Quality Control “Approve” app reduces variant testing efforts by 90 percent
In the production of variants, complete quality inspection of all parts is a necessity. To reduce inspection efforts, the research project “Approve” was launched to develop a practicable procedure.
Quality inspections are indispensable in production to ensure quality. In order to keep the testing effort as low as possible, random tests are used in large-scale production. Despite the reduced scope of testing, they allow statistically justified statements to be made about product quality. In variant production, however, random inspections cannot be carried out without further ado. Particularly in small and medium-sized companies, the statistical knowledge or personnel capacity required for a sampling inspection is often not available. Due to the high variability, a 100-percent inspection with complete inspection of all inspection characteristics is therefore common, especially for small quantities of individual variants. This high level of testing is a direct disadvantage for small and medium-sized companies in terms of competitiveness.
In the research project "Approve", a procedure has been developed over the past two and a half years to enable a reduction of the inspection effort even in variant production. It relies on adaptive testing, in which the scope of testing is determined on the basis of already recorded test process data. The reduction of the inspection effort takes place in three steps:
- the definition of key characteristics,
- the formation of mixed lots
- as well as the determination of sample sizes and the specification of a risk factor.
When defining key characteristics, those characteristics are selected that represent all relevant information about the component. The formation of mixed lots aims at combining similar variants into a common lot. By increasing the lot size in this way, a random inspection is made possible. In the last step, the sample size is determined for each key characteristic in the individual mixed lots. Further, the risk for wrong decisions is given, which results from the reduction of the inspection scope compared to a 100 percent inspection of all characteristics. The algorithms developed to reduce the inspection effort are based on machine learning methods, such as grouping algorithms, and statistical methods.
In order to make the procedure tangible for practical application, the algorithms were implemented in the freely accessible programming language “R” and combined in a web app. The web app is licence-free and enables adaptive test planning, even without prior statistical knowledge and high personnel input. The web app guides the user through the various steps of test planning and then makes a test plan available for download. It is possible to carry out a fully automated evaluation as well as to make individual settings manually. First applications of the web app within the companies of the project-accompanying committee showed that a reduction of the testing effort by up to 90 percent would be theoretically possible. Such a reduction in effort results in an increase in competitiveness for the small and medium-sized companies through relieved testing personnel, increased resource efficiency and reduced production costs.
The “APProVe” research project was launched in March 2019 and was concluded in August 2021 with the holding of the final meeting of the project-accompanying committee. It was carried out in cooperation with the Chair of Production Metrology and Quality Management of the Machine Tool Laboratory WZL at RWTH Aachen University and the companies GFE Präzisionstechnik Schmalkalden, iqs Software, Lauscher Präzisionstechnik, Ovalo, PFW Aerospace, TCG Unitech, Tebit, Transfact and Q-Das | Hexagon.