• PDF / 4,168,065 Bytes
• 18 Pages / 595.276 x 790.866 pts Page_size
• 17 Downloads / 193 Views

DOWNLOAD

REPORT

---

Prediction and analysis of process failures by ANN classification during wire-EDM of Inconel 718 Abhilash P. M.1

•

Chakradhar D.1

Received: 11 June 2020 / Revised: 11 September 2020 / Accepted: 20 October 2020 Ó Shanghai University and Springer-Verlag GmbH Germany, part of Springer Nature 2020

Abstract Wire breakages and spark absence are two typical machining failures that occur during wire electric discharge machining (wire-EDM), if appropriate parameter settings are not maintained. Even after several attempts to optimize the process, machining failures cannot be eliminated completely. An offline classification model is presented herein to predict machining failures. The aim of the current study is to develop a multiclass classification model using an artificial neural network (ANN). The training dataset comprises 81 full factorial experiments with three levels of pulse-on time, pulse-off time, servo voltage, and wire feed rate as input parameters. The classes are labeled as normal machining, spark absence, and wire breakage. The model accuracy is tested by conducting 20 confirmation experiments, and the model is discovered to be 95% accurate in classifying the machining outcomes. The effects of process parameters on the process failures are discussed and analyzed. A microstructural analysis of the machined surface and worn wire surface is conducted. The developed model proved to be an easy and fast solution for verifying and eliminating process failures. Keywords Wire electric discharge machining (wireEDM)
Process failure
Spark absence
Wire breakage
Artificial neural network (ANN) classification
Failure prediction

& Abhilash P. M. [email protected] 1

Department of Mechanical Engineering, Indian Institute of Technology Palakkad, Palakkad, Kerala, India

1 Introduction Wire electric discharge machining (wire-EDM) is a nontraditional machining process that can cut any electrically conductive materials, irrespective of its hardness. The process is applicable for machining components that are difficult to machine using conventional techniques. The process offers many advantages over traditional machining processes, such as lower cutting force and minimal residual stress. Even though wire-EDM is extremely accurate and economical, the prediction of response is challenging because many uncontrollable factors are involved [1]. Parametric optimizations have been performed to achieve the maximum results from wire-EDM. However, process failures occurred even after parameters were tuned owing to the inherent variability in wire-EDM. Two typical process failures associated with wire-EDM are wire breakage and spark absence. Material removal occurs by controlled repetitive sparks. The supplied pulsed direct current voltage comprises ‘‘pulse on’’ and ‘‘pulse off’’ durations. During the pulse-on time, the dielectric fluid between the conductive workpiece and wire electrode ionizes and high-energy discharge spark occurs. During the pulse-off time, debris is flushed off and the dielectric property is restored