Industrial machines commissioning consumes a great amount of man-hours, due to control designers lack of knowledge about the final controller gains before they start working with it. Virtual commissioning has been postulated as an optimal solution to deal with this lack of knowledge when the Real-Time simulation of the digital models reproduces an identical behaviour as the industrial machines they represent. Cyber-Physical Systems (CPSs) offer new opportunities in this field, however, in the case of industrial machines, acquiring this level of accuracy requires to slow down the simulation. On this paper, novel modelling techniques for industrial CPSs have been presented. They are introduced to help in the evolution from conventional control design to a virtual commissioning process combining software and hardware capabilities. This methodology has been tested with a hydraulic-press model designed following manufacturer specifications, initially under a Software in the Loop (SiL) validation platform and, afterwards, in a Hardware in the Loop (HiL) validation platform. The control algorithms are designed in laboratory conditions harmless for the machine, embedding them later in the industrial environment without further modifications.

Fault-Tolerant Controllers (FTCs) modify system behaviour to overcome faults without human interaction. These control algorithms, when based on active approach, detect, quantify and isolate the faults during Fault Detection and Isolation (FDI) phase. Afterwards, during Control Re-design (CR) phase, the controller is reconfigured and adapted to the faulty situation. This last phase has been approached by a wide variety of algorithms, being Adaptive Controllers (ACs) the ones studied in this paper. Despite their potentiality to overcome faults, industrial manufacturing systems demand robustness and flexibility levels hardly achievable by these algorithms. On this context, the paper proposes to upgrade them introducing novel Digital-Twin (DT) models to increase its flexibility and Anti-Windup (AW) techniques to improve their robustness. These novelties reach their maximum potential when FDI and CR phases merge to generate a novel FTC platform based on a Bank of Controllers (BC), improving the fault avoidance process as controller gains are switched to the ones that recover the machine more efficiently.

Accurate energy prediction is essential for energy-aware planning and navigation of autonomous mobile robots (AMRs). This study investigates whether a compact feed-forward neural network (FFNN) can predict relative energy consumption from operational variables with high accuracy and interpretability. Using a curated dataset of controlled translation and rotation trials on a KUKA KMP 1500P, energy demand is expressed as the per-trial reduction in battery state of charge (SoC), defined as $N_{1\mathrm{\%}}$. For unit-free reporting, it is also considered the normalized SoC consumed per trial, defined as $E=1/N_{1\mathrm{\%}}$. Model development followed a two-stage optimization pipeline, (i) systematic feature-subset screening and (ii) cross-validated architecture and regularization search with early stopping, assessed by a composite of MSE, MAE, ${\mathrm{R}}^2$, and the 68th-percentile absolute error ($∆X_{68}$) as the prediction precision index. The selected FFNN (ReLU multilayer perceptron with L2 weight decay) achieved strong generalization on the independent test set (MAE = 0.9954, MSE = 4.5512, ${\mathrm{R}}^2$ = 0.9795, $∆X_{68}$ = 0.0193). Post hoc explainability methods (SHAP and input perturbation) identified angular velocity and linear acceleration as the dominant predictors, with payload mass exerting secondary effects. These results demonstrate that a compact, regularized FFNN provides accurate, repeatable, and interpretable energy predictions suitable for integration into digital twin platforms and downstream industrial scheduling.

Energy consumption optimisation has emerged as a critical need in Autonomous Mobile Robots (AMRs). Conventional A* implementations typically minimise path distance, neglecting energy-relevant factors such as directional changes and trajectory smoothness that significantly impact battery life and operational costs. This work proposes two energy-aware A* variants trained on empirical data from the KUKA KMP 1500 platform, where energy consumption is measured as battery SoC depletion: A*-RF, which integrates a Random Forest (RF) model directly into the cost function, and A*-MOD, which approximates the energy model through RF feature importance weights, achieving linear computational complexity O(nf). The RF model predicted energy consumption with an RMSE below 1.5% relative error, identifying travel distance and rotation angle as the dominant energy factors. Experimental validation across 42 path planning scenarios on a real industrial factory floor demonstrates that A*-MOD reduces energy consumption by up to 58.91% and improves operational autonomy by 2.21 times, with statistically significant improvements (p < 0.01) across all evaluated metrics.