Intelligent control system of bridge floor maintenance robot

Abstract

The invention discloses an intelligent control system of a bridge floor maintenance robot, and belongs to the technical field of bridge floor maintenance robots. The intelligent control system of the bridge floor maintenance robot comprises a position acquisition module, a path decision module and an intelligent control module. The problem that the robot cannot be accurately controlled according to the working environment when the action path of the robot is optimized in an existing patent is solved, the real-time condition of the bridge floor can be accurately obtained, the maintenance efficiency is greatly improved, and the maintenance cost is reduced. The bridge floor maintenance robot can be accurately adjusted according to the real-time change of the bridge floor environment, so that each bridge floor can be properly maintained, the maintenance quality is improved, the maintenance cost is reduced, the operation effect of the robot can be accurately mastered, and the maintenance standard is ensured to reach the standard; abnormal conditions in the operation process of the bridge floor maintenance robot can be found in time through real-time monitoring, and intelligent and refined management of bridge floor maintenance can be achieved.

Description

Technical Field

[0001] The invention relates to the technical field of bridge deck maintenance robot control, and in particular to an intelligent control system of a bridge deck maintenance robot. Background Art

[0002] In highway bridge construction, bridge deck paving is a vital link, and its bridge deck maintenance process is directly related to the service life of the bridge, driving safety and subsequent maintenance costs. With the continuous development of science and technology, the continuous maturity of artificial intelligence, 5G, Beidou and satellite Internet technologies, it has become an inevitable trend for machines to replace people to complete work. Robots are intelligent machines that can work semi-autonomously or fully autonomously. Robots have basic characteristics such as perception, decision-making, and execution. They can assist or even replace humans to complete dangerous, heavy, and complex tasks, improve work efficiency and quality, serve human life, and expand or extend the scope of human activities and capabilities. With the integration of the Internet of Things and big data technologies, robots have gradually realized comprehensive intelligent control and remote operation.

[0003] The Chinese patent with publication number CN119115930A discloses a robot operation control method, system and robot. The method includes the following steps: obtaining spatial data of aquaculture vessels; deploying a multi-source sensor network according to the spatial data of aquaculture vessels to generate a multi-source sensor network; integrating sensor data of the multi-source sensor network to generate environmental perception integrated data of aquaculture vessels; updating the environmental perception integrated data of aquaculture vessels in real time to generate real-time environmental monitoring data of aquaculture vessels; synchronizing the spatiotemporal data of the real-time environmental monitoring data of aquaculture vessels to generate environmental synchronization data of aquaculture vessels; constructing an environmental model according to the environmental synchronization data of aquaculture vessels to generate a comprehensive aquaculture environment model, and improving the stability and intelligence level of robot operation control through real-time environmental perception, dynamic path planning, intelligent feeding control and abnormality detection.

[0004] In actual use, the above patent can only optimize the robot's movement path, but cannot achieve precise control of the robot according to the working environment; therefore, it cannot meet existing needs. In response to this, we propose an intelligent control system for the bridge deck maintenance robot. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent control system for a bridge deck maintenance robot, which can accurately obtain the real-time status of the bridge deck, greatly improve the maintenance efficiency, and avoid excessive or insufficient maintenance operations. The bridge deck maintenance robot can be accurately adjusted according to the real-time changes in the bridge deck environment, thereby ensuring that each bridge deck can receive appropriate maintenance treatment, improving the maintenance quality, and reducing the maintenance cost by accurately controlling the watering frequency and amount. By generating real-time monitoring data of the bridge deck and analyzing the maintenance effect based on the real-time monitoring data of the bridge deck, the robot's operation effect can be accurately grasped to ensure that the maintenance standards are met. At the same time, real-time monitoring can instantly feedback the working status of the bridge deck maintenance robot, quickly discover and correct problems, reduce invalid operation time, optimize the working path and operation strategy of the bridge deck maintenance robot, and further improve work efficiency. Real-time monitoring can promptly discover abnormal situations during the operation of the bridge deck maintenance robot, and immediately take measures to avoid accidents, which is helpful to realize the intelligent and refined management of bridge deck maintenance and solves the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: an intelligent control system for a bridge deck maintenance robot, comprising: The position acquisition module is used to establish a three-dimensional spatial model of the bridge deck environment, obtain the positioning information of the bridge deck maintenance robot, and calibrate and correct the positioning information of the bridge deck maintenance robot; A path decision module is used to set a threshold between the bridge deck maintenance robot and obstacles, distinguish the obstacles and free space information in the movement path of the bridge deck maintenance robot according to the set threshold, and plan a preliminary obstacle avoidance path for the bridge deck maintenance robot; The intelligent control module is used to obtain the initial control data corresponding to the bridge deck maintenance robot, drive the bridge deck maintenance robot to move along the movement path of the bridge deck maintenance robot according to the initial control data, judge the maintenance effect of the bridge deck maintenance robot, and generate maintenance monitoring data of the bridge deck maintenance robot.

[0007] Preferably, the location acquisition module includes: A data acquisition module is used to acquire bridge deck monitoring data, synchronize the bridge deck monitoring data in time and space, and generate bridge deck environment synchronization data; A model generation module is used to construct an environmental model based on the bridge deck environment synchronization data and generate a three-dimensional spatial model of the bridge deck environment; An identification and positioning module is used to obtain the positioning information of the bridge deck maintenance robot by marking the current position of the bridge deck maintenance robot in the map information through comparison between the map information and the three-dimensional spatial model of the bridge deck; The information calibration module is used to obtain images captured by multiple cameras on the bridge deck, calibrate and correct the three-dimensional spatial model of the bridge deck environment through the images captured by multiple cameras, and calibrate and correct the positioning information of the bridge deck maintenance robot according to the correction results of the three-dimensional spatial model of the bridge deck environment.

