Fault diagnosis on production systems with support vector machine and decision trees algorithms

In this study, the operation of the didactic modular production system of the Festo Company was monitored by using eight sensors. The output of the linear potentiometer, magazine optic sensor, vacuum analog pressure sensor, material holding P/E switch, material handling arm pressure sensor, vacuum information P/E switch, optic sensor, and pressure sensor of main system were recorded while the system was operating in the perfect condition and various problems were artificially created. Some of these defects were empty magazine, zero vacuum, inappropriate material, no pressure, closed manual pressure valve, missing drilling stroke, poorly located material, not vacuuming the material and low air pressure. In all cases, one or more sensors clearly indicated the defect. The results indicated that the system support vector machine (SVM) and decision tree algorithm correctly identified all the presented cases.