On-line monitoring and diagnosis of tapping process using Neuro Fuzzy Systems

Abstract

Tapping has been widely used throughout industry, and its proper operation is paramount in ensuring product quality. Therefore, monitoring and diagnosis is needed to detect the tapping process conditions. In this work, a combination of ten indices of the tapping process was extracted from tapping torque, thrust force, and lateral forces. The Sequential Forward Search (SFS) algorithm has been used to select the best feature sets. Adaptive Neuro Fuzzy Inference Systems (ANFIS) were used for the monitoring and diagnosis of tapping process. A 3x2 ANFIS structure can distinguish normal tapping process from abnormal tapping process with 100% reliability. The tapping process conditions can be further classified into five categories with over 95% success rate using a 10x2 ANFIS structure. In simple words, monitoring and diagnosis of tapping process can be carried out successfully using SFS and ANFIS.