A Novel Recurrent Adaptive Backstepping Optimal Control Strategy for a Single Inverted Pendulum System

TL;DR

This paper introduces a new control strategy combining recurrent neural networks with backstepping and optimal control to stabilize a single inverted pendulum, addressing nonlinear dynamics and constraints.

Contribution

It proposes a novel recurrent adaptive backstepping optimal control method using RNNs and quadratic programming for improved stabilization of nonlinear systems.

Findings

Effective stabilization of the inverted pendulum demonstrated.

The control strategy handles nonlinear dynamics and constraints.

Stability verified via Lyapunov analysis.

Abstract

In this paper, a novel recurrent adaptive backstepping optimal control strategy for a single inverted pendulum system is studied. By this method, an inverted pendulum is stabilized using projection recurrent neural network-based adaptive backstepping control (PRNN-ABC). The inverted pendulum is a popular nonlinear system that is used in both industry and academic and is applied various control approaches since it has many applications. Here, first of all, the backstepping control laws are investigated based on the nonlinear dynamic model of the system. Second, by considering control constrains and performance index, the constrained optimization problem is formulated. Later, the optimization problem will be converted to a constrained quadratic problem (QP). To study the recurrent neural network (RNN) according to the Karush- Kuhn-Tucker (KKT) optimization conditions and the variational inequality, the dynamic model of the RNN will be derived. At last, the stability analysis of the system is studied using Lyapunov function.