This paper compares the performance of different control techniques applied to a high-performance brushless DC (BLDC) motor. The first controller is a classical proportional integral (PI) controller. In contrast, the second one is based on adaptive neuro-fuzzy inference systems (proportional integral-adaptive neuro-fuzzy inference system (PI-ANFIS) and particle swarm optimization-proportional integral-adaptive neuro-fuzzy inference system (PSO-PI-ANFIS)). The control objective is to regulate the rotor speed to its desired reference value in the presence of load torque disturbance and parameter variations. The proposed controller uses a dSPACE platform (MicroLabBox controller board). The experimental prototype comprises a PEMFC system (the Nexa Ballard FC power generator: 1.2 kW, 52 A) and a brushless DC motor BLDC of 1 kW 1000 rpm. The PSO-PI-ANFIS controller presents better performance than the PI-ANFIS and classical PI controllers due to its ability to optimize the PI-ANFIS controller’s parameters using the particle swarm optimization (PSO) algorithm. This optimization results in improved tracking accuracy and reduced overshoot and settling time.

When the controlled system is subject to parameter variations and external disturbances, a fixed-parameter proportional integral derivative (PID) controller cannot ensure its stabilization. In this case, its control requires online parameter adjustment. Specifically, as the quadrotor is a multi-input multi-output, nonlinear, and underactuated system, robust control is necessary to ensure efficient trajectory tracking flights. In this paper, an adaptive proportional integral derivative (APID) controller is proposed to control the quadrotor systems. This APID-based control strategy uses a two hidden layer deep feedforward network (DFN), where the one-step secant algorithm is chosen for initializing the DFN parameters. All the design steps of the proposed adaptive controller are described. The multidimensional particle swarm optimization (PSO) algorithm is used for tuning the DFN parameters. Then, using two simulation efficiency tests, a comparison between the proposed PSO-based APID-DFN, the (non-optimized) APID-DFN, the feedforward network APID, and the fixed-parameter PID controllers proves much efficiency of the proposed adaptive controller. The results illustrate that the proposed PSO-based APID-DFN controller can ensure good quadrotor system stabilization and achieve minimum overshoot and faster convergence speed for all quadrotor motions. Thus, the proposed control strategy could be considered an additional intelligent method-based adaptive control for unmanned aerial vehicles.