检索结果-内蒙古大学图书馆

Towards energy and material efficient laser cladding process: Modeling and optimization using a hybrid TS-GEP algorithm and the NSGA-II

引用

JOURNAL OF CLEANER PRODUCTION 2019年 227卷 58-69页

作者： Peng, Shitong Li, Tao Zhao, Jiali Lv, Shengping Tan, George Z. Dong, Mengmeng Zhang, Hongchao Dalian Univ Technol Inst Sustainable Design & Mfg Dalian Peoples R China Lanzhou Univ Technol Sch Mech & Elect Engn Lanzhou Gansu Peoples R China South China Agr Univ Coll Engn Guangzhou Guangdong Peoples R China Texas Tech Univ Dept Ind Mfg & Syst Engn Lubbock TX 79409 USA

The soaring global additive manufacturing (AM) market implies considerable potentials of energy and material savings. However, very few researches have addressed the energy and material efficiency issue in AM process through processing parameters optimization. In this study, we developed a predictive model of specific energy consumption (SEC) and metallic powder usage rate in laser cladding process. Three approaches were adopted to perform the modeling, namely, basic gene expression programming (GEP), response surface methodology (RSM), and integrated Tabu search and GEP (TS-GEP). Comparison amongst these methods revealed that TS-GEP demonstrated the highest fitting performance in terms of the root mean square deviation (RMSD) and coefficient of determination (R-2). The experimental validation showed that TS-GEP enabled high robustness and precision of the modeling even though the accuracy of prediction was slightly lower than that of RSM in some cases. Analysis of variance was conducted to examine the contribution of the processing parameters. Results presented that the dominating factor was powder feed rate followed by laser power, Z-increment, and scanning speed irrespective of the interactive effects. With the predictive models, the Pareto front was determined by non-dominated sorting genetic algorithm II (NSGA-II) to provide the optimal set of processing parameters for the maximization of energy and metallic powder efficiency. This study would facilitate appropriate parameter selection of laser cladding process and assist the sustainable manufacturing in AM domain. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： Parameter optimization Additive manufacturing gene expression programming Tabu search Multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

Impact of climate variation and human activities on groundwater quality in northwest of Iran

引用

JOURNAL OF WATER SUPPLY RESEARCH AND TECHNOLOGY-AQUA 2019年第2期68卷 121-135页

作者： Khalaj, M. Kholghi, M. Saghafian, B. Bazrafshan, J. Islamic Azad Univ Sci & Res Branch Tech & Engn Fac Dept Civil Engn Tehran Iran Univ Tehran Agr & Nat Resource Coll Dept Irrigat & Reclamat Engn Karaj Iran

Groundwater plays a significant role in domestic, agricultural, and industrial water supply in semi-arid regions. In such areas, rapid growth of population and water demand in conjunction with climate change negatively impacts groundwater quantity and quality. In this research, human activities and climate change effects on groundwater quality in a semi-arid region was studied. First, a numerical groundwater model was calibrated as a tool for simulating an aquifer system. Then, groundwater salinity, as a measure of water quality, was simulated using the gene expression programming 'GEP' algorithm. In order to identify major factors influencing the salinity, the grey relational analysis (GR) technique was adopted. Furthermore, in the case study of Mahabad aquifer in northwestern Iran, decreasing precipitation has reduced river flow and aquifer recharge. Crop pattern change, through groundwater exploitation and irrigation return flow, impacted groundwater quality. Changes in temperature, evaporation and crop water requirement has also influenced the surface water-groundwater budget in the region. Groundwater simulations showed a decreasing trend in groundwater level while GEP analysis demonstrated that groundwater electrical conductivity (EC) increased over the past 40 years. Finally, GRA application showed that groundwater withdrawal and agricultural return flow had the highest correlation with increasing EC, compared with the effect of precipitation and temperature as climatic factors.

关键词： climate variation gene expression programming grey relational analysis groundwater quality Mahabad Valley

来源：评论

学校读者我要写书评

暂无评论

Presentation of a new hybrid approach for forecasting economic growth using artificial intelligence approaches

引用

NEURAL COMPUTING & APPLICATIONS 2019年第12期31卷 8661-8680页

作者： Ahmadi, Mohsen Jafarzadeh-Ghoushchi, Saeid Taghizadeh, Rahim Sharifi, Abbas UUT Dept Ind Engn POB 57166-419 Orumiyeh Iran

