Gradient-based PIV using neural networks
This paper proposes a new gradient-based PIV using an artificial neural network for acquiring the characteristics of a two-dimensional flow field. The neural network can effectively realize an accurate approximation of the vector field by introducing some knowledge on the characteristic property. The neural network is trained by using spatial and temporal image gradients so that the basic equation of the gradient-based method is satisfied. Since the neural network itself learns the stream function, the continuity equation of flow is consequently satisfied in the measured velocity vector field. The new gradient-based PIV can be applied to even partly lacking visualized images.
KeywordsPIV neural networks gradient-based method stream function
Unable to display preview. Download preview PDF.
- Grant, I., Particle Image Velocimetry: a review, Proc. Instn. Mech. Engrs., 211-C, (1997), 55–76.Google Scholar
- Ido, T., Murai, Y., Ohta, J. and Yamamoto, F., High Resolution Measurement of Flow Based on High-Order Image Reconstruction, CD-ROM Proc. 3rd ASME/JSME Joint Fluids Engineering Conference, FEDSM99-7071, (1999).Google Scholar
- Kuroe, Y., Mitsui, M., Kawakami, H. and Mori, T., A Learning Method for Vector Field Approximation by Neural Networks, Proc. of 1998 IEEE International Joint Conference on Neural Networks (IJCNN’98) (Anchorage), (1998), 2300–2305.Google Scholar
- Okuno, T., Image Measurement by means of Spatio-Temporal Derivative Method, Proc. The International Workshop on PIV-Fukui ’95 (Fukui, Japan), (1995), 167–173.Google Scholar