Classification of Faults Operation of a Robotic Manipulator Using Symbolic Classifier

Abstract

In autonomous manufacturing lines, it is very important to detect the faulty operation of robot manipulators to prevent potential damage. In this paper, the application of a genetic programming algorithm (symbolic classifier) with a random selection of hyperparameter values and trained using a 5-fold cross-validation process is proposed to determine expressions for fault detection during robotic manipulator operation, using a dataset that was made publicly available by the original researchers. The original dataset was reduced to a binary dataset (fault vs. normal operation); however, due to the class imbalance random oversampling, and SMOTE methods were applied. The quality of best symbolic expressions (SEs) was based on the highest mean values of accuracy (ACC¯), area under receiving operating characteristics curve (AUC¯), Precision¯, Recall¯, and F1−Score¯. The best results were obtained on the SMOTE dataset with ACC¯, AUC¯, Precision¯, Recall¯, and F1−Score¯ equal to 0.99, 0.99, 0.992, 0.9893, and 0.99, respectively. Finally, the best set of mathematical equations obtained using the GPSC algorithm was evaluated on the initial dataset where the mean values of ACC¯, AUC¯, Precision¯, Recall¯, and F1−Score¯ are equal to 0.9978, 0.998, 1.0, 0.997, and 0.998, respectively. The investigation showed that using the described procedure, symbolically expressed models of a high classification performance are obtained for the purpose of detecting faults in the operation of robotic manipulators.