Wind-Tunnel Investigation on the Compressive-Sensing Technique for Aeroengine Fan Noise Detection

Bu, Huanxian; Wang, Ye; Kwan, Pok-Wang; Huang, Xun

doi:10.2514/1.j057261

Cited by 26 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The inversion method itself, compared to the construction of forward models, is actually straightforward. To explain this point, the compressive sensing method is used here as an example, because it has found ever-increasing applications in aerospace engineering in general [38,39] and aeroengine acoustic experiments in particular [1][2][3]. Through compressive sensing, an inversion can be achieved by solving the following linear programming [40]:…”

Section: Preliminary Knowledge (A) Statement Of the Problemsmentioning

confidence: 99%

“…Hence, the current paper is focused on the forward modelling topic. It is also worthwhile to mention that most fan noise testing techniques [1,2] currently used in aeroengine applications belong to mode detections, for which the transfer function G would simply be Fourier expansions (that mapŝ to azimuthal modes) or Bessel functions (that mapŝ to radial modes). In contrast, the mode inversion task calls for a transfer function G that maps fan noise source to far-field measurements, which would be much more difficult to achieve (figure 3) and is therefore one of the focal points in this work.…”

Section: Preliminary Knowledge (A) Statement Of the Problemsmentioning

confidence: 99%

“…In practice, the turbofan noise is so dominant that would overwhelm testing facility (e.g. wind tunnel) background noise [2] and, hence, n is simply set to 0 in this work. An inversion requires all the associated G mn , which would be quite computational intensive by using (2.22) and (2.23).…”

Section: Neural Network Assisted By Wiener-hopf (A) For Problem Imentioning

confidence: 99%

“…In the training of the U-net, we deliberately choose a dataset of 10 000 items that only covers 4 modes, that is, (m, n) = (6, 1), (6,2), (7,1) and (7,2), with uniform background flows of M 0 = M 1 = 0.1. The corresponding training loss is similar to figure 10.…”

Section: (B) Problem Imentioning

confidence: 99%

“…the Wiener-Hopf technique are proposed in this paper for duct acoustics and spatial derivatives, respectively. The first network model can find practical applications in (radial) wave mode detections, which is a popular topic in the aerospace research community for low-noise aircraft engine design [1][2][3][4], because of the connection between duct acoustics and aeroengine fan noise problems [5][6][7]. The second network can find applications in solving various partial differential equations that has attracted increasing research attentions recently [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Deep neural networks for waves assisted by the Wiener–Hopf method

Huang

2020

Proc. R. Soc. A.

Self Cite

View full text Add to dashboard Cite

In this work, the classical Wiener–Hopf method is incorporated into the emerging deep neural networks for the study of certain wave problems. The essential idea is to use the first-principle-based analytical method to efficiently produce a large volume of datasets that would supervise the learning of data-hungry deep neural networks, and to further explain the working mechanisms on underneath. To demonstrate such a combinational research strategy, a deep feed-forward network is first used to approximate the forward propagation model of a duct acoustic problem, which can find important aerospace applications in aeroengine noise tests. Next, a convolutional type U-net is developed to learn spatial derivatives in wave equations, which could help to promote computational paradigm in mathematical physics and engineering applications. A couple of extensions of the U-net architecture are proposed to further impose possible physical constraints. Finally, after giving the implementation details, the performance of the neural networks are studied by comparing with analytical solutions from the Wiener–Hopf method. Overall, the Wiener–Hopf method is used here from a totally new perspective and such a combinational research strategy shall represent the key achievement of this work.

show abstract