Портал психологических изданий PsyJournals.ru
Каталог изданий 108Рубрики 53Авторы 9084Новости 1792Ключевые слова 5095 Правила публикацииВебинарыRSS RSS

РИНЦ

0,727 — двухлетний импакт-фактор

Моделирование и анализ данных

Издатель: Московский государственный психолого-педагогический университет

ISSN (печатная версия): 2219-3758

ISSN (online): 2311-9454

DOI: https://doi.org/10.17759/mda

Лицензия: CC BY-NC 4.0

Издается с 2011 года

Периодичность: 4 номера в год

Язык журнала: русский

Доступ к электронным архивам: открытый

 

Acoustic characterization of the conditions of a water-filled siphon 1000

Feng Z.
School of Engineering, University of Bradford, Bradford, West Yorkshire, United Kingdom

Horoshenkov K.
School of Engineering, University of Bradford, Bradford, West Yorkshire, United Kingdom

Noras J.
School of Engineering, University of Bradford, Bradford, West Yorkshire, United Kingdom

Аннотация

Pattern recognition has been used and developed as a process of advanced analysis of acoustic signal. Designing a robust pattern recognition system involves three fundamental tasks: signal pre-processing, feature extraction and selection, and finally classifier design and optimization. This paper reports on an application to detect and monitor conditions of a large, water-filled siphon used in underground tunnels. Acoustic signals were collected from 4 hydrophones under various typical siphon conditions and used as input data to study the variation of the acoustic field. The discrete wavelet transform (DWT) was used in feature extraction and K-nearest neighbors (KNN) classification was applied. Subsequently, the system was tested on new unknown data and compared with supervised training samples. The results demonstrated that the acoustic sensors have high reproducibility for collecting signals under operational conditions. The pattern recognition system is also capable of discriminating different pipe conditions but further refinement is needed to improve sensitivity and to compensate for the effect of variable water level and sensor misalignment.

Ключевые слова: Acoustics, siphon, wavelet transform, pattern recognition

Рубрика: Научная жизнь

Тип: научная статья

Ссылка для цитирования

Фрагмент статьи

Acoustic data were collected in a siphon which was constructed from 450mm diameter concrete pipes in the Hydraulics Laboratory in the University of Bradford. The siphon was 4.2 m long and 2.0 m high. It was installed on a 500 mm layer of fine sand in an open top box made of 12mm ply­wood. The siphon was instrumented with four 25 mm hydrophones, 3 of which were installed in the left leg of the siphon. The other hydrophone was installed in the right leg of the siphon 75 mm above the speaker and used as a reference receiver. The source was a 50 mm diameter water re­sistant speaker in a PVC enclosure which is able to operate underwater. The hydrophones and the speaker were attached securely to two aluminum tubes which were lowered into the opposite legs of the siphon and kept at the same positions in all of the experiments conducted in the siphon. Figure 1 illustrates the equipment used in this experiment. The siphon was filled with clean water to the level of 900 mm below the top of the right vertical pipe (reference water level) in all the experiments ex­cept water level test.

Литература
  1. Grosse C. U., Finck F., "Improvements of AE technique using wavelet algorithms, coherence functions and automatic data analysis", Construction and Building Materials Vol 18, pp 203­213,2004.
  2. Cohen L. "Time-frequency Analysis", Prentice-Hall, New York,1995.
  3. Debnath L, "Recent developments in the Wigner-Ville distribution and time-frequency signal analysis", PINSA, 68.A.No 1, pp 35-56, 2002.
  4. Michael Cowling R.S., "Comparison of techniques for environmental sound recognition", Pattern Recognition Letters, pp 2895-2907, 2003.
  5. Richard O., Duda P.E., "Pattern classification", John Wiley & Sons,Inc., New York, 2001.
  6. Singh B.N., Tiwari A.K., "Optimal selection of wavelet basis function applied to ECG signal denoising", Digital Signal Processing, Vol 16, pp 275-287, 2006.
  7. Strang G., "Wavelets and filter banks", Wellesley-Cambridge Press,Wellesley MA, USA, 1996.
  8. Hugo T., Grimmelius Meiler P.P., Maas H.L. and Bonnier B., "Three state-of-the-art methods for condition monitoring", IEEE Transactions on Industrial Electronics, pp 407-416, 1999.
 
О проекте PsyJournals.ru

© 2007–2020 Портал психологических изданий PsyJournals.ru  Все права защищены

Свидетельство регистрации СМИ Эл № ФС77-66447 от 14 июля 2016 г.

Издатель: ФГБОУ ВО МГППУ

Creative Commons License Репозиторий открытого доступа     Рейтинг репозиториев Webometrics

Яндекс.Метрика