| 2021, 03 March |
|
DOI: 10.14489/td.2021.03.pp.060-064 Danilevich S. B., Tretyak V. V. Abstract. Product quality control methods must be effective, that is, ensure minimal risks of making erroneous decisions during control. Uncertainty of measurements during control and other factors lead to errors of the 1-st kind (a good product is rejected) or 2-nd kind (the wrong one is mistakenly accepted). The indicators of the quality control of mass-produced products are the risks of the customer and the manufacturer. The accuracy of these risks assessment depends on a number of factors, including the batch size. When developing and certifying control methods, it is proposed to use the upper confidence limits of the indicated risks. It was proposed to find these confidence limits and requirements for the measurement accuracy during control by the Monte Carlo method (simulation). The article discusses examples of determining the reliability of control depending on the accuracy of measurements, taking into account the volume of the batch of products. Keywords: multiparameter testing, accuracy of the testing, risk of a customer, risk of a producer, Monte Carlo method, imitation modeling, uncertainty of measurement.
S. B. Danilevich (Novosibirsk Branch of Academy of Standardization, Metrology and Certification; Novosibirsk State Technical University (NSTU), Novosibirsk, Russia) Е-mail:
Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.
1. Evaluation of measurement data. The role of measurement uncertainty in conformity assessment. (2012). Guidance document No. JCGM 106:2012.
This article is available in electronic format (PDF). DOI: 10.14489/td.2021.03.pp.060-064 Copy the article DOI and follow the link https://id-spektr.ru/product/pokupka-elektronnoy-stati-iz-zhurnala-kontrol-diagnostika Please specify the article DOI in the order comments.
|
Current Issue
Разработка концепции и создание сайта - ООО «Издательский дом «СПЕКТР»