Seismic fault identification in coal mines based on SOM–GWO–SVM algorithm

Accurate fault identification in coal mines is important to improve mine safety and economic benefits. We compared various intelligent algorithms for data pre-processing and optimisation, and analysed the construction methods of seismic attribute datasets and the performance of intelligent optimisation algorithms using fault identification accuracy as the discrimination index to find a better combined model for seismic fault identification. First, the training dataset is constructed by mining the fault and non-fault information revealed by the roadway. The distribution characteristics of the seismic attribute data show similarities among them, and they are non-linearly separable. Directly using the attributes to construct the dataset, the accuracy of fault identification using the support vector machine model was 78.41%. Principal Component Analysis and Self-Organising Mapping Neural Network were used to extract effective information, and then combined with the SVM classification model, the accuracy of fault identification was 83.82% and 87.47%, respectively. Compared with the original data and PCA dimensionality reduction data, the accuracy of fault detection is improved by 9.06% and 3.66%, respectively, indicating that SOM can effectively improve the accuracy of fault detection by eliminating similar attributes and reducing the weight of redundant information. Then, through fixed attribute data set, Genetic Algorithm, Particle Swarm Optimization and Grey Wolf Optimizer intelligent optimization algorithms were used to find the optimal kernel function parameter and penalty parameter of SVM classifier, the accuracy rate of SOM-GWO-SVM model reached 91.12%, compared with SOM-PSO-SVM and SOM-GA-SVM, the model accuracy is increased by 5.2% and 5.61%, respectively. Compared with PSO and GA, the GWO algorithm has a better global search ability. The identification result of the SOM-GWO-SVM model is closest to the actual fault exposure, especially for the identification of "short" faults and associated faults, which has obvious advantages over the traditional manual interpretation in terms of efficiency and accuracy.