[0008] Preferably, the path decision module includes: A space distinction module is used to set a threshold between the bridge deck maintenance robot and obstacles, and to distinguish information about obstacles and free space in the movement path of the bridge deck maintenance robot according to the set threshold; The path generation module is used to construct a path planning model, input the information of obstacles and free space into the path planning model, and obtain the preliminary obstacle avoidance path of the bridge deck maintenance robot.

[0009] Preferably, the path decision module includes: A threshold between the bridge deck maintenance robot and obstacles is set, and information about obstacles and free space in the movement path of the bridge deck maintenance robot is distinguished according to the set threshold; Select the neural network architecture, adjust the number of layers and nodes of the neural network, build a path planning model, input the information of obstacles and free space into the path planning model, and obtain the preliminary obstacle avoidance path of the bridge deck maintenance robot; After obtaining the preliminary obstacle avoidance path planning results, the path is smoothed by an interpolation algorithm, and the motion path of the bridge deck maintenance robot is drawn on the map after smoothing.

[0010] Preferably, the step of setting a threshold between the bridge deck maintenance robot and the obstacle includes: Extracting length data and width data of the bridge deck maintenance robot; Extracting the detection area of ​​the sensor of the bridge deck maintenance robot for detecting obstacles; Obtaining a characteristic coefficient of the bridge deck maintenance robot by using the length data and width data of the bridge deck maintenance robot in combination with a detection area of ​​a sensor of the bridge deck maintenance robot for detecting obstacles; The robot characteristic coefficient of the bridge deck maintenance robot is obtained by the following formula:

[0011] Wherein, Q represents the robot characteristic coefficient of the bridge deck maintenance robot; L and D represent the length data and width data of the bridge deck maintenance robot respectively; S represents the detection area of ​​the sensor of the bridge deck maintenance robot for detecting obstacles; L y It represents the straight-line distance between the farthest point in the detection area and the sensor of the bridge deck maintenance robot used to detect obstacles; comparing a robot characteristic coefficient of the bridge deck maintenance robot with a preset characteristic coefficient threshold; The threshold is set according to the quantitative relationship between the robot characteristic coefficient of the bridge deck maintenance robot and a preset characteristic coefficient threshold.

[0012] Preferably, the threshold is set according to the quantitative relationship between the robot characteristic coefficient of the bridge deck maintenance robot and a preset characteristic coefficient threshold, including: Extracting a quantitative relationship between a robot characteristic coefficient of the bridge deck maintenance robot and a preset characteristic coefficient threshold; When the robot characteristic coefficient of the bridge deck maintenance robot exceeds a preset characteristic coefficient threshold, the maximum forward speed and maximum acceleration that the bridge deck maintenance robot can achieve are retrieved; The maximum forward speed and the maximum acceleration that the bridge deck maintenance robot can achieve are combined with the robot characteristic coefficient of the bridge deck maintenance robot to set a threshold value, and obtain a threshold value between the bridge deck maintenance robot and the obstacle; The threshold between the bridge deck maintenance robot and the obstacle is obtained by the following formula:

[0013] Where Y represents the threshold between the bridge maintenance robot and the obstacle; Y 0 represents the preset threshold initial value; Q represents the robot characteristic coefficient of the bridge deck maintenance robot; V max V represents the maximum forward speed that the bridge deck maintenance robot can achieve; b represents the standard deviation of the forward speed of the bridge deck maintenance robot; P represents the cumulative running time ratio of the maximum forward speed of the bridge deck maintenance robot during operation; A max A represents the maximum acceleration that the bridge deck maintenance robot can achieve; d Indicates the current acceleration of the bridge deck maintenance robot; A c Indicates the preset acceleration reference value; When the robot characteristic coefficient of the bridge deck maintenance robot does not exceed a preset characteristic coefficient threshold, the current average forward speed and maximum acceleration of the bridge deck maintenance robot are retrieved; The threshold is set by using the current average forward speed and maximum acceleration of the bridge deck maintenance robot in combination with the robot characteristic coefficient of the bridge deck maintenance robot to obtain the threshold between the bridge deck maintenance robot and the obstacle; The threshold between the bridge deck maintenance robot and the obstacle is obtained by the following formula:

[0014] Where Y represents the threshold between the bridge maintenance robot and the obstacle; Y 0 represents the preset threshold initial value; Q represents the robot characteristic coefficient of the bridge deck maintenance robot; V max V represents the maximum forward speed that the bridge deck maintenance robot can achieve; b represents the standard deviation of the forward speed of the bridge deck maintenance robot; V d Indicates the current forward speed of the bridge deck maintenance robot; V p represents the average forward speed of the bridge deck maintenance robot; P represents the cumulative running time ratio of the maximum forward speed of the bridge deck maintenance robot during operation; A max A represents the maximum acceleration that the bridge deck maintenance robot can achieve; d Indicates the current acceleration of the bridge deck maintenance robot; A p Represents the average acceleration of the bridge deck maintenance robot during operation.

[0015] Preferably, the selecting of a neural network architecture, adjusting the number of layers and nodes of the neural network, and constructing a path planning model specifically includes: Select the number of layers of the neural network, which includes input layer, hidden layer and output layer, and select the number of nodes in the neural network layer; Collect a dataset containing obstacle and path planning information, and divide the dataset into training dataset, validation dataset, and test dataset; Use the training data set to train the neural network to obtain the path planning model, and update the weights and biases through the back-propagation algorithm; After the update is completed, the learning rate and batch size are adjusted to optimize the performance of the path planning model. After the optimization is completed, the performance of the path planning model is evaluated using the validation data set and the test data set to obtain the optimized path planning model.

[0016] Preferably, the space differentiation module specifically includes: Set a safe distance threshold between the bridge maintenance robot and obstacles. This distance needs to take into account the vehicle's braking distance, reaction time, and possible error range, and collect detailed data on the bridge environment through cameras. Process and analyze the data obtained by the camera to extract specific information about obstacles and free space; The processed data is compared with the set threshold. If the distance of the obstacle is less than or equal to the threshold, it is identified as an obstacle. If the distance is greater than the threshold, it is identified as a free space.

