检索结果-内蒙古大学图书馆

Novel strategies based on a gradient boosting regression tree predictor for dynamic multi-objective optimization

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartC期237卷

作者： Gao, Kai Xu, Lihong Tongji Univ Coll Elect & Informat Engn Shanghai 201804 Peoples R China Michigan State Univ BEACON Ctr Study Evolut Act E Lansing MI 48824 USA

Prediction-based dynamic multiobjective optimization evolutionary algorithms have become one of the main-stream methods for solving dynamic multiobjective optimization problems. However, the unknown nonlinear relationships in sequential environments bring great challenge to the construction of prediction model and the inevitable error between the historical obtained solutions and the real pareto-optimal solutions troubles the prediction accuracy. In this paper, a gradient boosting regression tree based dynamic multiobjective optimization evolutionary algorithm is proposed, called MOEA/D-XGB. The time series solutions formed by subspace decomposition are trained in the XGBoost-based predictor to produce a high-quality initial population when environmental change occurs. And a novel population promotion strategy based on generalized additive model is proposed to improve the quality of historical obtained solutions. The performance comparisons with five state-of-the-art algorithms have shown that MOEA/D-XGB achieves best performance in 59 out of 70 experiments on MIGD and 60 out of 70 experiments on MHV, respectively, which demonstrates that the proposed design is capable of significantly improving the performance of dynamic multiobjective optimization.

关键词： Dynamic multiobjective optimization Evolutionary algorithm Predictor gradient boosting regression tree Population promotion strategy

来源：评论

学校读者我要写书评

暂无评论

gradient boosting regression tree Optimized with Slime Mould Algorithm to Predict the Higher Heating Value of Municipal Solid Waste

引用

ENERGIES 2024年第17期17卷 4213页

作者： Shehab, Esraa Q. Taha, Farah Faaq Muhodir, Sabih Hashim Imran, Hamza Ostrowski, Krzysztof Adam Piechaczek, Marcin Univ Diyala Coll Engn Dept Civil Engn Baqubah 32001 Iraq Cihan Univ Erbil Dept Architectural Engn Erbil 44001 Iraq Al Karkh Univ Sci Dept Construct & Projects Baghdad 10081 Iraq Cracow Univ Technol Fac Civil Engn Warszawska 24 PL-31155 Krakow Poland

The production of municipal solid waste (MSW) has led to an unprecedented level of environmental pollution, worsening the global challenges posed by climate change. Researchers and policymakers have recently made significant strides in the field of sustainable and renewable energy sources, which are viable from technological, environmental, and economic perspectives. Consequently, the waste-to-energy programs enhance nations' socioeconomic status while positively impacting the environment. To predict the higher heating value (HHV) of MSW fuel based on carbon, hydrogen, oxygen, nitrogen, and sulfur content, the current study introduces a gradient boosting regression tree (GBRT) model optimized with the Slime Mold Algorithm (SMA). This model was evaluated using an additional 50 data points after being trained with 202 MSW biomass data points. The performance of the model was assessed using three metrics: root mean square error (RMSE), mean absolute error (MAE), and the coefficient of determination (R2). The results indicated that our model outperformed previously developed models in terms of accuracy and reliability. Additionally, a graphical user interface (GUI) was developed to facilitate the practical application of the model, allowing users to easily input data and receive predictions on the enthalpy of the combustion of MSW fuel.

关键词： gradient boosting regression tree machine learning municipal solid waste higher heating value

来源：评论

学校读者我要写书评

暂无评论

Prediction of home energy consumption based on gradient boosting regression tree

引用

ENERGY REPORTS 2021年 7卷 1246-1255页

作者： Nie, Peng Roccotelli, Michele Fanti, Maria Pia Ming, Zhengfeng Li, Zhiwu Xidian Univ Sch Electromech Engn Xian 710071 Peoples R China Polytech Univ Bari I-70125 Bari Italy Macau Univ Sci & Technol Inst Syst Engn Taipa 999078 Macao Peoples R China

Energy consumption prediction of buildings has drawn attention in the related literature since it is very complex and affected by various factors. Hence, a challenging work is accurately estimating the energy consumption of buildings and improving its efficiency. Therefore, effective energy management and energy consumption forecasting are now becoming very important in advocating energy conservation. Many researchers work on saving energy and increasing the utilization rate of energy. Prior works about the energy consumption prediction combine software and hardware to provide reasonable suggestions for users based on the analyzed results. In this paper, an innovative energy consumption prediction model is established to simulate and predict the electrical energy consumption of buildings. In the proposed model, the energy consumption data is more accurately predicted by using the gradient boosting regression tree algorithm. By comparing the performance index Root Mean Square Error of different prediction models through experiments it is shown that the proposed model obtains lower values on different testing data. More detailed comparison with other existing models through experiments show that the proposed prediction model is superior to other models in energy consumption prediction. (C) 2021 The Authors. Published by Elsevier Ltd.

