检索结果-内蒙古大学图书馆

Integrative numerical modeling and thermodynamic optimal design of counter-flow plate-fin heat exchanger applying neural networks

引用

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER 2020年 159卷 120097-120097页

作者： Richter do Nascimento, Carlos Augusto Mariani, Viviana Cocco Coelho, Leandro dos Santos Pontificia Univ Catolica Parana Dept Mech Engn Curitiba Parana Brazil Univ Fed Parana Dept Elect Engn Curitiba Parana Brazil Pontificia Univ Catolica Parana Ind & Syst Engn Grad Program Curitiba Parana Brazil

In this study, an optimization technique combined with a random vector functional link (RVFL) network in the form of a surrogate-assisted approach was carried out for the optimal design of counter-flow plate-fin compact heat exchanger (PFHE) with offset-strip fins considering different mass flow rates. Computational Fluid Dynamics (CFD) simulations generated dataset for training and testing by RVFL network, reducing processing time and assuring PFHE accuracy when applied in many-objective optimization based on Non-Dominated Sorting Genetic Algorithm III (NSGA-III). Next, the NSGA-III was designed to achieve the maximum effectiveness, minimum volume, and pressure drop at the hot and cold sides in PFHE design. For experimental validation the Shear Stress Transport (SST) k-omega turbulence model was used to simulate the flow and heat transfer in PFHE showing 4.36% and 3.27% of error, respectively, to pressure drop and convective heat transfer coefficient measurements. The optimized results by NSGA-III indicated that the volume and effectiveness values are in agreement with the literature, decreasing approximately 55.4% and 72.3% of pressure drop at the hot and cold sides, respectively, which showed that the convective heat transfer was enhanced and the flow resistance was also significantly reduced. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Plate-fin heat exchanger Offset-strip fin Many-objective optimization Non-dominated sorting genetic algorithm random vector functional link network Effectiveness

来源：评论

学校读者我要写书评

暂无评论

Privileged information-driven random network based non-iterative integration model for building energy consumption prediction

引用

APPLIED SOFT COMPUTING 2021年 108卷 107438-107438页

作者： Sun, Hongchang Zhai, Wenwen Wang, Yugang Yin, Lei Zhou, Fengyu Shandong Univ Sch Control Sci & Engn Jinan 250061 Shandong Peoples R China Shandong Dawei Int Architecture Design Co LTD Inst Intelligent Buildings Jinan 250101 Shandong Peoples R China

Accurate building energy consumption (BEC) prediction plays an increasingly significant role in energy control and conservation. However, owing to the high level of randomness of BEC data, acquiring accurate prediction results is difficult. To further enhance the predicted precision and robustness, we herein present a non-iterative decomposition-integration model to realise BEC prediction. Our proposed method merges the ensemble empirical mode decomposition (EEMD), learning using a privileged information (LUPI) paradigm-based random vector functional link network (RVFL+), and support vector regression (SVR) to generate satisfactory results. In this model, EEMD is first adopted for the decomposition of historical energy consumption data. Subsequently, the decomposed subsignals are input into the RVFL+ network, and the features of high correlation with BEC are selected as privileged information to constrain the weight of the output layer of RVFL+ network in order to obtain their corresponding output RVFL+ models of each subsignal. Finally, the resulting RVFL+ output models are aggregated and input into the SVR model to acquire the prediction results, thereby breaking through the limitation of the single-prediction model and improving prediction accuracy. To verify our proposed model, five actual BEC datasets were employed for experiments: Jinan in China, Fairbanks and California in the USA, Vancouver in Canada, and Sydney in Australia. Experiment results indicated that our proposed EEMD-RVFL+-SVR method had better accuracy and anti-noise performance. Specially, the mean absolute percentage error of the proposed method, compared with the EMD-SVR, EEMD-SVR, EEMD-PSO-GA-SVR, EEMD-RVFL, ARIMA-SVM, FLS-SVM, EMD-RVFL+-SVR, CEEMD-RVFL+-SVR, SVR, RVFL, RVFL+, BPNN, and Wavelet neural network, was reduced by 65.07%, 37.20%, 40.61%, 52.27%, 44.66%, 34.76%, 50.01%, 39.06%, 43.04%, 53.77%, 46.38%, 41.82% and 56.14% respectively. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Ensemble empirical mode decomposition Learning using privileged information random vector functional link network Support vector regression Building energy consumption prediction

