Predicting manufacturing defects using machine learning algorithms

R. Gopi, Aditya Sharma, Savita Sangam and Saurabh Pratap

Chapter 9 in Handbook on Artificial Intelligence and the Circular Economy, 2026, pp 120-135 from Edward Elgar Publishing

Abstract: A reduction in product defects is imperative due to the direct impact of defects in quality on the end user in the production chain. Modern manufacturing can guarantee high-quality output by minimizing defects. This study explores modern machine learning algorithms to predict defects in the manufacturing process through real-time and efficient data processing. A multi-stage process is employed to develop the model, which includes data acquisition, pre-processing, model selection and training, and evaluation to address defects. To predict production defects, operational parameters such as production volume, cost, supplier quality, and defect rates are considered and analyzed by the developed model using six machine learning algorithms, such as K-Nearest Neighbors, Decision Trees, Support Vector Machine, Gradient Boosting, Random Forest, and Recurrent Neural Networks. In the results, the Random Forest model provides robust and reliable performance in defect prediction with a high accuracy of 95.52%. Furthermore, the structured models accurately predict manufacturing defects, thereby facilitating early defect detection, cost savings, increased efficiency, and optimized product quality. In addition, the study's findings offer a perspective on the potential of machine learning for manufacturing defect prediction, which will enable manufacturers and consumers to enhance the reliability and accuracy of their manufacturing processes.

Keywords: Manufacturing defects; Machine learning; Supply chain; Predictive model; Quality control (search for similar items in EconPapers)
Date: 2026
ISBN: 9781035343379
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.elgaronline.com/doi/10.4337/9781035343386.00017 (application/pdf)
Our link check indicates that this URL is bad, the error code is: 403 Forbidden

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:elg:eechap:23783_9

Ordering information: This item can be ordered from
http://www.e-elgar.com

Access Statistics for this chapter

More chapters in Chapters from Edward Elgar Publishing
Bibliographic data for series maintained by Jack Sweeney ().