Wind and Structures

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

A proof-of-concept study of estimating wind speed from acoustic frequency-domain signal using machine learning

  • Yang Ling (National Key Laboratory of Bridge Intelligent and Green Construction, Southwest Jiaotong University) ;
  • Zilong Ti (National Key Laboratory of Bridge Intelligent and Green Construction, Southwest Jiaotong University) ;
  • Hengrui You (National Key Laboratory of Bridge Intelligent and Green Construction, Southwest Jiaotong University) ;
  • Yongle Li (National Key Laboratory of Bridge Intelligent and Green Construction, Southwest Jiaotong University)
  • Received : 2022.08.26
  • Accepted : 2023.01.14
  • Published : 2023.05.25
⟨ Previous Next ⟩

Abstract

Wind speed measurement is one of the most fundamental tasks for multidiscipline applications and plays an important role in the design and maintenance of modern infrastructures. Wind speed is usually measured using conventional gauges which require additional connections to sensors or collection boxes, and their complex operating principles make these devices largely serve only professionals. This study proposed a novel framework associated with a machine learning architecture to estimate wind speed directly from acoustic signal collected using smartphones. The one-dimensional convolutional network is employed to characterize the underlying relationship between the frequency domain features of the acoustic signal and wind speed. An experimental dataset is collected in wind tunnel laboratory in which the wind speed is measured using cobra probe and the acoustic signal is recorded using smartphone. The influence of encountering direction angle on the 1D-CNN wind speed measurement model is also discussed, as well as the ability of the model to resist noise. The favorable robustness and generalization performance of the 1D-CNN model are verified from multiple perspectives, illustrating the feasibility and practical value of using smartphones to measure wind speed.

Keywords

Acknowledgement

The financial support from the National Natural Science Foundation of China (52008349), the Postdoctoral Science Foundation of China (2020M683356, 2021T140573), Natural Science Foundation of Sichuan Province (2022NSFSC1163) and the Fundamental Research Funds for the Central Universities (2682021CX004) are greatly appreciated by the authors.

