Multivariate Statistical Process Monitoring Strategy for a Steel Making Shop
- 55 Downloads
Monitoring of a manufacturing process ensures production of consistently good quality end production. In this paper, an attempt has been made to develop a monitoring strategy for a serial multistage manufacturing facility based on multi-block partial least squares regression, a multivariate regression technique. The developed monitoring strategy has been applied to a medium scale steel making shop. The monitoring strategy thus developed was employed for detection as well as for diagnosis of the faults responsible for the poor quality end product. The results obtained were found to be in sync with actual conditions.
KeywordsHotelling T2 statistic Monitoring chart Multi-block partial least squares regression Process monitoring Steel making shop
- 1.Ganguly A, Patel SK (2015) Computer-aided design of X and R charts using teaching-learning-based optimization algorithm. Int J Prod Qual Manage 16(3):325–346Google Scholar
- 2.Doshi JA, Desai DA (2016) Statistical process control an approach for continuous quality improvement in automotive SMEs-Indian case study. Int J Prod Qual Manage 19:387–407Google Scholar
- 8.Botre C, Mansouri M, Karim MN, Nounou H, Nounou M (2017) Multiscale PLS based GLRT for fault detection of chemical processes. J Loss Prev Process Ind 46:143–153Google Scholar
- 13.Tupkary RH, Tupkary VR (1998) An introduction to modern steel making, 6th edn. Khanna Publishers, New DelhiGoogle Scholar