Surface Roughness Prediction Based on Markov Chain and Deep Neural Network for Wire Electrical Discharge Machining

Chen Lun Fan, Jehn Ruey Jiang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

This paper proposes methods for predicting the WEDM surface roughness by analyzing manufacturing parameters which are set before production and machining conditions that are gathered during production. The methods are based on the deep neural network (DNN), and the Markov chain integrated with deep neural network (MC-DNN), respectively. The prediction errors of the proposed methods are evaluated and compared with those of related methods in terms of the mean absolute percentage error (MAPE). The comparison results show that the proposed methods have comparatively good performance.

Original languageEnglish
Title of host publication2019 IEEE Eurasia Conference on IOT, Communication and Engineering, ECICE 2019
EditorsTeen-Hang Meen
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages191-194
Number of pages4
ISBN (Electronic)9781728125015
DOIs
StatePublished - Oct 2019
Event2019 IEEE Eurasia Conference on IOT, Communication and Engineering, ECICE 2019 - Yunlin, Taiwan
Duration: 3 Oct 20196 Oct 2019

Publication series

Name2019 IEEE Eurasia Conference on IOT, Communication and Engineering, ECICE 2019

Conference

Conference2019 IEEE Eurasia Conference on IOT, Communication and Engineering, ECICE 2019
Country/TerritoryTaiwan
CityYunlin
Period3/10/196/10/19

Keywords

  • deep neural network
  • Markov chain
  • surface roughness
  • wire electrical discharge machining

Fingerprint

Dive into the research topics of 'Surface Roughness Prediction Based on Markov Chain and Deep Neural Network for Wire Electrical Discharge Machining'. Together they form a unique fingerprint.

Cite this