Advances in Intelligent Control and Engineering Applications

1. Introduction

Intelligent control is a discipline that is progressively maturing and has a real and significant transfer in a multitude of industrial applications and other engineering sectors today. These innovative contributions are clearly reflected in areas as diverse as the service sector, automated production process systems, assistive robotics, renewable energy generation systems, and intelligent transport. For example, the work of Navarro-Almanza et al. [1] (Interpretable Mamdani neuro-fuzzy model through context awareness and linguistic adaptation) combines fuzzy logic techniques and genetic algorithms to extract grey box models, using initial context information to provide the models with inter-predictable natural language properties. Another prominent example in an academic environment is presented by Mehdi and Nachouki [2] (A neuro-fuzzy model for predicting and analysing student graduation performance in computing programmes), where a hybrid model based on neural networks and fuzzy systems is presented as a solution for predicting the academic performance of a set of students. In the field of control, countless contributions can be found, such as the one presented by Sain and Mohan [3] (Modelling of a nonlinear fuzzy three-input PID controller and its simulation and experimental realisation), where an experimental presentation is made of a proposal for a nonlinear fuzzy controller in a magnetic levitation plant. On the other hand, new control strategies integrating several intelligent techniques can be found, such as the one presented by Larrea et al. [4] (Model-Based Design of the IMO-NMPC Strategy: Real-Time Implementation) where, starting from an MPC strategy developed with multi-objective optimisation processes based on genetic algorithms and neural networks, its applicability in real time on complex nonlinear dynamic systems is studied.

Although interesting and important new proposals continue to emerge, multiple challenges remain in the field of intelligent control. The complex multivariable dynamics of real systems, the demand for robust decision making under conditions of significant uncertainty in the systems to be controlled, and the actual implementation of intelligent control strategies are still very interesting areas in which the scientific community needs to continue its research. There are recent studies that have analysed the stability of fuzzy control systems from a membership-functions point of view, such as the work of Lam [5] (A review on stability analysis of continuous time fuzzy model-based control systems: From membership function-independent to membership function-dependent analysis.), or with a polynomial approach as presented by Xie et al. [6] (A polynomial membership function approach for stability analysis of fuzzy systems). It is also possible to find innovative work applying reinforcement learning to intelligent control strategies, as presented by Fernandez-Gauna et al. [7] (Experiments of conditioned reinforcement learning in continuous space control tasks), where these proposals are evaluated on systems such as the speed control of a submarine vehicle, the pitch control of an aeroplane, and the rotation control of a wind turbine.

2. An Overview of Published Articles

This Special Issue presents ten papers that address different aspects of intelligent control and its applications in engineering. Each of these studies presents fresh methodologies, theoretical advances, and practical implementations that expand the boundaries of the fields studied.

For example, a discrete time-design approach for dual internal model-based repetitive control systems has been proposed to improve tracking and disturbance rejection in precision control applications (Discrete Time Design of Dual Internal Model-Based Repetitive Control Systems). Meanwhile, energy efficiency optimisation in onboard seawater reverse osmosis desalination plants has been enhanced using genetic neuro-fuzzy systems (Energy Efficiency Optimisation in Onboard SWRO Desalination Plants Based on a Genetic Neuro-Fuzzy System).

In robotics, vision- and LIDAR-based systems have been implemented for autonomous docking and recharging of mobile robots, improving machine tending in autonomous manufacturing environments (Vision- and Lidar-Based Autonomous Docking and Recharging of a Mobile Robot for Machine Tending in Autonomous Manufacturing Environments). Additionally, an emotional model based on fuzzy logic and social psychology has been proposed for personal assistant robots to improve human–robot interaction (An Emotional Model Based on Fuzzy Logic and Social Psychology for a Personal Assistant Robot).

In the field of renewable energy, fuzzy logic controllers have been developed to enhance the performance of wind turbines on semi-submersible platforms under varying wind conditions (Development and Evaluation of Fuzzy Logic Controllers for Improving Performance of Wind Turbines on Semi-Submersible Platforms under Different Wind Scenarios). Moreover, fault-tolerant model predictive control has been successfully applied to sewer networks to enhance reliability and efficiency (Fault-Tolerant Model Predictive Control Applied to a Sewer Network).

These contributions collectively highlight the latest trends and technological advancements in intelligent control and engineering applications, providing valuable insights into both theoretical and practical aspects of all this fields.

3. Conclusions

As intelligent control systems continue to evolve, new keys are being found that keep numerous lines of research open. The development of hybrid models that efficiently combine traditional control theories with data-driven learning approaches needs to be further explored.

Continued collaborative efforts between academia, industry, and government institutions will be crucial in framing the future of intelligent engineering applications. By fostering interdisciplinary research and innovation, it is possible to drive significant advances that will further improve the capabilities, efficiency, robustness, and reliability of intelligent control systems.

We extend our sincere gratitude to the authors, reviewers, and editorial board members whose contributions have made this Special Issue possible. We hope that the findings presented here will inspire further research and encourage new collaborations in this rapidly evolving area.