journal article·2021-07-01Open access

Unsupervised clustering and performance prediction of vortex wakes from bio-inspired propulsors

Alejandro G Calvet, Mukul Dave, Jennifer A Franck

Bioinspiration & Biomimetics· Volume 16· Issue 4

Abstract

-means++ algorithm performs the clustering. The results are assessed by comparing clusters to a thrust versus propulsive efficiency map, which confirms that wakes of similar performance metrics are successfully clustered together. This automated clustering has the potential to identify complex vorticity patterns in the wake and modes of propulsion not easily discerned from traditional classification methods.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Biomimetic flight and propulsion mechanisms · Fluid Dynamics and Vibration Analysis · Fluid Dynamics and Turbulent Flows

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (37)

Show source-provided references
1. Vortex formation in the wake of an oscillating cylinder10.1016/s0889-9746(88)90058-8 ↗
2. Vortex wakes of a flapping foil10.1017/s0022112009007964 ↗
3. Vortical patterns in the wake of an oscillating airfoil10.2514/3.10246 ↗
4. Jet characteristics of a plunging airfoil10.2514/2.641 ↗
5. Vortex shedding and frequency selection in flapping flight10.1017/s0022112099008071 ↗
6. Effect of angle of attack profiles in flapping foil propulsion10.1016/j.jfluidstructs.2003.10.003 ↗
7. Numerical investigation of angle of attack profile on propulsion performance of an oscillating foil10.1016/j.compfluid.2010.04.006 ↗
8. Swimmers’ wake structures are not reliable indicators of swimming performance10.1088/1748-3190/ab6fb9 ↗
9. Classifying vortex wakes using neural networks10.1088/1748-3190/aaa787 ↗
10. Detecting exotic wakes with hydrodynamic sensors10.1007/s00162-019-00493-z ↗
11. Classifying wakes produced by self-propelled fish-like swimmers using neural networks10.1016/j.taml.2020.01.010 ↗
12. Vortex dynamics and Reynolds number effects of an oscillating hydrofoil in energy harvesting mode10.1016/j.jfluidstructs.2020.102888 ↗
13. k-means++: the advantages of careful seeding
14. Variable thrust and high efficiency propulsion with oscillating foils at high Reynolds numbers10.1016/j.oceaneng.2020.107833 ↗
15. Robust mesh deformation using the linear elasticity equations
16. Numerical simulations of flapping foil and wing aerodynamics: mesh deformation using radial basis functions
17. Simulation of flow about flapping airfoils using finite element incompressible flow solver10.2514/3.14725 ↗
18. Performance of flapping foil propulsion10.1016/j.jfluidstructs.2005.05.009 ↗
19. Propulsive performance of biologically inspired flapping foils at high Reynolds numbers10.1242/jeb.012849 ↗
20. Large-amplitude oscillations of foils for efficient propulsion10.1103/physrevfluids.4.093102 ↗
21. A deep convolutional auto-encoder with embedded clustering
22. TensorFlow: large-scale machine learning on heterogeneous systems
23. Chollet · Keras · 2015
24. ImageNet classification with deep convolutional neural networks
25. Visualizing and understanding convolutional networks10.1007/978-3-319-10590-1_53 ↗
26. Cross entropy error function in neural networks: forecasting gasoline demand
27. Generalized cross entropy loss for training deep neural networks with noisy labels
28. Adam: a method for stochastic optimization
29. Image restoration using very deep convolutional encoder–decoder networks with symmetric skip connections
30. The vanishing gradient problem during learning recurrent neural nets and problem solutions10.1142/s0218488598000094 ↗
31. Jin · 2010 · 564
32. A study of hierarchical clustering algorithms
33. A density-based algorithm for discovering clusters in large spatial databases with noise
34. Scikit-learn: machine learning in Python10.5555/1953048.2078195 ↗
35. Least squares quantization in PCM10.1109/tit.1982.1056489 ↗
36. Who belongs in a family?10.1007/BF02289263 ↗
37. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis10.1016/0377-0427(87)90125-7 ↗