Machine Learning for Vortex Flowmeter Design

Vortex flowmeters are one of the broadly used flow measurement devices in various industrial applications. The shape of the bluff body is the most critical parameter in the design of vortex flowmeter. The conventional approach of bluff body design relies on parametric shape optimization of a bluff body using experimentation and computational fluid dynamics simulations, which are expensive and time-consuming. In this study, we propose a novel machine learning (ML)-based approach to design bluff body shapes. Two ML models are developed using supervised ML using an artificial neural network (ANN). The first model predicts new optimum bluff body shapes for a given input flow characteristic. The second model predicts the deviation in Strouhal number for a given bluff body to determine its optimality. Data from the literature on the geometry of bluff bodies and fluid flow properties such as blockage ratio, Reynolds number, and Strouhal number are used for training ML models. The obtained ML results are in close agreement (±3.0%) compared with the computational fluid dynamics simulation results. This approach may find broad applicability for designing other fluid flowmeters.