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

Inspired from the low wetting properties of Lotus leaves, the fabrication of dual micro/nanoscale topographies is of interest to many applications. In this research, superhydrophobic surfaces are fabricated by a process chain combining ultrashort pulsed laser texturing of steel inserts and injection molding to produce textured polypropylene (PP) parts. This manufacturing route is very promising and could be economically viable for mass production of polymeric parts with superhydrophobic properties. However, surface damages, such as wear and abrasion phenomena, can be detrimental to the attractive wetting properties of replicated textured surfaces. Therefore, the final product lifespan is investigated using mechanical cleaning of textured PP surfaces with multipurpose cloths following the ASTM D3450 standard. Second, the surface damage of replication masters after 350 injection molding cycles with glass-fiber-reinforced PP, especially to intensify mold wear, was investigated. In both cases, the degradation of the dual-scale surface textures had a clear impact on surface topography of the replicas and thus on their wetting properties, too.

The mass production of polymeric parts with functional surfaces requires economically viable manufacturing routes. Injection moulding is a very attractive option, however, wear and surface damage can be detrimental to the lifespan of replication masters. In this research, austenitic stainless steel inserts were hardened by low temperature plasma carburising and then different micro and nano scale surface textures, inspired by Lotus leaves and Springtail skins, were laser fabricated. A commonly available talc-loaded polypropylene was used to produce 5000 replicas and thus to investigate the evolution of surface textures both on inserts and replicas together with their functional response. The progressive wear or surface damage on the inserts during the injection moulding process had a clear impact on surface roughness and peak-to-peak topographies of the replicas. In general, polymer replicas produced with the carburised inserts retained wetting properties for longer periods compared with those produced with the untreated replication masters.