learning and updating based on the environment and reward function. The environment includes the state of the locomotive body and components, such as dirt level, surface temperature, surface material, etc., as well as the state of the cleaning robot, such as position, angle, speed, water pressure, water temperature, etc. In the process of determining the cleaning strategy, the reward function guides the model to generate high-quality cleaning strategies by considering cleaning efficiency, cleaning quality, and cleaning cost. In terms of cleaning efficiency, the reward function rewards the cleaning coverage area or progress, encouraging the improvement of cleaning speed; in terms of cleaning quality, a target quality standard is set to score the thoroughness of dirt removal and surface cleanliness, and a high reward is given if the target value is reached or approached; in terms of cleaning cost, factors such as dry ice, electricity, and time are considered, and operations that consume fewer resources but achieve the same cleanliness will receive higher rewards, thus guiding the model to choose low-cost solutions. During model training, through sampling and exploration, the model constantly tries different combinations of cleaning actions, gradually finding the best cleaning strategy. Using the zero-code digital twin development tools provided by the self-developed zero-code platform, the intelligent cleaning strategy and solution model is quickly constructed and deployed, realizing real-time cleaning operations and feedback for locomotive bodies and components.

[0018] As a possible implementation, locomotive cleaning image data is acquired, and cleaning effect evaluation and analysis are performed to establish a cleaning effect evaluation model, including: according to the locomotive cleaning image data, using a full convolution network method, using a U-Net model as a segmentation network, training and testing according to a data set, wherein: the data set includes images of locomotive bodies and components before and after cleaning, and corresponding segmentation labels.

[0019] In the present application, an image segmentation model is constructed using computer vision techniques to detect and evaluate the cleaning effect of locomotive bodies and components. A full convolution network (FCN) method is used, with a U-Net model as the segmentation network, trained and tested according to a data set. The data set includes images of locomotive bodies and components before and after cleaning, and corresponding segmentation labels, such as clean areas, dirt areas, water stain areas, etc. Using the zero-code digital twin development tools provided by the self-developed zero-code platform, the intelligent cleaning effect and evaluation model is quickly constructed and deployed, realizing real-time cleaning effect and evaluation analysis and display for locomotive bodies and components.

[0020] As a possible implementation manner, the locomotive cleaning operation is performed based on the mechanical arm optimized cleaning scheme data, real-time cleaning data is collected for operation monitoring and maintenance analysis, and real-time monitoring and maintenance analysis result data is formed, including: using Internet of Things technology, realizing collection and transmission of real-time operation data of the cleaning mechanical arm through various sensors and communication modules installed on the cleaning robot; using big data technology, establishing a database of historical data and fault data for the real-time operation data of the cleaning mechanical arm, and using artificial intelligence technology to realize operation monitoring and maintenance analysis of the cleaning mechanical arm, and forming real-time monitoring and maintenance analysis result data.

[0021] In the present application, using Internet of Things technology, through various sensors and communication modules installed on the cleaning robot, the real-time collection and transmission of data such as the working state, operating parameters and environmental information of the cleaning robot are realized. Remote control and scheduling of the cleaning robot are realized. Using the zero-code digital twin development tool provided by the self-developed zero-code platform, the digital twin model of the cleaning robot is quickly built and deployed, realizing real-time visualization and interaction of the cleaning robot. Using big data technology, a database of historical data and fault data is established for the cleaning robot, realizing data mining and statistical analysis of the cleaning robot. Using artificial intelligence technology, a deep neural network (DNN) model is constructed for detecting and identifying faults of the cleaning robot. Using the method of transfer learning, a pre-trained ResNet-50 model is used as the base network, and fine-tuning and training are performed according to the data set. The data set includes fault data of different types of cleaning robots and corresponding labels, such as motor failure, water pump failure, nozzle blockage, sensor failure, etc. Using the zero-code digital twin development tool provided by the self-developed zero-code platform, the intelligent diagnosis model is quickly built and deployed, realizing real-time fault detection and identification of the cleaning robot. In addition, using data analysis and visualization technology, comprehensive performance evaluation and optimization suggestions are provided for the cleaning robot. Using data analysis technology, the running data of the cleaning robot is analyzed in multiple dimensions, such as cleaning efficiency, cleaning quality, cleaning cost, cleaning energy consumption, etc., the key performance indicators (KPI) of the cleaning robot are calculated, and compared with industry standards and similar robots. Using visualization technology, the performance evaluation results of the cleaning robot are intuitively displayed, such as line chart, column chart, pie chart, dashboard, etc., and optimization suggestions and improvement measures for the cleaning robot are provided.

[0022] As a possible implementation manner, according to the real-time monitoring and maintenance analysis result data, intelligent operation analysis is performed, and intelligent operation analysis result data is formed, including: using data analysis and machine learning technology, establishing an operation cost evaluation model for the cleaning mechanical arm according to the real-time monitoring and maintenance analysis result data, realizing accounting and evaluation of the operation cost of the cleaning robot.

