4.6 Article

A liquid loading prediction method of gas pipeline based on machine learning

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Artificial Intelligence

A distributed density estimation algorithm and its application to naive Bayes classification

Ahmad Khajenezhad et al.

Summary: The proposed nested Log-Poly model provides an accurate density estimation in a distributed setting by transferring small-sized statistics from client nodes to a central node for estimation. It is particularly suitable for one-dimensional density estimations and is a good choice for naive Bayes classifier.

APPLIED SOFT COMPUTING (2021)

Article Thermodynamics

A new skeletal mechanism for simulating MILD combustion optimized using Artificial Neural Network

Jicang Si et al.

Summary: This work developed a new skeletal mechanism of methane MILD combustion using the DRG-CSP-ANN method, which significantly outperformed other skeletal mechanisms in predicting autoignition time and flame propagation speed. The study highlighted the importance of mechanism optimization in reduction work for better predictions matching those by the detailed mechanism.

ENERGY (2021)

Article Energy & Fuels

A new transient model for hydrate slurry flow in oil-dominated flowlines

Guoyun Shi et al.

Summary: This study proposes a new transient model for gas hydrate slurry flow, which combines a two-fluid model and temperature equation for describing the two-phase flow and establishes equations for the particulate phase flow using Eulerian and Lagrangian approaches. The model is verified and applied to analyze the transient behavior of gas hydrate slurry multiphase flow, as well as conducting sensitivity analysis on flowrate, initial droplet size, and drag force. These results provide practical insight into hydrate slurry multiphase flow and contribute to better hydrate management in the petroleum industry.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2021)

Article Engineering, Industrial

Monte Carlo simulation using support vector machine and kernel density for failure probability estimation

Seunggyu Lee

Summary: In this study, a support vector machine was used as a metamodel to reduce the numerical cost of large numerical models in Monte Carlo simulations. A modified margin of the support vector machine was utilized for active learning, with the proportion in the design space serving as the criterion to end the learning process. The proposed method was successfully applied to various numerical examples in the study.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2021)

Article Energy & Fuels

A new transient model of multi-scale bubble migration and evolution during gas-liquid flow in pipelines

Sihang Chen et al.

Summary: This study investigated the migration and evolution of bubbles in oil-pipelines during gas-liquid flow, revealing that bubbles interact and migrate in multi-scales, affecting the transportation of both gas and liquid phases. A new transient model combined with the population balance model and Eulerian-Lagrangian coupling scheme was proposed to describe bubble movement and interaction. The results showed that the inclination of the pipe and liquid Froude number had a significant impact on bubble migration capacity and size distribution.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2021)

Article Energy & Fuels

Experimental measurement and modeling of water-based drilling mud density using adaptive boosting decision tree, support vector machine, and K-nearest neighbors: A case study from the South Pars gas field

Abbas Hashemizadeh et al.

Summary: Accurate prediction of mud weight is crucial for drilling operations, with ABR-DT and DT models showing the highest accuracy in estimating mud weight.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2021)

Article Computer Science, Artificial Intelligence

Electrical load forecasting: A deep learning approach based on K-nearest neighbors

Yunxuan Dong et al.

Summary: This study proposes a deep learning approach based on K-nearest neighbors to address the high computing costs and improve accuracy of electrical load forecasting. Experimental results demonstrate that the proposed method can enhance both forecasting efficiency and accuracy while simplifying the forecasting process.

APPLIED SOFT COMPUTING (2021)

Review Energy & Fuels

Status of Natural Gas Hydrate Flow Assurance Research in China: A Review

Bohui Shi et al.

Summary: This review discusses the significant progress in gas hydrate flow assurance research in China, including hydrate structures, management strategies, development of phase equilibrium models, and kinetics research. Additionally, the current research status and existing problems of hydrate slurry flow are analyzed, indicating significant room for improvement in accurate quantitative calculations and risk assessments.

ENERGY & FUELS (2021)

Article Green & Sustainable Science & Technology

Thermo-physical properties prediction of carbon-based magnetic nanofluids based on an artificial neural network

Lei Shi et al.

Summary: This study utilizes a neural network model to predict the thermophysical properties of magnetic nanofluids, demonstrating its accuracy compared to previous theoretical models and providing a theoretical basis for heat transfer.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2021)

Article Energy & Fuels

Decision tree-based optimization for flexibility management for sustainable energy microgrids

Yuchong Huo et al.

Summary: In this paper, a new method for generating microgrid energy dispatch rule base using decision trees is proposed to match the control performance of full mixed-integer optimization while achieving effectiveness and computational efficiency.

APPLIED ENERGY (2021)

Article Business, Finance

A firefly algorithm modified support vector machine for the credit risk assessment of supply chain finance

Hao Zhang et al.

Summary: This paper utilized the firefly algorithm support vector machine (FA-SVM) for supply chain financial evaluation, selected appropriate indicators for accurate credit risk assessment, and demonstrated the improvement in classification prediction compared to LIBSVM.

