| Under the background of "carbon peaking and carbon neutrality",as the main body of traditional fossil energy consumption and the ballast of China’s energy security,the intelligent development and utilization of coal is the general trend.Existing inspection methods such as manual inspection and inspection with the help of video are unable to meet the demand for intelligent review of the fully mechanized coal mining face.This paper proposed a control system design scheme for inspection robots based on flexible track state recognition,based on the group’s previous design of flexible track inspection robot for fully mechanized coal mining faces.With the help of machine vision,robot control,image processing,and sensor information processing,the system realized routine inspection of the work face and the autonomous operation of the flexible track inspection robot,laying the foundation for the robotization of the inspection in fully mechanized coal mining face.A visual method was proposed to distinguish the state of the segmented flexible track,which affected the passage of the inspection robot at the working face when the segmented flexible track was pushed with the hydraulic support.Because of the characteristics of the acquired images,such as uneven illumination and low illumination,this paper proposed an image adaptive enhancement method based on the correction of uneven illumination to enhance the images and evaluated the way subjectively and objectively.Then,the enhanced image was used to extract the ROI of the track image by distortion correction,filtering,perspective transformation,and other methods.The Sobel edge detection algorithm and Probabilistic Hough Transform were studied to realize the edge detection of the flexible connection mechanism.The Kmeans algorithm was used to classify the left and right sides of the edge.The RANSAC algorithm was used to fit the edge of the flexible connection mechanism,and the bending angle of the flexible connection mechanism was obtained.The condition recognition of the segmented flexible track was realized,and the condition classification of the flexible connection mechanism was completed,which laid the foundation for the autonomous operation of the inspection robot.A motion control scheme combining fuzzy PID algorithm with acceleration and deceleration algorithm was proposed to solve the problem of speed regulation and speed stability of the inspection robot through flexible tracks under different working conditions.The motion variation law of the inspection robot on the flexible track was mastered through the dynamic analysis and simulation of the fully mechanized mining face inspection robot.And the inspection motion control strategy combining the fuzzy PID algorithm and the acceleration and deceleration algorithm was proposed.The advantages and disadvantages of different acceleration and deceleration algorithms were analyzed and compared,and the S-type acceleration and deceleration algorithm was selected.Comparative experiments verified the feasibility of the control algorithm.The design of the inspection robot system should meet the requirements of inspection performance and visual processing.In this paper,a control system of inspection robot based on Raspberry pi and STM32 was developed.The hardware selection and software design of the robot control system were carried out.The related functions of the upper computer monitoring system and the lower computer control system were realized,and the inspection requirements of the flexible track robot in fully mechanized coal mining face were achieved.Finally,an experimental platform of the flexible track inspection robot for working face was built to verify the function and performance of the control system.The system realizes the functions of environmental detection,equipment monitoring,data interaction and display,remote control,image enhancement,and adaptive control.The results show that the control system meets the design requirements,and the research has a certain reference for the construction of intelligent inspection in fully mechanized coal mining face. |