[0017] Preferably, the intelligent control module comprises: An operation control module is used to obtain initial control data corresponding to the bridge deck maintenance robot and drive the bridge deck maintenance robot to move according to the initial control data; The environmental perception module is used to obtain bridge deck environmental parameters and bridge deck maintenance status data. The bridge deck environmental parameters include the temperature and humidity parameters of the bridge deck pavement materials, as well as changes in the bridge deck environment; The control feedback module is used to analyze the bridge deck environmental parameters and the bridge deck maintenance status data, control the normal operation control operation of the bridge deck maintenance robot according to the analysis results, and detect operation anomalies of the bridge deck maintenance robot maintenance monitoring data.

[0018] Preferably, the control feedback module specifically includes: When the bridge deck maintenance robot performs bridge deck maintenance according to the movement path of the bridge deck maintenance robot, it obtains bridge deck environmental parameters and bridge deck maintenance status data; Analyze the real-time temperature, real-time humidity and real-time changes of environmental conditions of bridge deck pavement materials according to bridge deck environmental parameters; According to the real-time temperature, real-time humidity and real-time changes of environmental conditions of the bridge deck paving materials, the watering frequency and water volume of the bridge deck maintenance robot are automatically adjusted by adjusting the number and form of fuzzy rules and optimizing the membership function of fuzzy variables; The operation status of the bridge deck maintenance robot is analyzed according to the bridge deck maintenance status data, and whether the bridge deck maintenance robot has a fault is analyzed according to the operation status of the bridge deck maintenance robot. If a fault exists, a fault warning signal is issued.

[0019] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention can accurately obtain the real-time status of the bridge deck by acquiring the bridge deck environmental parameters and the bridge deck maintenance status data in real time, and provide accurate data support for the bridge deck maintenance robot. The bridge deck maintenance robot timely adjusts the watering frequency and watering amount according to the bridge deck environmental parameters and the bridge deck maintenance status data to ensure that the bridge deck is maintained in a timely and appropriate manner, which greatly improves the maintenance efficiency and avoids excessive or insufficient maintenance operations. The bridge deck maintenance robot can be accurately adjusted according to the real-time changes in the bridge deck environment, thereby ensuring that each bridge deck can receive appropriate maintenance treatment, improving the maintenance quality, and reducing the maintenance cost by accurately controlling the watering frequency and watering amount.

[0020] 2. The present invention can accurately grasp the robot's operating effect and ensure that maintenance standards are met by generating real-time monitoring data of the bridge deck and analyzing the maintenance effect based on the real-time monitoring data of the bridge deck. At the same time, real-time monitoring can instantly feedback the working status of the bridge deck maintenance robot, quickly discover and correct problems, reduce ineffective operation time, optimize the working path and operation strategy of the bridge deck maintenance robot, and further improve work efficiency. Real-time monitoring can promptly discover abnormal situations during the operation of the bridge deck maintenance robot and take immediate measures to avoid accidents, which is helpful to realize the intelligent and refined management of bridge deck maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 Schematic diagram of the intelligent control system of the bridge deck maintenance robot of the present invention; Figure 2 This is a diagram of the intelligent control system method of the bridge deck maintenance robot of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] In order to solve the problem that the existing patent can only optimize the robot's action path, but cannot achieve precise control of the robot according to the working environment, please refer to Figure 1-Figure 2 , this embodiment provides the following technical solutions: The intelligent control system of the bridge deck maintenance robot includes: The position acquisition module is used to establish a three-dimensional spatial model of the bridge deck environment, obtain the positioning information of the bridge deck maintenance robot, and calibrate and correct the positioning information of the bridge deck maintenance robot; A path decision module is used to set a threshold between the bridge deck maintenance robot and obstacles, distinguish the obstacles and free space information in the movement path of the bridge deck maintenance robot according to the set threshold, and plan a preliminary obstacle avoidance path for the bridge deck maintenance robot; The intelligent control module is used to obtain the initial control data corresponding to the bridge deck maintenance robot, drive the bridge deck maintenance robot to move along the movement path of the bridge deck maintenance robot according to the initial control data, judge the maintenance effect of the bridge deck maintenance robot, and generate maintenance monitoring data of the bridge deck maintenance robot.

[0024] Location acquisition module, including: A data acquisition module is used to acquire bridge deck monitoring data, synchronize the bridge deck monitoring data in time and space, and generate bridge deck environment synchronization data; A model generation module is used to construct an environmental model based on the bridge deck environment synchronization data and generate a three-dimensional spatial model of the bridge deck environment; An identification and positioning module is used to obtain the positioning information of the bridge deck maintenance robot by marking the current position of the bridge deck maintenance robot in the map information through comparison between the map information and the three-dimensional spatial model of the bridge deck; The information calibration module is used to obtain images captured by multiple cameras on the bridge deck, calibrate and correct the three-dimensional spatial model of the bridge deck environment through the images captured by multiple cameras, and calibrate and correct the positioning information of the bridge deck maintenance robot according to the correction results of the three-dimensional spatial model of the bridge deck environment.

[0025] Path decision module, including: A space distinction module is used to set a threshold between the bridge deck maintenance robot and obstacles, and to distinguish information about obstacles and free space in the movement path of the bridge deck maintenance robot according to the set threshold; The path generation module is used to construct a path planning model, input the information of obstacles and free space into the path planning model, and obtain the preliminary obstacle avoidance path of the bridge deck maintenance robot.

[0026] Path decision module, including: A threshold between the bridge deck maintenance robot and obstacles is set, and information about obstacles and free space in the movement path of the bridge deck maintenance robot is distinguished according to the set threshold; Select the neural network architecture, adjust the number of layers and nodes of the neural network, build a path planning model, input the information of obstacles and free space into the path planning model, and obtain the preliminary obstacle avoidance path of the bridge deck maintenance robot; After obtaining the preliminary obstacle avoidance path planning results, the path is smoothed through the interpolation algorithm. After smoothing, the movement path of the bridge deck maintenance robot is drawn on the map, which can ensure that the path planning map clearly and accurately reflects the robot's movement path and obstacle distribution.

