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.
1 January 2017 in CIRP Journal of Manufacturing Science and Technology
Understanding the micro milling phenomena involved in the process is critical and difficult through physical experiments. This study presents a 3D finite element modeling (3D FEM) approach for the micro end-milling process on Al6082-T6. The proposed model employs a Lagrangian explicit finite element formulation to perform coupled thermo-mechanical transient analyses. FE simulations were performed at different cutting conditions to obtain realistic numerical predictions of chip formation, temperature distribution, and cutting forces by considering the effect of tool run-out in the model. The radial run-out is a significant issue in micro milling processes and influences the cutting stability due to chip load and force variations. The Johnson–Cook (JC) material constitutive model was applied and its constants were determined by an inverse method based on the experimental cutting forces acquired during the micro end-milling tests. The FE model prediction capability was validated by comparing the numerical model results with experimental tests. The maximum tool temperature was predicted in a different angular position of the cutter which is difficult or impossible to obtain in experiments. The predicted results of the model, involving the run-out influence, showed a good correlation with experimental chip formation and the signal shape of cutting forces.
28 May 2009 in The International Journal of Advanced Manufacturing Technology