An Algorithm for Shape-Based Distance of Microseismic Time Series Waveforms and its Application in Clustering Mining Events

To improve the efficiency and accuracy of microseismic event extraction from time-series data and enhance the detection of anomalous events, this paper proposes a Multi-scale Fusion Convolution and Dilated Convolutions Autoencoder (MDCAE) combined with a Constraints Shape-Based Distance algorithm incorporating volatility (CSBD-Vol). MDCAE extracts low-dimensional features from waveform signals through multi-scale fusion and dilated convolutions while introducing the concept of waveform volatility (Vol) to capture variations in microseismic waveforms. An improved Shape-Based Distance (SBD) algorithm is then employed to measure the similarity of these features. Experimental results on a microseismic dataset from the 802 working face of a mining site demonstrate that the CSBD-Vol algorithm significantly outperforms SBD, Shape-Based Distance with volatility (SBD-Vol), and Constraints Shape-Based Distance (CSBD) in classification accuracy, verifying the effectiveness of constrained time windows and volatility in enhancing performance. The proposed clustering algorithm reduces time complexity from \((O(n^2))\) to \((O(n \log n))\), achieving substantial improvements in computational efficiency. Furthermore, the MDCAE-CSBD-Vol approach achieves 87% accuracy in microseismic time-series waveform classification. These findings highlight that MDCAE-CSBD-Vol offers a novel, precise, and efficient solution for detecting anomalous events in microseismic systems, providing valuable support for accurate and high-efficiency monitoring in mining and related applications.