[0027] Specifically, the step of setting the threshold between the bridge deck maintenance robot and the obstacle includes: Extracting length data and width data of the bridge deck maintenance robot; Extracting the detection area of ​​the sensor of the bridge deck maintenance robot for detecting obstacles; Obtaining a characteristic coefficient of the bridge deck maintenance robot by using the length data and width data of the bridge deck maintenance robot in combination with a detection area of ​​a sensor of the bridge deck maintenance robot for detecting obstacles; The robot characteristic coefficient of the bridge deck maintenance robot is obtained by the following formula:

[0028] Wherein, Q represents the robot characteristic coefficient of the bridge deck maintenance robot; L and D represent the length data and width data of the bridge deck maintenance robot respectively; S represents the detection area of ​​the sensor of the bridge deck maintenance robot for detecting obstacles; L y It represents the straight-line distance between the farthest point in the detection area and the sensor of the bridge deck maintenance robot used to detect obstacles; comparing a robot characteristic coefficient of the bridge deck maintenance robot with a preset characteristic coefficient threshold; The threshold is set according to the quantitative relationship between the robot characteristic coefficient of the bridge deck maintenance robot and a preset characteristic coefficient threshold.

[0029] The technical effect of the above technical solution is: by extracting the physical dimensions (length L and width D) of the bridge deck maintenance robot and the detection area S of its sensor for detecting obstacles, and combining these parameters to calculate a robot characteristic coefficient Q, this coefficient can comprehensively reflect the space occupancy and detection capability of the bridge deck maintenance robot when operating on the bridge deck. By comparing this characteristic coefficient with the preset characteristic coefficient threshold, the safe distance or obstacle avoidance strategy between the bridge deck maintenance robot and the obstacle can be set more accurately, thereby improving the safety and efficiency of the operation. By accurately calculating the robot characteristic coefficient and setting a reasonable obstacle threshold accordingly, the bridge deck maintenance robot can avoid frequent parking or path adjustment due to misjudgment of obstacles during the operation process, thereby reducing unnecessary operation interruptions and improving overall operation efficiency. Different bridge deck maintenance robots may have different sizes and detection capabilities. The technical solution can calculate the characteristic coefficient according to the specific parameters of different robots and set personalized obstacle thresholds accordingly. This personalized setting enables the technical solution to be applicable to many different types of bridge deck maintenance robots, enhancing its versatility and adaptability. This technical solution achieves intelligent management of the distance between the bridge maintenance robot and obstacles by introducing a comparison mechanism between the robot characteristic coefficient and the preset characteristic coefficient threshold. This intelligent management method not only improves the safety of the operation, but also makes the operation of the bridge maintenance robot more convenient and efficient. By accurately setting the obstacle threshold, the damage caused by collision with obstacles during the operation of the bridge maintenance robot can be reduced, thereby reducing the maintenance cost and use cost of the equipment.

[0030] In summary, this technical solution achieves precise management and intelligent control of the operation process of the bridge deck maintenance robot by comprehensively considering the physical size and detection capabilities of the bridge deck maintenance robot and setting a reasonable obstacle threshold accordingly, thereby improving the safety and efficiency of the operation and reducing maintenance costs.

[0031] Specifically, the threshold is set according to the quantitative relationship between the robot characteristic coefficient of the bridge deck maintenance robot and a preset characteristic coefficient threshold, including: Extracting a quantitative relationship between a robot characteristic coefficient of the bridge deck maintenance robot and a preset characteristic coefficient threshold; When the robot characteristic coefficient of the bridge deck maintenance robot exceeds a preset characteristic coefficient threshold, the maximum forward speed and maximum acceleration that the bridge deck maintenance robot can achieve are retrieved; The maximum forward speed and the maximum acceleration that the bridge deck maintenance robot can achieve are combined with the robot characteristic coefficient of the bridge deck maintenance robot to set a threshold value, and obtain a threshold value between the bridge deck maintenance robot and the obstacle; The threshold between the bridge deck maintenance robot and the obstacle is obtained by the following formula:

[0032] Where Y represents the threshold between the bridge maintenance robot and the obstacle; Y 0 represents the preset threshold initial value; Q represents the robot characteristic coefficient of the bridge deck maintenance robot; V max V represents the maximum forward speed that the bridge deck maintenance robot can achieve; b represents the standard deviation of the forward speed of the bridge deck maintenance robot; P represents the cumulative running time ratio of the maximum forward speed of the bridge deck maintenance robot during operation; A max A represents the maximum acceleration that the bridge deck maintenance robot can achieve; d Indicates the current acceleration of the bridge deck maintenance robot; A c Indicates the preset acceleration reference value; When the robot characteristic coefficient of the bridge deck maintenance robot does not exceed a preset characteristic coefficient threshold, the current average forward speed and maximum acceleration of the bridge deck maintenance robot are retrieved; The threshold is set by using the current average forward speed and maximum acceleration of the bridge deck maintenance robot in combination with the robot characteristic coefficient of the bridge deck maintenance robot to obtain the threshold between the bridge deck maintenance robot and the obstacle; The threshold between the bridge deck maintenance robot and the obstacle is obtained by the following formula:

[0033] Where Y represents the threshold between the bridge maintenance robot and the obstacle; Y 0 represents the preset threshold initial value; Q represents the robot characteristic coefficient of the bridge deck maintenance robot; V max V represents the maximum forward speed that the bridge deck maintenance robot can achieve; brepresents the standard deviation of the forward speed of the bridge deck maintenance robot; V d Indicates the current forward speed of the bridge deck maintenance robot; V p represents the average forward speed of the bridge deck maintenance robot; P represents the cumulative running time ratio of the maximum forward speed of the bridge deck maintenance robot during operation; A max A represents the maximum acceleration that the bridge deck maintenance robot can achieve; d Indicates the current acceleration of the bridge deck maintenance robot; A p Represents the average acceleration of the bridge deck maintenance robot during operation.

