With the aim of improving the shortcomings of the traditional single hidden layer back propagation (BP) neural network structure and learning algorithm, this paper proposes a centrifugal pump performance prediction method based on the combination of the Levenberg–Marquardt (LM) training algorithm and double hidden layer BP neural network. MATLAB was used to establish a double hidden layer BP neural network prediction model to predict the head and efficiency of a centrifugal pump. The average relative error of the head between the experimental and prediction obtained by the double hidden layer BP neural network model was 4.35%, the average relative error of the model prediction efficiency and the experimental efficiency was 2.94%, and the convergence time was 1/42 of that of the single hidden layer. The double hidden layer BP neural network model effectively solves the problems of low learning efficiency and easy convergence into local minima—issues that were common in the traditional single hidden layer BP neural network training. Furthermore, the proposed model realizes hydraulic performance prediction during the design process of a centrifugal pump.
30 September 2024 in Journal of Fluids Engineering
The driving mechanism of ferrofluid micropumps under the constraints of an annular microscale morphology is not fully understood. The gap between microfabrication technology and the fundamental theory of microfluidics has become a substantial obstacle to the development and application of ferrofluid micropumps. In this study, we first theoretically analyzed the Knudsen numbers of millimeter-scale microfluids using Jacobson's molecular hard sphere model, obtaining the initial conclusion that liquid flow conforms to the continuum hypothesis in geometric morphologies with characteristic dimensions greater than 7 × 10-8 m. Subsequently, using a microscopic lens combined with the particle image velocimetry optical measurement method, the flow patterns in millimeter-scale annular flow channels were captured and we observed wall slip phenomena in which the slip length of the millimeter-scale channel approached the micron level. The slip velocity and flow rate through the cross-section of the microscale channel followed a logarithmic function relationship and could be divided into rapid growth, slow growth, and stable stages. As the characteristic scale of the channel was further reduced, the linear relationship between the slip velocity and cross-sectional flow rate in the rapid growth stage was broken, and the nonlinear relationship approximated an exponential function. Finally, a theoretical model for the flow behavior of the driving fluid in a ferrofluid micropump was established using slip boundary conditions. The flow patterns in microscale ring flow under slip conditions conformed to a quadratic function.
Significant breakthroughs in the theory and applications of ferrofluid have broadened their usage in areas such as sealing and actuation. However, the development of numerical ferrofluid dynamics has been slow owing to inadequate multi-field coupling techniques and incomplete equations for turbulence in ferrofluid flow. The understanding of low-Reynolds-number turbulent flow mechanisms in ferrofluid at small scales, particularly in sealing and actuation applications, remains limited, therefore hindering further advancements. This article delves into the turbulent flow equations for general fluid and discusses the influence of different-scale vortices on the average fluid motion. An anisotropic turbulence model was introduced and verified using fluid flow around a cylinder. Magnetic and flow fields data were coupled through node ranking and interpolation methods. By introducing the interaction force of magnetic dipoles, the turbulent equations were refined within Euler grids, thereby establishing a numerical model for the turbulent motion of ferrofluids influenced by multiple fields. This model was applied to study the deformation and migration processes of ferrofluid under an external magnetic field. The variations in ferrofluid motion under magnetic forces were encapsulated, and macroscopic flow comparisons were made through experiments, which demonstrated good consistency. This research provides new methods and ideas for use in ferrofluid numerical studies. Additionally, it offers valuable technical support that can aid in developing industrial products such as sealing and driving devices based on ferrofluids.
1 January 2021 in International Journal of Agricultural and Biological Engineering
With the decrease of oil and gas resources on land, increased attention has been paid to multiphase oil–gas exploitation and the transportation technology represented by oil–gas multiphase pumps. The helical–axial multiphase pump has become the focus of research on oil and gas mixed transmission technology due to its relatively high operating efficiency and adaptability to a wide range of gas volume fraction changes. In order to investigate the thickness variation in the air foil from the hub to the shroud of the blade on the mixture transportation characteristics of the gas–liquid two-phase flow in a helical–axial pump, the thickness ratio coefficient ξ was introduced, and the hydraulic performance of the single compression unit with different thickness ratio coefficients was investigated. A single compression unit including an impeller, diffuser, inlet section and outlet section of a helical–axial multiphase pump. The hydraulic performance including the hydraulic head and efficiency was investigated by numerical simulation with the Eulerian multiphase model and the shear stress transport (SST) k-w turbulence model. In order to demonstrate the validity of the numerical simulation approach, the hydraulic head and efficiency of the basic model was measured based on a gas–liquid two-phase flow pump performance test bench. The simulation results agreed well with the experimental results; the error between the simulation results and experimental results of different inlet gas volume fractions was within 10% at the design point, which indicated the numerical simulation method can be used in the research. The thickness ratio coefficient ξ, which was taken as a variable, and the aggregation degree λ of the gas were introduced to analyze the gas–liquid mixture transportation characteristics of the pump. The thickness ratio coefficient was selected in a range from 0.8 to 1.8. The results showed that, for the same hub thickness, the head coefficient and efficiency increase, and the aggregation degree of gas decreases with the decreasing of the thickness ratio coefficient. The head coefficient of the modification multiphase pump was 5.8% higher in comparison to the base pump while the efficiency was 3.1% higher than that of the base pump, the aggregation degree of this model was the lowest, which was 30.3%; the optimal model in the research was the model of scheme 1 with ξ = 0.8. The accumulation of gas in the flow passage of the impeller could be delayed to the trailing edge of the blade by adjusting the thickness ratio coefficient, which produced a super-separated airfoil for helical–axial multiphase pumps and effectively ensured reliable operation under high gas volume fraction conditions. The accumulation area of gas was consistent with the area in which the gradient of turbulent kinetic energy was large.
Sediment erosion caused by the collision of solid particles is a challenge for the safety, reliability, unit efficiency, and vibration noise of the hydroelectric engineering system located at China’s Yellow River and northwest inland basin. The sediment-laden flow of the guide vane end-clearance of the Francis Turbine at Dongshuixia hydroelectric station was used as the research object, and the large eccentric shaft structure of a guide vane was considered. Numerical calculations with the large eddy simulation (LES) and discrete phase models (DPMs) were carried out to study the erosion characteristics and mechanism of the end-surface of the guide vane and head cover, the flow mechanism of adverse erosion behind the shaft, and the influence law of the turbulence integral scale, turbulent kinetic energy, and turbulent flow angle on erosion. The flow field with a 1 mm clearance should set the number of particle trajectory per unit inlet area at about 1/mm2 to ensure the accuracy of calculation. The von Kármán vortex street is the main reason for adverse erosion behind the shaft and the low frequency energy of the turbulence plays a leading role in erosion. The above results provide a reference for the optimization design of an anti-wear guide vane and wear-protection of the clearance with sediment-laden water.