A Test and Evaluation Method for Smart Fully Mechanized Mining Robot Production System

Abstract

A test and evaluation method for smart fully mechanized mining robot production system is proposed. Based on the actual operation data of the geology and equipment of a particular working face, the kinematic models between equipment and coal seam are established. The virtual off-line operation system of fully mechanized coal mining face is constructed. The mining situation of virtual operation of working face reproduced and the simulation initial data and virtual scene operation data are determined. The perception operation model is added to the virtual equipment and AI robot analysis system is constructed. Based on sensor error analysis, execution error analysis and other error analysis, the equipment and geological exploration means are input according to the parameters of smart development and operation in the future. The operation evaluation system of fully mechanized coal mining face which considers cutting track, straightness, working space and dynamic coal seam is constructed. The operation of fully mechanized mining robot in the future is simulated, the development trend is determined and the robot operation performance is tested. The related prototype system is developed, and the testing of the overall operation of the working face was improved from the aspects of smart equipment and digital sensing elements. It shows that this method realizes the reappearance of fully mechanized mining operation process based on actual operation data and operation parameters. The current level of smart mining and some local or a small aspect of technological progress on the overall operation of the working face are analyzed and evaluated. The test and evaluation method points out the direction for the development of coal mine robot and smart mining.

An adaptive enhancement algorithm for low-illumination images based on HSV chromaticity space

“…Step 3: If the calculated H-value is less than 0, add 360 to the value to get the final H-value; the calculation formula is shown in equation (3):…”

“…Images captured under low-light conditions or with insufficient camera exposure time are called low-light images. Lowlight images are usually characterized by low brightness, low contrast, and blurred structural information, which brings difficulties to numerous visual image tasks, such as face recognition, target tracking [1], automatic driving [2], feature extraction [3], etc., for low-light images, and therefore, performing low-light image enhancement has some practical application value. In addition, today's commonly used image enhancement methods are divided into three categories: air domain, frequency domain, and human perception model.…”