[0034] The technical effect of the above technical solution is: the technical solution can dynamically adjust the threshold between the bridge deck maintenance robot and the obstacle according to the quantitative relationship between the robot characteristic coefficient of the bridge deck maintenance robot and the preset characteristic coefficient threshold. This dynamic adjustment mechanism enables the bridge deck maintenance robot to maintain the best obstacle avoidance effect in different working environments and working conditions, and improves its adaptability and flexibility. Comprehensively consider multiple factors to ensure safety: when setting the threshold, the technical solution not only considers the robot characteristic coefficient of the bridge deck maintenance robot, but also comprehensively considers the maximum forward speed, maximum acceleration, current forward speed, forward speed average, forward speed standard deviation, cumulative time ratio of the maximum forward speed during operation, current acceleration and average acceleration, etc. that the bridge deck maintenance robot can achieve. This comprehensive consideration method can more comprehensively evaluate the dynamic performance of the bridge deck maintenance robot during operation, thereby ensuring that the safe distance between it and the obstacle is set more reasonably. By dynamically adjusting the threshold, the technical solution can avoid the bridge deck maintenance robot from reducing its operating efficiency due to frequent obstacle avoidance during operation. When the characteristic coefficient of the bridge deck maintenance robot is high, it means that it has a strong detection and obstacle avoidance capability. At this time, the threshold between it and the obstacle can be appropriately increased to reduce unnecessary obstacle avoidance actions; on the contrary, when the characteristic coefficient is low, the threshold needs to be appropriately reduced to ensure safety. This dynamic adjustment mechanism can maximize the operation efficiency while ensuring safety. By introducing a variety of sensors and algorithms, this technical solution realizes real-time monitoring and evaluation of the dynamic performance of the bridge deck maintenance robot, and dynamically adjusts the threshold according to the evaluation results. This intelligent management method not only improves the safety and efficiency of the operation, but also makes the operation of the bridge deck maintenance robot more convenient and intelligent. By setting the threshold reasonably, this technical solution can reduce the damage caused by collision with obstacles during the operation of the bridge deck maintenance robot, thereby reducing the maintenance cost and use cost of the equipment. At the same time, since the technical solution can dynamically adjust the threshold, it can also adapt to the needs of different working environments and working states, further reducing the maintenance cost.

[0035] In summary, this technical solution dynamically adjusts the threshold between the bridge deck maintenance robot and obstacles, comprehensively considers multiple factors to ensure safety, improves work efficiency, enhances the level of intelligence, and reduces maintenance costs, providing strong technical support for the safe and efficient operation of the bridge deck maintenance robot.

[0036] If it is found that the robot frequently encounters obstacles and cannot avoid them during automatic navigation, it can analyze the reasons, such as sensor failure, navigation algorithm defects, etc., and propose improvement measures.

[0037] Select the neural network architecture, adjust the number of layers and nodes of the neural network, and build a path planning model, including: Select the number of layers of the neural network, which includes input layer, hidden layer and output layer, and select the number of nodes in the neural network layer; The input layer is used to receive the raw data from the camera, the hidden layer is used to extract the features of the input data and perform complex nonlinear transformations. The number of hidden layers depends on the complexity of the task and the features of the data. The output layer is used to output the recognition results and path planning information. For obstacle recognition, the output layer may contain information such as the location and shape of the obstacle. For path planning, the output layer may contain the planned path coordinates. The number of nodes in each layer is determined according to the dimension of the input data, the complexity of the task, and the computing resources. The number of nodes in the input layer should match the number of features of the input data. The number of nodes in the hidden layer can be determined through experiments, using different numbers of nodes for training and comparing the performance of the model. The number of nodes in the output layer depends on the specific requirements of the task. For example, if the output is the path coordinates, the number of nodes should match the dimension of the path. Collect a dataset containing obstacle and path planning information, and divide the dataset into training dataset, validation dataset, and test dataset; The neural network is trained using the training data set to obtain a path planning model. The weights and biases are updated through the back-propagation algorithm so that the path planning model can accurately identify obstacles and plan obstacle avoidance paths.

[0038] After the update is completed, the learning rate and batch size are adjusted to optimize the performance of the path planning model. After the optimization is completed, the performance of the path planning model is evaluated using the validation data set and the test data set to obtain the optimized path planning model to ensure that the path planning model has good generalization ability; Collect detailed data on the bridge deck environment through a three-dimensional spatial model of the bridge deck environment, including the location, size, shape of obstacles and the overall layout of the bridge deck; The key features of the bridge deck environment are extracted from the detailed data and input into the path planning model to obtain the preliminary obstacle avoidance path of the bridge deck maintenance robot. These features can be used to distinguish between obstacles and free space. The features include the distance, speed, direction of obstacles and the width and curvature of the bridge deck.

[0039] The spatial differentiation module includes: Set a safe distance threshold between the bridge maintenance robot and obstacles. This distance needs to take into account the vehicle's braking distance, reaction time, and possible error range, and collect detailed data on the bridge environment through cameras. Processing and analyzing the data acquired by the camera to extract specific information about obstacles and free spaces. Processing the data acquired by the camera specifically includes filtering, denoising and classifying the data, so as to more accurately identify obstacles and free spaces. The information about obstacles and free spaces includes information such as the location, distance, shape and size of the obstacles, as well as the scope and boundaries of the free space. The processed data is compared with the set threshold. If the distance of the obstacle is less than or equal to the threshold, it is identified as an obstacle. If the distance is greater than the threshold, it is identified as a free space. Intelligent control module, including: An operation control module is used to obtain initial control data corresponding to the bridge deck maintenance robot and drive the bridge deck maintenance robot to move according to the initial control data; The environmental perception module is used to obtain bridge deck environmental parameters and bridge deck maintenance status data. The bridge deck environmental parameters include the temperature and humidity parameters of the bridge deck pavement materials, as well as changes in the bridge deck environment; The control feedback module is used to analyze the bridge deck environmental parameters and bridge deck maintenance status data, control the normal operation control operation of the bridge deck maintenance robot according to the analysis results, and perform operation anomaly detection on the maintenance monitoring data of the bridge deck maintenance robot to improve the control accuracy and response speed of the bridge deck maintenance robot.

