检索结果-内蒙古大学图书馆

Predicting specific wear rate of laser powder bed fusion AlSi10Mg parts at elevated temperatures using machine learning regression algorithm: Unveiling of microstructural morphology analysis

引用

JOURNAL OF MATERIALS RESEARCH AND TECHNOLOGY-JMR&T 2024年 33卷 3684-3695页

作者： Jatti, Vijaykumar S. Krishnan, R. Murali Saiyathibrahim, A. Preethi, V. Priyadharshini, G. Suganya Kumar, Abhinav Sharma, Shubham Islam, Saiful Kozak, Drazan Lozanovic, Jasmina Symbiosis Int Univ Symbiosis Inst Technol Dept Mech Engn Pune 412115 India Chandigarh Univ Univ Ctr Res & Dev Chandigarh 140413 Punjab India Coimbatore Inst Technol Dept Mech Engn Coimbatore 641014 Tamil Nadu India Ural Fed Univ Dept Nucl & Renewable Energy Boris Yeltsin 19 Mira St Ekaterinburg 620002 Russia Karpagam Acad Higher Educ Dept Mech Engn Coimbatore 641021 India Karpagam Acad Higher Educ Ctr Energy & Environm Coimbatore 641021 India Western Caspian Univ Dept Tech Sci Baku Azerbaijan Chitkara Univ Inst Engn & Technol Ctr Res Impact & Outcome Rajpura 140401 Punjab India Qingdao Univ Technol Sch Mech & Automot Engn Qingdao 266520 Peoples R China King Khalid Univ Coll Engn Civil Engn Dept Abha 61421 Saudi Arabia Univ Slavonski Brod Mech Engn Fac Slavonski Brod Trg Ivane Brl Mazuran 2 HR-35000 Slavonski Brod Croatia Univ Appl Sci Dept Engn FH Campus WienFavoritenstr 226 A-1100 Vienna Austria

Precisely predicting the Specific Wear Rate (SWR) of AlSi10Mg components produced using Laser Powder Bed Fusion (LPBF) at high temperatures, which is an essential concern in additive manufacturing. This study aims to address the gap in literature by developing accurate predictive models for SWR via machine learning regression techniques. Experiments using a dry sliding wear rig shown that wear loss in AlSi10Mg print specimens increased with temperature and load, reaching a maximum wear rate of 1.5444E-06 mm3/Nm at 200 degrees C, 10 N, and 1.2 m/ s, compared to the minimum wear rate of 6.4672E-07 mm3/Nm seen at 100 degrees C, 20 N, and 1.4 m/s. However, to accurately predict the wear rate at high temperatures, six different machine learning regression algorithms were used, namely Support Vector machine (SVM), Linear regression (LR), Random Forest regression (RFR), Gaussian Process regression (GPR), XGBoost regression (XGB) and Decision Tree (DT). R-squared values and various error functions were employed to validate these strategies against the anticipated outcomes. Within this set of models, GPR model has a lower Mean Absolute Error of 0.3177, Root Mean Square Error of 0.6704 and higher R2 value of 0.9686, resulting a prediction accuracy of 96.86%. From these findings, it is suggested that GPR is a very useful model for predicting the rate at which LPBFed AlSi10Mg printed parts wear under high temperature conditions in comparison with other developed models. These machine learning methods are anticipated to be beneficial for additive manufacturing enterprises.

关键词： Laser powder bed fusion machine learning regression algorithm Prediction Specific wear rate MAE RMSE Gaussian process regression algorithm

来源：评论

学校读者我要写书评

暂无评论

The best performing color space and machine learning regression algorithm for the accurate estimation of chromium (VI) and iron (III) in aqueous samples using low-cost and portable flatbed scanner colorimetry

引用

JOURNAL OF THE IRANIAN CHEMICAL SOCIETY 2024年第9期21卷 2335-2349页

作者： Ichsan, Chairul Rodiah, Siti Univ Islam Negeri Raden Fatah Palembang Fac Sci & Technol Dept Chem Palembang Indonesia

The study utilizes the colorimetric method (involving 1,5-diphenylcarbazide and potassium thiocyanate as complexing agents), computer vision, and machine learning (ML) regression algorithms to determine the content of Cr (VI) and Fe (III) in water samples. To process digital images of water samples, the integration technique utilized a flatbed scanner known as the CanoScan LiDE 100, operating as a digital image capture device, and its performance was compared to that of conventional instruments. The study reveals that PolyReg and SVR-Poly are the most reliable ML regression algorithms for processing color space data (G and B of RGB, c* of CIELch, and b* of CIELab) of digital images of water samples that contain Cr (VI) and Fe (III). The mean absolute percentage error (MAPE) of the ML regression algorithms PolyReg and SVR-Poly for determining the content of Cr (VI) and Fe (III) is < 10% (with 8.48% error for Cr (VI) determination using PolyReg G of RGB and 6.78% error for Fe (III) determination using PolyReg B of RGB) in the estimation algorithm model. The Mean Absolute Percentage Error (MAPE) indicates that the prediction method is highly accurate. The Limit of Detection (LOD) value of the flatbed scanner colorimetric method integrated with PolyReg G of Red-Green-Blue (RGB) for Chromium (VI) and Blue of RGB for Iron (III) is approximately 0.02 mg/L. The Limit of Detection (LOD) for Chromium (VI) and Iron (III) is 0.0209 mg/L and 0.0257 mg/L, respectively. The limit of detection (LOD) values from this technique are superior to those obtained from certain UV-vis spectrometric and colorimetric methods. The low LOD values demonstrate that this technique is suitable for estimating the concentration of Cr (VI) and Fe (III) in water samples for quality assessment purposes, as these values are below the maximum concentration levels established by various regulations, including US-EPA, ASEAN, and EECCA.

