Man-vehicle linkage control system in coal mines

Abstract

In order to ensure the safety of people in the roadway during the movement of unmanned transportation vehicles in coal mines, a man-vehicle linkage control system in coal mines is proposed. A deep separable convolutional network is used to replace the DarkNet-53 feature extraction network of the YOLOv3 target detection model to improve the real-time performance of target detection. Based on the idea of upsampling and feature pyramid network, the feature map scale is expanded so as to ensure the accuracy of target detection. The improved YOLOv3 target detection model is used to detect the position of man in coal mines as the vehicle is moving. Based on the distance between the man and the vehicle, the PID control optimized by the genetic algorithm is used to achieve speed and precise adjustment of the vehicle. The experimental results show that the system can quickly detect the position of target man and control the vehicle speed according to the distance between the man and the vehicle with high reliability.

Keywords

• underground unmanned transportation
• man-vehicle linkage control
• target person detection
• improved yolov3
• vehicle speed control
• genetic algorithm
• pid control