DESIGN OF BRAIN EMOTIONAL LEARNING BASED ON CEREBELLAR ARCHITECTURE FOR INVERTED PENDULUM CONTROL

A bio-inspired controller called Brain Emotional Learning (BEL) was developed through research on the limbic system of the mammalian brain. Based on BEL structure design of intelligent and cognitive controllers with different tuning algorithms has attracted more attention. In contrast to the traditional formulation of BEL, the paper analyzes and designs certain functions used in Brain Emotional Learning to improve the system's performance. It focuses on the critical parameters that influence the dynamics of BEL and based on Cerebellar Architecture emotional cues are formed. The controller mimics the emotional behavior of the brain and ensures improved dynamic control performance. Stability analysis of the system is described using Jacobian formulation. The method is used for the inverted pendulum model as the benchmark case study and is applicable to the design of system controllers in general. Hardware-in-Loop simulations show the effects of parameter variations within a specific range and the dynamic control performance is compared with PID formulations.