Study of Smart Condition Monitoring using Deep Neural Networks with Dropouts and Cross-Validation

Hwee Fang Cindy Tan, Wai Lok Woo, Anurag Sharma, T. Logenthiran, D. S. Kumar

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

4 Citations (Scopus)

Abstract

The main focus of this paper to develop and analyse computational intelligence algorithm for smart condition monitoring. Smart condition monitoring is important and helps to solve some of the difficulties faced in terms of maintaining types of mechanical or electrical machines. This paper focuses on the ability to predict if a particular machine is in working condition or not based on a dataset provided. The dataset would consist of the actual data output that the smart condition algorithm can predict, and that there would be an accuracy based on the number of correct predictions. The implementation of the proposed work will be based on using deep neural network (DNN) with programming software Python. The algorithm will be trained on some of the parameters, while the remaining would be used for the testing process.
Original languageEnglish
Title of host publication2019 IEEE PES Innovative Smart Grid Technologies Asia, ISGT 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3965-3969
Number of pages5
ISBN (Electronic)9781728135205
ISBN (Print)9781728135205
DOIs
Publication statusPublished - 1 May 2019

Publication series

Name2019 IEEE PES Innovative Smart Grid Technologies Asia, ISGT 2019

Keywords

  • Deep Neural Network
  • Predictive Maintenance
  • Python programming
  • Smart Condition Monitoring

Fingerprint

Dive into the research topics of 'Study of Smart Condition Monitoring using Deep Neural Networks with Dropouts and Cross-Validation'. Together they form a unique fingerprint.

Cite this