Machine-Learning-Based Reconstruction of Turbulent Vortices From Sparse Pressure Sensors in a Pump Sump
-
- Kai Fukami
- Department of Mechanical and Aerospace Engineering, University of California, Los Angeles , Los Angeles, CA 90095
-
- Byungjin An
- Fundamental Technologies, R&D Department, Ebara Corporation , Tokyo 144-8510, Japan
-
- Motohiko Nohmi
- Fundamental Technologies, R&D Department, Ebara Corporation , Tokyo 144-8510, Japan
-
- Masashi Obuchi
- Fundamental Technologies, R&D Department, Ebara Corporation , Tokyo 144-8510, Japan
-
- Kunihiko Taira
- Department of Mechanical and Aerospace Engineering, University of California, Los Angeles , Los Angeles, CA 90095
この論文をさがす
説明
<jats:title>Abstract</jats:title> <jats:p>Getting access to the state of turbulent flow from limited sensor measurements in engineering systems is a major challenge. Development of technologies to accurately estimate the state of the flow is now possible with the use of machine learning. We present a supervised machine learning technique to reconstruct turbulent vortical structures in a pump sump from sparse surface pressure measurements. For the current flow reconstruction technique, a combination of multilayer perceptron and three-dimensional convolutional neural network is utilized. This technique provides accurate flow estimation from only a few sensor measurements, identifying the presence of adverse vortices. The dependence of the model performance on the amount of training data, the number of input sensors, and the noise levels are investigated. The present machine learning-based flow estimator supports safe operations of pumps and can be extended to a broad range of applications for industrial fluid-based systems.</jats:p>
収録刊行物
-
- Journal of Fluids Engineering
-
Journal of Fluids Engineering 144 (12), 121501-, 2022-08-23
ASME International
