Pemilihan Fitur untuk Monitoring dan Klasifikasi Kondisi Pahat

Abstract

Tool Condition Monitoring system (TCM) is an application for monitoring  condition of tool where mounted on a CNC machining system. A good of TCM application is that which is capable of features mapping the signals obtained from the sensor system to appropriate class (tool condition). This study aimed to optimizing the dataset from the sensor signal in the previous study, with the features selection or features reduction, and with optimization parameters decision-making system to separate the two conditions,that is normal tool and breakage tool.

There are 1800x282 dimensional data, where obtained from the two transformed feature in the time domain and frequency domain. The results of the transformation are selected features by comparing three methods of feature selection that is Fishers Discriminant Ratio (FDR), Sequential Forward Selection (SFS). The result of selected method is L-SVM, and there are selected 10 best features by FDR to be input to the neural network backpropagation method. The system had accuracy test 97,8% in normal conditon of tool and 98,9% in breakage condition of tool. Reduction feature by Principal component Analysis (PCA) it's using from selected feature. It takes for understanding how spindle rotate influence to classification the tool condition.

Keywords: Optimization, Feature Selection, Feature Reduction, Tool Condition Monitoring, Neural Networks