Prediction of oil flow rate through an orifice flow meter: Artificial intelligence alternatives compared

Fluid-flow measurements of petroleum can be performed using a variety of equipment such as orifice meters and wellhead chokes.It is useful to understand the relationship between flow rate through orifice meters(Qv)and the five fluid-flow influencing input variables:pressure(P),temperature(T),viscosity(μ),square root of differential pressure(ΔP^0.5),and oil specific gravity(SG).Here we evaluate these relationships using a range of machine-learning algorithms applied to orifice meter data from a pipeline flowing from the Cheshmeh Khosh Iranian oil field.Correlation coefficients indicate that(Qv)has weak to moderate positive correlations with T,P,andμ,a strong positive correlation with theΔP^0.5,and a weak negative correlation with oil specific gravity.In order to predict the flow rate with reliable accuracy,five machine-learning algorithms are applied to a dataset of 1037 data records(830 used for algorithm training;207 used for testing)with the full input variable values for the data set provided.The algorithms evaluated are:Adaptive Neuro Fuzzy Inference System(ANFIS),Least Squares Support Vector Machine(LSSVM),Radial Basis Function(RBF),Multilayer Perceptron(MLP),and Gene expression programming(GEP).The prediction performance analysis reveals that all of the applied methods provide predictions at acceptable levels of accuracy.The MLP algorithm achieves the most accurate predictions of orifice meter flow rates for the dataset studied.GEP and RBF also achieve high levels of accuracy.ANFIS and LSSVM perform less well,particularly in the lower flow rate range(i.e.,<40,000 stb/day).Some machine learning algorithms have the potential to overcome the limitations of idealized streamline analysis applying the Bernoulli equation when predicting flow rate across an orifice meter,particularly at low flow rates and in turbulent flow conditions.Further studies on additional datasets are required to confirm this.

THE MOTION OF A SPHERICAL PARTICLE IN THE STOKES FLOW OUTSIDE A CIRCULAR ORIFICE

For any study ofa suspension entering a pore, the knowledge of the force and moment exerted on a solute particle in an arbitrary position outside the pore is essential, 'This paper for the first lime presents approximate analytical expressions (in closed form) of all the twelve force and moment coefficienis for a sphere outsied a circular orifice, on the basis of a number of discrete data computed by Yan et al(1987).These coefficients are then applied to calculate the trajectory and angular velocity of a spherical particle approaching the pore at zero Reynolds number. The trajectory is in excellent agreement with the available experimental results. An analysis of the relative importance of the coefficients shows that the rotation effect cannot be neglected near the pore opening or near the wall, and that the lateral force effect must be taken into account in the neighborhood of the edge of the pore opening. It is due to neglecting these factors that previous theoretical results deviate from the experimental ones near the pore opening. The effects of the ratio of the particle to pore radii as well as the influences of the graritytbuoyance on the particle trajectory, velocity distribution and rotation are discnssed in detail. It is pointed out that in the experiments of neutrally-buoyant suspensions, the restriction on the density of the particle is most demanding for a large particle size.The expressions of forces and moments presenled herein are complete, relatively accurate and convenient, thus providing a good prerequisite for further studies of any problems involving the entrance of particles to a pare.

Pressure performance for a thin-walled ring and turbulent-jet orifice modeled elastic squeeze film damper

This paper explores an analytical model for Elastic Ring Squeeze Film Damper(ERSFD) with thin-walled ring and turbulent-jet orifices, and uncovers its Oil Film Pressure Performance(OFPP). Firstly, the ring deformation is addressed by using the Fourier series expansion approach and the orifice outflow rate is characterized with the Prandtl boundary layer theory. Secondly, applying finite difference scheme, the influence of elastic ring flexibility, orifice diameter, and attitude angle on the OFPP is analyzed. Finally, Outer chamber pressure was measured experimentally at different rotor speeds. The results indicate that the outer chamber pressure coats an individual load-carrying region and spreads symmetrically pertaining to the attitude angle. Its amplitude drops as the elastic ring flexibility decreases but boosts with the reduction of the orifice diameter.For inner chamber pressure, the orifice diameter effects a similar trend to the outer cavity, but exhibits more stable distribution regarding the attitude angle. Minimizing the elastic ring flexibility causes an increase in amplitude. The model is validated by the test results giving that the outer chamber pressure shifts synchronously and periodically with the variation of the attitude angle,while the pressure amplitude increases slightly at higher rotor speeds.

The effect of a curved bed on the discharge equation in a spillway with a breast wall

The flow through a breast wall spillway is greatly affected by the centripetal force due to a downstream curved profile. Therefore, the mean vertical pressure distribution at the outlet section is not consistent with the hydrostatic pressure law. This distribution in turn affects the discharge capacity of the breast wall spillway. This paper experimentally studies the effect of a convex downstream profile on the mean pressure variation and the discharge of a breast wall spillway without gates. It is indicated that the effect of the curvilinear streamline on the mean vertical pressure variation is significant. The regression analysis method is used to determine the water head effect Z o of the orifice opening through the mean pressure variation. A discharge prediction formula of the breast wall spillway is obtained under the limited conditions of a laboratory flume. The predicted discharge is compared to the measured discharge. A good agreement is evidenced for the free orifice flow with errors within ？5%, while a big error（20% or even more） is obtained if the hydrostatic pressure law is used for the determination of Zo.