[0040] Control feedback module, specifically including: When the bridge deck maintenance robot performs bridge deck maintenance according to the movement path of the bridge deck maintenance robot, it obtains bridge deck environmental parameters and bridge deck maintenance status data; Analyze the real-time temperature, real-time humidity and real-time changes of environmental conditions of bridge deck pavement materials according to bridge deck environmental parameters; According to the real-time temperature, real-time humidity and real-time changes of environmental conditions of the bridge deck paving materials, the watering frequency and water volume of the bridge deck maintenance robot are automatically adjusted by adjusting the number and form of fuzzy rules and optimizing the membership function of fuzzy variables, which can improve the control accuracy and response speed of the bridge deck maintenance robot and ensure the continuity and stability of the bridge deck maintenance process; The operation status of the bridge deck maintenance robot is analyzed according to the bridge deck maintenance status data. Whether there is a fault in the bridge deck maintenance robot is analyzed according to the operation status of the bridge deck maintenance robot. If there is a fault, a fault warning signal is issued. The robot can self-diagnose, discover and report faults in time, and reduce maintenance costs.

[0041] By real-time monitoring of key parameters such as temperature and humidity of bridge deck paving materials, as well as changes in environmental conditions, data support is provided for automatic adjustment of bridge deck maintenance parameters. Based on the real-time monitored data, bridge deck maintenance parameters such as watering frequency and water volume are automatically adjusted to ensure the continuity and stability of the bridge deck maintenance process. Construction personnel can view real-time information such as bridge deck maintenance progress and equipment status through mobile phone APP or computer terminals to achieve remote scheduling and management. At the same time, the equipment has self-diagnosis function to detect and report faults in time, reducing maintenance costs.

[0042] The control process of the operation control module includes: Obtaining initial control data corresponding to the bridge deck maintenance robot; According to the initial control data, the bridge deck maintenance robot is driven to move forward, backward and rotate in place according to the movement path of the bridge deck maintenance robot to maintain the bridge deck; During the bridge deck maintenance process, the bridge deck space information is obtained in real time, and a multi-source sensor network is deployed based on the bridge deck space information to generate a multi-source sensor network; Integrate sensor data from multi-source sensor networks to generate bridge deck environment perception integrated data, perform real-time environmental updates on the bridge deck environment perception integrated data, and generate bridge deck real-time monitoring data; Determine whether the maintenance effect of the bridge deck maintenance robot meets the maintenance standards based on the real-time monitoring data of the bridge deck; If the maintenance standard is met, the bridge deck maintenance robot is controlled to continue maintenance according to the movement path of the bridge deck maintenance robot; If the maintenance standards are not met, the bridge deck maintenance robot is controlled to continue maintaining the current bridge deck until the maintenance standards are met.

[0043] By generating real-time monitoring data of bridge decks and analyzing the maintenance effects based on the real-time monitoring data of bridge decks, we can accurately grasp the robot's operating effects, such as the degree of cleaning, repair quality, etc., to ensure that maintenance standards are met. At the same time, real-time monitoring can provide instant feedback on the working status of the bridge deck maintenance robot, quickly discover and correct problems, reduce ineffective operation time, optimize the working path and operation strategy of the bridge deck maintenance robot, and further improve work efficiency. Real-time monitoring can promptly discover abnormal situations during the operation of the bridge deck maintenance robot, such as collisions, failures, etc., and take immediate measures to avoid accidents. For complex environments such as bridge decks, real-time monitoring helps to assess operating risks, ensure the safety of bridge deck maintenance robots, and help realize intelligent and refined management of bridge deck maintenance, reduce the cost of manual intervention, and improve the scientificity and efficiency of maintenance work.

[0044] Working principle: When using the intelligent control system of the bridge deck maintenance robot of the present invention, according to Figure 1 and Figure 2 , including the following steps: Step 1: Establish a three-dimensional spatial model of the bridge deck environment, obtain the positioning information of the bridge deck maintenance robot, and calibrate and correct the positioning information of the bridge deck maintenance robot; Step 2: Set a threshold between the bridge deck maintenance robot and the obstacle, distinguish the obstacle and free space information of the bridge deck maintenance robot's motion path according to the set threshold, and plan a preliminary obstacle avoidance path for the bridge deck maintenance robot; Step 3: During the bridge deck maintenance process, bridge deck environmental parameters, bridge deck maintenance status data and bridge deck space information are obtained in real time, and the bridge deck space information is used to generate real-time bridge deck monitoring data; Step 4: Analyze the real-time temperature, real-time humidity and real-time changes of environmental conditions of the bridge deck paving materials according to the bridge deck environmental parameters, and automatically adjust the watering frequency and water volume of the bridge deck maintenance robot according to the analysis results; Step 5: Determine whether the maintenance effect of the bridge deck maintenance robot meets the maintenance standards based on the real-time monitoring data of the bridge deck; Step 6: If the maintenance standard is met, the bridge deck maintenance robot is controlled to continue maintenance according to the movement path of the bridge deck maintenance robot; if the maintenance standard is not met, the bridge deck maintenance robot is controlled to continue maintaining the current bridge deck until it meets the maintenance standard; Step seven: Analyze the operating status of the bridge deck maintenance robot based on the bridge deck maintenance status data, and analyze whether the bridge deck maintenance robot has any faults based on the operating status of the bridge deck maintenance robot. If a fault exists, issue a fault warning signal.

