检索结果-内蒙古大学图书馆

Hydrocarbon production dynamics forecasting using machine learning: A state-of-the-art review

FUEL 2023年第1期337卷

作者： Liang, Bin Liu, Jiang You, Junyu Jia, Jin Pan, Yi Jeong, Hoonyoung Southwest Petr Univ State Key Lab Oil & Gas Reservoir Geol & Exploitat Chengdu 610500 Peoples R China Chongqing Univ Sci & Technol Chongqing 401331 Peoples R China Res Inst Petr Explorat & Dev Beijing 100086 Peoples R China Seoul Natl Univ Res Inst Energy & Resources Inst Engn Res Dept Energy Syst Engn Seoul 08826 South Korea

Accurate prediction of hydrocarbon production is crucial for the oil and gas industry. However, the strong heterogeneity of underground formation, the inconsistency in oil-gas-water distribution, and the complex flow mechanisms make hydrocarbon production forecasting (HPF) difficult, which leads to a high level of uncertainty in the prediction results. The explosion of machine learning (ML) methodologies that are capable of analyzing big data shed new light on HPF using production data. In this article, an in-depth review is provided regarding HPF using ML methodologies. Firstly, the merits and drawbacks of traditional HPF methods are analyzed and summarized. Then, the applications of ML algorithms in HPF are reviewed in detail, especially concentrating on artificial neural network, support vector machine, and ensemble learning. For each algorithm, the basic theory and its variants are first introduced, and its applications in HPF are comprehensively demonstrated subsequently. Finally, this article presents the challenge and prospects of machine-learning-based HPF. Sophisticated ML proxy models can be con-structed and employed to deal with an extended type of input data such that improving the efficacy of data utilization. On the other hand, deep learning models designed to handle time-series data can gain more attention. Modeling approaches for multivariate time-series hydrocarbon production data using deep neural networks with similar functionality to LSTM may lead to more accurate and computationally efficient production forecasting.

关键词： AI Artificial intelligence ANN Artificial neural network SVM Support vector machine DCA Decline curve analysis MFNN Multilayer feed-forward neural networks MLP Multilayer perceptron BP back propagation algorithm DNN Deep neural network LSTM Long short-term memory GAN Generative adversarial network CNN Convolutional neural network FCNN Fully connected neural network RNN Recurrent neural network BPANN back propagation artificial neural network NN Neural network cDC-GAN Conditional deep convolutional generative neural network CONV-1D 1D convolutional neural network GA Genetic algorithm DE Differential evolution SA Simulated annealing GSA Gravitational search algorithm PSO Particle swarm optimization MPA Marine predator algorithm ICA Imperialist competitive algorithm LM Levenberg Marquardt BRA Bayesian regularization algorithm MNN Multiple-neural-network HONN Higher-order neural network HOSO Higher-order synaptic operations MLMVN Multilayer neural network with multi-valued neurons DLSTM Deep long-short term memory EEMD Ensemble empirical mode decomposition FNN Feed-forward neural network BFGS Quasi-newton algorithm ORF Oil recovery factor GOR Gas oil ratio ADAM Adaptive moment estimation method WOPR well oil production rate SGD stochastic gradient descent SVR Support vector regression LSSVM Least squares support vector machine RSM Response surface method LR Linear regression RF Random forest AdaBoost Adaptive boosting GBDT Gradient boosting decision tree GBM Gradient-boosting machine MORF Multi-objective random forest GBT Gradient boosting tree PCA Principal component analysis RREE Reverse recursive feature elimination

来源：评论

学校读者我要写书评

暂无评论

Random input based prediction and transfer of heat in soil temperature using artificial neural network

Random input based prediction and transfer of heat in soil t...

引用

International Conference on Advances in Materials Research (ICAMR)

作者： Jebamalar, S. Christopher, Jaslin J. Ajisha, M. Angelina Thanga Nesamony Mem Christian Coll Dept Phys Marthandam 629165 India MS Univ Constituent Coll Dept Chem Palkulam 629401 India Francis Xavier Engn Coll Dept Civil Engn Tirunelveli 627003 India

The soil temperature affects the climate in a great manner and the soil temperature data can be used to make predictions about how the ecosystem is affected by heat or cold in global temperature. Various measurement techniques have been employed in analyzing the soil temperature. Among them, Artificial Neural Network (ANN) is used to perform mathematical formulation to learn patterns and relationships in the data. The present study provides a tool to predict the soil temperature for the year 2004 using random inputs taken between 1993 and 2003 under different cases at two different soil depths 10 cm and 20 cm using ANN. The analysis was carried out for both the annual and the seasonal waves. Thereby, heat gets depleted during the monsoon seasons and gets accumulated in the annual and the other season which help to study the atmospheric changes. The statistical validation of the predictions possesses an insignificant error when compared with that of the observed soil temperature. (c) 2021 Elsevier Ltd. All rights reserved. Selection and peer-review under responsibility of the scientific committee of the International Conference on Advances in Materials Research-2019.

