Impelled by digitalization and rapid advances in machine learning, data-driven methods are becoming more important for manufacturing. Often replacing or augmenting modelling and knowledge-based approaches, these data-driven methods serve many purposes. They can help optimize individual steps in the workflow and control complex processes to minimize waste and maximize productivity. They can detect anomalies, enable predictive maintenance and optimize the logistics of complex supply chains. Computers can use sensors and actuators to learn how process parameters and outcomes are related. This enables engineers to develop and roll out ‘immature’
processes – that is, production processes that are not yet fully understood in terms of the physics or engineering.