Machine learning to predict the field reliability of electric steam irons

Silas Muzorewa and A. Telukdarie

International Journal of Intelligent Enterprise, 2024, vol. 11, issue 2, 141-156

Abstract: The purpose of this research is to apply machine learning methods to predict field reliability of household electromechanical appliances. The scope of household electro-mechanical appliances was narrowed down to include only electric steam irons. The research approach involved data collection, data exploration, selection of a machine learning technique, model training, model performance evaluation, and performance improvement. Using physical, performance, and reliability data, we trained a Naïve Bayes model to predict the field reliability of steam irons. The highest prediction accuracy achieved was 78%. To evaluate the discrimination ability of the prediction model, we performed receiver operating characteristic (ROC) analysis, which yielded an average area under curve (AUC) of 0.86. Our proposed method allows industry practitioners to evaluate the field reliability of new electromechanical appliances using limited data in a timeous and cost-effective manner. The method presented solely utilises the design and performance features of an appliance to predict field reliability.

Keywords: reliability prediction; electromechanical appliances; household appliances; Naïve Bayes; NB. (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=137686 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijient:v:11:y:2024:i:2:p:141-156

Access Statistics for this article

More articles in International Journal of Intelligent Enterprise from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().