基于视觉感知的柴油机单轨吊制动控制策略OA

Diesel monorail crane is one of the main equipment used for the transportation of equipment,personnel and materials in coal mine roadway.It has the advantages of large transportation capacity,strong adaptability to roadways,long continuous transportation distance,etc.,which can greatly improve the underground transportation efficiency of coal mines.Reasonable braking control strategy is the fundamental guarantee of safe and efficient ope-ration of diesel monorail cranes.To improve the braking safety and stability of monorail cranes,a braking control strategy based on visual perception is proposed.First,a detection and recognition scheme of pedestrian obstacles in front of monorail cranes is constructed by using binocular cameras,and the obstacle recognition and real-time dis-tance measurement are realized with the help of visual detection and stereo matching algorithm.Next,based on the pedestrian obstacle distance information obtained from real-time detection,as well as the current running speed in-formation and the load condition of monorail cranes,the overall braking control strategy for monorail cranes under different working conditions is designed with the consideration of the braking stopping distance and braking dece-leration requirements.Then,to effectively control the operation status during the braking process,by taking the un-certain disturbance during the running process into account,a real-time tracking control strategy of pump-controlled-motor system for monorail cranes is constructed on the basis of disturbance observer and robust reverse step control principle.Finally,experimental verifications of the proposed braking control strategy are carried out for monorail cranes under different pedestrian obstacle distances,running speeds and simulated loads,with the help of a simulated braking control test platform.The results indicate that the proposed visual perception-based braking control strategy can effectively improve the safety and stability of monorail crane braking process,with the real-time distance measurement error of pedestrian obstacles being controlled within 4.4%.