Manufacturing Process Optimization using Statistical Methodologies

TL;DR

This paper demonstrates how Response Surface Methodology (RSM) can optimize manufacturing processes, specifically in diesel engine nozzle production, by identifying key factors influencing response variables using statistical experimental design.

Contribution

The paper applies RSM with Central Composite Design to a manufacturing process, illustrating its effectiveness in optimizing process parameters.

Findings

One factor significantly improves response values.

RSM effectively identifies influential process variables.

Implementation using R's DoE plugin simplifies optimization.

Abstract

Response Surface Methodology (RSM) introduced in the paper (Box & Wilson, 1951) explores the relationships between explanatory and response variables in complex settings and provides a framework to identify correct settings for the explanatory variables to yield the desired response. RSM involves setting up sequential experimental designs followed by application of elementary optimization methods to identify direction of improvement in response. In this paper, an application of RSM using a two-factor two-level Central Composite Design (CCD) is explained for a diesel engine nozzle manufacturing sub-process. The analysis shows that one of the factors has a significant influence in improving desired values of the response. The implementation of RSM is done using the DoE plug-in available in R software.