Results of Quantitative Analysis of High-Speed Shadowgraphy of Shock Tube Flows Using Machine Vision and Machine LearningстатьяИсследовательская статья
Информация о цитировании статьи получена из
Web of Science,
Scopus
Статья опубликована в журнале из списка Web of Science и/или Scopus
Дата последнего поиска статьи во внешних источниках: 1 апреля 2022 г.
Аннотация:This paper presents the results of studies on unsteady gas-dynamic flows up to six milliseconds in duration in the shock tube channel. The results were acquired by continuous high-speed shadowgraphy and subsequent big data processing based on machine vision (edge detection and the Hough transform) and machine learning (convolutional neural networks). The evolution of flows with discontinuities in the rectangular shock tube channel behind a shock wave at Mach numbers 2–3.5 was studied with a recording frame rate of 150 000 fps. The time dependence of the angle of oblique shock inclination was plotted, and the time for the flow to reach a subsonic regime was estimated. This paper shows the possibility of conducting research in gas dynamics based on big data analysis of digital recordings using the approach suggested