[0023] In the present application, data analysis and machine learning techniques are used to establish an operation effect evaluation model for the cleaning robot, realizing the quantification and evaluation of the operation effect of the cleaning robot. Data analysis and machine learning techniques are used to establish an operation cost evaluation model for the cleaning robot, realizing the accounting and evaluation of the operation cost of the cleaning robot. Data analysis and machine learning techniques are used to establish an operation risk evaluation model for the cleaning robot, realizing the identification and evaluation of the operation risk of the cleaning robot. In addition, on this basis, optimization algorithm and reinforcement learning techniques are used to establish an operation effect optimization model for the cleaning robot, realizing the improvement and optimization of the operation effect of the cleaning robot. Optimization algorithm and reinforcement learning techniques are used to establish an operation cost optimization model for the cleaning robot, realizing the reduction and optimization of the operation cost of the cleaning robot. Optimization algorithm and reinforcement learning techniques are used to establish an operation risk optimization model for the cleaning robot, realizing the control and optimization of the operation risk of the cleaning robot. Visualization and virtual reality techniques are used to provide visual and interactive display of operation data for the cleaning robot, allowing the operator to intuitively understand the operation status and operation effect of the cleaning robot. The zero-code digital twin development tool provided by the self-developed zero-code platform is used to quickly build and deploy intelligent display models, realizing real-time visualization and interaction of the cleaning robot.

[0024] In a second aspect, the present application provides a mechanical arm cleaning robot system based on zero-code digital twin, which adopts the mechanical arm cleaning robot design method based on zero-code digital twin of the first aspect, comprising: an Internet of Things system for collecting Internet of Things data including locomotive body cleaning scene, locomotive body identification and classification data, locomotive cleaning image data, and real-time cleaning data; a big data system for collecting big data information including mechanical arm data twin model; an analysis and processing system for generating mechanical arm basic driving data using the mechanical arm data twin model collected by the big data system, performing cleaning strategy and scheme generation optimization analysis using the locomotive body identification and classification data collected by the Internet of Things system combined with the mechanical arm basic driving data, forming mechanical arm optimized cleaning scheme data, performing cleaning effect evaluation analysis using the locomotive cleaning image data collected by the Internet of Things system, establishing a cleaning effect evaluation model, performing running monitoring and maintenance analysis using the real-time cleaning data collected by the Internet of Things system, forming real-time monitoring and maintenance analysis result data, and performing intelligent operation analysis using the real-time monitoring and maintenance analysis result data, forming intelligent operation analysis result data; a zero-code platform for establishing a three-dimensional digital twin model of a locomotive object scene, and quickly building and deploying the mechanical arm optimized cleaning scheme data, the cleaning effect evaluation model, the real-time monitoring and maintenance analysis result data, and the intelligent operation analysis result data on the platform.

[0025] In the application, the system forms a close mechanical arm cleaning robot design comprehensive system through an Internet of Things system, a big data system, an analysis processing system and a zero code platform, fully guarantees real-time monitoring and intelligent cleaning of the locomotive body and parts, and improves the operation and maintenance efficiency and reliability of the cleaning robot, and is an important material basis for establishing a good mechanical arm cleaning robot design system.

[0026] The application provides a mechanical arm cleaning robot system based on zero code digital twinning.

[0027] The method improves the intelligentization, self-adaptation and collaboration of the cleaning robot through real-time digital twinning driving of the locomotive body and parts, improves the quality and efficiency of cleaning services, and provides technical support for the innovative development of the cleaning industry.

[0028] The system forms a close mechanical arm cleaning robot design comprehensive system through an Internet of Things system, a big data system, an analysis processing system and a zero code platform, fully guarantees real-time monitoring and intelligent cleaning of the locomotive body and parts, and improves the operation and maintenance efficiency and reliability of the cleaning robot, and is an important material basis for establishing a good mechanical arm cleaning robot design system. BRIEF DESCRIPTION OF DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments of the application. It should be understood that the following drawings only show some embodiments of the application, and therefore should not be regarded as a limitation to the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0030] Figure 1 The application provides a mechanical arm cleaning robot system based on zero code digital twinning. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the application will be described below with reference to the drawings in the embodiments of the application.

[0032] With the development of industrialization and urbanization, the cleaning work of high-rise buildings, airplanes, ships and other large facilities is increasing, but the traditional manual cleaning method has low efficiency, high cost, poor safety and other problems, which limits the quality and scale of cleaning services. According to statistics, the global cleaning service market size reached 1.74 trillion US dollars in 2020, and is expected to grow to 2.41 trillion US dollars in 2027, with a compound annual growth rate of 4.8%. However, the cleaning industry still faces technical bottlenecks and development challenges, such as the complexity of the surface shape and structure of the cleaning object, the variability of the environmental conditions of the cleaning object, the difference of the cleaning requirements and standards of the cleaning object, and the complexity of the collaborative task of the cleaning object and the cleaning tool. Therefore, it is of great engineering significance and social value to develop an intelligent, efficient and safe cleaning robot system.

