Measurement of water content of oil-water two-phase flows using dual-frequency microwave method in combination with deep neural network

This paper presents a microwave dual frequency correction algorithm to measure the water content of the oil-water two-phase flows, which can eliminate the influence of conductivity and obtain the water content. Subsequently, based on the advantages of dual-frequency this paper proposes a deep neural network model to predict complex nonlinear relationship between the mixture permittivity and water content. In order to avoid falling into a local optimal solution, the adaptive moment estimation algorithm is used to replace the gradient descent method. The experimental results are applied to estimate the performance of the discussed deep neural network algorithm.