This study presents a new hybrid algorithm for forecasting economic growth using indicators of knowledge-based economy (KBE). The algorithm consists of three steps, namely preprocessing, processing, and postprocessing. Preprocessing consists of principal component analysis and reproduction algorithm, which are used to decrease the number of variables and increase the volume of data. Economic growth is predicted during processing using multilayer perceptron (MLP), adaptive neuro-fuzzy inferences system, and gene expression programming (GEP). The variables are added separately to the process. The best model is selected during the postprocessing step to forecast economic growth. GEP model is used to forecast unique indicators. The last step involves substitution of forecasted indicators in the best model. In this study, the KBE indicators of Iran from 1993 to 2013 are predicted in the processing step. The MLP model is used, which includes four indicators, namely technological foundation, structure of trained manpower, export and trademark, and employee. Indicators are also forecasted using the GEP model between 2013 and 2020. The results are used to estimate economic growth between forecasting periods. A self-organizing map is used to recognize relationships between variables. The results show the efficiency of the algorithm in multivariate forecasting.

关键词： Hybrid forecasting Artificial neural network gene expression programming Economy growth

来源：评论

学校读者我要写书评

暂无评论

GEP-based predictive modeling of breathing resistances of wearing respirators on human body via sEMG and RSP sensors

引用

SENSOR REVIEW 2019年第4期39卷 439-448页

作者： Chen, Yumiao Yang, Zhongliang East China Univ Sci & Technol Sch Art Design & Media Shanghai Peoples R China Donghua Univ Coll Mech Engn Shanghai Peoples R China

Purpose Breathing resistance is the main factor that influences the wearing comfort of respirators. This paper aims to demonstrate the feasibility of using the gene expression programming (GEP) for the purpose of predicting subjective perceptions of breathing resistances of wearing respirators via surface electromyography (sEMG) and respiratory signals (RSP) sensors. Design/methodology/approach The authors developed a physiological signal monitoring system with a specific garment. The inputs included seven physical measures extracted from (RSP) and (sEMG) signals. The output was the subjective index of breathing resistances of wearing respirators derived from the category partitioning-100 scale with proven levels of reliability and validity. The prediction model was developed and validated using data collected from 30 subjects and 24 test combinations (12 respirator conditions x 2 motion conditions). The subjects evaluated 24 conditions of breathing resistances in repeated measures fashion. Findings The results show that the GEP model can provide good prediction performance (R-2 = 0.71, RMSE = 0.11). This study demonstrates that subjective perceptions of breathing resistance of wearing respirators on the human body can be predicted using the GEP via sEMG and RSP in real-time, at little cost, non-invasively and automatically. Originality/value This is the first paper suggesting that subjective perceptions of subjective breathing resistances can be predicted from sEMG and RSP sensors using a GEP model, which will remain helpful to the scientific community to start further human-centered research work and product development using wearable biosensors and evolutionary algorithms.

关键词： Breathing resistances gene expression programming Respirators Respiratory signals Surface electromyography

来源：评论

学校读者我要写书评

暂无评论

Identification of Physical Processes via Data Driven Methods

Identification of Physical Processes via Data Driven Methods

引用

作者： Vaddireddy, Harsha Vardhan Reddy Oklahoma State University

学位级别：M.S.

Extracting governing equations from data can be viewed as reverse engineering of Nature- using data to identify the physical laws/models. This approach is crucial for fields where data is abundant ( such as geophysical flows, finance, and neuroscience) but the physical laws based on the first principles are not available. In recent years, the use of machine learning (ML) methods complemented the need for formulating mathematical models through the application of data analysis algorithms that allow accurate estimation of observed dynamics by learning automatically from the given observations. The neural networks and symbolic regression (SR) based approaches are the most popular ML frameworks used to learn the underlying physical process by only the observing data. While neural network approaches have shown great promise, its black-box nature makes it difficult to interpret the learned models. On the other hand, symbolic regression algorithms are capable of learning/finding an analytically tractable function in symbolic form. Hence to address the functional expressibility, a key limitation of the black-box machine learning methods, this study has explored the use of symbolic regression approaches for identifying relations and operators that accurately represent the underlying physical processes. This study demonstrates the use of an evolutionary algorithm called gene expression programming (GEP) and a sparse optimization algorithm called sequential threshold ridge regression (STRidge) in discovering physical models. The effectiveness of these algorithms is demonstrated on four different applications: (1) partial differential equation (PDE) discovery, (2) truncation error analysis, (3) hidden physics discovery and (4 ) discovering subgrid-scale closure models. This study shows the GEP and STRidge algorithms are able to distill various linear/nonlinear PDEs, truncation error terms and unknown source terms of 1D and 2D PDEs. Furthermore, the classical Smagorinsky model i

关键词： compressive sensing gene expression programming model discovery neural networks sparse regression symbolic regression