[0033] Locomotives are widely used transportation tools, and the cleaning work of their bodies and parts is an important part of ensuring the performance and safety of locomotives. However, the current cleaning work of locomotives mainly relies on manual or cleaning robots based on tracks, vehicles, drones, etc. These methods have some shortcomings, such as insufficient adaptability to the complex shape and structure of the locomotive body and parts, weak positioning and recognition ability of the locomotive body and parts, difficulty in achieving precise and flexible cleaning actions, low adjustment ability of cleaning parameters, poor evaluation ability of cleaning effect, low utilization efficiency of cleaning resources, low adaptability to cleaning environment, poor cleaning safety and reliability, etc.

[0034] Reference Figure 1 The embodiment of the present application provides a kind of mechanical arm cleaning robot design method based on zero code digital twinning, which improves the intelligentization, self-adaptation and collaboration ability of cleaning robot by realizing the real-time digital twinning driving of locomotive body and parts, improves the quality and efficiency of cleaning service, and provides technical support for the innovation and development of cleaning industry.

[0035] The mechanical arm cleaning robot system based on zero code digital twinning is configured to:

[0036] S1: based on the locomotive body cleaning scene, a three-dimensional digital twin model of the locomotive object scene for the cleaning object is established through the zero code platform.

[0037] Based on the locomotive body cleaning scene, a three-dimensional digital twin model of the locomotive cleaning scene for the cleaning object is established through the zero-code platform, including: based on the locomotive body cleaning scene, the digital twin model of the main equipment in the scene is established through the zero-code platform, forming a three-dimensional digital twin model of the locomotive cleaning scene matching the real cleaning scene; collecting real-time data of the locomotive body and parts, and using the zero-code platform to establish data twin models of different locomotive bodies and parts, forming a three-dimensional data twin model of the locomotive body.

[0038] Taking the locomotive body cleaning scene as a specific application scene, using a self-developed zero-code platform and using zero-code technology, a digital twin model of the locomotive body and the locomotive cleaning scene, as well as the main equipment in the scene, such as the cleaning disc of the belt member, the dry ice tank, the ice maker, the AGV trolley, the AGV parking space, and the AGV charging pile, is quickly constructed. Among them, through the zero-code digital twin development platform, the digital twin application can be quickly built and delivered through drag-and-drop without writing any code, greatly reducing the development threshold and difficulty.

[0039] S2: Collect the mechanical arm digital twin model of the cleaning mechanical arm, and combine the three-dimensional data twin model of the locomotive object scene to perform digital twin driving to form the basic driving data of the mechanical arm.

[0040] Collect the mechanical arm digital twin model of the cleaning mechanical arm, and combine the three-dimensional data twin model of the locomotive object to perform digital twin driving to form the basic driving data of the mechanical arm, including: combining the plug-in technology, Internet of Things technology, and big data technology for locomotive cleaning, determining the basic driving information of the cleaning robot according to the three-dimensional data twin model of the locomotive cleaning scene and the three-dimensional data twin model of the locomotive body, and forming the basic driving data of the mechanical arm.

[0041] Based on the digital twin model, using plug-in technology, Internet of Things technology, and big data technology, real-time digital twin driving of the mechanical arm of the cleaning robot and collaborative control with the AGV trolley are realized, and real-time cleaning operation and feedback of the locomotive body are realized. Through rich industry templates and resources, the basic parameters of the digital twin body model can be set according to the actual parameters and models of the locomotive cleaning mechanical arm, such as joint sensitivity, joint activity range, upper limit of linear velocity and acceleration of each joint, motion data compensation, etc., to realize digital twin driving of the locomotive cleaning mechanical arm.

[0042] S3: Obtain locomotive body recognition and classification data, and combine the basic driving data of the mechanical arm to perform cleaning strategy and scheme generation and optimization analysis to form mechanical arm optimized cleaning scheme data.

[0043] The locomotive body recognition classification data is acquired, and the cleaning strategy and scheme generation optimization analysis is performed in combination with the mechanical arm basic driving data to form the mechanical arm optimized cleaning scheme data, including: acquiring image data of different locomotive bodies and parts, and performing feature extraction and classification to form locomotive body classification recognition data; collecting cleaning action control data, and combining the locomotive body classification recognition data and the mechanical arm basic driving data to generate a strategy scheme based on model training, and acquiring cleaning effect data in the model training process, taking the cleaning effect data as the direction guide for realizing the model training, optimizing the strategy scheme, and forming the mechanical arm optimized cleaning scheme data.

