Back to Search
Start Over
A Fast Method of Feature Extraction for Lowering Vehicle Pass-By Noise Based on Nonnegative Tucker3 Decomposition
- Source :
- Archives of Acoustics. 42:619-629
- Publication Year :
- 2017
- Publisher :
- Walter de Gruyter GmbH, 2017.
-
Abstract
- Usually, the judgement of one type fault of vehicle pass-by noise is difficult for engineers, especially when some significant features are disturbed by other interference noise, such as the squealing noise is almost simultaneous with the whistle in the exhaust system. In order to cope with this problem, a new method, with the antinoise ability of the algorithm on the condition by which the features are entangled, is developed to extract clear features for the fault analysis. In the proposed method, the nonnegative Tucker3 decomposition (NTD) with fast updating algorithm, signed as NTD_FUP, can find out the natural frequency of the parts/components from the exhaust system. Not only does the NTD_FUP extract clear features from the confused noise, but also it is superior to the traditional methods in practice. Then, an aluminium-foil alloy material, which is used for the heat shield for its lower noise radiation, replaces the aluminium alloy alone. Extensive experiments show that the sound pressure level of the vehicle pass-by noise is reduced 0.9 dB(A) by the improved heat shield, which is also considered as a more lightweight design for the exhaust system of an automobile.
- Subjects :
- Acoustics and Ultrasonics
Computer science
Feature extraction
Natural frequency
02 engineering and technology
Fault (power engineering)
Noise
020303 mechanical engineering & transports
0203 mechanical engineering
Interference (communication)
Control theory
Heat shield
0202 electrical engineering, electronic engineering, information engineering
Decomposition (computer science)
020201 artificial intelligence & image processing
Sound pressure
Subjects
Details
- ISSN :
- 2300262X
- Volume :
- 42
- Database :
- OpenAIRE
- Journal :
- Archives of Acoustics
- Accession number :
- edsair.doi...........01692adc333ca9399291d9e85a3247bc