Rotary Inverted Pendulum Identification for Control by Paraconsistent Neural Network

Arnaldo De Carvalho,Bruno Augusto Angelico,Joao Francisco Justo,Joao Inacio Da Silva Filho,Alexandre Manicoba De Oliveira

doi:10.1109/access.2021.3080176

Arnaldo De Carvalho, Bruno Augusto Angelico + Show 3 more

Open Access

https://doi.org/10.1109/access.2021.3080176

Copy DOI

Abstract

Artificial neural networks (ANNs) have been used over the last few decades to perform tasks by learning with comparisons. Fitting input-output models, system identification, control, and pattern recognition are some fields for ANN applications. However, problems involving uncertain situations could be challenging for them. The family of paraconsistent logics (PL) is a powerful tool that can deal with uncertainty and contradictory information, so getting attention from researchers for its implications and applications in artificial intelligence. This investigation describes a novel activation function reasoned on the paraconsistent annotated logic by two-value annotations (PAL2v) rules, a variation of PL, allowing the design of a new paraconsistent neural net (PNN), applied in model identification for control (I4C) of a closed-loop rotary inverted pendulum (RIP) system.

Highlights

Artificial neural networks are mathematical algorithms that can learn a specific function or pattern [1], [2], could be applied in a wide range of applications [3]
We propose a novel paraconsistent neural net (PNN), built with activation functions reasoned on the Paraconsistent Annotated Logic with 2-value annotations (PAL2v) equations and rules
We describe the respective algorithm and its application on the model identification of a rotary inverted pendulum (RIP) system stabilized by closed-loop control

Summary

Introduction

Artificial neural networks are mathematical algorithms that can learn a specific function or pattern [1], [2], could be applied in a wide range of applications [3]. Because of those characteristics, the ANN is a powerful tool for identification and system control [1], [2]. Disturbances, and uncertainties are inherent aspects of real-world problem description [9], not usually considered by the state estimation methods for nonlinear control techniques [10]. The ANN attractiveness in identification and control derives from its intrinsic ability to use experimental data to model unknown systems, even with perturbations or uncertainties, enabling a notable alternative in situations

Methods

Results

Conclusion