The study of machine learning for wire rupture prediction in WEDM

Ping Hsien Chou, Yean Ren Hwang, Bling Hwa Yan

Research output: Contribution to journalArticlepeer-review

3 Scopus citations

Abstract

During wire electrical discharge machining (WEDM), wire rupture may deteriorate workpieces’ machined surfaces and increase the processing time. However, only a few referenced papers focused on wire rupture during past decades because of its complexity. In this research, machine learning (ML) technique was applied to analyze the relationship between manufacturing parameters and the chance of wire rupture. Three parameters, including gap voltage (GV), feed rate (FR), and water resistance (WR), were considered as training features, and a total of 298 sets were used to train an artificial neural network (ANN). The results show that the prediction accuracy of wire rupture for 10 s in advance is above 85%. This research developed a new method to apply the real-time predict wire rupture and is faster, more accurate than prior research. Besides, this method is extendable for future measured data when the usable sensor data are increasing.

Original languageEnglish
Pages (from-to)1301-1311
Number of pages11
JournalInternational Journal of Advanced Manufacturing Technology
Volume119
Issue number1-2
DOIs
StatePublished - Mar 2022

Keywords

  • Artificial neural network
  • WEDM
  • Wire rupture

Fingerprint

Dive into the research topics of 'The study of machine learning for wire rupture prediction in WEDM'. Together they form a unique fingerprint.

Cite this