Abstract
Machine learning (ML) is unlocking patterns and insight into data to provide financial value and knowledge for organizations. Use of machine learning in manufacturing environments is increasing, yet sometimes these applications fail to produce meaningful results. A critical review of how defects are classified is needed to appropriately apply machine learning in a production foundry and other manufacturing processes. Four elements associated with defect classification are proposed: Binary Acceptance Specifications, Stochastic Formation of Defects, Secondary Process Variation, and Visual Defect Inspection. These four elements create data space overlap, which influences the bias associated with training supervised machine learning algorithms. If this influence is significant enough, the predicted error of the model exceeds a critical error threshold (CET). There is no financial motivation to implement the ML model in the manufacturing environment if its error is greater than the CET. The goal is to bring awareness to these four elements, define the critical error threshold, and offer guidance and future study recommendations on data collection and machine learning that will increase the success of ML within manufacturing.
Highlights
Machine learning (ML), a specific subset of technology in the Artificial Intelligence (AI) field, has seen an explosion in commercial use in the past 30 years
The section will provide insight into how the bias-variance tradeoff within ML is influenced by these misclassifications and the importance of a critical error threshold with highly unbalanced data that exists in manufacturing
critical error threshold (CET) ! Accuracy of the ML model in terms of FN%; TN%; FP% is such that : ðS%ÞðC$ þ V$ÞðEAUÞ [ ðFN% þ TN%ÞðC$ÞðEAUÞ þ ðFP%ÞðC$ þ V$ÞðEAUÞ þ ML$ Eqn: 6 where: CET 1⁄4 Critical Error Threshold S% 1⁄4 Current Scrap % of Casting as decimal C$ 1⁄4 Casting Scrap Cost per part V$ 1⁄4 Processing Value Add per part EAU 1⁄4 Estimated Annual Usage or Volume FN% 1⁄4 Percentage of False Negatives as decimal TN% 1⁄4 Percentage of True Negatives as decimal FP% 1⁄4 Percentage of False Positives as decimal ML$ 1⁄4 Annualized Machine Learning Implementation Cost
Summary
Machine learning (ML), a specific subset of technology in the Artificial Intelligence (AI) field, has seen an explosion in commercial use in the past 30 years. The random formation of the porosity causes one casting to be scrap and the other needed to train ML algorithms for accurate predictions is not collected by traditional means within manufacturing. These four elements of Binary Acceptance Specifications, Stochastic Formation of Defects, Secondary Process Variation, and Visual Defect Inspection all influence the final classification of a part.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
