A decision fusion algorithm for tool condition monitoring in drilling using Hidden Markov Model (HMM)

In today’s world, the leading industries are very much concerned about reducing down-time and increasing the productivity as well as the quality. To increase the product quality, the tool should have good performance. Drilling process is widely used in the manufacturing operations in all the manufacturing industries. In this study, two Hidden Markov Models (HMM) such as bar-graph method and the multiple modeling methods have been used to determine the tool wear states in drilling operations. Cutting speed, feed rate, drill diameter and torque are taken as input parameters for the HMM bar-graph method. Cutting speed, feed rate, drill diameter, thrust force and feed-motor power are taken as input parameters for the HMM multiple modeling methods. In order to increase the reliability of these outputs, a Decision Fusion Center Algorithm (DFCA) is proposed which combines the outputs of the individual methods to make a global decision about the wear status of the drill tool.