Soft Sensing of Non-Newtonian Fluid Flow in Open Venturi Channel Using an Array of Ultrasonic Level Sensors—AI Models and Their Validations
نویسندگان
چکیده
In oil and gas and geothermal installations, open channels followed by sieves for removal of drill cuttings, are used to monitor the quality and quantity of the drilling fluids. Drilling fluid flow rate is difficult to measure due to the varying flow conditions (e.g., wavy, turbulent and irregular) and the presence of drilling cuttings and gas bubbles. Inclusion of a Venturi section in the open channel and an array of ultrasonic level sensors above it at locations in the vicinity of and above the Venturi constriction gives the varying levels of the drilling fluid in the channel. The time series of the levels from this array of ultrasonic level sensors are used to estimate the drilling fluid flow rate, which is compared with Coriolis meter measurements. Fuzzy logic, neural networks and support vector regression algorithms applied to the data from temporal and spatial ultrasonic level measurements of the drilling fluid in the open channel give estimates of its flow rate with sufficient reliability, repeatability and uncertainty, providing a novel soft sensing of an important process variable. Simulations, cross-validations and experimental results show that feedforward neural networks with the Bayesian regularization learning algorithm provide the best flow rate estimates. Finally, the benefits of using this soft sensing technique combined with Venturi constriction in open channels are discussed.
منابع مشابه
Analytical study of flow field and heat transfer of a non-Newtonian fluid in an axisymmetric channel with a permeable wall
In this study, the momentum and energy equations of laminar flow of a non-Newtonian fluid are solved in an axisymmetric porous channel using the least square and Galerkin methods. The bottom plate is heated by an external hot gas, and a coolant fluid is injected into the channel from the upper plate. The arising nonlinear coupled partial differential equations are reduced to a set of coupled no...
متن کاملNumerical Simulation of Non-Newtonian Inelastic Flows in Channel based on Artificial Compressibility Method
In this study, inelastic constitutive modelling is considered for the simulation of shear-thinning fluids through a circular channel. Numerical solutions are presented for power-law inelastic model, considering axisymmetric Poiseuille flow through a channel. The numerical simulation of such fluid is performed by using the Galerkin finite element approach based on artificial compression method (...
متن کاملEffects of non-newtonian properties of blood flow on magnetic nanoparticle targeted drug delivery
Objective(s): One applications of nanotechnology is in the area of medicine which is called nanomedicine. Primary instruments in nanomedicine can help us to detect diseases and used for drug delivery to inaccessible areas of human tissues. An important issue in simulating the motion of nanoparticles is modeling blood flow as a Newtonian or non-Newtonian fluid. Sometimes blood flow is simulated ...
متن کاملAssessment of Turbulent Models in Computation of Strongly Curved Open Channel Flows
Several rigorous turbulent models have been developed in the past years and it can be seen that more research is needed to reach a better understanding of their generality and precision by verifying their applications for distinct hydraulic phenomena; under certain assumptions. This survey evaluates the performance of Standard k-ε, Realizable k-ε, RNG k-ε, k-ω and RSM models in predicting flow ...
متن کاملEffect of six non-Newtonian viscosity models on hemodynamic parameters of pulsatile blood flow in stenosed artery
A numerical study of hemodynamic parameters of pulsatile blood flow is presented in a stenotic artery with A numerical study of hemodynamic parameters of pulsatile blood flow is presented in a stenotic artery with non-Newtonian models using ADINA. Blood flow was considered laminar, and the arterial wall was considered rigid. Studied stenosis severities were 30, 50, and 70% of the cross-section...
متن کامل