Fault diagnosis of full-hydraulic drilling rig based on RS–SVM data fusion method

Abstract

In order to improve the fault diagnosis accuracy of the full-hydraulic drilling rig, RS–SVM multi-sensor data fusion fault diagnosis method is proposed based on the rough set theory (RS) and support vector machine (SVM). In the method, the feature layer fusion structure is adopted and energy-normalized feature vectors of the fault signal sub-band are extracted by wavelet packet decomposition. Because of the advantages in evaluating fault identification parameters, removing redundant data and retaining the minimum core attribute set, the RS was introduced to the multi-sensor data fusion fault diagnosis method to avoid the dimension disaster and decrease the time consumption. In this way, the computational complexity of SVM is reduced, but its efficiency and accuracy are improved. Finally, the new fault diagnosis method was used to monitor the hydraulic motor internal leakage fault and gear tooth fracture fault of the full-hydraulic drilling rig. The experiment result shows that the classification accuracy of the new method is 64 and 100%, respectively, for hydraulic motor leakage fault and gear tooth fracture fault, and the new fault diagnosis method is effective and superior to traditional RS theory and SVM.