Recognition of pick wear condition based on Grey-Markov chain model

Abstract

An attempt is made in this paper to solve the pick wear problem of mining machinery and propose a pick wear degradation model based on the Grey-Markov chain by using generated characteristics signals and certain pick wear parameters to enhance the prediction accuracy. The vibration and acoustic emission signals generated during the catting pick are extracted and analyzed. The energy and the value of the characteristic signal are obtained by wavelet analysis to construct a characteristic sample library of the signals. Two kinds of signals are applied to the model to analyze the error between the real and the predicted values. The model prediction results demonstrate a 1.43% error of the vibration signal, 1.64% error of the acoustic emission signal with 98% prediction accuracy, thus offers a new method for monitoring the pick wear of mining machinery.