Application of artificial neural network to multiphase flow metering: A review

Flow Measurement and Instrumentation, Journal Year: 2024, Volume and Issue: 97, P. 102601 - 102601

Published: April 26, 2024

Language: Английский

---

A hybrid differential evolution particle swarm optimization algorithm based on dynamic strategies

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 6, 2025

Particle Swarm Optimization (PSO), a meta-heuristic algorithm inspired by swarm intelligence, is widely applied to various optimization problems due its simplicity, ease of implementation, and fast convergence. However, PSO frequently converges prematurely local optima when addressing single-objective numerical inherent rapid To address this issue, we propose hybrid differential evolution (DE) particle based on dynamic strategies (MDE-DPSO). In our proposed algorithm, first introduce novel inertia weight method along with adaptive acceleration coefficients dynamically adjust the particles' search range. Secondly, velocity update strategy that integrates center nearest perturbation term. Finally, mutation crossover operator DE PSO, selecting appropriate improvement, which generates mutant vector. This vector then combined current particle's best position through crossover, aiding particles in escaping optima. validate efficacy MDE-DPSO, evaluated it CEC2013, CEC2014, CEC2017, CEC2022 benchmark suites, comparing performance against fifteen algorithms. The experimental results indicate demonstrates significant competitiveness.

Language: Английский

---

Digital Twinning of a Magnetic Forging Holder to Enhance Productivity for Industry 4.0 and Metaverse

Processes, Journal Year: 2023, Volume and Issue: 11(6), P. 1703 - 1703

Published: June 2, 2023

The concept of digital twinning is essential for smart manufacturing and cyber-physical systems to be connected the Metaverse. These representations physical objects can used real-time analysis, simulations, predictive maintenance. A combination manufacturing, Industry 4.0, Metaverse lead sustainable productivity in industries. This paper presents a practical approach implementing twins magnetic forging holder that was designed manufactured this project. Thus, makes two important contributions: first contribution holder, second significant creation its twin. benefits from special design implementation, making it user-friendly powerful tool materials research. More specifically, employed thermomechanical influencing structure and, hence, final properties under development. In addition, mechanism allows us produce new type creep-resistant composite material based on Fe, Al, Y. consolidates powder form solid state after mechanical alloying. We bars components using suitable process which extreme grain coarsening occurs heat treatment. one conditions achieving very high resistance creep at temperatures.

Language: Английский

---

A novel metering system consists of capacitance-based sensor, gamma-ray sensor and ANN for measuring volume fractions of three-phase homogeneous flows

Nondestructive Testing And Evaluation, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 27

Published: July 7, 2024

Measuring the volume fraction of different types fluids with two or three phases is so vital. Among all available methods, them, capacitance-based and gamma-ray attenuation, are popular widely used. Moreover, nowadays, AI which stands for Artificial Intelligence can be seen almost in areas, measuring section no exception. In this paper, main goal to predict a three-phase homogeneous fluid contains water, oil, gas materials. To opt an optimised method, combination sensors, attenuation sensor Neural Networks (ANN) utilised. train proposed metering system MLP type, inputs considered. For first input, concave simulated COMSOL Multiphysics software combinations (different fractions) applied. Then through theoretical investigations sensor, Barium-133 radiates 0.356 MeV This way, second required input generated. Finally, implement new accurate system, number networks characteristics run MATLAB software. The best structure had Mean Absolute Error (MAE) equal 0.33, 3.68 3.75 oil phases, respectively. accuracy presented illustrated by received outcomes. novelty study proposing combined method that measure fluid's fractions containing precisely.

Language: Английский

---

Regime independent flow rate prediction in a gas-liquid two-phase facility based on gamma ray technique and one detector using multi-feature extraction

Flow Measurement and Instrumentation, Journal Year: 2023, Volume and Issue: 92, P. 102388 - 102388

Published: May 8, 2023

Language: Английский

---

Reinforced covariance weighted mean of vectors optimizer: insight, diversity, deep analysis and feature selection

Applied Intelligence, Journal Year: 2024, Volume and Issue: 54(4), P. 3351 - 3402

Published: Feb. 1, 2024

Language: Английский

---

Salinity and flow pattern independent flow rate measurement in a gas-liquid flow with optimum feature selection and novel detection geometry using ANNs

Flow Measurement and Instrumentation, Journal Year: 2024, Volume and Issue: 97, P. 102605 - 102605

Published: May 1, 2024

Language: Английский

---

DEVELOPMENT OF ANALYTICAL EQUATIONS FOR VOID FRACTION IN BIPHASIC SYSTEMS USING GAMMA RADIATION AND MCNP6 CODE

Applied Radiation and Isotopes, Journal Year: 2024, Volume and Issue: 214, P. 111549 - 111549

Published: Oct. 10, 2024

Language: Английский

---

AI-Based Evaluation of Homogeneous Flow Volume Fractions Independent of Scale Using Capacitance and Photon Sensors

ARO-The Scientific Journal of Koya University, Journal Year: 2024, Volume and Issue: 12(2), P. 167 - 178

Published: Nov. 9, 2024

Metering fluids is critical in various industries, and researchers have extensively explored factors affecting measurement accuracy. As a result, numerous sensors methods are developed to precisely measure volume fractions multi-phase fluids. A significant challenge fluid pipelines the formation of scale within pipes. This issue particularly problematic petroleum industry, leading narrowed internal diameters, corrosion, increased energy consumption, reduced equipment lifespan, and, most crucially, compromised flow paper proposes non-destructive metering system incorporating an artificial neural network with capacitive photon attenuation address this challenge. The simulates thicknesses from 0 mm 10 using COMSOL multiphysics software calculates counted rays through Beer Lambert equations. simulation considers 10% interval variation each phase, generating 726 data points. proposed network, two inputs—measured capacity rays-and three outputs—volume gas, water, oil—achieves mean absolute errors 0.318, 1.531, 1.614, respectively. These results demonstrate system’s ability accurately gauge proportions three-phase gas-water-oil fluid, regardless pipeline thickness.

Language: Английский

---

Classical pressure profile prediction using a hybrid form of artificial neural network algorithm applied to building drainage systems

Building Services Engineering Research and Technology, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 26, 2024

Classical pressure profile data for building drainage systems (BDS) represent a temporal snapshot of the regime within system following an event such as water discharge from appliance, and therefore can be indicator performance. This research describes, first time, method predicting using FF(Feed Forward -PSO(Particle Swarm Optimization) artificial neural network (ANN) algorithm. The ANN model was validated against two sets data: dedicated 32-storey experimental test rig at National Lift Tower (NLT) facility in Northampton, UK, second set numerical model, AIRNET. Both were used to assess FF- PSO-ANN Model. Calculation errors minimized by refining weight vectors with PSO scheme. convergence algorithm managed through adjusted inertia weights, population size, damping factor, acceleration coefficients. A generic prediction developed database similar types configurations. refines trains enhancing its applicability across various applications. study confirms that FF-PSO effectively predicts BDS Practical application presented develops new approach which performance design stage. is based on philosophy natural search helps attain global optimisation vectors. It envisaged this form part assessment designs early stage provide useful information system. in-built learning allows accuracy improved existing profiles increases, thus making tool more relevant time.

Language: Английский

---