Neural Network to Failure Classification in Robotic Systems

José Jair Alves Mendes Júnior,Sérgio Okida,Sergio Luiz Stevan Jr,Mário Elias Marinho Vieira,Marcelo Bissi Pires

doi:10.3895/bjic.v4n1.4663

Abstract

A robotic system is a reconfigurable element, and inits programming, an algorithm can be implemented in order todetect and classify failures. This is an important step to ensurethat errors in actions do not cause damage or bring risks.Considering this, a Neural Network Multi Layer Perceptron(MLP) was used, in order to classify a set of failures in robotactuators, present in a database. This purpose is to analyze ifrobotic failures could be classified by MLP. The raw data aredivided in a temporal progression manner and torque in x, y andz axes. In total, five MLP neural networks were implemented foreach type of failure classification, using two different topologies.The number of neurons in the hidden layer is in accord with thecriteria of Kolmogorov and Weka, being the latter the besttopology for such application. In comparison to an algorithm(SKIL) using the same set of data, the MLP obtained the bestperformance in any topology of classification, with hit rates in80 to 90%.

Highlights

Robots replace human jobs and are used in hazardous environments, in which access may be difficult and in places where are present repetitive tasks
As in any system, every robot is susceptible to failures and errors while executing a task
A robotic manipulator is a mechanical structure composed of links connected to each other through joints, which are free to move according to one or more degrees of freedom [1,3]

Summary

Introduction

Robots replace human jobs and are used in hazardous environments, in which access may be difficult and in places where are present repetitive tasks. They bring efficiency regarding time and costs while minimizing risky situations. As in any system, every robot is susceptible to failures and errors while executing a task. When its structures and movements have anthropomorphic behavior, they are known as robot manipulator, which carry the same functionalities as a human arm, controlling position and orientation [4,5]. A notable characteristic of a robotic system is the capability to reconfigure the control system (usually executed by a microcontroller, microprocessor or other type of intelligent system) [4]

Objectives

Results

Conclusion