Surface texturing is an effective method to reduce friction without the need to change materials. In this study, surface textures were transferred to rubber samples in the form of dimples, using a novel laser surface texturing (LST)—based texturing during moulding (TDM) production process, developed within the European Project MouldTex. The rubber samples were used to experimentally determine texture-induced friction variations, although, due to the complexity of manufacturing, only a limited amount was available. The tribological friction measurements were hence combined with an artificial intelligence (AI) technique, i.e., Reduced Order Modelling (ROM). ROM allows obtaining a virtual representation of reality through a set of numerical strategies for problem simplification. The ROM model was created to predict the friction outcome under different operating conditions and to find optimised dimple parameters, i.e., depth, diameter and distance, for friction reduction. Moreover, the ROM model was used to evaluate the impact on friction when manufacturing deviations on dimple dimensions were observed. These results enable industrial producers to improve the quality of their products by finding optimised textures and controlling nominal surface texture tolerances prior to the rubber components production.

A novel experimental methodology is developed for the characterization of the vulcanization and foaming processes of an ethylene propylene diene (EPDM) cellular rubber and for establishing the relationship of its physical and mechanical property evolution with vulcanization and foaming process temperature. To establish this relationship, the vulcanization and foaming reaction kinetics and their coupling have been determined, as well as important parameters in the behaviour of the material, such as conductivity, specific heat capacity and coefficients of expansion and foaming. This aforementioned strategy allows the setting of a material model that can be implemented into finite-element (FE) codes to reproduce the material changes during the vulcanization and foaming processes. The material model developed reproduces with enough accuracy the coupling of chemical kinetics of vulcanization and foaming reactions. The results provided by the numerical material model fit a similar trend, and values with an accuracy of 90–99% to those observed in the experiments conducted for the determination of the cellular rubber expansion in function of the temperature. Moreover, the cellular rubber expansion values agree with the structural analysis of vulcanized and foamed samples at different isothermal temperatures and with the proportional loss of mechanical properties in the function of the vulcanization and foaming degree.

Industrial manufacturing management can benefit from the use of modeling. For a correct representation of the manufacturing process and the subsequent management, the models must incorporate the effect of the uncertainty propagation throughout the stages considered. In this paper, the proposed methodology for uncertainty management uses a nonintrusive method that is based on building a deterministic physics-informed real-time model for the a posteriori computation of output uncertainties. This model is built using tensor factorization as the Model Order Reduction technique. It includes as model parameters: material properties, process operations, and those random and epistemic uncertainties of known variables. The resulting model is used off-line to identify sensitivities and therefore to unify uncertainty management across the material transformation process. This method is presented by its direct application to an automotive door seal manufactured by continuous co-extrusion of several rubbers and reinforcement (metal strip and glass fiber thread).

Reaching a zero-defect manufacturing is one of the biggest challenge for the current manufacturing industry. One of the barriers to overcome is to handle appropriately the uncertainty propagation across manufacturing lines, that hinder the development of accurate control systems. Within this framework, we introduce a non-intrusive method for uncertainty management that relies on a Monte Carlo approach building on a deterministic parametric real-time simulation model. The real-time simulation model is a Reduced Order Model (ROM) based on a generalized Canonical Polyadic Decomposition. The method is introduced using an industrial test case as demonstrator, namely car door/body seals manufacturing by means of continuous coextrusion of a metal strip and various types of rubber. The resulting model is used to unify uncertainty management of: (i) aleatory and epistemic origin, and (ii) material characterization and process parameters.

This work presents a novel algorithm for failure prediction in manufacturing processes using online unsupervised learning based on Kullback–Leibler divergence (KLD). The proposed method continuously monitors sensor data by comparing the probability distributions of a test window against those of a reference window to detect deviations that signal potential system degradation. These distributions are modeled as multivariate Gaussians to capture interdependencies between sensor signals. The algorithm is applied to real-world data from an electric arc furnace in the steel industry, demonstrating its ability to predict failures without prior offline training. Experimental results reveal that multivariate KLD analysis offers a more favorable balance between early fault detection and false alarm rates than univariate approaches. The method provides a lightweight, data-efficient, and practical solution for predictive maintenance in industrial settings where labeled failure data is limited or unavailable.