References

  1. Chen, Z. (2005), Bridge Wind Engineering [M], China Communications Press, Beijing. (in Chineses) 
  2. Dwork, C., Feldman, V., Hardt, M., Pitassi, T., Reingold, O. and Roth, A. (2015), "The reusable holdout: Preserving validity in adaptive data analysis", Science, 349(6248), 636-638. https://doi.org/10.1126/science.aaa9375.
  3. Goodfellow, I., Bengio, Y. and Courville, A. (2016), Deep Learning, MIT Press, Cambridge, UK.
  4. Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G. and Cai, J. (2018), "Recent advances in convolutional neural networks", Pattern Recogn., 77, 354-377. https://doi.org/10.1016/j.patcog.2017.10.013.
  5. Guo, F., Zhang, Y., Wang, Y., Wang, P., Ren, P., Guo, R. and Wang, X. (2020), "Fault detection of reciprocating compressor valve based on one-dimensional convolutional neural network", Math. Probl. Eng., 2020, 1-10. https://doi.org/10.1155/2020/8058723.
  6. Hamm, J., Stone, B., Belkin, M. and Dennis, S. "Automatic annotation of daily activity from smartphone-based multisensory streams", Lecture Notes Inst. Comp. Sci., Soc. Info. Telecom. Eng., 110, 328-342. https://doi.org/10.1007/978-3-642-36632-1_19.
  7. Kingma, D. and Ba, J. (2014), "Adam: a method for stochastic optimization", Int. Conf. Learning Represent., San Diego. https://doi.org/10.48550/arXiv.1412.6980.
  8. Le Prell, C.G. and Clavier, O.H. (2017), "Effects of noise on speech recognition: challenges for communication by service members", Hearing Res., 349, 76-89. https://doi.org/10.1016/j.heares.2016.10.004.
  9. Lester, J., Choudhury, T. and Borriello, G. (2006), "A practical approach to recognizing physical activities", Pervasive Comput.: 4th Int. Conf., Dublin, May. https://doi.org/10.1007/11748625_1.
  10. Li, B.Z., Liu, K., Gu, J.J. and Jiang, W.Z. (2021), "Review of the researches on convolutional neural networks", Comp. Era, 4, 12-17. https://doi.org/10.19595/j.cnki.1000-6753.tces.L90390.
  11. Li, J. (1997), "Chat about wind measurement", Meteorol., Hydrol. Marine Instru., 2, 47-52. https://doi.org/10.19441/j.cnki.issn1006-009x.1997.02.008.
  12. Liang, X., Xiong, Z., Liu, Y., Qu, Y., Bi, W. and Di, H. (2020), "Fiber optic anti-magnetic anemometer", Int. Core J. Eng., 6(11), 290-293. https://doi.org/10.6919/ICJE.202011_6(11).0037.
  13. Ma, J., Dong, S., Chen, G., Peng, P., and Qian, L. (2021), "A data-driven normal contact force model based on artificial neural network for complex contacting surfaces", Mech. Syst. Signal Process., 156, 107612. https://doi.org/10.1016/j.ymssp.2021.107612.
  14. Novak, A. and Honzik, P. (2021), "Measurement of nonlinear distortion of MEMS microphones", Appl. Acoust., 175, 107802. https://doi.org/10.1016/j.apacoust.2020.107802.
  15. Ramos-Cenzano, A ., Ogueta-Gutierrez, M. and Pindado, S. (2019), "Cup anemometers' performance analysis today: still room for improvement", J. Energy Syst., 3(4), 129-138. https://doi.org/10.30521/jes.614212.
  16. Senjoba, L., Sasaki, J., Kosugi, Y., Toriya, H., Hisada, M. and Kawamura, Y. (2021), "One-dimensional convolutional neural network for drill bit failure detection in rotary percussion drilling", Mining, 1(3), 297-314. https://doi.org/10.3390/mining1030019.
  17. Shao, L. and Wen, S. (2021), "Research on obtaining average wind speed of roadway based on GRU neural network", Gold Sci. Tech., 29(5), 709-718. https://doi.org/10.11872/j.issn.1005-2518.2021.05.054.
  18. Song, J., Shen, S. and Jin, H. (2018), "Wireless wind speed measurement based on three-axis ultrasonic anemometer", DEStech Transactions Comp. Sci. Eng., 19807. https://doi.org/10.12783/DTCSE/WCNE2017/19807.
  19. Stoilov, G., Pashkouleva, D. and Kavardzhikov, V. (2020), "Smartphone application for structural health monitoring", IOP Conf. Series: Mater. Sci. Eng., 951(1), 012026. http://dx.doi.org/10.1088/1757-899X/951/1/012026.
  20. Tanaka, T., Nakayoshi, M. and Tanaka, T. (2017), "Development of a new wind velocimetry based on balloon trajectory analysis using a computer vision theory", J. Japan Soc. Civil Eng., Ser. B1 (Hydraul. Eng.), 73(4), I_451-I_456. https://doi.org/10.2208/jscejhe.73.I_451.
  21. Wang, X., Yu, Z. and Mao, S. (2020), "Indoor localization using smartphone magnetic and light sensors: a deep LSTM approach", Mobile Netw. Appl., 25(2), 819-832. https://doi.org/10.1007/s11036-019-01302-x.
  22. Wang, Y., Qi, J., Ma, Z. and Wang, W. (2009), "Computational method of anemography by proportion", Meteorol., Hydrol. Marine Instru., 26(1), 12-16. https://doi.org/10.3969/j.issn.1006-009X.2009.01.004
  23. Wu, C., Jiang, P., Ding, C., Feng, F. and Chen, T. (2019), "Intelligent fault diagnosis of rotating machinery based on one-dimensional convolutional neural network", Comp. Ind., 108, 53-61. https://doi.org/10.1016/j.compind.2018.12.001.
  24. Xiaohui, W. (2015), "Design and development of Android-based smartphone application for measuring wind direction", M.A. Thesis, Zhejiang University, Hangzhou, China.
  25. Yang, M., Liu, S., Wang, Z., Zhang, W., Ding, G. (2015), "Kalman filter and wavelet neural network wind speed prediction", Proceedings of the CSU-EPSA, 27(12), 42-46. https://doi.org/ 10.3969/j.issn.1003-8930.2015.12.08.
  26. Yang, Z., Yang, C. and Han. (2005), "Research and design of silicon piezoresistive solid state wind detecting instrument", Meteorol., Hydrol. Marine Instru., 2, 17-21. https://doi.org/10.3969/j.issn.1006-009X.2005.02.002.
  27. Zhang, Y., Wang, H., Bai, Y., Mao, J. and Xu, Y. (2022), "Bayesian dynamic regression for reconstructing missing data in structural health monitoring", Struct. Health Monitor., 21(5), 2097-2115. https://doi.org/10.1177/14759217211053779.
  28. Zhang, Y., Wang, H., Wan, H., Mao, J., and Xu, Y. (2020), "Anomaly detection of structural health monitoring data using the maximum likelihood estimation-based Bayesian dynamic linear model", Struct. Health Monitor., 20(6), 2936-2952. https://doi.org/10.1177/1475921720977020.
  29. Zhang, Y.M., Wang, H., Mao, J.X., Xu, Z.D., and Zhang, Y.F. (2021), "Probabilistic framework with Bayesian optimization for predicting typhoon-induced dynamic responses of a long-span bridge", J. Struct. Eng., 147(1), 04020297. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002881.