Statistical process control applied to gas metal arc welding

An algorithm to prioritize welding quality deterioration factors

“…These charts will exhibit a central defect level, around which will cluster the values for percentage of defectives in each sample. This level represents the random variations (Maul et al, 1996). A significant divergence from it, in either quantity or kind, probably represents the presence of assignable variations which need to be investigated and corrected.…”

“…The random variations take place from many unrelated causes. There is no possibility to prevent, when the random variations occur by chance (Maul et al, 1996).…”

“…On the other hand, a fabrication process can also produce non-random or assignable variations. The non-random or assignable variations are comparatively larger or more numerous, whilst they are attributable to non-random and identifiable causes (Maul et al, 1996). For instance, wrong welding parameter settings leading to lack of welder competence or partial machine failure are some of the possible events that can produce assignable variations.…”

“…Consequently, a number of different factors must be inspected to determine whether the product is acceptable. Hence, it may be necessary to maintain separate control charts on each of the different types of factors or defects (Maul et al, 1996). Finally, the random level for total repairs and cutouts are analyzed based on: all control charts for spreads, any historical records on similar projects that may be available, the results of any corrective feedback given to the welders, and the specific types of defects.…”

A review of non‐standard applications of statistical process control (SPC) charts

“…It is interesting to note that healthcare applications represent the second largest group with approximately 31 per cent of reported applications. The Paul and Barnett (1995): monitoring chemical measuring systems Hansen et al (1996): monitoring early detection of feed water heater leaks Kegel (1996): monitoring the maintenance process in a flow calibration laboratory Maul et al (1996): monitoring a gas metal arc welding process Jennings and Drake (1997): monitoring machine tool performance parameters Zimmerman et al (1996): monitoring the quality of water Cook et al (1997): monitoring welding processes Hayes et al (1997): monitoring hygiene performance measurement in food manufacture Katter et al (1998): setting up a predictive maintenance plan Maurer et al (1998): monitoring environmental variables Ipek et al (1999): monitoring concentrations in mineral processing Jun and Suh (1999): monitoring automatic detection of tool breakage in NC milling processes Nijhuis et al (1999): monitoring a chromatographic process Ben-Daya and Rahim (2000): setting up a preventive maintenance plan Cassady et al (2000): setting up a preventive maintenance plan Health care (31%) Hand et al (1994): detecting variations in outcome of pneumonia patients Gentleman et al (1994): monitoring the performance of an HIV test Chesher and Burnett (1996): monitoring the long-term performance of a clinical chemistry laboratory Piccirillo (1996): comparing patient satisfaction with the visit to an academic otolaryngology office before and after quality improvement efforts Wardell and Candia (1996): monitoring customer satisfaction in a major hospital Boggs et al (1998): monitoring peak expiratory flow rate in asthma patients Clark et al (1998): monitoring trends in trauma mortality Vitez and Macrio (1998): monitoring the effect of performance improvement in an anaesthesia department Konrad et al (1998): determining the effects of introduction of a new monitoring system for fluid absorption Kahn et al (1996): detecting problems in chronic diseases Green (1999): monitoring the process of out patient service delivery General service sector (17%)…”