A study on fault diagnosis and maintenance of CNC-WEDM based on binary relational analysis and expert system

Abstract

The paper presents a binary relational analysis and expert system base module for maintenance and fault diagnosis of CNC wire EDM. The module proposes a framework of integrated maintenance and fault diagnosis system. The study explores the binary coded matrix system, which plays an important role in prediction and diagnosis of wire electrical discharge machining (WEDM) faults on the spot by expert guidance. In this study, 15 inputs were considered to observe eight probable causes with the help of the forward and backward propagation algorithms. Inputs and output matrices were considered in the form of a square matrix. To explain the fault diagnosis and to realize the importance of maintenance through advice, the detection of faults is investigated through forward and back propagation of matrix transformation on the spot. It is an integrated backup that can be individually focused when input and output parameter do not match. It is a time saving, knowledge acquisition, easy to maintain, and capable of self-learning system. To verify the developed framework, 120 data sets were generated for proper analyzing of acquired output through graphical representation. The paper also presents some of the important features of maintenance schedule and probable causes of wire breakage with remedial actions in tabular form. The developed system can help the operators, trainees, and manufacturing engineers in achieving trouble free machining through quick detection of faults and proper maintenance of machines in actual practice.