Optimizing Traditional Clustering Methods Using Metaheuristic Algorithms for Joint Set Identification in Copper Mines

Clustering assessment is crucial for identifying the primary characteristics of joints in mining and rock engineering. Orientation is commonly used to characterize the deformation patterns and mechanical properties of rock formations. This study introduces an enhanced clustering method by integrating the harmony search (HS) algorithm and the particle swarm optimization (PSO) algorithm to classify joint sets based on orientation parameters—namely, dip and dip direction—in the Sungun copper mine. First, the joint characteristics were clustered using K-means and fuzzy clustering techniques. The elbow method was applied to determine the optimal number of clusters, ultimately selecting a four-cluster classification. Subsequently, both K-means and fuzzy C-means (FCM) were optimized using HS and PSO algorithms, and the joint data were clustered and evaluated based on three clustering quality assessment criteria. The results demonstrated that the FCM-PSO method achieved the highest ranking among all tested methods, yielding a Davis-Bouldin index of ۰.۸۰, a Calinski-Harabasz index of ۳۴۸.۴۷, and a Silhouette score of ۰.۵۶۵. In contrast, integrating the HS algorithm with K-means and FCM did not enhance clustering performance as expected. Furthermore, the K-means-PSO method exhibited inferior performance compared to the FCM clustering approach, ranking third overall. Based on these findings, the FCM-PSO clustering method, by effectively determining optimal cluster centers, provides a reliable approach for classifying joint sets. The obtained results can be effectively utilized in rock mass behavior analysis for large-scale open-pit mines such as the Sungun copper mine.

کلیدواژه ها:

Joint set ، Clustering method ، K-means and C-means Mmethod ، Harmony search algorithm ، PSO Algorithm ، Sungun copper mine