Quality Determination by Using Support Vector Machine in Gas Welding Applications

Abstract

The robots used in the manufacturing industry and the sensors from the automation system can be used to automatically perform quality checks. Gas welding robots can operate autonomously, but quality controls are carried out manually by means of laboratory tests. In this study, a method which can work fast in real time quality control applications is proposed by using the data obtained from the robots used in the production system. In this study, comparison of other classification algorithms which can be used in this field has been made. First of all, sensor data on the robots and production system were taken and quality control of the product at the end of the process was made and the entire process was classified. The processes in the obtained data were analyzed as raw data and statistical values were examined. Support Vector Machines, Decision Trees, Random Forests and Logistic Regression algorithms are used to classify the data. The algorithms used in the data set were successfully applied and a success rate of 87% was obtained with the Support Vector Machines.