Neural Network to Failure Classification in Robotic Systems
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) wa...
| Principais autores: | Mendes Júnior, José Jair Alves, Pires, Marcelo Bissi, Vieira, Mário Elias Marinho, Okida, Sérgio, Stevan Jr, Sergio Luiz |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado em: |
Universidade Tecnológica Federal do Paraná (UTFPR)
2016
|
| Acesso em linha: |
http://periodicos.utfpr.edu.br/bjic/article/view/4663 |
| Tags: |
Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
|
| id |
peri-article-4663 |
|---|---|
| recordtype |
ojs |
| spelling |
peri-article-46632017-09-20T14:52:16Z Neural Network to Failure Classification in Robotic Systems Mendes Júnior, José Jair Alves Pires, Marcelo Bissi Vieira, Mário Elias Marinho Okida, Sérgio Stevan Jr, Sergio Luiz Controle de Processos Eletrônicos, Retroalimentação; Neural Networks; Robotics; Classification. 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%. Universidade Tecnológica Federal do Paraná (UTFPR) 2016-09-24 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf http://periodicos.utfpr.edu.br/bjic/article/view/4663 10.3895/bjic.v4n1.4663 Journal of Applied Instrumentation and Control; v. 4, n. 1 (2016); 1-6 Journal of Applied Instrumentation and Control; v. 4, n. 1 (2016); 1-6 2594-3553 10.3895/bjic.v4n1 eng http://periodicos.utfpr.edu.br/bjic/article/view/4663/3110 Direitos autorais 2016 CC-BY http://creativecommons.org/licenses/by/4.0 |
| institution |
Universidade Tecnológica Federal do Paraná |
| collection |
PERI |
| language |
Inglês |
| format |
Artigo |
| author |
Mendes Júnior, José Jair Alves Pires, Marcelo Bissi Vieira, Mário Elias Marinho Okida, Sérgio Stevan Jr, Sergio Luiz |
| spellingShingle |
Mendes Júnior, José Jair Alves Pires, Marcelo Bissi Vieira, Mário Elias Marinho Okida, Sérgio Stevan Jr, Sergio Luiz Neural Network to Failure Classification in Robotic Systems |
| author_sort |
Mendes Júnior, José Jair Alves |
| title |
Neural Network to Failure Classification in Robotic Systems |
| title_short |
Neural Network to Failure Classification in Robotic Systems |
| title_full |
Neural Network to Failure Classification in Robotic Systems |
| title_fullStr |
Neural Network to Failure Classification in Robotic Systems |
| title_full_unstemmed |
Neural Network to Failure Classification in Robotic Systems |
| title_sort |
neural network to failure classification in robotic systems |
| description |
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%. |
| publisher |
Universidade Tecnológica Federal do Paraná (UTFPR) |
| publishDate |
2016 |
| url |
http://periodicos.utfpr.edu.br/bjic/article/view/4663 |
| _version_ |
1805292610694152192 |
| score |
10,814766 |