[0044] Based on the digital twin model, the intelligent recognition and classification of the locomotive body and parts are realized by using the machine learning technology, and the corresponding cleaning strategy and scheme are generated and optimized according to different vehicle types, vehicle numbers, vehicle lengths, vehicle widths, vehicle heights, vehicle ages, vehicle conditions and other information.

[0045] Among them, the image data of different locomotive bodies and parts is acquired, and the feature extraction and classification are performed to form the locomotive body classification recognition data, including: using the transfer learning method, selecting a pre-trained ResNet-50 model as a basic network, and performing fine-tuning and training according to a specific data set, wherein: in the model training process, the feature extraction ability of the ResNet-50 is preserved by freezing part of the layers, and the fine-tuning is performed on the unfrozen layers, so that the model better adapts to the locomotive recognition requirement; the training uses a labeled data set, and the model parameters are adjusted by using a loss function and an optimization algorithm to improve the recognition accuracy, and the generalization ability of the model is guaranteed through cross-validation and test set evaluation.

[0046] The intelligent recognition and classification scheme constructs a convolutional neural network (CNN) model through deep learning technology for feature extraction and classification of locomotive body and component images. The transfer learning method is adopted, and the pre-trained ResNet-50 model is selected as the basic network, and then fine-tuned and trained according to the specific data set. The data set contains images and labels of various types of locomotive bodies and components, including high-speed trains, bullet trains, ordinary trains, and components such as locomotive heads, carriages, wheels, and windows. During the model training process, the feature extraction ability of the ResNet-50 model is preserved by freezing part of its layers, and the model is fine-tuned on the unfrozen layers to better adapt to the locomotive recognition requirements. The training uses the labeled data set, and the loss function and optimization algorithm are used to adjust the model parameters to improve the recognition accuracy. Cross-validation and test set evaluation are used to ensure the generalization ability of the model. Through the digital twin development tool of the self-developed zero-code platform, the model is quickly deployed to the intelligent recognition system to realize real-time image acquisition and processing. The model performs feature extraction and classification on the collected images and outputs the corresponding labels to help maintenance personnel identify different types of locomotive bodies and components. At the same time, the system continuously accumulates data through a feedback mechanism to continuously optimize the model performance and realize fault recognition and automatic warning functions, such as triggering a warning and maintenance task when identifying body damage or component wear, thereby improving the intelligent and automated level of locomotive maintenance.

[0047] The generation of the strategy scheme is generated in the following way: a strategy-based method is adopted, and the Actor-Critic algorithm is used as the learning framework to learn and update according to the environment and reward function, where: the environment includes the state of the locomotive body and components and the state of the cleaning robot; during the determination of the cleaning strategy, the cleaning efficiency, cleaning quality, and cleaning cost are comprehensively considered, and the reward function guides the model to generate high-quality cleaning strategies.

[0048] A deep reinforcement learning (DRL) model is constructed using reinforcement learning techniques to generate and optimize cleaning strategies and solutions for locomotive bodies and components. A policy-based approach is adopted, using the Actor-Critic algorithm as the learning framework, and learning and updating based on the environment and reward function. The environment includes the state of the locomotive body and components, such as dirt level, surface temperature, surface material, etc., as well as the state of the cleaning robot, such as position, angle, speed, water pressure, water temperature, etc. In determining the cleaning strategy, the reward function guides the model to generate high-quality cleaning strategies by considering cleaning efficiency, cleaning quality, and cleaning cost. In terms of cleaning efficiency, the reward function rewards the cleaning coverage area or progress, encouraging the improvement of cleaning speed; in terms of cleaning quality, a target quality standard is set to score the thoroughness of dirt removal and surface cleanliness, and a high reward is given if the target value is reached or approached; in terms of cleaning cost, factors such as dry ice, electricity, and time are considered, and operations that consume fewer resources but achieve the same cleanliness will receive higher rewards, guiding the model to choose low-cost solutions. During model training, the model continuously tries different combinations of cleaning actions through sampling and exploration, gradually finding the best cleaning strategy. Using the zero-code digital twin development tools provided by the self-developed zero-code platform, the intelligent cleaning strategy and solution model is quickly constructed and deployed, realizing real-time cleaning operations and feedback for locomotive bodies and components.

[0049] S4: Obtain locomotive cleaning image data and perform cleaning effect evaluation analysis to establish a cleaning effect evaluation model.

[0050] Obtain locomotive cleaning image data and perform cleaning effect evaluation analysis to establish a cleaning effect evaluation model, including: based on the locomotive cleaning image data, using the full convolution network method, using the U-Net model as the segmentation network, training and testing according to the data set, wherein: the data set includes images of locomotive bodies and components before and after cleaning, and corresponding segmentation labels.

