An adaptive PID neural network for complex nonlinear system control

Abstract

Usually it is difficult to solve the control problem of a complex nonlinear system. In this paper, we present an effective control method based on adaptive PID neural network and particle swarm optimization (PSO) algorithm. PSO algorithm is introduced to initialize the neural network for improving the convergent speed and avoiding weights getting trapped into local optima. To adapt the initially uncertain and varying parameters in the control system, we introduce an improved gradient descent method to adjust the network parameters. The stability of our controller is analyzed according to the Lyapunov method. The simulation of complex nonlinear multiple-input and multiple-output (MIMO) system is presented with strong coupling. Empirical results illustrate that the proposed controller can obtain good precision with shorter time compared with the other considered methods. It provides a novel control approach for complex nonlinear systems.

Direct Torque Control with Adaptive PI Speed Controller based on Neural Network for PMSM Drives

“…Numerous works [13][14][15] have demonstrated that ANN is suitable for dynamic and nonlinear control systems due to the capability of processing, analysing and learning. The speed controller of DTC structure is a nonlinear system, which hasdisturbances of load inertia and motor parametersvariation against temperature [12].…”

“…For convenience of program coding work, the equation (8) can be described as incremental form as (9) [15]:…”

ZD, ZG and IOL Controllers and Comparisons for Nonlinear System Output Tracking with DBZ Problem Conquered in Different Relative‐Degree Cases

“…In light of the complexity and uncertainty of nonlinear systems, which widely exist in scientific and engineering fields, many efforts have been devoted to the solving of nonlinear system problems [1][2][3][4][5][6][7][8][9][10][11][12][13][14]. As an important part of nonlinear system problems, the tracking control of nonlinear systems has attracted much attention in recent decades [6,7,9,10,[14][15][16][17].…”

Adaptive two-degree-of-freedom PI for speed control of permanent magnet synchronous motor based on fractional order GPC

“…Fuzzy logic theory and neural network algorithm have been broadly researched to auto-tune the controller parameters on the basis of the prior rules [11][12][13][14]. However, large amounts of learning cost may be needed in these methods.…”