RESEARCH IN INTERNATIONAL BUSINESS AND FINANCE (2021)

Article Computer Science, Hardware & Architecture

Automatic detection of cyberbullying using multi-feature based artificial intelligence with deep decision tree classification

Natarajan Yuvaraj et al.

Summary: Recent studies have shown that cyberbullying is a rising youth epidemic. The paper introduces a novel automated classification model that identifies cyberbullying texts without fitting them into large dimensional space, addressing overfitting issues and improving classification accuracy. This study also develops a Deep Decision Tree classifier that utilizes hidden layers of Deep Neural Network for input processing.

COMPUTERS & ELECTRICAL ENGINEERING (2021)

Article Thermodynamics

Performance prediction of proton-exchange membrane fuel cell based on convolutional neural network and random forest feature selection

Weiwei Huo et al.

Summary: This paper utilizes deep learning techniques to design a performance prediction method for proton exchange membrane fuel cells, reducing unnecessary experiments and improving prediction accuracy to optimize performance. The proposed method combines random forest algorithm and convolutional neural networks, achieving good agreement with real data. This study demonstrates the effectiveness of using deep learning technologies for optimizing PEMFCs.

ENERGY CONVERSION AND MANAGEMENT (2021)

Article Engineering, Mechanical

Identification of gas-liquid two-phase flow patterns in a horizontal pipe based on ultrasonic echoes and RBF neural network

Fachun Liang et al.

Summary: This paper proposes a novel method for flow pattern identification using ultrasonic echo signals within the pipe wall, with experiments demonstrating that the attenuation of ultrasonic pulses varies between different flow patterns. An RBF neural network is constructed for online flow pattern identification, achieving an accuracy of 94.0% in identifying stratified flow, slug flow, and annular flow.

FLOW MEASUREMENT AND INSTRUMENTATION (2021)

Review Energy & Fuels

An improved model for predicting liquid loading onset in inclined pipes with non-uniform liquid wall films

Cleide Vieira et al.

Summary: This paper introduces a new model for predicting liquid loading onset in mature gas wells, which successfully reproduces experimental and field data with high prediction accuracy and low average error. The model represents a significant improvement on existing models in predicting liquid loading in gas wells, with restricted applicability to specific conditions.

JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING (2021)

Article Computer Science, Interdisciplinary Applications

An integrated MILP model for optimal planning of multi-period onshore gas field gathering pipeline system

Bingyuan Hong et al.

COMPUTERS & INDUSTRIAL ENGINEERING (2020)

Article Energy & Fuels

Droplet entrainment measurements under high-pressure two-phase low-liquid loading flow in slightly inclined pipes

H. T. Rodrigues et al.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2020)

Article Green & Sustainable Science & Technology

Performance improvement of empirical models for estimation of global solar radiation in India: A k-fold cross-validation approach

Sheikh Saud et al.

SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS (2020)

Article Engineering, Chemical

A new transient simulation method of natural gas-condensate two-phase flow in pipeline network

Guoyun Shi et al.

CHEMICAL ENGINEERING SCIENCE (2020)

Article Energy & Fuels

Automated coal petrography using random forest

Avinash Kumar Tiwary et al.

INTERNATIONAL JOURNAL OF COAL GEOLOGY (2020)

Article Computer Science, Interdisciplinary Applications

A methodology for the optimal design of gathering pipeline system in old oilfield during its phased development process

Guoxi He et al.

COMPUTERS & INDUSTRIAL ENGINEERING (2019)

Article Energy & Fuels

A predictive model for steady-state multiphase pipe flow: Machine learning on lab data

E. A. Kanin et al.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2019)

Article Engineering, Chemical

An integrated MILP method for gathering pipeline networks considering hydraulic characteristics

Bingyuan Hong et al.

CHEMICAL ENGINEERING RESEARCH & DESIGN (2019)

Article Energy & Fuels

An improved model for gas-liquid flow pattern prediction based on machine learning

Gene Mask et al.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2019)

Article Construction & Building Technology

Neural network and particle swarm optimization for predicting the unconfined compressive strength of cemented paste backfill

Chongchong Qi et al.

CONSTRUCTION AND BUILDING MATERIALS (2018)

Article Energy & Fuels

Measurements of local droplet velocities in horizontal gas-liquid pipe flow with low liquid loading

Netaji R. Kesana et al.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2018)

Article Energy & Fuels

A new model for improving the prediction of liquid loading in horizontal gas wells

Ruiqing Ming et al.

JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING (2018)

Article Energy & Fuels

Experimental investigation of oil-water two-phase flow in horizontal pipes: Pressure losses, liquid holdup and flow patterns

Ahmad Shamsul Izwan Ismail et al.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2015)

Article Mechanics

Investigation of two-phase flow pattern, liquid holdup and pressure drop in viscous oil-gas flow

Hatef A. Khaledi et al.

INTERNATIONAL JOURNAL OF MULTIPHASE FLOW (2014)

Article Economics

Socio-economic status and z-score standardized height-for-age of US-born children (ages 2-6)

Brian Karl Finch et al.

ECONOMICS & HUMAN BIOLOGY (2011)