An Enhanced EWMA Model for Statistical Insights in Process Monitoring with Application in Brake Pad Failure and Carbon Fiber Strength
Abstract Conventional control charts often assume normality, which may not hold for many engineering processes. In cases where processes follow an Inverse Maxwell $$\left( {{\text{IM}}} \right)$$ IM distribution, as seen in various industrial applications, it becomes crucial to employ suitable monit...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-04-01
|
| Series: | Journal of Statistical Theory and Applications (JSTA) |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44199-025-00110-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract Conventional control charts often assume normality, which may not hold for many engineering processes. In cases where processes follow an Inverse Maxwell $$\left( {{\text{IM}}} \right)$$ IM distribution, as seen in various industrial applications, it becomes crucial to employ suitable monitoring methods. To address this gap, this study introduces the hybrid exponentially weighted moving average ( $${\text{HEWMA}}_{{{\text{IM}}}}$$ HEWMA IM ) chart for the $${\text{IM}}$$ IM distribution. Performance evaluation includes metrics like average run length, median run length, and standard deviation run length. Comparative analysis with existing IM distribution-based charts such as the Shewhart V chart ( $${\text{V}}_{{{\text{IM}}}}$$ V IM ), exponentially weighted moving average ( $${\text{EWMA}}_{{{\text{IM}}}}$$ EWMA IM ), and extended EWMA ( $${\text{EEWMA}}_{{{\text{IM}}}}$$ EEWMA IM ) charts reveal the $${\text{HEWMA}}_{{{\text{IM}}}}$$ HEWMA IM chart’s superior efficiency. Real-world applications in brake pad production and carbon fiber strength testing validate its practicality and engineering applications. In conclusion, $${\text{HEWMA}}_{{{\text{IM}}}}$$ HEWMA IM is a novel tool tailored to monitor $${\text{IM}}$$ IM processes efficiently, offering enhanced process monitoring for diverse industries. Graphical abstract |
|---|---|
| ISSN: | 2214-1766 |