The digitalization of manufacturing processes offers great potential in quality control, traceability, and the planning and setup of production. In this regard, process simulation is a well-known technology and a key step in the design of manufacturing processes. However, process simulations are computationally and time-expensive, typically beyond the manufacturing-cycle time, severely limiting their usefulness in real-time process control. Machine Learning-based surrogate models can overcome these drawbacks, and offer the possibility to achieve a soft real-time response, which can be potentially developed into full close-loop manufacturing systems, at a computational cost that can be realistically implemented in an industrial setting. This paper explores the novel concept of using a surrogate model to analyze the case of the press hardening of a steel sheet of 22MnB5. This hot sheet metal forming process involves a crucial heat treatment step, directly related to the final part quality. Given its common use in high-responsibility automobile parts, this process is an interesting candidate for digitalization in order to ensure production quality and traceability. A comparison of different data and model training strategies is presented. Finite element simulations for a transient heat transfer analysis are performed with ABAQUS software and they are used for the training data generation to effectively implement a ML-based surrogate model capable of predicting key process outputs for entire batch productions. The resulting final surrogate predicts the behavior and evolution of the most important temperature variables of the process in a wide range of scenarios, with a mean absolute error around 3 °C, but reducing the time four orders of magnitude with respect to the simulations. Moreover, the methodology presented is not only relevant for manufacturing purposes, but can be a technology enabler for advanced systems, such as digital twins and autonomous process control.

Nowadays, water utilities face the rising challenge of ensuring water availability amidst a rapidly growing society and a shifting climate. Our research aims to develop a household clustering solution based on water consumption behaviour in Southwest England, to enable utilities to identify different profiles and enhance customized control of household consumption, resulting in improved resource management. The solution is composed of three modules. The first one is based on a K-Means clustering model, designed to group domestic water use behaviours. This module uses the Dynamic Time Wrapping algorithm as a similarity mechanism to process the high-resolution water meter data. In parallel, the second module processes the market segmentation data through an Autoencoder, a specific Neural Network architecture used to reduce the high dimensionality of such data to a low dimension dataset by extracting its latent encoded space. Finally, to assemble the final household water use profiles, a blending K-Means algorithm is used to merge previous modules outputs, based on the Euclidean distance. The solution provides insightful information to water companies to better understand consumer behaviour, habits, and routines.

Hot stamping is a hot metal forming technology increasingly in demand that produces ultra-high strength parts with complex shapes. A major concern in these systems is how to shorten production times to improve production Key Performance Indicators. In this work, we present a Reinforcement Learning approach that can obtain an optimal behavior strategy for dynamically managing the cycle time in hot stamping to optimize manufacturing production while maintaining the quality of the final product. Results are compared with the business-as-usual cycle time control approach and the optimal solution obtained by the execution of a dynamic programming algorithm. Reinforcement Learning control outperforms the business-as-usual behavior by reducing the cycle time and the total batch time in non-stable temperature phases.