BLDC Motor Control using Novel Swarm Intelligence Algorithms

Abstract— This study introduces two novel control
strategies designed to substantially enhance the
performance of Brushless DC (BLDC) motors in
renewable energy applications, specifically targeting
the challenges posed by dynamic energy fluctuations,
instability, and inefficiencies. The first proposed
method, termed Adaptive Crayfish-MPC Neuro-
Fuzzy Control (ACM-NFC), represents a synergistic
integration of Model Predictive Control (MPC) for
real-time system forecasting, an Adaptive Neuro-
Fuzzy Inference System (ANFIS) for intelligent
dynamic adaptation, and a Hybrid Crayfish
Optimization (CFO) algorithm for optimal parameter
tuning. The second method, referred to as the Hybrid
Fuzzy Sliding Mode Sine Cosine Algorithm (HFSCA),
presents a composite control architecture
combining Fuzzy Logic Control (FLC) for precise setpoint
regulation, Sliding Mode Control (SMC) for
high robustness against disturbances, and the Sine
Cosine Algorithm (SCA) for multi-objective
optimization. This hybrid approach addresses the
limitations of conventional control techniques by
achieving a superior trade-off between energy
efficiency, system stability, and rapid responsiveness
under fluctuating load conditions.