Machine Learning-Based Predictive Modeling and Control of Lean Manufacturing in Automotive Parts Manufacturing Industry

Nitin S. Solke (), Pritesh Shah (), Ravi Sekhar () and T. P. Singh ()
Additional contact information
Nitin S. Solke: Symbiosis International (Deemed University)
Pritesh Shah: Symbiosis International (Deemed University)
Ravi Sekhar: Symbiosis International (Deemed University)
T. P. Singh: LM Thapar School of Management

Global Journal of Flexible Systems Management, 2022, vol. 23, issue 1, No 5, 89-112

Abstract: Abstract The auto industry is critically dependent on lean and flexible manufacturing systems to sustain in today’s dynamic and price sensitive markets. In the current work, a machine learning-based predictive modeling and control strategy is proposed for the attainment of lean manufacturing (LM) through effective management of manufacturing flexibility. Firstly, lean manufacturing models were identified based on machine, labour, volume, routing, product flexibilities and material handling for forty six auto parts manufacturing companies in Pune region (India). As many as twenty three lean manufacturing models were derived based on system identification (control theory) structures: auto regressive with exogenous variables (ARX), auto regressive moving average with exogenous variables (ARMAX), output error (OE) and Box Jenkins (BJ) methods. All predictive models were compared for their relative performances based on validation indices such as the FIT%, mean squared error (MSE), final prediction error (FPE) and the number of model parameters. The ARX 750 structure attained the best predictive characteristics for LM (FIT 91.86%). This model was controlled for a set point of 0.8 LM level and corresponding levels of flexibilities were determined. The machine flexibility (MF) was identified to be the most significant contributor to lean manufacturing at a level of 0.7596. Consequently, MF was also modeled based on its seven sub parameters. The ARMAX 2120 structure obtained the best performance characteristics (FIT 99.94%) for MF modeling. Furthermore, this MF model was controlled at a level of 0.7596 (corresponding to 0.8 LM) and the required levels of MF sub parameters were determined. Thus, the current work provides definite guidelines for company managers to target quantitative attainment of specific machine flexibility parameters to ultimately attain an improved lean manufacturing level in the automotive industry.

Keywords: Automotive industry; Lean manufacturing; Machine learning; Manufacturing flexibility; Predictive modeling (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
http://link.springer.com/10.1007/s40171-021-00291-9 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:spr:gjofsm:v:23:y:2022:i:1:d:10.1007_s40171-021-00291-9

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/40171

DOI: 10.1007/s40171-021-00291-9

Access Statistics for this article

Global Journal of Flexible Systems Management is currently edited by Sushil

More articles in Global Journal of Flexible Systems Management from Springer, Global Institute of Flexible Systems Management
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().