 Classifying of welding time series based on multi-scale time irreversibility analysis and extreme learning machineYong Huang, Dongqing Yang, Lei Wang and Kehong Wang Chaos, Solitons & Fractals, 2020, vol. 139, issue C Abstract: In welding, previous research has proven that the behavior of its arc droplet is chaotic and fractal by the complex analysis of time series. In this study, the multi-scale time irreversibility (MSTI) method is used to analyze welding time series, and then used to classify the weld quality. By comparing the results of shuffled time series with original time series, it is confirmed that the time irreversibility is an intrinsic property of welding time series and it can extend over multiple scales. The superposition effect of multiple frequency components of welding time series results in enhances time irreversibility. The MSTI index (Pm%, Gm%) is used to quantify the time irreversibility, and has a capable of distinguishing different series. In the finally, the index (Pm%, Gm%) is combined with extreme learning machine (ELM) to classify the weld quality, and obtain good classification results. Keywords: Time irreversibility; Multi-scale analysis; Extreme learning machine; Welding time series (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:eee:chsofr:v:139:y:2020:i:c:s0960077920304380 DOI: 10.1016/j.chaos.2020.110040 Access Statistics for this article Chaos, Solitons & Fractals is currently edited by Stefano Boccaletti and Stelios Bekiros More articles in Chaos, Solitons & Fractals from Elsevier |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.