کنفرانس مهندسی برق ایران

صفحه اصلی / سی و چهارمین کنفرانس بین المللی مهندسی برق

Active Disturbance Rejection Control of Uncertain Systems Based on Neural Network: An Approach for Achieving Implementable Control Signal

نویسندگان :

Ali Naseh¹ Arman Marzban² Mohammad Hossein Bayati³ Mahsan Tavakoli-Kakhki⁴

1- دانشگاه صنعتی خواجه نصیرالدین طوسی 2- دانشگاه صنعتی خواجه نصیرالدین طوسی 3- دانشگاه صنعتی خواجه نصیرالدین طوسی 4- دانشگاه صنعتی خواجه نصیرالدین طوسی

کلمات کلیدی :

Active Disturbance Rejection (ADR)،Uncertainty Model،Disturbance Rejection PID (DR-PID)،Multi-Layer Perceptron Neural Network

چکیده :

Disturbance rejection is of great importance in many industrial applications. Disturbance Rejection – PID (DR-PID) control structure would be an implementable approach for active disturbance rejection in practical applications. But its excessively large control input signal amplitude, make this structure impractical for real-world applications. In this paper, by integrating the DR-PID structure with multi-layer perceptron neural network, a Neural Network-based Disturbance Rejection PID (NN-DRPID) controller is designed. The proposed method is implementable in practical applications while it addresses the problem of excessive control signal amplitudes deficiency existing in the classical methods. The efficiency of the proposed NN-DRPID in active disturbance reaction control of uncertain systems are demonstrated through numerical simulation.