关键词： Energy management Energy consumption gradient boosting regression tree Data prediction

来源：评论

学校读者我要写书评

暂无评论

Prediction of higher heating value of coal based on gradient boosting regression tree model

引用

INTERNATIONAL JOURNAL OF COAL GEOLOGY 2023年第1期274卷

作者： Xu, Na Wang, Zhiwei Dai, Yuchen Li, Qiang Zhu, Wei Wang, Ru Finkelman, Robert B. China Univ Min & Technol Beijing Coll Geosci & Survey Engn Beijing 100083 Peoples R China Columbia Univ Grad Sch Architecture Planning Preservat New York NY 10027 USA Univ Texas Dallas Richardson TX 75080 USA

Higher heating value, also known as the coal calorific value, is an important indicator of coal quality. Nevertheless, traditional experimental determination of higher heating value is expensive, tedious, and timeconsuming. Some regression models have been commonly used to solve this problem. However, the prediction accuracy still needs to be improved. Accordingly, based on the correlation between proximate analysis of coal and higher heating value, a gradient boosting regression tree model was established in this study to predict the higher heating value as a means to a less intensive procedure to estimate coal heating values. This approach used data from the U.S. Geological Survey Coal Quality database and Kentucky Coal Database to evaluate coal quality. The hyperparameters of the regression tree model were tuned by cross-validation. A comparative study was conducted between the model established in this paper and the existing methods. Experimental results indicate that the coefficient of determination of the gradient boosting regression tree model of two databases achieves 0.9862 and 0.9541, respectively. Thus, the prediction capability of the gradient boosting regression tree model outperforms the existing methods.

关键词： Coal Higher heating value gradient boosting regression tree Proximate analysis

来源：评论

学校读者我要写书评

暂无评论

Analysing the determinants of the Turkish household electricity consumption using gradient boosting regression tree

引用

ENERGY FOR SUSTAINABLE DEVELOPMENT 2023年 77卷

作者： Guven, Denizhan Kayalica, M. Ozgur Istanbul Tech Univ Eurasia Inst Earth Sci Istanbul Turkiye Istanbul Tech Univ Energy Inst Istanbul Turkiye ITU Eurasia Inst Earth Sci Ayazaga Campus TR-34469 Istanbul Turkiye

Residential buildings are the second largest electricity consumer in Turkey. Thus, the goal here is to detect the factors that determine the electricity consumption of the households in Turkey using the Household Budget Survey (HBS). This study applies Decision tree (DT), Random Forest (RF) and gradient Boosted regression tree (GBRT) methods. Since the GBRT method provides the lowest Root Mean Squared Error (RMSE), the impact of each variable on the electricity consumption is analysed with this method. The most critical determinant is found to be the household size, while income level and heating type are discovered as 2nd and 3rd most prominent determinants for household electricity demand. With the help of the Partial Dependence Plots (PDP) provided by the GBRT method, the impact of each categorical and continuous variable is presented. Using the results of PDPs, the monetary values of both electricity generation and the social cost of CO2 emissions emitted into the atmosphere due to electricity generation are calculated for the most important determinants.

关键词： Household electricity demand Household Budget Survey Social cost of Carbon gradient boosting regression tree Machine Learning Turkey

来源：评论

学校读者我要写书评

暂无评论

Fatigue life prediction of concrete under cyclic compression based on gradient boosting regression tree

引用

MATERIALS AND STRUCTURES 2023年第9期56卷 172-172页

作者： Liang, Gui-Qin Chen, Xuan Jiang, Bing-Yu Jiang, Chun-Song Guilin Univ Technol Coll Informat Sci & Engn Guangxi Key Lab Green Bldg Mat & Construct Industr Guilin 541004 Peoples R China Guilin Univ Aerosp Technol Audit Div Guilin 541004 Peoples R China Guilin Univ Technol Coll Environm Sci & Engn Guilin 541004 Peoples R China Guilin Univ Technol Coll Civil & Architecture Engn Guilin 541004 Peoples R China

