Machine Learning to Estimate Gross Loss of Jewelry for Wax Patterns

TL;DR

This paper explores using machine learning regression techniques to accurately estimate gross loss in jewelry manufacturing, significantly reducing estimation errors from +-2-3 to +-0.5 with limited data.

Contribution

The study demonstrates the potential of machine learning algorithms to improve gross loss estimation accuracy in jewelry manufacturing using CAD data and historic records.

Findings

Error reduction from +-2-3 to +-0.5 using ML algorithms

Potential for early design phase estimation improvements

Requires larger datasets for validation

Abstract

In mass manufacturing of jewellery, the gross loss is estimated before manufacturing to calculate the wax weight of the pattern that would be investment casted to make multiple identical pieces of jewellery. Machine learning is a technology that is a part of AI which helps create a model with decision-making capabilities based on a large set of user-defined data. In this paper, the authors found a way to use Machine Learning in the jewellery industry to estimate this crucial Gross Loss. Choosing a small data set of manufactured rings and via regression analysis, it was found out that there is a potential of reducing the error in estimation from +-2-3 to +-0.5 using ML Algorithms from historic data and attributes collected from the CAD file during the design phase itself. To evaluate the approach's viability, additional study must be undertaken with a larger data set.