A Hybrid Algorithm for Adaptive Neuro-controllers

In this study, a novel hybrid algorithm consisting of the least mean square and backpropagation neural network is proposed to auto-adjust adaptive proportional integral derivative (PID) controller gains for improving transient response linear systems. The approach comprises scheme two algorithms running in parallel updates PID simultaneously. All are implemented on same system present general framework different scenarios such as initial gains, learning rates, target functions. results show that presented has better accuracy, precision, F1-score, adaptability, robustness than origin algorithms, significantly improves controllability most scenarios. It also exhibits performance periodic incremental decremental targets compared algorithms. Different hybridization levels simulated highlighted significant features their performance. This work can be expanded combination other well-known paving way improvements control applications.