While attracting increasing research attention in science and technology, Machine Learning (ML) is playing a critical role in the digitalization of manufacturing operations towards Industry 4.0. Recently, ML has been applied in several fields of production engineering to solve a variety of tasks with different levels of complexity and performance. However, in spite of the enormous number of ML use cases, there is no guidance or standard for developing ML solutions from ideation to deployment. This paper aims to address this problem by proposing an ML application roadmap for the manufacturing industry based on the state-of-the-art published research on the topic. First, this paper presents two dimensions for formulating ML tasks, namely, ’Four-Know’ (Know-what, Know-why, Know-when, Know-how) and ’Four-Level’ (Product, Process, Machine, System). These are used to analyze ML development trends in manufacturing. Then, the paper provides an implementation pipeline starting from the very early stages of ML solution development and summarizes the available ML methods, including supervised learning methods, semi-supervised methods, unsupervised methods, and reinforcement methods, along with their typical applications. Finally, the paper discusses the current challenges during ML applications and provides an outline of possible directions for future developments.

Injection compression molding (ICM) provides enhanced optical performances of molded polymer optics in terms of birefringence and transmission of light compared to Injection molding (IM). Nevertheless, ICM requires case-dedicated process optimization to ensure that the required high accuracy geometrical replication is achieved, particularly especially in the case of surface micro-features. In this study, two factorial designs of experiments (DOE) were carried out to investigate the replication capability of IM and ICM on a micro structured Fresnel lens. A laser scanning confocal microscope was employed for the quality control of the optical components. Thus, a detailed uncertainty budget was established for the dimensional measurements of the replicated Fresnel lenses, considering specifically peak-to-valley (PV) step height and the pitch of the grooves. Additional monitoring of injection pressure allowed for the definition of a manufacturing signature, namely, the process fingerprint for the evaluation of the replication fidelity under different process conditions. Moreover, considerations on the warpage of parts were related to a manufacturing signature of the molding processes. At last, the global part mass average and standard deviation were measured to correlate local geometrical replication performances with global part quality trends.