Intelligent recognition of rock hardness for excavation support and anchor equipment based on feature optimization and improved sine cosine algorithm

Abstract To address the problem of rock hardness recognition in comprehensive excavation-face anchorage operations, a rock hardness recognition method based on feature optimization and an improved sine cosine algorithm optimised decision tree (CART) is proposed. First, the signal was reconstructed by successive variational mode decomposition (SVMD) and the waveform factor method. Second, the time–frequency matrix of the signal was calculated using short-time Fourier transform (STFT), S transform (ST), and frequency-corrected generalised S-transform (FCGST), and the dimension was reduced employing singular value decomposition (SVD). Finally, based on the improved sine cosine optimization algorithm (ISCA), the minimum leaf node size and maximum number of splits in the decision tree were optimised, and different rock hardness recognition models were established. Based on a self-developed experimental platform for the integration of excavation, support, and anchor, multiple lithologic combinations were determined. The results of drilling experiments show that by using the recognition model with SVMD, waveform factorisation method reconstruction, FCGST feature extraction, and ISCA key parameter optimization, the accuracy of rock hardness recognition was improved by 9% and 4%, respectively, and the recognition efficiency reached 97.33% compared with STFT and ST feature extraction. The effectiveness of the rock hardness identification method for drilling of excavation support and anchor equipment based on feature preference and decision tree was further verified. This study can provide technical support for the identification of rock hardness under complex working conditions of a comprehensive excavation face.