Advanced Adaptive PID Controller for BLDC Motor

Modeling and adaptive neuro-fuzzy inference system control of quarter electric vehicle

“…Implication layer 2: its output is the cumulative total of all acquired signals. As illustrated in (15), the formula for the output node of this layer is given by (15). The firing strength of a rule is indicated by each node output.…”

“…The categories of available controllers are conventional namely proportional integral derivative (PID) and adaptive among others fuzzy and adaptive neuro-fuzzy inference system (ANFIS) controllers [13], the PID control parameter tuning is very challenging and robustness is limited [14]. A fixed controller does not function properly at all speeds and an adaptive controller is preferable because of the load non-linearity and evolving machine requirements at different speed ranges [15]. Fuzzy control can take appropriate control parameters and do calculations more quickly than PID controller, which has difficulty taking the proper characteristics [16].…”

AI based Optimization of EV Control based on Fractional Order PID Controller and Meta-Heuristic Techniques

“…Smell index = sort (S) Where state identifies that 𝑆(𝑖) is in the first haif of the swarm, r means the random value in the range of [0, 1], bF denotes the best fitness gotten in the current iterative process, wF means worst fitness value originate in the iterative procedure now, S designates the fitness value of all populations at a specified iteration, Smell Index is the outcome of an ascending classification of S clearly simulates the negative and positive feedback between the vein width of the slime mould and the absorption of the food being explored. The authors of the article, after several tests, decided that when the arbitrary value is less than 0.03, there is another means to achieve the minimum value, or to permit the slime mould to acquire a high absorption of food, which is determined as follows: To improve the performance of the FOPID control we employed several meta-heuristic optimization algorithms (AEFA, AEO, SMA, GOA, AND WCA) where on one side, the SMA shows better performance with step reference as in figure (15) and table (4). Table (5,6) shows some common non-senstive comparison parameters.…”