关键词： Soil temperature Artificial neural network Seasonal variation back propagation algorithm Statistical validation

来源：评论

学校读者我要写书评

暂无评论

Using 2W-PE method based on machine learning to accurately predict field strength distribution in flat-top obstacle environment

引用

AEU-INTERNATIONAL JOURNAL OF ELECTRONICS AND COMMUNICATIONS 2022年 144卷

作者： Li Anqi Yin Chengyou Zhang Qianqian Natl Univ Def Technol Coll Elect Engn Hefei 230037 Anhui Peoples R China

A new two-way parabolic equation (2W-PE) method is proposed in this paper which uses machine learning to determine boundary condition equations, and accurately predicts the electromagnetic field strength distribution in the environment of media ground and obstacles. On the basis of previous researches, the obstacle area is decomposed according to the principle of domain decomposition, and the processes of solving 2W-PE in each subdomain are briefly explained. Because the direction and strength of the incident waves on the boundaries vary greatly with the propagation environment, it is difficult for us to determine boundary condition equations. The machine learning method is introduced here, and method of moments (MoM) is applied to generate sample data sets, thus, coefficients in boundary condition equations can be trained through the non-end-to-end neural network combined with backpropagation algorithm and gradient descent method. So that no matter how the environment changes, appropriate boundary conditions can be obtained by the well-trained neural network and help improving the accuracy of 2W-PE. Simulation results show that the accuracy of the new 2W-PE method based on machine learning is better than that of 2W-PE with traditional boundary conditions by comparing with the results of MoM, which also reflects the advantages of machine learning in radio wave propagation analysis. Therefore, this paper provides an innovative and reliable method for accurately predicting field distribution in flat-top obstacle environments.

关键词： Two-way parabolic equation Machine learning Artificial neural network back propagation algorithm Surface impedance boundary condition Field strength prediction

来源：评论

学校读者我要写书评

暂无评论

Prediction of aging of battery for electric vehicles based on a modified version of neural networks 29

Prediction of aging of battery for electric vehicles based o...

引用

29th Mediterranean Conference on Control and Automation (MED)

作者： Hemdani, Jamila Soltani, Moez Telmoudi, Achraf Jabeur Chaari, Abdelkader Univ Tunis Natl Higher Engn Sch Tunis ENSIT Lab Ingn Syst Ind & Energies Renouvelables LISIER Tunis Tunisia

ISBN: (纸本)9781665422581

The battery is the key element to store and then supply electricity to the various components of Electric Vehicles (EV). However, the battery cannot be charged and discharged indefinitely. The main objective of this study is to develop a novel methodology for estimation of the ageing rate of a Lithium-Fer-Phosphate (LFP) battery used in electric vehicles in order to predict its Remaining Useful Life (RUL). Indeed, a new method based a modified version of neural networks is proposed. It is used to estimate the LFP battery's Discharge Capacity (DC) and to conclude about the battery's end of life.

关键词： Lithium-Fer-Phosphate batteries artificial neural networks electric vehicles back propagation algorithm discharge capacity remaining useful life

来源：评论

学校读者我要写书评

暂无评论

Predicting the solution of fractional order differential equations with Artificial Neural Network

引用

Partial Differential Equations in Applied Mathematics 2024年 10卷

作者： Khan, A.M. Gaur, Sanjay Suthar, D.L. Department of Mathematics Jodhpur Institute of Engineering & Technology Jodhpur Rajasthan India Department of Electronics & Communication Engineering Jodhpur Institute of Engineering & Technology Jodhpur Rajasthan India Department of Mathematics Wollo University Ethiopia

The present paper aims to propose an approximation method of Caputo fractional operator using discretization based on quadrature theory to minimize the error function for an Artificial Neural Network (ANN) with higher convergence rate. In the proposed work authors have verified the suitability of multilayer feed forward ANN architecture to get an estimated solution of fractional order differential equations. The back propagation algorithm and an unsupervised learning, was imposed in order to minimize the error function including the optimizing the network parameters such as weights of synapses and the biases. The algorithm uses truncated power series to replace the unknown function in the fractional differential equations. The novelty of the present work is an approximation of a fractional operator using discretization based on quadrature theory to construct an error function to provide an appropriate estimated solution of the nonlinear fractional differential equations. Four illustrative examples with different orders of nonlinear fractional differential equations are unraveled to approve the validity of the model along with demonstration of effectiveness and fast convergence of the proposed method. © 2024 The Authors