来源：评论

学校读者我要写书评

暂无评论

Estimation of discharge with free overfall in rectangular channel using artificial intelligence models

引用

FLOW MEASUREMENT AND INSTRUMENTATION 2019年第0期67卷 118-130页

作者： Jahanpanah, Edris Khosravinia, Payam Sanikhani, Hadi Kisi, Ozgur Univ Kurdistan Agr Fac Water Sci & Engn Dept Sanandaj Iran Ilia State Univ Fac Nat Sci & Engn Tbilisi Georgia

In open channels, free overfall can be used as a flow-measuring device in various flow regimes for different shapes of channels. The aim of this paper is to accurately estimate the discharge in rectangular channels by applying four soft computing models [i.e., artificial neural network (ANN), gene expression programming (GEP), multivariate adaptive regression spline (MARS) and M5 tree model]. The variables including brink depth, roughness coefficient, channel width and channel bed slope taken from earlier published works were used as inputs for the models. Data were divided according to three different splitting scenarios, 50%-50%, 60%-40% and 75%-25%, for training-testing phases to obtain more robust evaluation of the models. The computed discharges were then compared with experimental results. In order to evaluate the accuracy of discharge estimations by ANN, GEP, MARS and M5 tree models, six statistical measures including correlation coefficient (R), mean absolute error (MAE), root mean square error (RMSE), Nash-Sutcliffe (NS), Willmott index (WI) and Legates and McCabe index (LMI) have been applied. For different training-testing scenarios, the performance of the ANN model is better than the other methods. Regarding 50%-50% training-testing scenario, ANN has the best accuracy with R, RMSE, MAE, NS, WI and LMI of 0.994, 0.004 m(3)/s/m, 0.002 m(3)/s/m, 0.986, 0.999 and 0.909 by considering all inputs.

关键词： Discharge Artificial neural network gene expression programming Multivariate adaptive regression spline M5 tree model

来源：评论

学校读者我要写书评

暂无评论

Exploring the value of machine learning for weighted multi-model combination of an ensemble of global hydrological models

引用

ENVIRONMENTAL MODELLING & SOFTWARE 2019年 114卷 112-128页

作者： Zaherpour, Jamal Mount, Nick Gosling, Simon N. Dankers, Rutger Eisner, Stephanie Gerten, Dieter Liu, Xingcai Masaki, Yoshimitsu Schmied, Hannes Mueller Tang, Qiuhong Wada, Yoshihide Univ Nottingham Sch Geog Sir Clive Granger Bldg Nottingham NG7 2RD England Met Off FitzRoy Rd Exeter EX1 3PB Devon England Univ Kassel Ctr Environm Syst Res Wilhelmshoher Allee 47 D-34109 Kassel Germany Potsdam Inst Climate Impact Res D-14473 Potsdam Germany Humboldt Univ Dept Geog D-10099 Berlin Germany Chinese Acad Sci Inst Geog Sci & Nat Resources Res Key Lab Water Cycle & Related Land Surface Proc Beijing Peoples R China Hirosaki Univ Bunkyocho 3 Hirosaki Aomori 0368561 Japan Goethe Univ Frankfurt Inst Phys Geog Altenoferallee 1 D-60438 Frankfurt Germany Senckenberg Biodivers & Climate Res Ctr SBiK F Senckenberganlage 25 D-60325 Frankfurt Germany IIASA Schlosspl 1 A-2361 Laxenburg Austria Norwegian Inst Bioecon Res POB 115 N-1431 As Norway

This study presents a novel application of machine learning to deliver optimised, multi-model combinations (MMCs) of Global Hydrological Model (GHM) simulations. We exemplify the approach using runoff simulations from five GHMs across 40 large global catchments. The benchmarked, median performance gain of the MMC solutions is 45% compared to the best performing GHM and exceeds 100% when compared to the ensemble mean (EM). The performance gain offered by MMC suggests that future multi-model applications consider reporting MMCs, alongside the EM and intermodal range, to provide end-users of GHM ensembles with a better contextualised estimate of runoff. Importantly, the study highlights the difficulty of interpreting complex, non-linear MMC solutions in physical terms. This indicates that a pragmatic approach to future MMC studies based on machine learning methods is required, in which the allowable solution complexity is carefully constrained.