来源：评论

学校读者我要写书评

暂无评论

Reliability of velocity-deviation logs for shale content evaluation in clastic reservoirs: a case study, Egypt

引用

ARABIAN JOURNAL OF GEOSCIENCES 2021年第6期14卷 507-507页

作者： Nabih, Muhammad Zagazig Univ Dept Geol Fac Sci Zagazig 44519 Egypt

The shale content is important in reservoir quality evaluation. There are good relations between effective porosity, permeability, and shale content in clastic rocks. One of the main objectives of the velocity-deviation log is that it could indicate permeability qualitatively. The velocity-deviation logs could be calculated from density and neutron porosity logs in carbonate rocks. The velocity deviation calculated from the density log is more reliable than that from neutron log in various clastic rocks to assess its validity in shale volume estimation. This study is carried out in clastic reservoirs drilled by four wells from different hydrocarbon fields in various. Three wells act as train wells and the fourth one is used as a test well. The regression analysis method is used to show the effectiveness of the relationships between the different velocity deviations using density and neutron logs. The relations of the three train wells clarify that there are excellent reliable relations in case of the density log and poor in case of the neutron log. This may be attributed to the effects of hydrogen in shale lattice leading to erroneously overestimated neutron porosity. The correlation coefficients between the compiled three studied train wells and velocity deviation from density porosity log are high and good with very dependable relations. Shale content can be predicted from density velocity-deviation log by using these excellent relationships. The deduced equation is used to predict shale content in the fourth testing well with excellent reliability. The shale content is estimated by the random vector functional link (RVFL) network method to evaluate the predicted results. The matching between the three curves of V-sh, V-sh (VDd), and V-sh (RVFL) is very good with standard errors of V-sh (VDd) and V-sh (RVFL) are 0.13 and 0.17, respectively, which clarify that the two methods are close to each other.

关键词： Velocity-deviation log Shale content Neutron porosity log Density porosity log Sonic porosity log random vector functional link network

来源：评论

学校读者我要写书评

暂无评论

Multi-objective optimization and machine learning for the temperature distribution measurement using acoustic tomography

引用

Applied Thermal Engineering 2025年 277卷

作者： Yan Li Jing Lei Siyuan Ren Shaanxi Coal Industry New Energy Technology Co. Ltd. Chang’an District Xi’an 710100 Shaanxi China School of Energy Power and Mechanical Engineering North China Electric Power University Changping District Beijing 102206 China School of Electronic and Control Engineering North China Institute of Aerospace Engineering Langfang 065000 Hebei China

The limited accuracy of reconstruction restricts the practical application of acoustic tomography in temperature distribution measurement. To alleviate this challenge, this study focuses on transforming reconstruction methodology by introducing a novel temperature distribution reconstruction method to mitigate the challenges posed by insufficient measurement information and inaccurate model. In the first stage, a multi-objective reconstruction model is established to reconstruct a preliminary temperature distribution. This model addresses measurement inaccuracies and model uncertainties, integrates the low-rank prior, and automatically balances the data fidelity term and the regularization term, thereby alleviating the challenge of selecting regularization parameters. In the second stage, the multi-objective random vector functional link network is proposed to infer the fine temperature distribution. This new multi-objective optimization learning engine addresses uncertainties in data and model, integrates the sparsity prior of the weight vector, overcomes the challenge of parameter tuning, and enhances the model’s robustness and generalization performance. The performance evaluation results confirm that, in comparison to widely-used reconstruction algorithms, the proposed reconstruction method not only achieves innovation in the reconstruction paradigm but also improves reconstruction accuracy and robustness. This new reconstruction methodology fuses measurement physics, machine learning, and multi-objective optimization, providing new perspectives for designing more effective reconstruction algorithms and unleashing the potential of acoustic tomography.

关键词： Acoustic tomography Multi-objective optimization reconstruction model random vector functional link network Temperature distribution measurement

来源：评论

学校读者我要写书评

暂无评论

Ensemble Neural networks with random Weights for Classification Problems 20

Ensemble Neural Networks with Random Weights for Classificat...