[0045] In summary, the intelligent control system of the bridge deck maintenance robot of the present invention provides data support for automatically adjusting the bridge deck maintenance parameters by real-time monitoring of key parameters such as temperature and humidity of the bridge deck paving materials and changes in environmental conditions. According to the real-time monitored data, the bridge deck maintenance parameters such as watering frequency and water volume are automatically adjusted to ensure the continuity and stability of the bridge deck maintenance process. Construction personnel can view the bridge deck maintenance progress, equipment status and other information in real time through mobile phone APP or computer terminal to achieve remote scheduling and management. At the same time, the equipment has a self-diagnosis function to detect and report faults in time, reduce maintenance costs, and control the bridge deck maintenance robot to adjust the bridge deck watering frequency and watering volume according to the bridge deck environmental parameters and bridge deck maintenance status data, which can improve maintenance efficiency, ensure maintenance quality, save resources and Improve safety, obtain bridge deck environmental parameters and bridge deck maintenance status data in real time, and be able to accurately obtain the real-time status of the bridge deck, such as temperature, humidity, pollution level, etc., which provides accurate data support for the bridge deck maintenance robot. The bridge deck maintenance robot adjusts the watering frequency and amount in time according to the bridge deck environmental parameters and bridge deck maintenance status data to ensure that the bridge deck is maintained in a timely and appropriate manner, greatly improving the maintenance efficiency and avoiding excessive or insufficient maintenance operations. The bridge deck maintenance robot can make precise adjustments according to the real-time changes in the bridge deck environment, thereby ensuring that each bridge deck can receive proper maintenance treatment, improving the maintenance quality, and reducing maintenance costs by accurately controlling the watering frequency and amount. At the same time, this intelligent maintenance method can also reduce manpower input and further save resources.

[0046] Finally, the application of real-time monitoring and bridge deck maintenance robots has also improved the safety of maintenance work. Traditional bridge deck maintenance work often requires manual operation, which poses certain safety hazards. However, bridge deck maintenance robots can work unattended, greatly reducing the risks of manual operation.

[0047] In summary, by real-time monitoring of the bridge deck environment and controlling the bridge deck maintenance robot to adjust the bridge deck watering frequency and amount, it is possible to improve maintenance efficiency, ensure maintenance quality, save resources and improve safety, which is a major advancement in the field of modern bridge maintenance.

[0048] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0049] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. The intelligent control system of the bridge deck maintenance robot is characterized by: include: The position acquisition module is used to establish a three-dimensional spatial model of the bridge deck environment, obtain the positioning information of the bridge deck maintenance robot, and calibrate and correct the positioning information of the bridge deck maintenance robot; A path decision module is used to set a threshold between the bridge deck maintenance robot and obstacles, distinguish the obstacles and free space information in the movement path of the bridge deck maintenance robot according to the set threshold, and plan a preliminary obstacle avoidance path for the bridge deck maintenance robot; The intelligent control module is used to obtain the initial control data corresponding to the bridge deck maintenance robot, drive the bridge deck maintenance robot to move along the movement path of the bridge deck maintenance robot according to the initial control data, judge the maintenance effect of the bridge deck maintenance robot, and generate maintenance monitoring data of the bridge deck maintenance robot.

2. The intelligent control system of the bridge deck maintenance robot according to claim 1 is characterized in that: The location acquisition module comprises: A data acquisition module is used to acquire bridge deck monitoring data, synchronize the bridge deck monitoring data in time and space, and generate bridge deck environment synchronization data; A model generation module is used to construct an environmental model based on the bridge deck environment synchronization data and generate a three-dimensional spatial model of the bridge deck environment; An identification and positioning module is used to obtain the positioning information of the bridge deck maintenance robot by marking the current position of the bridge deck maintenance robot in the map information through comparison between the map information and the three-dimensional spatial model of the bridge deck; The information calibration module is used to obtain images captured by multiple cameras on the bridge deck, calibrate and correct the three-dimensional spatial model of the bridge deck environment through the images captured by multiple cameras, and calibrate and correct the positioning information of the bridge deck maintenance robot according to the correction results of the three-dimensional spatial model of the bridge deck environment.

3. The intelligent control system of the bridge deck maintenance robot according to claim 1 is characterized in that: The path decision module includes: A space distinction module is used to set a threshold between the bridge deck maintenance robot and obstacles, and to distinguish information about obstacles and free space in the movement path of the bridge deck maintenance robot according to the set threshold; The path generation module is used to construct a path planning model, input the information of obstacles and free space into the path planning model, and obtain the preliminary obstacle avoidance path of the bridge deck maintenance robot.

4. The intelligent control system of the bridge deck maintenance robot according to claim 3 is characterized in that: The path decision module includes: A threshold between the bridge deck maintenance robot and obstacles is set, and information about obstacles and free space in the movement path of the bridge deck maintenance robot is distinguished according to the set threshold; Select the neural network architecture, adjust the number of layers and nodes of the neural network, build a path planning model, input the information of obstacles and free space into the path planning model, and obtain the preliminary obstacle avoidance path of the bridge deck maintenance robot; After obtaining the preliminary obstacle avoidance path planning results, the path is smoothed by an interpolation algorithm, and the motion path of the bridge deck maintenance robot is drawn on the map after smoothing.

