Diagnosing of Risk State and Prediction of Machinability Parameters in Machining Operations using Interval Type 2 Fuzzy Logic System

Abstract

Precise monitoring, diagnosing, and controlling of CNC machines like turning and drilling centres are challenging tasks in automated manufacturing industries. To perform data analysis of a CNC machine, all the required parameters need to be recorded, stored, and retrieved systematically for effective monitoring and control. In this work, the experimental data of a CNC machine (turning and drilling) are classified with interval type 2 fuzzy logic system (IT2FLS) using membership function (MF) to predict the required maintenance action, and to find the risk state of each subsystem and the associated machinability parameters. newlineAn analytical model-based maintenance scheme is proposed for an IoT-enabled hybrid flow shop (HFS). This model estimates the machine health index by fusing performance metrics data such as cycle time, work in process (WIP), and squared coefficient of variance (SCV) service time. These performance metrics reveal hidden risk factors of the machine s health state. A particular maintenance activity can be proposed before the failure of the machine based on a threshold value of performance metrics data. The proposed maintenance scheme is optimised using IT2FLS. The developed model is also validated with a case study related to an IoT-enabled HFS. newline