引用

Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence

作者： Ye Liu Weipeng Cao Zhong Ming Qiang Wang Jiyong Zhang Zhiwu Xu Shenzhen University China Southern University of Science and Technology China Hangzhou Dianzi University China

ISBN: (纸本)9781450388115

To improve the prediction accuracy and stability of neural networks with random weights (NNRWs), we propose a novel ensemble NNRWs (E-NNRW) in this paper, which initializes its base learners by different distributions to improve their diversity. The final prediction results of the E-NNRW model are determined by these base learners through a voting mechanism, which minimizes the specific "blind zone" of a single learner, thus achieving higher prediction accuracy and better stability. Taking the random vector functional link network (RVFL), one of the most representative algorithms in NNRWs, as an example, we fully evaluate the performance of the proposed algorithm on nine benchmark classification problems. Extensive experimental results fully demonstrate the effectiveness of our method.

关键词： randomized neural networks random vector functional link network Neural networks with random weights ensemble learning

来源：评论

学校读者我要写书评

暂无评论

An unsupervised parameter learning model for RVFL neural network

引用

NEURAL networkS 2019年 112卷 85-97页

作者： Zhang, Yongshan Wu, Jia Cai, Zhihua Du, Bo Yu, Philip S. China Univ Geosci Sch Comp Sci Wuhan 430074 Hubei Peoples R China Macquarie Univ Dept Comp Fac Sci & Engn Sydney NSW 2109 Australia Wuhan Univ Sch Comp Sci Wuhan 430072 Hubei Peoples R China Univ Illinois Dept Comp Sci Chicago IL 60607 USA

With the direct input-output connections, a random vector functional link (RVFL) network is a simple and effective learning algorithm for single-hidden layer feedforward neural networks (SLFNs). RVFL is a universal approximator for continuous functions on compact sets with fast learning property. Owing to its simplicity and effectiveness, RVFL has attracted significant interest in numerous real-world applications. In reality, the performance of RVFL is often challenged by randomly assigned network parameters. In this paper, we propose a novel unsupervised network parameter learning method for RVFL, named sparse pre-trained random vector functional link (SP-RVFL for short) network. The proposed SP-RVFL uses a sparse autoencoder with l(1)-norm regularization to adaptively learn superior network parameters for specific learning tasks. By doing so, the learned network parameters in SP-RVFL are embedded with the valuable information of input data, which alleviate the randomly generated parameter issue and improve the algorithmic performance. Experiments and comparisons on 16 diverse benchmarks from different domains confirm the effectiveness of the proposed SP-RVFL. The corresponding results also demonstrate that RVFL outperforms extreme learning machine (ELM). (C) 2019 Elsevier Ltd. All rights reserved.

关键词： random vector functional link network randomized feedforward neural networks Autoencoder l(1)-norm regularization Pre-trained parameters Classification applications

来源：评论

学校读者我要写书评

暂无评论

An Initial Study on the Relationship Between Meta Features of Dataset and the Initialization of NNRW

An Initial Study on the Relationship Between Meta Features o...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Cao, Weipeng Patwary, Muhammed J. A. Yang, Pengfei Wang, Xizhao Ming, Zhong Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen Peoples R China Univ Chinese Acad Sci CAS Inst Software State Key Lab Comp Sci Beijing Peoples R China

ISBN: (纸本)9781728119854

The initialization of neural networks with random weights (NNRW) has a significant impact on model performance. However, there is no suitable way to solve this problem so far. In this paper, the relationship between meta features of a dataset and the initialization of NNRW is studied. Specifically, we construct seven regression datasets with known attributes' distributions, then initialize NNRW with different distributions and trained them based on the datasets to get the corresponding models respectively. The relationship between the attributes' distributions of the datasets and the initialization of NNRW is analyzed by the performance of the models. Several interesting phenomena are observed: firstly, initializing NNRW with the Gaussian distribution can help the model to have a faster convergence rate than ones with the Gamma and Uniform distribution. Secondly, if one or more attributes in a dataset that follow the Gamma distribution, using Gamma distribution to initialize NNRW may result in a slower convergence rate and easy overfitting. Thirdly, initializing NNRW with a specific distribution with smaller variances can always achieve faster convergence rate and better generalization performance than the one with larger variances. The above experimental results are not sensitive to the activation function and the type of NNRW. Some theoretical analyses about the above observations are also given in the study.

关键词： Neural networks with random weights extreme learning machine random vector functional link network meta feature

来源：评论

学校读者我要写书评

暂无评论

Ensemble Neural networks with random Weights for Classification Problems

Ensemble Neural Networks with Random Weights for Classificat...