5. The intelligent control system of the bridge deck maintenance robot according to claim 4 is characterized in that: The step of setting a threshold between the bridge deck maintenance robot and an obstacle includes: Extracting length data and width data of the bridge deck maintenance robot; Extracting the detection area of ​​the sensor of the bridge deck maintenance robot for detecting obstacles; Obtaining a characteristic coefficient of the bridge deck maintenance robot by using the length data and width data of the bridge deck maintenance robot in combination with a detection area of ​​a sensor of the bridge deck maintenance robot for detecting obstacles; The robot characteristic coefficient of the bridge deck maintenance robot is obtained by the following formula: ； Wherein, Q represents the robot characteristic coefficient of the bridge deck maintenance robot; L and D represent the length data and width data of the bridge deck maintenance robot respectively; S represents the detection area of ​​the sensor of the bridge deck maintenance robot for detecting obstacles; L y It represents the straight-line distance between the farthest point in the detection area and the sensor of the bridge deck maintenance robot used to detect obstacles; comparing a robot characteristic coefficient of the bridge deck maintenance robot with a preset characteristic coefficient threshold; The threshold is set according to the quantitative relationship between the robot characteristic coefficient of the bridge deck maintenance robot and a preset characteristic coefficient threshold.

6. The intelligent control system of the bridge deck maintenance robot according to claim 5 is characterized in that: The threshold is set according to the quantitative relationship between the robot characteristic coefficient of the bridge deck maintenance robot and a preset characteristic coefficient threshold, including: Extracting a quantitative relationship between a robot characteristic coefficient of the bridge deck maintenance robot and a preset characteristic coefficient threshold; When the robot characteristic coefficient of the bridge deck maintenance robot exceeds a preset characteristic coefficient threshold, the maximum forward speed and maximum acceleration that the bridge deck maintenance robot can achieve are retrieved; The maximum forward speed and the maximum acceleration that the bridge deck maintenance robot can achieve are combined with the robot characteristic coefficient of the bridge deck maintenance robot to set a threshold value, and obtain a threshold value between the bridge deck maintenance robot and the obstacle; The threshold between the bridge deck maintenance robot and the obstacle is obtained by the following formula: ； Where Y represents the threshold between the bridge maintenance robot and the obstacle; Y0 represents the preset threshold initial value; Q represents the robot characteristic coefficient of the bridge maintenance robot; V max V represents the maximum forward speed that the bridge deck maintenance robot can achieve; b represents the standard deviation of the forward speed of the bridge deck maintenance robot; P represents the cumulative running time ratio of the maximum forward speed of the bridge deck maintenance robot during operation; A max A represents the maximum acceleration that the bridge deck maintenance robot can achieve; d Indicates the current acceleration of the bridge deck maintenance robot; A c Indicates the preset acceleration reference value; When the robot characteristic coefficient of the bridge deck maintenance robot does not exceed a preset characteristic coefficient threshold, the current average forward speed and maximum acceleration of the bridge deck maintenance robot are retrieved; The threshold is set by using the current average forward speed and maximum acceleration of the bridge deck maintenance robot in combination with the robot characteristic coefficient of the bridge deck maintenance robot to obtain the threshold between the bridge deck maintenance robot and the obstacle; The threshold between the bridge deck maintenance robot and the obstacle is obtained by the following formula: ； Where Y represents the threshold between the bridge maintenance robot and the obstacle; V d Indicates the current forward speed of the bridge deck maintenance robot; V p A represents the average forward speed of the bridge deck maintenance robot; p Represents the average acceleration of the bridge deck maintenance robot during operation.

7. The intelligent control system of the bridge deck maintenance robot according to claim 4 is characterized in that: The selecting of the neural network architecture, adjusting the number of layers and nodes of the neural network, and constructing the path planning model specifically include: Select the number of layers of the neural network, which includes input layer, hidden layer and output layer, and select the number of nodes in the neural network layer; Collect a dataset containing obstacle and path planning information, and divide the dataset into training dataset, validation dataset, and test dataset; Use the training data set to train the neural network to obtain the path planning model, and update the weights and biases through the back-propagation algorithm; After the update is completed, the learning rate and batch size are adjusted to optimize the performance of the path planning model. After the optimization is completed, the performance of the path planning model is evaluated using the validation data set and the test data set to obtain the optimized path planning model.

8. The intelligent control system of the bridge deck maintenance robot according to claim 3 is characterized in that: The space differentiation module specifically includes: Set the safe distance threshold between the bridge deck maintenance robot and obstacles, and collect detailed data on the bridge deck environment through cameras; Process and analyze the data obtained by the camera to extract specific information about obstacles and free space; The processed data is compared with the set threshold. If the distance of the obstacle is less than or equal to the threshold, it is identified as an obstacle. If the distance is greater than the threshold, it is identified as free space.

9. The intelligent control system of the bridge deck maintenance robot according to claim 1, characterized in that: The intelligent control module comprises: An operation control module is used to obtain initial control data corresponding to the bridge deck maintenance robot and drive the bridge deck maintenance robot to move according to the initial control data; The environmental perception module is used to obtain bridge deck environmental parameters and bridge deck maintenance status data. The bridge deck environmental parameters include the temperature and humidity parameters of the bridge deck pavement materials, as well as changes in the bridge deck environment; The control feedback module is used to analyze the bridge deck environmental parameters and the bridge deck maintenance status data, control the normal operation control operation of the bridge deck maintenance robot according to the analysis results, and detect operation anomalies of the bridge deck maintenance robot maintenance monitoring data.

10. The intelligent control system of the bridge deck maintenance robot according to claim 9, characterized in that: The control feedback module specifically includes: When the bridge deck maintenance robot performs bridge deck maintenance according to the movement path of the bridge deck maintenance robot, it obtains bridge deck environmental parameters and bridge deck maintenance status data; Analyze the real-time temperature, real-time humidity and real-time changes of environmental conditions of bridge deck pavement materials according to bridge deck environmental parameters; According to the real-time temperature, real-time humidity and real-time changes of environmental conditions of the bridge deck paving materials, the watering frequency and water volume of the bridge deck maintenance robot are automatically adjusted by adjusting the number and form of fuzzy rules and optimizing the membership function of fuzzy variables; The operation status of the bridge deck maintenance robot is analyzed according to the bridge deck maintenance status data, and whether there is a fault in the bridge deck maintenance robot is analyzed according to the operation status of the bridge deck maintenance robot. If there is a fault, a fault warning signal is issued.

Images