With the development of reinforced concrete bridges, the fatigue problem of concrete has attracted extensive attention. Failure occurs when concrete is subjected to cyclic compression that is less than the static compressive strength of concrete after a certain amount of cyclic loading (fatigue life). Compared to traditional methods with shortage of low accuracy, resulting uncertain safety problem, to address this issue, we utilized gradient boosting regression tree (GBRT) and multiple linear regression (MLR) to predict the fatigue life of concrete under repeated compression based on the collated 275 sets of experimental data. All prediction results were compared with that calculated by the existing European codes. Results analysis reveal that both proposed GBRT and MLR models have lower errors and higher correlation coefficients than that of existing formula/code models. Furthermore, the prediction accuracy of the GBRT model can be improved by using the existing classical formulas to reconstruct the features and selecting suitable features by ranking the feature importance, without increasing the number of features. Experimental results reveal that GBRT model can achieve the best performance with lowest RMSE and highest R2. Moreover, the sensitivity analysis revealed that the proposed GBRT model is insensitive to input characteristics of fatigue life, which can be used for accurate calculation and design analysis of concrete compressive fatigue life, providing important reference value for formulating concrete technical design specification based on fatigue life.

关键词： Fatigue life Concrete Cyclic compression Multiple linear regression gradient boosting regression tree

来源：评论

学校读者我要写书评

暂无评论

Prediction of Ecofriendly Concrete Compressive Strength Using gradient boosting regression tree Combined with GridSearchCV Hyperparameter-Optimization Techniques

引用

MATERIALS 2022年第21期15卷 7432-7432页

作者： Alhakeem, Zaineb M. Jebur, Yasir Mohammed Henedy, Sadiq N. Imran, Hamza Bernardo, Luis F. A. Hussein, Hussein M. Iraq Univ Coll Comp Engn Dept Basrah 61004 Iraq Al Mustaqbal Univ Coll Bldg & Construct Techn Engn Dept Hillah 51001 Iraq Mazaya Univ Coll Dept Civil Engn Nasiriya City 64001 Iraq Alkarkh Univ Sci Coll Energy & Environm Sci Dept Environm Sci Baghdad 10081 Iraq Univ Beira Interior Ctr Mat & Bldg Technol C MADE Dept Civil Engn & Architecture P-6201001 Covilha Portugal Hilla Univ Coll Med Phys Dept Babylon Iraq

A crucial factor in the efficient design of concrete sustainable buildings is the compressive strength (Cs) of eco-friendly concrete. In this work, a hybrid model of gradient boosting regression tree (GBRT) with grid search cross-validation (GridSearchCV) optimization technique was used to predict the compressive strength, which allowed us to increase the precision of the prediction models. In addition, to build the proposed models, 164 experiments on eco-friendly concrete compressive strength were gathered for previous researches. The dataset included the water/binder ratio (W/B), curing time (age), the recycled aggregate percentage from the total aggregate in the mixture (RA%), ground granulated blast-furnace slag (GGBFS) material percentage from the total binder used in the mixture (GGBFS%), and superplasticizer (kg). The root mean square error (RMSE) and coefficient of determination (R-2) between the observed and forecast strengths were used to evaluate the accuracy of the predictive models. The obtained results indicated that-when compared to the default GBRT model-the GridSearchCV approach can capture more hyperparameters for the GBRT prediction model. Furthermore, the robustness and generalization of the GSC-GBRT model produced notable results, with RMSE and R-2 values (for the testing phase) of 2.3214 and 0.9612, respectively. The outcomes proved that the suggested GSC-GBRT model is advantageous. Additionally, the significance and contribution of the input factors that affect the compressive strength were explained using the Shapley additive explanation (SHAP) approach.

关键词： gradient boosting regression tree machine learning SHAP eco-friendly concrete compressive strength prediction

来源：评论

学校读者我要写书评

暂无评论

Lifespan prediction of lithium-ion batteries based on various extracted features and gradient boosting regression tree model

引用

JOURNAL OF POWER SOURCES 2020年 476卷 228654-228654页

作者： Yang, Fangfang Wang, Dong Xu, Fan Huang, Zhelin Tsui, Kwok-Leung City Univ Hong Kong Sch Data Sci Hong Kong Peoples R China Shanghai Jiao Tong Univ State Key Lab Mech Syst & Vibrat Shanghai 200240 Peoples R China

