Research on Intelligent Identification Technology of Mine Microseismic Signals Based on Pattern Recognition and Machine Learning

With the increasing application of microseismic monitoring technology in mines, it is still difficult to automatically distinguish effective signals from noise signals, which limits its popularization and practical performance to a certain extent. This paper systematically analyzes six major identifiable signal patterns in high-noise mine environments, including rock drilling, trackless equipment operation, ore pass dumping, electromagnetic interference, blasting, and effective signals. The effective signals are further subdivided into low-energy and high-energy subcategories, and the generation mechanism of each pattern is discussed in depth. Based on a large number of collected sample data, the AIC algorithm, short-to-long window amplitude ratio, short-window amplitude average, and single-point amplitude triggering method are adopted to extract the recognition features of the above six patterns, including waveform interval time Δt, waveform duration tc, dominant frequency fd, number of independent events, and their combinations. Probability statistics are performed on each characteristic value, and an automatic pattern recognition algorithm for mine microseismic waveform characteristics is constructed. Meanwhile, a two-stage intelligent recognition model is established using the convolutional neural network machine learning method. A total of 1500 typical samples are selected and divided into training and test sets at a ratio of 7:3. After 5000 training iterations, the average accuracies of the three classifiers reached 87%, 84%, and 90%, respectively. The intelligent microseismic signal recognition method developed on this basis was field-tested at the Xianglushan Tungsten Mine, achieving a recognition accuracy of 94.9% for low-energy effective events. It shows favorable engineering adaptability and meets the expected research objectives.