Development of Control and Automation Systems with a Multiobjective Optimization Approach for Improving the Performance of Multivariable Processes within Digitalized Industrial Environments

This project addresses the increasing complexity of multivariable industrial processes, which face significant challenges regarding interoperability and data management within the Industry 4.0 context. Given the limitations of traditional control methods, the research proposes the development of intelligent systems based on artificial intelligence and multi-objective optimization techniques, such as Model Predictive Control (MPC). The quantitative and experimental methodology includes the characterization of industrial dynamics, the development of advanced algorithms, and their validation using simulation platforms such as MATLAB/SIMULINK and LABVIEW. The project aims not only to optimize process performance and energy efficiency but also to bridge the technological gap that limits industrial competitiveness. As a result, the project expects to publish three scientific articles in high-impact journals and create a Renewable Learning Object (ORA). This resource will be integrated into the virtual environments of the Universidad Politécnica Salesiana, directly benefiting students and faculty through the transfer of knowledge regarding emerging technologies and advanced automation.<br/><br/><b>Goal</b>: <br/>Develop intelligent control and automation systems for multivariable processes within the Industry 4.0 framework, integrating artificial intelligence and multi-objective optimization. The goal is to improve performance, operational efficiency, and decision-making in complex industrial environments.<br/><br/><b>Research lines</b>: <br/>Control engineering and automation technologies<br/>Artificial intelligence and machine learning