Accurate battery lifespan prediction is critical for the quality evaluation and long-term planning of battery management systems. As battery degradation process is typically nonlinear, accurate early prediction of cycle life with significantly less degradation is extremely challenging. Approaches using machine learning techniques, which are mechanism-agnostic alternatives, to predict battery lifespan are therefore becoming more and more attractive. In this paper, a gradient boosting regression tree (GBRT) is proposed to model complex nonlinear battery dynamics and predict battery lifespan through various extracted battery features. Essentially, the GBRT works by constructing additional trees through minimizing the prediction residues from existing base models. It can identify complex and nonlinear end-to-end relationship and meanwhile provide relative importance for each input feature. Various potential features including voltage-related features, capacity-related features, and temperature-related features are constructed in both discharge time dimension and life cycle dimension and explored for effective lifespan prediction. Key hyper-parameters including learning rate, number of trees, and maximum number of splits are investigated for optimal GBRT prediction. Comparative studies confirm that the proposed method is significantly superior to other machine learning algorithms for battery lifespan prediction with limited data samples and various input features, with mean average percentage error around 7%.

关键词： Lifespan prediction Lithium-ion batteries Machine learning gradient boosting regression tree Feature extraction

来源：评论

学校读者我要写书评

暂无评论

The energy efficiency prediction method based on gradient boosting regression tree 2

The energy efficiency prediction method based on Gradient Bo...

引用

2nd IEEE Conference on Energy Internet and Energy System Integration (EI2)

作者： Ma, Hongwei Yang, Xin Mao, Jianrong Zheng, Hao XJ Grp Corp R&D Ctr Beijing Peoples R China

ISBN: (纸本)9781538685495

The prediction of building energy efficiency is the key technology in building integrated energy management services. The results of energy efficiency prediction directly reflect the changes of energy efficiency of buildings under the current management level and management strategy. Data analysis can provide guidance for improving management level and adjusting management strategy. Firstly, according to the characteristics of building energy efficiency, an algorithm model of gradient-lifting regression tree is constructed;then, a method of building energy efficiency prediction based on gradient boosting regression tree model is designed, which is based on a large number of historical data, and established through feature extraction and iterative learning. To satisfy the operational requirements of the model, the first and two derivative of the customized objective function are defined. Finally, the predicted results are explained and analyzed by using LIME with an example, which provides a basis for the formulation of alternative strategy and the improvement of energy efficiency management level.

关键词： Integrated energy building energy efficiency gradient boosting regression tree

来源：评论

学校读者我要写书评

暂无评论

Application of PCA-GBRT/RF model for predicting heat flux on boiler water-cooled wall

引用

APPLIED THERMAL ENGINEERING 2025年 273卷

作者： Yang, Jiahui Jiang, Chongjun Li, Ruiyu Sun, Yi An, Hong Deng, Lei Che, Defu Xi An Jiao Tong Univ Sch Energy & Power Engn State Key Lab Multiphase Flow Power Engn Xian 710049 Peoples R China China Petr Univ Beijing Beijing Peoples R China Guangdong Inst Special Equipment Inspection & Res Shunde Inst Inspect Foshan 528300 Peoples R China Tsinghua Univ Dept Thermal Engn Key Lab Thermal Sci & Power Engn Minist Educ Beijing 100084 Peoples R China

Monitoring the heat flux on the water-cooled wall is essential for ensuring the safe operation of coal-fired boilers. The Computational Fluid Dynamics (CFD) method is employed to gather heat flux data on water-cooled walls under various boiler operations in this study. The heat flux data for 660 regions of the water-cooled wall under 38 operating conditions has been obtained. The Principal Component Analysis (PCA) method is adopted as the dimensionality reduction method, followed by training gradient boosting regression trees (GBRT) and Random Forest (RF) models. The number of principal components after dimensionality reduction (k), the maximum depth of the tree (m), and the number of trees (n) are taken as optimization indicators. For GBRT and RF, the optimal combinations of (k, m, n) are (14, 5, 110) and (13, 13, 60), respectively. At this point, the correlation coefficient (r) values of the models on the test set are 0.872 and 0.859, respectively. The goodness of fit (R2) values are 0.760 and 0.732, respectively. By performing a weighted average of the two models in a 3:1 ratio and calibration with actual measured data, the r and R2 values can be increased to 0.874 and 0.808. The combined model demonstrates superior performance relative to artificial neural network (ANN), exhibiting increases of 0.059 in r and 0.140 in R2, coupled with 24.7% and 24.3% reductions in mean absolute error (MAE) and root mean square error (RMSE), respectively. The model achieves a computational efficiency of 1.675 s per operating condition while maintaining accuracy validated against measurements, demonstrating its practicality.

关键词： Heat flux Water-cooled wall gradient boosting regression tree Random forest Computational fluid dynamics Principal component analysis

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：