A Data-Driven Approach Using Enhanced Bayesian-LSTM Deep Neural Networks for Picks Wear State Recognition

Abstract

Picks are key components for the mechanized excavation of coal by mining machinery, with their wear state directly influencing the efficiency of the mining equipment. In response to the difficulty of determining the overall wear state of picks during coal-mining production, a data-driven wear state identification model for picks has been constructed through the enhanced optimization of Long Short-Term Memory (LSTM) networks via Bayesian algorithms. Initially, a mechanical model of pick and coal-rock interaction is established through theoretical analysis, where the stress characteristic of the pick is analyzed, and the wear mechanism of the pick is preliminarily revealed. A method is proposed that categorizes the overall wear state of picks into three types based on the statistical relation of the actual wear amount and the limited wear amount. Subsequently, the vibration signals of the cutting drum from a bolter miner that contain the wear information of picks are decomposed and denoised using wavelet packet decomposition, with the standard deviation of wavelet packet coefficients from decomposed signal nodes selected as the feature signals. These feature signals are normalized and then used to construct a feature matrix representing the vibration signals. Finally, this constructed feature matrix and classification labels are fed into the Bayesian-LSTM network for training, thus resulting in the picks wear state identification model. To validate the effectiveness of the Bayesian-LSTM deep learning algorithm in identifying the overall picks wear state of mining machinery, vibration signals from the X, Y, and Z axes of the cutting drum from a bolter miner at the C coal mine in Shaanxi, China, are collected, effectively processed, and then input into deep LSTM and Back-Propagation (BP) neural networks respectively for comparison. The results showed that the Bayesian-LSTM network achieved a recognition accuracy of 98.33% for picks wear state, showing a clear advantage over LSTM, BP network models, thus providing important references for the identification of picks wear state based on deep learning algorithms. This method only requires the processing and analysis of the equipment parameters automatically collected from bolter miners or other mining equipment, offering the advantages of simplicity, low cost, and high accuracy, and providing a basis for a proper picks replacement strategy.