A novel adaptive control design method for stochastic nonlinear systems using neural network

Abstract This paper presents a novel method for designing an adaptive control system using radial basis function neural network. The is capable of dealing with nonlinear stochastic systems in strict-feedback form any unknown dynamics. proposed network allows the not only to approximate dynamic systems, but also compensate actuator nonlinearity. By employing surface method, common problem that intrinsically exists back-stepping design, called “explosion complexity”, resolved. applied comprising various types nonlinearities such as Prandtl–Ishlinskii (PI) hysteresis, and dead-zone performance compared two different baseline methods: direct backstepping adaptation named APIC-DSC , which contributed compensating It observed improves failure-free tracking terms Integrated Mean Square Error (IMSE) by 25%/11% backstepping/ method. depression IMSE further improved 76%/38% 32%/49%, when it comes nonlinearity PI hysteresis dead-zone, respectively. demands shorter period methods.