[0051] An image segmentation model is constructed using computer vision technology to detect and evaluate the cleaning effect of locomotive bodies and components. A full convolution network (FCN) method is used, with a U-Net model as the segmentation network, trained and tested according to the data set. The data set includes images of locomotive bodies and components before and after cleaning, and corresponding segmentation labels such as clean areas, dirt areas, and water stains. Using the zero-code digital twin development tools provided by the self-developed zero-code platform, the intelligent cleaning effect and evaluation model is quickly constructed and deployed, realizing real-time cleaning effect and evaluation analysis and display for locomotive bodies and components.

[0052] S5: Perform locomotive cleaning operation based on the mechanical arm optimized cleaning scheme data, and collect real-time cleaning data for operation monitoring and maintenance analysis to form real-time monitoring and maintenance analysis result data.

[0053] Perform locomotive cleaning operation based on the mechanical arm optimized cleaning scheme data, and collect real-time cleaning data for operation monitoring and maintenance analysis to form real-time monitoring and maintenance analysis result data, including: using Internet of Things technology, through various sensors and communication modules installed on the cleaning robot, realizing the collection and transmission of real-time operation data of the cleaning mechanical arm; using big data technology, establishing a database of historical data and fault data for the real-time operation data of the cleaning mechanical arm, and using artificial intelligence technology to realize the operation monitoring and maintenance analysis of the cleaning mechanical arm, forming real-time monitoring and maintenance analysis result data.

[0054] Using Internet of Things technology, through various sensors and communication modules installed on the cleaning robot, realize the real-time collection and transmission of data such as the working state, operating parameters, and environmental information of the cleaning robot. Realize the remote control and scheduling of the cleaning robot. Through the zero-code digital twin development tool provided by the self-developed zero-code platform, quickly build and deploy the digital twin model of the cleaning robot, realize the real-time visualization and interaction of the cleaning robot. Using big data technology, a database of historical data and fault data is established for the cleaning robot, realizing data mining and statistical analysis of the cleaning robot. Using artificial intelligence technology, a deep neural network (DNN) model is constructed for detecting and identifying the faults of the cleaning robot. Using the method of transfer learning, a pre-trained ResNet-50 model is used as the base network, and fine-tuning and training are performed according to the data set. The data set includes fault data of different types of cleaning robots and corresponding labels, such as motor failure, water pump failure, nozzle blockage, and sensor failure. Using the zero-code digital twin development tool provided by the self-developed zero-code platform, quickly build and deploy the intelligent diagnosis model, realize the real-time fault detection and identification of the cleaning robot. In addition, using data analysis and visualization technology, comprehensive performance evaluation and optimization suggestions are provided for the cleaning robot. Using data analysis technology, the running data of the cleaning robot is analyzed in multiple dimensions, such as cleaning efficiency, cleaning quality, cleaning cost, and cleaning energy consumption, and the key performance indicators (KPI) of the cleaning robot are calculated and compared with industry standards and similar robots. Using visualization technology, the performance evaluation results of the cleaning robot are visually displayed, such as line charts, column charts, pie charts, and dashboards, and optimization suggestions and improvement measures for the cleaning robot are provided.

[0055] S6: Perform intelligent operation analysis according to the real-time monitoring and maintenance analysis result data to form intelligent operation analysis result data.

[0056] Intelligent operation analysis is performed according to the real-time monitoring maintenance analysis result data to form intelligent operation analysis result data, including: an operation cost evaluation model is established for the cleaning robot according to the real-time monitoring maintenance analysis result data by using data analysis and machine learning technology, and operation cost of the cleaning robot is calculated and evaluated.

[0057] An operation effect evaluation model is established for the cleaning robot by using data analysis and machine learning technology, and operation effect of the cleaning robot is quantified and evaluated. An operation cost evaluation model is established for the cleaning robot by using data analysis and machine learning technology, and operation cost of the cleaning robot is calculated and evaluated. An operation risk evaluation model is established for the cleaning robot by using data analysis and machine learning technology, and operation risk of the cleaning robot is identified and evaluated. In addition, on this basis, an operation effect optimization model is established for the cleaning robot by using optimization algorithm and reinforcement learning technology, and operation effect of the cleaning robot is improved and optimized. An operation cost optimization model is established for the cleaning robot by using optimization algorithm and reinforcement learning technology, and operation cost of the cleaning robot is reduced and optimized. An operation risk optimization model is established for the cleaning robot by using optimization algorithm and reinforcement learning technology, and operation risk of the cleaning robot is controlled and optimized. Visualization and virtual reality technology is used to provide visualized and interactive display of operation data of the cleaning robot, so that the operator can intuitively understand the operation status and operation effect of the cleaning robot. A zero-code digital twin development tool provided by a self-developed zero-code platform is used to quickly build and deploy an intelligent display model, and real-time visualization and interaction of the cleaning robot are realized.

