Malita, Alin Ciprian (Technical University of Cluj Napoca), Muresan, Cristina Ioana (Technical University of Cluj-Napoca)

Optimisation of Fractional Order Controllers Using Genetic Algorithms for Bispectral Index Regulation

Scheduled for presentation during the Regular Session "Genetic and evolutionary computation" (WeAD), Wednesday, June 11, 2025, 11:30−11:50, Room C

33rd Mediterranean Conference on Control and Automation, June 10-13, 2025, Tangier, Morocco

This information is tentative and subject to change. Compiled on May 9, 2025

Abstract

In anesthesia, even minor miscalculations can pose significant risks to patient safety, underscoring the need for precise and resilient control systems. This paper explores the optimisation of Fractional-Order Proportional-Integral-Derivative controllers using Genetic Algorithms for Bispectral Index regulation during general anesthesia. The proposed approach fine-tunes controller parameters by leveraging a model closed-loop response, enabling the algorithm to handle both transient and steady-state aspects of the response. By incorporating a fitness function that evaluates key performance metrics, including steady-state error, overshoot, and oscillatory behaviour, the genetic algorithm efficiently explores the search space to identify optimal controller configurations. The optimised controller demonstrates the ability to regulate Bispectral Index levels while maintaining stability and robustness against disturbances.