Technical gazette, Vol. 28 No. 4, 2021.
Preliminary communication
https://doi.org/10.17559/TV-20201112163731
Neural Network-Based Model for Classification of Faults During Operation of a Robotic Manipulator
Sandi Baressi Šegota*
orcid.org/0000-0002-3015-1024
; Faculty of Engineering, University of Rijeka, Vukovarska 58, 51000 Rijeka
Nikola Anđelić
; Faculty of Engineering, University of Rijeka, Vukovarska 58, 51000 Rijeka
Zlatan Car
; Faculty of Engineering, University of Rijeka, Vukovarska 58, 51000 Rijeka
Mario Šercer
; Razvojno edukacijski centar za metalsku industriju Metalska jezgra Čakovec Bana Josipa Jelačića 22 D, 40 000 Čakovec
Abstract
The importance of error detection is high, especially in modern manufacturing processes where assembly lines operate without direct supervision. Stopping the faulty operation in time can prevent damage to the assembly line. Public dataset is used, containing 15 classes, 2 types of faultless operation and 13 types of faults, with 463 force and torsion datapoints. Four different methods are used: Multilayer Perceptron (MLP) selected due to high classification performance, Support Vector Machines (SVM) commonly used for a low number of datapoints, Convolutional Neural Network (CNN) known for high performance in classification with matrix inputs and Siamese Neural Network (SNN) novel method with high performance in small datasets. Two classification tasks are performed-error detection and classification. Grid search is used for hyperparameter variation and F1 score as a metric, with a 10 fold cross-validation. Authors propose a hybrid system consisting of SNN for detection and CNN for fault classification.
Keywords
Convolutional Neural Network; Multilayer Perceptron; Robot Fault Detection; Siamese Neural Network; Support Vector Machine
Hrčak ID:
260863
URI
Publication date:
22.7.2021.
Visits: 1.529 *