A study of micromanufacturing process fingerprints in micro-injection moulding for machine learning and Industry 4.0 applications

Abstract This paper discusses micromanufacturing process quality proxies called “process fingerprints” in micro-injection moulding for establishing in-line assurance and machine learning models Industry 4.0 applications. Process fingerprints that we present this study are purely physical of the product need tangible rationale regarding their selection criteria such as sensitivity, cost-effectiveness, robustness. Proposed methods reasons also justified by analysing temporally collected data with respect to microreplication efficiency. Extracted were used a multiple linear regression scenario where they bring actionable insights creating traceable cost-effective supervised challenging environments. Multiple model demonstrated %84 accuracy predicting process, which is significant far extreme conditions features concerned.