关键词： Approximation using quadrature method back propagation algorithm Caputo fractional derivative operator Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Method of Short-Circuit Fault Diagnosis in Transmission Line Based on Deep Learning

引用

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 2022年第5期36卷

作者： Li, Tong Zhao, Hai Zhou, Xiaoming Zhu, Shidong Yang, Zheng Yang, Hongping Liu, Wei Zhou, Zhenliu Northeastern Univ Shenyang 110819 Liaoning Peoples R China State Grid Liaoning Elect Power Supply Co Ltd Elect Power Res Inst Shenyang 110004 Liaoning Peoples R China State Grid Liaoning Elect Power Supply Co Ltd Shenyang 110004 Liaoning Peoples R China Shenyang Inst Engn Shenyang 110136 Liaoning Peoples R China Shenyang LIGONG Univ Shenyang 110159 Liaoning Peoples R China

It is important to locate the fault distance and identify the fault types quickly, take effective measures to maintain line stability, and minimize the losses timely when there are short-circuit faults in transmission lines. For this purpose, a method based on deep learning is proposed for short-circuit faults identification in the transmission line. According to the similarity of samples in the reconstruction phase, a minimum neighborhood sample set is selected from the massive samples firstly, and then, the samples are trained using the back propagation algorithm along time in a recurrent neural network (RNN) with long-short term memory (LSTM) units. Compared with existing algorithms, the experimental results show that this algorithm meets the requirements of rapid fault diagnosis in the case of variable parameters, and higher fault type recognition accuracy and lower fault distance error can be obtained.

关键词： Short-circuit fault diagnosis deep learning recurrent neural network back propagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Log-sum enhanced sparse deep neural network

引用

NEUROCOMPUTING 2020年 407卷 206-220页

作者： Qiao, Chen Shi, Yan Diao, Yu-Xian Calhoun, Vince D. Wang, Yu-Ping Xi An Jiao Tong Univ Sch Math & Stat Xian 710049 Peoples R China Georgia State Univ Triinst Ctr Translat Res Neuroimaging & Data Sci Georgia Inst Technol Atlanta GA 30303 USA Emory Univ Atlanta GA 30303 USA Tulane Univ Dept Biomed Engn New Orleans LA 70118 USA Tulane Univ Ctr Genom & Bioinformat New Orleans LA 70112 USA

How to design deep neural networks (DNNs) for the representation and analysis of high dimensional but small sample size data is still a big challenge. One solution is to construct a sparse network. At present, there exist many approaches to achieve sparsity for DNNs by regularization, but most of them are carried out only in the pre-training process due to the difficulty in the derivation of explicit formulae in the fine-tuning process. In this paper, a log-sum function is used as the regularization terms for both the responses of hidden neurons and the network connections in the loss function of the fine-tuning process. It provides a better approximation to the L-0-norm than several often used norms. Based on the gradient formula of the loss function, the fine-tuning process can be executed more efficiently. Specifically, the commonly used gradient calculation in many deep learning research platforms, such as PyTorch or TensorFlow, can be accelerated. Given the analytic formula for calculating gradients used in any layer of DNN, the error accumulated from successive numerical approximations in the differentiation process can be avoided. With the proposed log-sum enhanced sparse deep neural network (LSES-DNN), the spar-sity of the responses and the connections can be well controlled to improve the adaptivity of DNNs. The proposed model is applied to MRI data for both the diagnosis of schizophrenia and the study of brain developments. Numerical experiments demonstrate its superior performance among several classical classifiers tested. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Deep neural network Log-sum enhanced sparsity back propagation algorithm Concise gradient formula Magnetic resonance imaging.

来源：评论

学校读者我要写书评

暂无评论

An application of Artificial Neural Network solution in the apparel industry for Job distribution to subcontractors

引用

ADVANCES IN ENGINEERING SOFTWARE 2022年 174卷

作者： Mumcu, Yelda Karatepe Kayar, Mahmut Bulur, Oyku Ceren Marmara Univ Vocat Sch Tech Sci Dept Elect Educ Istanbul Turkey Marmara Univ Tech Educ Fac Dept Text Educ Istanbul Turkey Marmara Univ Inst Pure & Appl Sci Departent Text Engn Istanbul Turkey

In this study, the results of the work distribution made with the TOPSIS method, which is frequently used in the distribution of work to the subcontractor workshops, were estimated using the Artificial Neural Networks Method (ANN). Here, the C* values used in the work distribution with the TOPSIS method were estimated by ANN. The correlation coefficient of the data obtained from the created model was found to be 99.99895% for learning. According to the results, it has been concluded that work distribution can be made by using the ANN method without making complex mathematical calculations in the distribution of work to the contract workshops.