[0058] The application also provides a mechanical arm cleaning robot system based on zero-code digital twinning, which adopts the mechanical arm cleaning robot design method based on zero-code digital twinning, and comprises: an Internet of Things system, which is used for collecting Internet of Things data including locomotive body cleaning scenes, locomotive body identification and classification data, locomotive cleaning image data, and real-time cleaning data; a big data system, which is used for collecting big data information including a mechanical arm data twin model; an analysis and processing system, which is used for generating mechanical arm basic driving data by using the mechanical arm data twin model collected by the big data system, performing cleaning strategy and scheme generation optimization analysis by using the locomotive body identification and classification data collected by the Internet of Things system and combining the mechanical arm basic driving data, forming mechanical arm optimized cleaning scheme data, evaluating and analyzing cleaning effect by using the locomotive cleaning image data collected by the Internet of Things system, establishing a cleaning effect evaluation model, performing operation monitoring and maintenance analysis by using the real-time cleaning data collected by the Internet of Things system, forming real-time monitoring and maintenance analysis result data, and performing intelligent operation analysis by using the real-time monitoring and maintenance analysis result data to form intelligent operation analysis result data; and a zero-code platform, which is used for establishing a locomotive object scene three-dimensional digital twin model, and realizing rapid construction and deployment of the mechanical arm optimized cleaning scheme data, the cleaning effect evaluation model, the real-time monitoring and maintenance analysis result data and the intelligent operation analysis result data on the platform.

[0059] The system forms a close mechanical arm cleaning robot design comprehensive system through the Internet of Things system, the big data system, the analysis and processing system and the zero-code platform, fully guarantees real-time monitoring and intelligent cleaning of the locomotive body and parts, and improves the operation and maintenance efficiency and reliability of the cleaning robot, and is an important material basis for establishing a good mechanical arm cleaning robot design system.

[0060] In summary, the mechanical arm cleaning robot system based on zero-code digital twinning has the following beneficial effects:

[0061] The method realizes real-time digital twin driving of the locomotive body and parts, improves the intelligent, adaptive and collaborative capabilities of the cleaning robot, improves the quality and efficiency of cleaning services, and provides technical support for the innovative development of the cleaning industry.

[0062] The system forms a close mechanical arm cleaning robot design comprehensive system through the Internet of Things system, the big data system, the analysis and processing system and the zero-code platform, fully guarantees real-time monitoring and intelligent cleaning of the locomotive body and parts, and improves the operation and maintenance efficiency and reliability of the cleaning robot, and is an important material basis for establishing a good mechanical arm cleaning robot design system.

[0063] In the embodiments of the present application, the indication can include direct indication and indirect indication, and can also include explicit indication and implicit indication. The information indicated by certain information is referred to as to-be-indicated information. In the implementation process, there are many ways to indicate the to-be-indicated information, for example, but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or an index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. The to-be-indicated information can also be indicated only by a part of the to-be-indicated information, and the other part of the to-be-indicated information is known or agreed in advance. For example, the indication of a specific information can also be achieved by means of the arrangement order of various information agreed in advance (for example, specified by a protocol), thereby reducing the indication overhead to a certain extent. Meanwhile, a common part of various information can be identified and uniformly indicated, so as to reduce the indication overhead caused by separately indicating the same information.

[0064] In addition, the specific indication manner can also be various existing indication manners, for example, but not limited to, the above indication manners and various combinations thereof. The specific details of various indication manners can refer to the prior art, and will not be described herein. As known from the above, for example, when multiple information of the same type needs to be indicated, the indication manners of different information can be different. In the implementation process, the required indication manner can be selected according to the specific needs, and the selected indication manner is not limited in the embodiments of the present application. In this way, the indication manner involved in the embodiments of the present application should be understood as covering various methods that can enable the to-be-indicated party to know the to-be-indicated information.

[0065] It should be understood that the to-be-indicated information can be sent as a whole, or can be divided into multiple sub-information and sent separately, and the sending period and / or sending occasion of the sub-information can be the same or different. The specific sending method is not limited in the embodiments of the present application. The sending period and / or sending occasion of the sub-information can be pre-defined, for example, pre-defined according to a protocol, or configured by the sending end device by sending configuration information to the receiving end device.

[0066] The "pre-definition" or "pre-configuration" can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate related information in the device, and the specific implementation manner is not limited in the embodiments of the present application. The "saving" can mean saving in one or more memories. The one or more memories can be separately set, or integrated in the encoder or decoder, processor, or communication device. The one or more memories can be partially separately set and partially integrated in the decoder, processor, or communication device. The type of the memory can be any form of storage medium, and the present application is not limited thereto.

[0067] The "protocol" referred to in the embodiments of the present application can refer to a protocol family in the communication field, a standard protocol similar to the protocol family frame structure, or a related protocol applied to a future communication system, and the embodiments of the present application do not make specific limitations thereon.

