A Machine Learning Based Prediction Model for the Sound Absorption Coefficient of Micro-Expanded Metal Mesh (MEMM)
Abstract
:1. Introduction
2. Materials and Methods
2.1. Experiment
2.2. The Conventional Models
2.2.1. The Semi-Theoretical Model of a Perforated Panel
2.2.2. Lee & Kwon’s Model
2.2.3. Maa’s Model for MPP
2.3. The Machine Learning Model
- The Gboost model
- 2.
- The average model
- 3.
- The stacking model
3. Results
3.1. The Conventional Model
3.2. The ML Model
4. Discussion and Conclusions
Author Contributions
Funding
Conflicts of Interest
Nomenclature
acoustic impedance of the hole (Pa·s/m3) | |
acoustic resistance based on the viscosity and heat conduction of the inner wall of the hole (Pa·s/m3) | |
the frequency (Hz) | |
the angular frequency (rad/s) | |
the density of air (kg/m3) | |
the panel thickness (m) | |
correction factor (-) | |
the orifice diameter (m) | |
cross section area of the hole (m2) | |
the perforation ratio (-) | |
characteristic impedance of air (Pa·s/m3) | |
propagation constant of air (rad/m) | |
the velocity of air (m/s) | |
the wave number (rad/m) | |
cavity thickness/airspace depth (m) | |
acoustic impedance of the absorber (Pa·s/m3) | |
the absorption coefficient (-) | |
the normalized acoustic impedance of the panel (Pa·s/m3) | |
The overall transfer matrix for perforated panel system | |
the pressure reflection coefficient (-) | |
acoustic impedance of the MPP (Pa·s/m3) | |
relative acoustic resistance (Pa·s/m3) | |
mass reactance (Pa·s/m3) | |
the perforate constant | |
the resistance coefficient | |
mass reactance coefficient | |
coefficient of viscosity (Pa·s) |
Appendix A
Training Set
Testing Set
References
- Mosa, A.I.; Putra, A.; Ramlan, R.; Esraa, A.A. Micro-Perforated Panel Absorber Arrangement Technique: A Review. J. Adv. Res. Dyn. Control. Syst. 2018, 10, 372–381. [Google Scholar]
- Iwase, T. Chapter 3.4 Sound reflection, absorption and insulation. In Handbook of Noise Control, 1st ed.; The Institute of Noise Control Engineering of Japan, Ed.; Gihodobooks: Tokyo, Japan, 2001; pp. 138–148. (In Japanese) [Google Scholar]
- Lee, D.H.; Kwon, Y.P. Estimation of the absorption performance of multiple layer perforated panel systems by transfer matrix method. J. Sound Vib. 2004, 278, 847–860. [Google Scholar] [CrossRef]
- Maa, D.Y. Theory and design of microperforated panel sound-absorbing constructions. Sci. Sin. 1975, 18, 55–71. [Google Scholar]
- Ciregan, D.; Meier, U.; Schmidhuber, J. Multi-Column Deep Neural Networks for Image Classification. In Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, 16–21 June 2012; pp. 3642–3649. [Google Scholar]
- Hinton, G.; Deng, L.; Yu, D.; Dahl, G.E.; Mohamed, A.R.; Jaitly, N.; Senior, A.; Vanhoucke, V.; Nguyen, P.; Sainath, T.A.; et al. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal. Process. Mag. 2012, 29, 82–97. [Google Scholar] [CrossRef]
- Patel, J.; Shah, S.; Thakkar, P.; Kotecha, K. Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques. Expert Syst. Appl. 2015, 42, 259–268. [Google Scholar] [CrossRef]
- Nannariello, J.; Fricke, F. The prediction of reverberation time using neural network analysis. Appl. Acoust. 1999, 58, 305–325. [Google Scholar] [CrossRef]
- Falcon Perez, R. Machine-Learning-Based Estimation of Room Acoustic Parameters. Master’s Thesis, Aalto University, Espoo, Finland, 2018. [Google Scholar]
- Gamper, H.; Tashev, I.J. Blind reverberation time estimation using a convolutional neural network. In Proceedings of the 2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC), Tokyo, Japan, 17–20 September 2018; pp. 136–140. [Google Scholar]
- ISO 354. Acoustics—Measurement of Sound Absorption in a Reverberation Room; ISO: Geneva, Switzerland, 2003. [Google Scholar]
- ISO 11654. Acoustics—Sound Absorbers for Use in Buildings—Rating of Sound Absorption; ISO: Geneva, Switzerland, 1997. [Google Scholar]
- Koyasu, M. Sound Absorbing Material, 1st ed.; Gihodobooks: Tokyo, Japan, 1976. (In Japanese) [Google Scholar]
- Hiroyuki, S. Acoustic analysis of acoustic structural features using Excel (2) Analysis of sound absorption structure. Soc. Heat. Air Cond. Sanit. Eng. Jpn. 2006, 80, 919–927. (In Japanese) [Google Scholar]
- Rao, K.N.; Munjal, M.L. Experimental evaluation of impedance of perforates with grazing flow. J. Sound Vib. 1986, 108, 283–295. [Google Scholar]
- Maa, D.Y. Potential of microperforated panel absorber. J. Acoust. Soc. Am. 1998, 104, 2861–2866. [Google Scholar] [CrossRef]
- Documentation of Scikit-Learn 0.16.1. Available online: https://scikit-learn.org/0.16/documentation.html (accessed on 5 September 2020).
