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.

High power ultrasonic technology can currently count on a number of industrial applications. Ultrasonic welding, which is a standard joining technique in many applications on plastics, has few but well established metal applications, such as copper wires, pipes and connectors welding, or, considering spot welding of aluminium thin sheets, is attractive for the automotive industry field, where it could represent a possible cost effective alternative to resistance spot welding, clinching or self‐pierce riveting. The present experimental study is addressed to this kind of application in order to evidence the effects of welding parameters and, most of all, their interactions on the tensile strength of tensile–shear spot welded lap joints. Relevant results have been achieved by dedicated and non‐conventional instrumentations applied to the welder for measuring and controlling the process parameters. The best static performance has been taken as an input for the second part of the study regarding the fatigue behaviour and the joints failure modes.