关键词： Machine learning Model weighting gene expression programming Global hydrological models Optimisation

来源：评论

学校读者我要写书评

暂无评论

Modeling reference evapotranspiration in island environments: Assessing the practical implications

引用

JOURNAL OF HYDROLOGY 2019年 570卷 265-280页

作者： Shiri, Jalal Univ Tabriz Dept Water Engn Fac Agr Tabriz Iran

Among the reference evapotranspiration (ETo) equations, temperature-based and radiation-based equations have been accepted as promising approaches when the available meteorological data are limited. The present paper aimed at assessing this general implication in island environments, which might be generally volatile than the interior/coastal zones. Using data from five island locations of Iran, daily ETo values were calculated by the benchmark FAO-Penman-Monteith (FAO56-PM) model, then the commonly used temperature-, radiation- and mass transfer-based ETo equations were evaluated against the benchmark values. An additional heuristic modeling of ETo was also performed through employing gene expressions programming (GEP), evaluated by k-fold testing. The obtained outcomes showed that the calibrated mass transfer-based equations and their corresponded GEP models generally surpassed the other applied models in the studied locations. This criticized the commonly accepted implication about applying temperature/radiation-based models in case of data scarcity for different locations. Nevertheless, analysis of the temporal variations of models performance among test years showed that fixing the minimum test size as 1 year for local k-fold testing (that is the case in similar studies) might be misleading as it could not show the fluctuations in modeling accuracy well. A minimum affordable size of at least one growing season was instead selected, tested and recommended in the current research.

关键词： Evapotranspiration gene expression programming Island PCA analysis

来源：评论

学校读者我要写书评

暂无评论

A Resource Aware Parallelized Back Propagation Neural Network in Enabling Efficient Large-Scale Digital Health Data Processing

引用

IEEE ACCESS 2019年 7卷 114700-114713页

作者： Liu, Yang Chen, Xianbang Xu, Lixiong Li, Huaqiang Li, Maozhen Sichuan Univ Coll Elect Engn Chengdu 610065 Sichuan Peoples R China Brunel Univ London Dept Elect & Comp Engn Uxbridge UB8 3PH Middx England

Along with the development of digital health, efficient machine learning is anxiously needed to handle the growing health data. Among various machine learning algorithms, back propagation neural network (BPNN) shows great effectiveness in both academia and industrial fields. However, it is frequently reported that the conventional BPNN algorithm encounters low efficiency issue in dealing with large-scale digital health data. Therefore this paper presents a Hadoop based parallelized BPNN algorithm which is able to process the large-scale data efficiently. In order to complement the potential accuracy loss issue for the parallelized data processing, ensemble learning techniques are also involved. Additionally although Hadoop supplies a number of default schedulers, the heterogeneous distributed computing environment may still impact the efficiency of the parallelized BPNN. Consequently, this paper also presents a gene expression programming (GEP) algorithm based load balancing approach, which enables the computing resource awareness and the optimal scheduling of the parallelized BPNN. The experiments employ the classification task as the underlying testing basis. Two types of the experiments are carried out, in which the first one focuses on evaluating the accuracy of the presented algorithm with classifying the benchmark dataset;the second one focuses on evaluating the efficiency of the presented algorithm with classifying the large-scale dataset. The experimental results show the effectiveness of the presented resource aware parallelized BPNN algorithm.

关键词： Back propagation neural network parallelization Hadoop load balancing gene expression programming

来源：评论

学校读者我要写书评

暂无评论

CSE: Complex-Valued System With Evolutionary Algorithm

引用

IEEE ACCESS 2019年 7卷 90268-90276页

作者： Yang, Bin Wang, Guan Bao, Wenzheng Chen, Yuehui Jia, Lina Zaozhuang Univ Sch Informat Sci & Engn Zaozhuang 277160 Peoples R China Xuzhou Univ Technol Sch Informat & Elect Engn Xuzhou 221018 Jiangsu Peoples R China Univ Jinan Sch Informat Sci & Engn Jinan 250022 Shandong Peoples R China

Complex-valued system identification has the ability to provide the basis for system analysis. So as to demonstrate the potential and internal mechanism of the complex-valued system, this paper proposes a novel complex-valued hybrid evolutionary (CSE) algorithm to optimize the complex-valued expression model (CEM). Complex-valued gene expression programming (CVGEP) is proposed to optimize the architectures of the CEM. Complex-valued water wave optimization (CVWWO) is first proposed to optimize complex-valued coefficients and constants of the CEM. The two artificial complex-valued function approximation problems and non-minimum phase equalization problem are utilized to test the performance of the proposed algorithm. The results demonstrate that this method could identify complex-valued systems more correctly than complex-valued neural networks, which could obtain above 90% smaller mean-squared error (MSE) performance than other complex-valued models. With 10% Gaussian white noise, the CSE could identify accurate complex-valued structure and parameters containing coefficients and constants. The CVWWO has better convergence performance than complex-valued particle swarm optimization and crow search algorithm.

关键词： Complex-valued expression model gene expression programming water wave optimization

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：