引用

作者： Ye Liu Weipeng Cao Zhong Ming Qiang Wang Jiyong Zhang Zhiwu Xu College of Computer Science and Software Engineering Shenzhen University Department of Computer Science and Engineering Southern University of Science and Technology School of Automation Hangzhou Dianzi University

To improve the prediction accuracy and stability of neural networks with random weights(NNRWs), we propose a novel ensemble NNRWs(E-NNRW) in this paper, which initializes its base learners by different distributions to improve their diversity. The final prediction results of the E-NNRW model are determined by these base learners through a voting mechanism, which minimizes the specific "blind zone" of a single learner, thus achieving higher prediction accuracy and better stability. Taking the random vector functional link network(RVFL), one of the most representative algorithms in NNRWs, as an example, we fully evaluate the performance of the proposed algorithm on nine benchmark classification *** experimental results fully demonstrate the effectiveness of our method.

关键词： Neural networks with random weights random vector functional link network ensemble learning randomized neural networks

来源：评论

学校读者我要写书评

暂无评论

A randomized-algorithm-based decomposition-ensemble learning methodology for energy price forecasting

引用

ENERGY 2018年 157卷 526-538页

作者： Tang, Ling Wu, Yao Yu, Lean Beihang Univ Sch Econ & Management Beijing 100191 Peoples R China Beijing Univ Chem Technol Sch Econ & Management Beijing 100029 Peoples R China

Inspired by the interesting idea of randomization, some powerful but time-consuming decomposition-ensemble learning paradigms can be extended into extremely efficient and fast variants by using randomized algorithms as individual forecasting tools. In the proposed methodology, Three major steps, (1) data decomposition via ensemble empirical mode decomposition, (2) individual prediction via a randomized algorithm (using randomization to mitigate training time and parameter sensitivity), and (3) results ensemble to produce final prediction, are included. Different from other existing decomposition-ensemble models using traditional econometric approaches or computational intelligence methods in individual prediction, this study employs some emerging randomized algorithms-extreme learning machine, random vector functional link network (using randomly fixed weights and bias in neural networks), and random kitchen sinks (using randomly mapping features to approximate kernels)-to dramatically save computational time and enhance prediction accuracy. With the Brent oil prices and the Henry Hub natural gas prices as studying samples, the empirical study statistically confirms that the proposed randomized-algorithm-based decomposition-ensemble learning models are proved to be excellently efficient and fast, relative to popular single techniques (including computational intelligence methods and randomized algorithms) and similar decomposition-ensemble counterparts (using the aforementioned single techniques as individual forecasting tools). (C) 2018 Elsevier Ltd. All rights reserved.

关键词： Decomposition-ensemble learning methodology randomized algorithm Energy price forecasting Extreme learning machine random vector functional link network random kitchen sinks

来源：评论

学校读者我要写书评

暂无评论

A non-iterative decomposition-ensemble learning paradigm using RVFL network for crude oil price forecasting

引用

APPLIED SOFT COMPUTING 2018年 70卷 1097-1108页

作者： Tang, Ling Wu, Yao Yu, Lean Beihang Univ Sch Econ & Management Beijing 100191 Peoples R China Beijing Univ Chem Technol Sch Econ & Management Beijing 100029 Peoples R China

To address time consuming and parameter sensitivity in the emerging decomposition-ensemble models, this paper develops a non-iterative learning paradigm without iterative training process. Different from the most existing decomposition-ensemble models using statistical or iterative approaches as individual forecasting tools, the proposed work otherwise employs the efficient and fast non-iterative algorithm random vector functional link (RVFL) network with randomly fixed weights and direct input-output links. Three major steps are included: decomposition via ensemble empirical mode decomposition (EEMD), prediction via RVFL network, and ensemble via linear addition. With crude oil price as studying sample, the proposed EEMD-based RVFL network performs significantly better in terms of prediction accuracy than not only single algorithms such as RVFL network, extreme learning machine (ELM), kernel ridge regression, random forest, back propagation neural network, least square support vector regression, and autoregressive integrated moving average, but also their respective EEMD-based ensemble variants. As for speed ranking, RVFL network developed in 1994 ranks the first among all the listed methods, and EEMD-based RVFL network defeats all the ensemble methods and most single methods, possibly due to the fact that RVFL network with direct input-output links needs far less enhancement nodes and hence a shorter computational time than those without the direct links such as the ELM developed in 2006. (C) 2017 Elsevier B.V. All rights reserved.

关键词： Decomposition and ensemble Non-iterative learning Fast algorithm random vector functional link network Time series forecasting Crude oil price

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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：