TY - JOUR AU - Kong, Huifang AU - Fang, Yao PY - 2018/02/28 Y2 - 2024/03/28 TI - Neural Network PID Algorithm for a Class of Discrete-Time Nonlinear Systems JF - International Journal of Online and Biomedical Engineering (iJOE) JA - Int. J. Onl. Eng. VL - 14 IS - 02 SE - Papers DO - 10.3991/ijoe.v14i02.7914 UR - https://online-journals.org/index.php/i-joe/article/view/7914 SP - pp. 103-116 AB - <p class="0abstract"><span lang="EN-US">The control of nonlinear system is the hotspot in the control field. The paper proposes an algorithm to solve the tracking and robustness problem for the discrete-time nonlinear system. The completed control algorithm contains three parts. First, the dynamic linearization model of nonlinear system is designed based on Model Free Adaptive Control, whose model parameters are calculated by the input and output data</span><span lang="EN-US"> of system</span><span lang="EN-US">. Second, the model error is estimated using the Quasi-sliding mode control algorithm</span><span lang="EN-US">, hence, the whole model of system is estimated</span><span lang="EN-US">. Finally, the neural network </span><span lang="EN-US">PID </span><span lang="EN-US">controller is designed to get the optimal control law. The convergence and BIBO stability of the control system is proved by the Lyapunov function. The simulation results </span><span lang="EN-US">in</span><span lang="EN-US"> the </span><span lang="EN-US">linear and </span><span lang="EN-US">nonlinear system validate the effectiveness and robustness of the algorithm.</span><span lang="EN-US"> The robustness </span><span lang="EN-US">effort </span><span lang="EN-US">of </span><span lang="EN-US">Quasi-sliding mode control algorithm</span><span lang="EN-US"> in nonlinear system is also verified in the paper.</span></p> ER -