An Unsupervised Intelligent Method for Cutting Pick State Recognition of Coal Mining Shearer

Abstract

This paper proposes an intelligent recognition method for shearer cutting state based on deep learning theory, to solve the problems where the picks are prone to various failure forms during the cutting of coal and rock masses by the shearer. The failure will lead to the decline on the stability of the entire machine of the shearer and affect the safety production. Specially, a 1:1 simulation bench is used for simulating underground mining conditions to measure and collect the cutting loads of picks and establish a sample database. Deep learning-based intelligent recognition method is an effective tool that can break away from the dependency of prior knowledge and recognition experience, and sparse. In this paper, a promising deep learning method called sparse filtering is proposed for intelligent recognition of shearer cutting. So sparse filtering is applied to construct an automatic feature extraction model, and softmax regression is adopted as a classifier for cutting pick state recognition. Furthermore, L1/2 regularization term is added to the cost function of sparse filtering to prevent the problem of excessive model training and weights. The proposed method for identifying the cutting status of the shearer can effectively monitor the cutting status of the picker, thereby improving the safety and stability of the cutting of the shearer and promote the coal mining efficiency. INDEX TERMS Shearer pick; sparse filtering; softmax regression; state recognition. K. Zhang et al.: An Unsupervised Intelligent Method for cutting pick state recognition

Design of Digital Twin Cutting Experiment System for Shearer

“…This yields the electromechanical coupled system dynamics mathematical model for the cutting section, as shown in Equation ( 9). (9) In the equation, X represents the generalized coordinate vector, with X = [xi yi θi], where i = m, 1, 2, ..., 5, d; M, TL, and Te are the generalized mass matrix, system load vector, and the electromagnetic torque vector of the cutting motor, respectively. Km, Kt, and Kb respectively represent the mesh stiffness matrix, torsional stiffness matrix, and bearing stiffness matrix, respectively; Cm and Ct represent the mesh damping matrix and torsional damping matrix, respectively.…”

“…The methodologies employed by researchers to conduct experimental investigations for coal and rock identification predominantly encompass:  In-situ experiments, where sensors and measurement instruments are deployed directly on the mining face to gather operational signals from coal and rock for subsequent analysis and evaluation [8].  Surface experiments, involving the use of an actual coal mining apparatus to perform real-life cutting tests on coal and rock on the surface, thereby collecting a range of performance metrics [9][10][11].  Simulating Shearer drum cutting tests, wherein scholars have devised and fabricated a simulating Shearer drum apparatus to replicate the cutting actions on coal and rock materials [12].…”

Design and Experimental Results of a Three-Dimensional Force Sensor for Shearer Cutting Pick Force Monitoring

“…However, they are all measured using a single-dimensional force transducer. Zhang et al [9] proposed that a welded strain gauge sensor should be used to test the cutting load of the picks, and a strain gauge rosette sensor should be used to measure the torsional stress. In the experiment, a welded strain gauge sensor was connected to an adjacent wireless strain acquisition module through a wire, and a total of six picks were selected for the cutting load test.…”