Neuro Fuzzy Controller Based Cruise Control of Electric Vehicle

currently, cruise controllers and cruise systems are given a lot of attention by the automotive industry since they are one of the most important factors that call for a precise controller that can keep up with technological advancement. Running vehicles have complicated and changeable motions. Due to this, the cruise control system (CCS) exhibits substantial non- linearity, making it difficult to employ a typical PID controller under all circumstances. An investigation of neural fuzzy logic controllers for an automotive cruise control system (ACCS) using a linearized model of the cruise system is presented in this work. The benefits of neural networks and fuzzy logics are combined using fuzzy membership function-based neural networks. Its quick training makes it suitable for online learning. The demonstration of how to control EV speed has been done using m-file and MATLAB/SIMULINK. According to the results, neuro fuzzy controller performance responds more favorably to overshoot and settling time. NFN combines the efficient calculation, neural network learning capability, and approximate reasoning decision-making of fuzzy logic. The Neuro fuzzy logic control technique is helpful to regulate the BLDC motor's speed. By adjusting the load torque and speed, the evaluation of the suggested method is assessed which performs remarkably well in both situations.