LAUSR

Hydraulic supports are important equipment used in coal mining. Detecting the real-time attitude and straightness of hydraulic support group in unmanned working faces of coal mines in complex geological conditions is difficult. To address this issue, a method that measures the position and attitude of the hydraulic support using binocular vision detection-aided mark points was proposed. First, a combination of binocular vision positioning and a convolutional neural network (CNN) object detection is used to achieve the 3-D location of mark points. Then, the attitude calculation model of the hydraulic support based on the dual quaternion method is established. This method achieves the space attitude detection between multiple hydraulic supports and the straightness detection of the hydraulic support group in 3-D space. In the laboratory environment, the position and attitude detection test of the hydraulic support is obtained through the working face equipment position detection test bench. This method can adapt to the worse working environment in coal mine production and can provide early data for the automatic control of the straightness of the working face.