Intelligent coal gangue identification: A novel amplitude frequency sensitive neural network

Abstract

Top caving is a crucial mining method for extracting thick coal seams, with the gangue content rate serving as a significant measure of effectiveness. However, the mixing of gangue with coal during the mining process results in economic waste. Therefore, accurate identification of gangue is essential to minimize this content. The detection of gangue encounters challenges due to inconsistent frequency representations arising from uncertain collapsing behavior, which consequently leads to low accuracy when utilizing vibration signals. To address this issue, this paper presents a deep-learning-based method for the efficient identification of collapsed coal and gangue vibration signals with high accuracy. The method comprises feature enhancement blocks, amplitude–frequency perception modules, and a classifier. The feature enhancement block prioritizes key signal sections, while the amplitude–frequency perception modules capture shock representations, and the classifier utilizes these features for decision-making. Additionally, a retention mechanism is incorporated to optimize model size and enhance inference speed. Comparative experiments and an ablation study show the method’s effectiveness, surpassing 25 baseline models with 93.17% accuracy and only 704.266 k parameters. Through the proposed method, this paper demonstrates a feasible solution for accurate and rapid identification of vibration signals, providing an exemplary direction for the future development of coal gangue identification.