Weld Bead Penetration State Recognition in GTAW Process Based on a Human Auditory Perception Model
The state of weld bead penetration is a crucial factor that affects the service performance of the welding products. Since arc sound signals contain abundant information of welding process, they were usually adopted to monitor the penetration states of weld bead online. However, the arc sound signals are susceptible to the environment noise, so they are seldom applied in industrial practice. In this study, a human auditory perception model was proposed to identify the penetration states in GTAW process. In this model, an auricle and middle ear transformation function were adopted firstly to remove partial noise in the arc sound signals. Then through simulating the functions of human ear basement membrane, a gamma-tone frequency resolution algorithm was used to decompose the arc sound signals into 64 channels. At last, based on the short-time energies of arc sound in these channels, the feature vectors were built to identify the penetration states. The experimental results show that the proposed method has high accuracy in recognition rates and strong anti-noise interference capabilities. The human auditory perception model proposed in this study has potential practical applications in industrial environment.
KeywordsWeld penetration Auditory mode State recognition Arc sound
The authors gratefully acknowledge the support from the National Natural Science Foundation of China (51465043).
- 1.Kaskinen P, Mueller G (1986) Acoustic arc length control. In: Proceedings of an international conference on trends in welding research, pp 763–765Google Scholar
- 4.Fan D, Shi Y, Ushio M (2001) Investigation of CO2 welding arc sound: correlation of welding arc sound signal with welding spatter. Trans JWRI 30:29–33Google Scholar
- 10.Patterson RD, Moore BCJ (1986) Auditory filters and excitation patterns as representations of frequency resolution. In: Proceedings of frequency selectivity in hearing London, Academic Press, pp 123–177Google Scholar
- 11.Ma Y, Chen K, Wang N et al (2009) Application of auditory spectrum-based features into acoustic target recognition. Acta Acust 34(2):142–150Google Scholar
- 12.Tucker S, Brown G (2003) Modelling the auditory perception of size, shape and material: applications to the classification of transient sonar sounds. In: Proceedings of 114th convention audio engineering society, Amsterdam, NetherlandsGoogle Scholar
- 13.Tucker S, Brown G (2002) Investigating the perception of the size, shape and material of damped and free vibrating plates. Department of Computer Science, University of Sheffield, Sheffield, U.K., Tech. Rep CS-02-10Google Scholar
- 14.Glasberg BR, Moore BCJ (2002) A model of loudness applicable to time-varying sounds. J Audio Eng Soc 50(5):331–342Google Scholar