[0068] In the embodiments of the present application, "when", "in the case of", "if", and the like all refer to the device making corresponding processing under certain objective conditions, and are not limited to time, and do not require the device to have a judgment action when implemented, nor does it mean that there are other limitations.

[0069] In the description of the embodiments of the present application, unless otherwise specified, " / " represents that the objects before and after the " / " are in an "or" relationship, for example, A / B can represent A or B; "and / or" in the embodiments of the present application is only a description of the association relationship of the associated objects, and represents that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. In addition, in the description of the embodiments of the present application, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following" or the like refers to any combination of these items, including any combination of single item or multiple items. For example, at least one of a, b, or c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple. In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, "first", "second", and the like are used to distinguish the same items or similar items with basically the same function and role. Those skilled in the art can understand that "first", "second", and the like do not limit the quantity and execution order, and "first", "second", and the like do not necessarily mean different. At the same time, in the embodiments of the present application, "exemplary" or "for example" is used to represent as an example, illustration, or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, "exemplary" or "for example" is used to present the relevant concept in a specific manner, and is convenient for understanding.

[0070] It should be appreciated that a processor in the embodiments of the present application can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can be any conventional processor.

[0071] It should also be understood that the memory in the embodiments of the present application can be a volatile memory or a nonvolatile memory, or can include both volatile and nonvolatile memory. Among them, the nonvolatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, and not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM) and direct rambus RAM (DR RAM).

[0072] The above-described embodiments can be implemented in part or in whole through software, hardware (e.g., circuitry), firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When loaded and executed by a computer, the computer instructions or computer programs can produce the processes or functions described above in accordance with the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, such as from a website site, a computer, a server, or a data center to another website site, a computer, a server, or a data center through a wired (e.g., infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium or a collection of medium accessible by a computer or a data storage device such as a server, a data center, etc. containing one or more available medium. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0073] It should be understood that the term "and / or" in this document is merely used to describe an associated relationship between associated objects, and can represent three relationships, for example, A and / or B can represent three cases of A alone, A and B together, and B alone, where A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the front and rear associated objects, but can also represent an "and / or" relationship. The specific meaning can be understood according to the context before and after.

[0074] In this application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions means any combination of the items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0075] It should be understood that in various embodiments of the present application, the size of the sequence number of the above-described processes does not mean the order of execution, and the execution order of the processes should be determined according to their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0076] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0077] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0078] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0079] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0080] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0081] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0082] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A robot design method for a mechanical arm cleaning robot based on zero-code digital twinning, characterized by, include: Based on the locomotive body cleaning scenario, a three-dimensional digital twin model of the locomotive object scenario is established through a zero-code platform; A digital twin model of the cleaning robot arm is collected and combined with the three-dimensional data twin model of the locomotive object scene to perform digital twin driving and form the basic driving data of the robot arm. Obtain locomotive body identification and classification data, and combine it with the basic drive data of the robotic arm to generate and optimize cleaning strategies and schemes, forming optimized cleaning scheme data for the robotic arm; Acquire locomotive cleaning image data, evaluate and analyze the cleaning effect, and establish a cleaning effect evaluation model; Based on the optimized cleaning scheme data of the robotic arm, locomotive cleaning operations are carried out, and real-time cleaning data is collected for operation monitoring and maintenance analysis to form real-time monitoring and maintenance analysis result data. Intelligent operation analysis is performed based on the real-time monitoring and maintenance analysis results to generate intelligent operation analysis result data.

2. The zero-code digital-twin-based robotic arm cleaning robot design method of claim 1, wherein, The process involves establishing a 3D digital twin model of the locomotive cleaning scene based on the locomotive body cleaning scenario, using a no-code platform. This includes: Based on the locomotive body cleaning scenario, a digital twin model of the main equipment in the scenario is established through a zero-code platform to form a three-dimensional digital twin model of the locomotive cleaning scenario that matches the real cleaning scenario. Real-time data of locomotive bodies and components are collected, and data twin models of different locomotive bodies and components are established using a zero-code platform to form a three-dimensional data twin model of the locomotive body.

3. The zero-code digital-twin-based robotic arm cleaning robot design method of claim 2, wherein, The digital twin model of the robotic arm used for collecting and cleaning data is combined with the three-dimensional data twin model of the locomotive object to perform digital twin driving, forming the basic driving data of the robotic arm, including: By combining plug-in technology, Internet of Things technology, and big data technology for locomotive cleaning, and based on the three-dimensional data twin model of the locomotive cleaning scene and the three-dimensional data twin model of the locomotive body, the basic driving information of the cleaning robot is determined, and the basic driving data of the robotic arm is formed.