- Kuncheva, L.I.; Bezdek, J.C.; Duin, R.P. Decision templates for multiple classifier fusion: An experimental comparison. Pattern Recognit. 2001, 34, 299–314. [Google Scholar] [CrossRef]
- Zhang, C.; Ma, Y. Ensemble Machine Learning: Methods and Applications; Zhang, C., Ma, Y., Eds.; Springer Science & Business Media: New York, NY, USA, 2012. [Google Scholar]
- ISO 10534-1. Acoustics—Determination of Sound Absorption Coefficient and Impedance in Impedance Tubes—Part. 1: Method Using Standing Wave Ratio; ISO: Geneva, Switzerland, 1996. [Google Scholar]
- ISO 10534-2. Acoustics—Determination of Sound Absorption Coefficient and Impedance in Impedance Tubes—Part. 2: Transfer-Function Method; ISO: Geneva, Switzerland, 1998. [Google Scholar]
Conventional Models | Machine Learning Models | |
---|---|---|
Panel thickness | O | O |
Airspace depth | O | O |
Perforation ratio | O | X |
Orifice diameter | O | X |
Coefficient of viscosity of air | O | X |
Density of air | O | X |
Velocity of air | O | X |
Horizontal center distance of the hole | X | O |
Vertical center distance of the hole | X | O |
Case Number | Horizontal Center Distance of the Hole (mm) | Vertical Center Distance of the Hole (mm) | Thickness of the Panel (mm) | Air Space Depth (mm) |
---|---|---|---|---|
A1 | 1 | 2 | 0.5 | 210 |
A2 | 260 | |||
A3 | 460 | |||
B1 | 2 | 4 | 0.5 | 210 |
B2 | 260 | |||
B3 | 460 | |||
C1 | 1 | 2 | 0.6 | 210 |
C2 | 260 | |||
C3 | 460 | |||
D1 | 2 | 4 | 0.6 | 210 |
D2 | 260 | |||
D3 | 460 | |||
E1 | 1 | 2 | 0.8 | 200 |
E2 | 450 |
Transforming Method | Diagram | |
---|---|---|
Equivalent perimeter | perimeter of the hole = L | |
Equivalent area | cross-sectional area of the hole = S | |
Circumcircle | |
Model | Objective Function |
Lasso | |
Elastic net (ENet) | |
Kernel ridge (KRR) | combines Ridge regression with the kernel trick
Ridge: |
Model | Converted Method | RMSE |
---|---|---|
Semi-theoretical model | Equivalent area | 0.248 |
Equivalent perimeter | 0.276 | |
Circumcircle | 0.413 | |
Lee & Kwon’s model | Equivalent area | 0.394 |
Equivalent perimeter | 0.301 | |
Circumcircle | 0.400 | |
Maa’s model | Equivalent area | 0.368 |
Equivalent perimeter | 0.212 | |
Circumcircle | 0.401 |
Model | RMSE | |
---|---|---|
Training set | Lasso | 0.069 |
ENet | 0.069 | |
KRR | 0.070 | |
Gboost | 0.033 | |
Average | 0.056 | |
Stack | 0.040 | |
Testing set | Lasso | 0.092 |
ENet | 0.092 | |
KRR | 0.095 | |
Gboost | 0.062 | |
Average | 0.081 | |
Stack | 0.067 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
TSAY, Y.-S.; YEH, C.-Y. A Machine Learning Based Prediction Model for the Sound Absorption Coefficient of Micro-Expanded Metal Mesh (MEMM). Appl. Sci. 2020, 10, 7612. https://doi.org/10.3390/app10217612
TSAY Y-S, YEH C-Y. A Machine Learning Based Prediction Model for the Sound Absorption Coefficient of Micro-Expanded Metal Mesh (MEMM). Applied Sciences. 2020; 10(21):7612. https://doi.org/10.3390/app10217612
Chicago/Turabian StyleTSAY, Yaw-Shyan, and Chiu-Yu YEH. 2020. "A Machine Learning Based Prediction Model for the Sound Absorption Coefficient of Micro-Expanded Metal Mesh (MEMM)" Applied Sciences 10, no. 21: 7612. https://doi.org/10.3390/app10217612
APA StyleTSAY, Y.-S., & YEH, C.-Y. (2020). A Machine Learning Based Prediction Model for the Sound Absorption Coefficient of Micro-Expanded Metal Mesh (MEMM). Applied Sciences, 10(21), 7612. https://doi.org/10.3390/app10217612