Noise source identification for industrial sewing machines based on non-linear partial least squares regression model

Abstract

This paper introduces an application of non-linear partial least squares for vibro-acoustic regression modeling and for an industrial sewing machine. In the vibro-acoustic regression model, the vibration accelerations of reference points are defined as explanatory variables, while the noise sound pressure of target points is defined as response variables, and the number of explanatory variables is determined initially by a correlation analysis in the time domain. To improve predictive accuracy while a non-linear relationship exists between the explanatory and response variables, the explanatory variables are preprocessed by kernel function transformation. The comparison of regressive noise sound pressure to experimental data indicates that the non-linear partial least squares regression model has high predictive accuracy. Furthermore, the contributions of vibration accelerations to noise sound pressure are analyzed, by which the structure optimizations are guided and practiced. The comparison of noise test results before and after optimization testifies to the effectiveness of the contribution analysis.

Keywords

Noise source identification vibro-acoustic regression model non-linear partial least squares kernel function transform industrial sewing machine

Get full access to this article

View all access options for this article.

References

Zajaczkowski

. Vibrations of a crank-shaft in a sewing machine induced by a zigzag mechanism. Int J Clothing Sci Technol 1999; 11(1): 53–59.

Vér

Beranek

. Noise and vibrations control engineering: principles and applications, 2nd ed. New Jersey: John Wiley & Sons, 2007.

Lan

Chiu

. Identification of noise sources in factory’s sound field by using genetic algorithm. Appl Acoust 2008; 69: 733–750.

Fana

Meng

. Application of sound intensity and partial coherence to identify interior noise sources on the high speed train. Mech Syst Signal Process 2014; 46: 481–493.

Lee

. Noise source localization by applying multiple signal classification with wavelet transformation. Proc IMechE, Part C: J Mechanical Engineering Science 2007; 221: 11–21.

Park

Kim

. Source identification using multi-input/single-output modeling and causality checking of correlated inputs. J Vib Acoust 1994; 116: 232–236.

Fouladi

Nor

MJM

Ariffin

. Spectral analysis methods for vehicle interior vibro-acoustics identification. Mech Syst Signal Process 2009; 23: 489–500.

Shu

Liang

. Identification of complex diesel engine noise sources based on coherent power spectrum analysis. Mech Syst Signal Process 2007; 21: 405–416.

Lee

Cheong

Shin

. A case study of localization and identification of noise sources from a pitch and a stall regulated wind turbine. Appl Acoust 2012; 73: 817–827.

10.

Mazzoni

. An efficient approximation for the vibro-acoustic response of a turbulent boundary layer excited panel. J Sound Vib 2003; 264: 951–971.

11.

Chandra

Raja

Gopal

NKV

. Vibro-acoustic response and sound transmission loss analysis of functionally graded plates. J Sound Vib 2014; 333: 5786–5802.

12.

Guasch

AragonèsÀ Janer

. A graph cut strategy for transmission path problems in statistical energy analysis. Mech Syst Signal Process 2012; 30: 343–355.

13.

Lei

Pan

Sheng

. Investigation of structural response and noise reduction of an acoustical enclosure using SEA method. Appl Acoust 2012; 73: 348–355.

14.

Dhandole

Modak

. A constrained optimization based method for acoustic finite element model updating of cavities using pressure response. Appl Math Modell 2012; 36: 399–413.

15.

Opperwall

Vacca

. A combined FEM/BEM model and experimental investigation into the effects of fluid-borne noise sources on the air-borne noise generated by hydraulic pumps and motors. Proc IMechE, Part C: J Mechanical Engineering Science 2014; 228: 457–471.

16.

Cho

. Multivariate calibration for machine health monitoring: kernel partial least squares combined with variable selection. Int J Adv Manuf Technol 2012; 48: 691–699.

17.

Wold

Sjöström

Eriksson

. PLS-regression: a basic tool of chemometrics. Chemom Intell Lab Syst 2001; 58: 109–130.

18.

Kim

Lee

. A novel multivariate regression approach based on kernel partial least squares with orthogonal signal correction. Chemom Intell Lab Syst 2005; 79: 22–30.

19.

Rosipal

Trejo

. Kernel partial least squares regression in reproducing kernel Hilbert space. J Mach Learn Res 2001; 2: 97–123.

20.

Zhou

. Satellite-based carbon stock estimation for bamboo forest with non-linear partial least square regression technique. Int J Remote Sens 2012; 33: 1917–1933.

21.

QB/T 1177-2007, Industrial sewing machine: testing method of sound pressure level, 2007 (in Chinese).

22.

QB/T 1178-2006, Industrial sewing machine: testing method of vibration, 2006 (in Chinese).

23.

Bendat

Piersol

. Random data: analysis and measurement procedures, 4th ed. New York: John Wiley & Sons, 2010.

24.

Walczak

Massartb

. The radial basis functions-partial least squares approach as a flexible non-linear regression technique. Anal Chim Acta 1996; 331: 177–185.

25.

Wang

Meng

. Partial least-squares regression-linear and nonlinear methods, Beijing: National Defense Industry Press, 2006. (in Chinese).

26.

Simonoff

. Smoothing methods in statistics, New York: Springer-Verlag, 1996.