Welding Journal · 1999 · 95 citations · 12 references
EngineeringIndustrial EngineeringManufacturing EngineeringAutomationProcess ControlQuality EngineeringArc WeldingChange-point DetectionCondition MonitoringRobotic WeldingWeldingWelding ProcessesExperimental Data CollectionQuality MonitoringSequential Probability Ratio TestingStatistical Change DetectionTest StatisticWeld Quality AssessmentWeld Quality ControlWelding Automation
This paper addresses the problems involved in the automatic monitoring of the weld quality produced by robotized short-arc welding. A simple statistical change detection algorithm for the weld quality, the repeated Sequential Probability Ratio Test (SPRT), was used. The algorithm may similarly be viewed as a cumulative sum (CUSUM) type test, and is well-suited to detecting sudden minor changes in the monitored test statistic. The test statistic is based on the variance of the weld voltage, wherein it will be shown that the variance decreases when the welding process is not operating under optimal conditions. The performance of the algorithm is assessed through the use of experimental data. The results obtained from the algorithm show that it is possible to detect changes in weld quality automatically and on-line.
12
Introduction to Statistical Quality Control
Roger Sauter, Douglas C. Montgomery · Technometrics · 1992 · 7.9K citations
Procedures for Reacting to a Change in Distribution
G. Lorden · The Annals of Mathematical Statistics · 1971 · 1.4K citations · Full text
The Effect of Serial Correlation on the Performance of CUSUM Tests
Richard A. Johnson, Michael Bagshaw · Technometrics · 1974 · 266 citations
Business, Economics, Econometrics +16