关键词： Apparel industry Artificial Neural Network back propagation algorithm TOPSIS Job distribution Multi Criteria Decision Making (MCDM)

来源：评论

学校读者我要写书评

暂无评论

Control of DSTATCOM Using ANN-BP algorithm for the Grid Connected Wind Energy System

引用

ENERGIES 2022年第19期15卷 6988-6988页

作者： Irfan, Mohammad Mujahid Malaji, Sushama Patsa, Chandrashekhar Rangarajan, Shriram S. Hussain, S. M. Suhail Jawaharlal Nehru Technol Univ Dept Elect & Elect Engn Hyderabad 500085 Telangana India SR Univ Dept Elect & Elect Engn Warangal 506371 Telangana India Mahatma Gandhi Inst Technol Dept Elect & Elect Engn Hyderabad 500075 Telangana India Clemson Univ Dept Elect & Comp Engn Clemson SC 29634 USA King Fahd Univ Petr & Minerals KFUPM Elect Engn Dept Dhahran 31261 Saudi Arabia

Green energy sources are implemented for the generation of power due to their substantial advantages. Wind generation is the best among renewable options for power generation. Generally, the wind system is directly connected with the power network for supplying power. In direct connection, there is an issue of managing power quality (PQ) concerns such as voltage sag, swells, flickers, harmonics, etc. In order to enhance the PQ in a power network with a wind energy conversion system (WECS), peripheral compensation is needed. In this paper, we highlight a novel control technique to improve the PQ in WECS by adopting an Artificial Neural Network (ANN)-based Distribution Static Compensator (DSTATCOM). In our proposed approach, an online learning-based ANN back propagation (BP) model is used to generate the gate pulses of the DSTATCOM, which mitigate the harmonics at the grid side. It is modelled using the MATLAB platform and the total harmonic distortion (THD) of the system is compared with and without DSTATCOM. The harmonics at the source side decreased to less than 5% and are within the IEEE limits. The results obtained reveal that the proposed online learning-based ANN-BP is superior in nature.

关键词： wind energy conversion system ANN back propagation algorithm power quality total harmonic distortion

来源：评论

学校读者我要写书评

暂无评论

Thermal performance investigation of the miniature revolving heat pipes using artificial neural networks and genetic algorithms

引用

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER 2020年第0期151卷 119394-000页

作者： Liang, Feng Gao, Jianmin Xu, Liang Xi An Jiao Tong Univ State Key Lab Mfg Syst Engn Xian 710054 Peoples R China Guangdong Xian Jiaotong Univ Acad Foshan 528300 Guangdong Peoples R China

The miniature revolving heat pipes (MRVHPs) are promising candidates for the cooling structure design of rotating machines, however, the relation between the thermal performance of MRVHPs and their thermo-physical properties is still absent. Therefore, MRVHPs are tested in various operational conditions firstly. And then, a power-law empirical correlation is developed based on experimental data, Ku, Ja, Pr, Bo and Fr are determined as main effective dimensionless parameters, phi while the structural parameters of MRVHPs D-i/R, L-e/L-c, L-e/L-eff and filling ratio yo are considered as well. However, the prediction accuracy is not satisfactory enough. Considering ANNs have been widely used in varied applications and demonstrated to be particularly credible in system modeling and identification, therefore, a BPNN model which parameterized by GA is developed for thermal performance prediction of the MRVHPs. The experimental data are divided into training data set and testing data set. Ja, Pr, Bo, Fr and phi are regarded as inputs, while Ku is output. The results show that the established GA-BPNN model could predict thermal performance of MRVHPs with a very good accuracy. Comparing with the predicted results of semi-empirical correlation, the square of correlation coefficient (R-2) is increased by 13.265%. Meanwhile, the evaluation method for the optimal filling ratio of the MRVHPs under specified working conditions is developed and an acceptable accuracy is obtained. (C) 2020 Published by Elsevier Ltd.

关键词： Miniature revolving heat pipes Thermal performance forecasting Artificial neural networks back propagation algorithm Genetic algorithm Optimal filling ratio estimation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：