4. The zero-code digital-twin-based robotic arm cleaning robot design method of claim 3, wherein, The process of acquiring locomotive body identification and classification data, and combining it with the basic drive data of the robotic arm to generate and optimize cleaning strategies and plans, resulting in optimized cleaning plan data for the robotic arm, includes: Image data of different locomotive bodies and components are acquired, and features are extracted and classified to form locomotive body classification and recognition data; Collect cleaning action control data, and combine the locomotive body classification and identification data and the robotic arm basic drive data to generate a strategy scheme based on model training. During the model training process, acquire cleaning effect data, use the cleaning effect data as a direction guide for model training, optimize the strategy scheme, and form optimized cleaning scheme data for the robotic arm.

5. The zero-code digital-twin-based robotic arm washing robot design method of claim 4, wherein, The process of acquiring image data of different locomotive bodies and components, performing feature extraction and classification to form locomotive body classification and recognition data includes: A transfer learning approach was adopted, selecting a pre-trained ResNet-50 model as the base network, and fine-tuning and training were performed based on a specific dataset, wherein: During the model training process, the feature extraction capability of the ResNet-50 is preserved by freezing part of the layers, and the model is fine-tuned on the unfrozen layers to better adapt to the locomotive recognition requirements. The training uses a labeled data set to adjust the model parameters using a loss function and optimization algorithm to improve recognition accuracy, and cross-validation and test set evaluation are used to ensure the generalization ability of the model.

6. The zero-code digital-twin-based robotic arm washing robot design method of claim 4, wherein, The generation of the strategy scheme is carried out in the following way: A strategy-based method is used, using the Actor-Critic algorithm as the learning framework, learning and updating according to the environment and reward function, wherein: The environment includes the state of the locomotive body and parts and the state of the cleaning robot; In the process of determining the cleaning strategy, the cleaning efficiency, cleaning quality and cleaning cost are comprehensively considered, and the reward function guides the model to generate high-quality cleaning strategies.

7. The zero-code digital-twin-based robotic arm washing robot design method of claim 4, wherein, The locomotive cleaning image data is obtained, and the cleaning effect is evaluated and analyzed to establish a cleaning effect evaluation model, including: According to the locomotive cleaning image data, a full convolution network method is used, using a U-Net model as a segmentation network, and training and testing are performed according to the data set, wherein: The data set includes images of the locomotive body and parts before and after cleaning, as well as corresponding segmentation labels.

8. The zero-code digital-twin-based robotic arm washing robot design method of claim 7, wherein, Based on the mechanical arm optimization cleaning scheme data, the locomotive cleaning operation is carried out, and real-time cleaning data is collected for operation monitoring and maintenance analysis to form real-time monitoring and maintenance analysis result data, including: Using Internet of Things technology, through various sensors and communication modules installed on the cleaning robot, real-time operation data of the cleaning mechanical arm is collected and transmitted; Using big data technology, a database of historical data and fault data is established for the real-time operation data of the cleaning mechanical arm, and artificial intelligence technology is used to realize operation monitoring and maintenance analysis of the cleaning mechanical arm to form the real-time monitoring and maintenance analysis result data.

9. The zero-code digital-twin-based robotic arm washing robot design method of claim 8, wherein, According to the real-time monitoring and maintenance analysis result data, intelligent operation analysis is carried out to form intelligent operation analysis result data, including: Using data analysis and machine learning technology, an operation cost evaluation model is established for the cleaning mechanical arm according to the real-time monitoring and maintenance analysis result data to realize the accounting and evaluation of the operation cost of the cleaning robot.

10. A zero-code digital twin based robotic arm cleaning robot system, adopting the zero-code digital twin based robotic arm cleaning robot design method of any one of claims 1-9, characterized in that, Including: An Internet of Things system for collecting Internet of Things data including locomotive body cleaning scenes, locomotive body recognition and classification data, locomotive cleaning image data, and real-time cleaning data; A big data system for collecting big data information including mechanical arm data twin models; An analysis processing system is used for generating basic driving data of a mechanical arm by using a mechanical arm data twin model collected by a big data system, generating, optimizing and analyzing cleaning strategies and schemes by using locomotive body identification and classification data collected by an Internet of Things system and combining the basic driving data of the mechanical arm, forming optimized cleaning scheme data of the mechanical arm, evaluating and analyzing cleaning effects by using locomotive cleaning image data collected by the Internet of Things system, establishing a cleaning effect evaluation model, performing running monitoring and maintenance analysis by using real-time cleaning data collected by the Internet of Things system, forming real-time monitoring and maintenance analysis result data, and performing intelligent operation analysis by using the real-time monitoring and maintenance analysis result data, and forming intelligent operation analysis result data. A zero-code platform is used for establishing a three-dimensional digital twin model of a locomotive object scene, and for quickly constructing and deploying the optimized cleaning scheme data of the mechanical arm, the cleaning effect evaluation model, the real-time monitoring and maintenance analysis result data, and the intelligent operation analysis result data on the platform.

Images