Feature extraction for gas metal arc welding based on EMD and time–frequency entropy

• Published in: International journal of advanced manufacturing technology Vol. 92; no. 1-4; pp. 1439 - 1448
• Main Authors: Huang, Yong, Wang, Kehong, Zhou, Qi, Fang, Jimi, Zhou, Zhilan
• Format: Journal Article
• Language: English
• Published: London Springer London 01.09.2017; Springer Nature B.V
• Subjects: Amplitudes; CAE) and Design; Computer-Aided Engineering (CAD; Current distribution; Energy distribution; Engineering; Entropy; Feature extraction; Frequency distribution; Frequency ranges; Frequency stability; Gas metal arc welding; Hilbert transformation; Industrial and Production Engineering; Mechanical Engineering; Media Management; Original Article; Stability analysis; Welding current; Gas metal arc welding; Empirical mode decomposition; Time–frequency entropy; Hilbert–Huang transform; Stability state
• ISSN: 0268-3768; 1433-3015
• DOI: 10.1007/s00170-016-9921-5

Hilbert–Huang transform (HHT) and time–frequency entropy were used to estimate the stability of short-circuiting gas metal arc welding (GMAW). First, the current signals were divided by empirical mode decomposition (EMD) into several intrinsic mode functions (IMFs). Then the IMFs were converted by Hilbert transform to Hilbert–Huang spectrum which describes the instantaneous time–frequency distribution of welding current signals. Since the uniformity of energy amplitude distribution with time–frequency reflects the stability, we introduced time–frequency entropy to quantify the energy distribution with time–frequency range in the HHT spectrum. We found HHT can effectively depict the amplitude with time and frequency distribution of welding current signals, and the welding was more stable when the time–frequency entropy was larger. Thus, this is a new way to assess and quantify the stability of short-circuiting GMAW.