关键词： Flatbed scanner colorimetry Chromium (VI) Iron (III) machine learning regression algorithm Color spaces Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

Mapping mangrove functional traits from Sentinel-2 imagery based on hybrid models coupled with active learning strategies

引用

INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION 2024年 130卷

作者： Jia, Mingming Guo, Xianxian Zhang, Lin Wang, Mao Wang, Wenqing Lu, Chunyan Zhao, Chuanpeng Zhang, Rong Wang, Ming Yan, Hengqi Wang, Zongming Verrelst, Jochem Int Res Ctr Big Data Sustainable Dev Goals Beijing 100094 Peoples R China Xiamen Univ Coll Environm & Ecol Key Lab Minist Educ Coastal & Wetland Ecosyst Xiamen 361102 Peoples R China Fujian Agr & Forestry Univ Coll Comp & Informat Sci Fuzhou 350002 Peoples R China Chinese Acad Sci Northeast Inst Geog & Agroecol State Key Lab Black Soils Conservat & Utilizat Changchun 130102 Peoples R China Jilin Earthquake Agcy Changchun 130117 Peoples R China Univ Valencia Image Proc Lab IPL Parc Cient Valencia Spain

Accurately quantifying functional traits across large scales is considered fundamental for the management and conservation of existing mangrove ecosystems. In recent years, hybrid models, which combine radiative transfer model simulations with machine learning regression algorithms (MLRA), have been effectively employed in satellite-based estimations of plant functional traits across diverse ecosystems. Nevertheless, the inevitable data redundancy stemming from heavy-parameterization radiative transfer models restricts the application of the hybrid model. Previous studies have indicated that active learning (AL) strategies can mitigate this redundancy through smart sampling selection criteria. While many studies have attempted to investigate mangrove functional traits using various models, there is limited understanding of the performance of hybrid models coupled with active learning strategies in retrieving the traits. In recent years, Sentinel-2 has become mainstream for retrieving detailed and reliable information across diverse ecosystems. The aim of this study is to utilize a retrieval scheme to extract four mangrove functional traits from Sentinel-2 imagery: leaf area index (LAI), leaf chlorophyll content (Cab), leaf dry matter content (Cm), and leaf equivalent water thickness (Cw). In order to achieve this goal, we systematically evaluated 36 different MLRA-AL models, which were combinations of six MLRAs and six AL strategies. Retrieval results showed that GPR (Gaussian processes regression)-ABD (anglebased diversity) and GPR-PAL (variance-based pool of regressors) yielded the highest accuracies for LAI (R 2 = 0.68, NRMSE = 10.488 %) and Cw (R 2 = 0.47, NRMSE =13.868 %), respectively. GPR-EBD (Euclidean distancebased diversity) had the highest accuracies of Cm (R 2 = 0.54, NRMSE = 11.695 %) and Cab (R 2 = 0.71, NRMSE = 13.764 %). The retrieval models were subsequently applied to produce distribution pattern maps of four mangrove functional traits within a Ram

关键词： Mangrove functional traits Active learning machine learning regression algorithm Radiative transfer model Sentinel-2

来源：评论

学校读者我要写书评

暂无评论

Data-driven analysis of influence between radiologists for diagnosis of breast lesions

引用

ANNALS OF OPERATIONS RESEARCH 2023年第1期328卷 419-449页

作者： Fu, Chao Wang, Dongyue Chang, Wenjun Hefei Univ Technol Sch Management POB 270 Hefei 230009 Anhui Peoples R China Minist Educ Key Lab Proc Optimizat & Intelligent Decis Making Hefei 230009 Anhui Peoples R China Minist Educ Engn Res Ctr Intelligent Decis Making & Informat S Hefei 230009 Peoples R China

Breast lesions are the most common threat to the health of women. The accumulation of historical examination reports for diagnosing breast lesions in clinical practice provides the necessary foundations for analyzing the diagnostic preferences of radiologists and the mutual influence between radiologists in a hospital. This mutual influence is important for indicating the development of an ultrasonic department in which radiologists work. To conduct a data-driven analysis of the influence between the two radiologists, the influence of the diagnostic preferences of one radiologist on the other was qualitatively defined using regression models. Following the qualitative definition, the process of analyzing the influence between two radiologists was designed, in which ten machine learning regression algorithms were included to make a reliable analysis. A statistical comparison method was developed using each machine learning regression algorithm to generate the indicator pair. The indicator pairs generated by ten machine learning regression algorithms were integrated using absolute majority voting to derive the overall indicator pair, from which the influence between two radiologists was determined, namely the unclear influence, clear influence, or significant influence. Experiments were conducted based on historical examination reports collected from two hospitals in Hefei, Anhui, China. The experimental results indicate that the trend in the influence between two radiologists in one hospital is different from that in the other hospital, which is associated with the management pattern, innovation incentive, and reward pattern of the two hospitals. A general conclusion on managerial insights was drawn to generalize the findings of this study.

关键词： Influence analysis machine learning regression algorithm Statistical comparison Diagnosis of breast lesion Organizational development

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Hybrid Models to Estimate Chlorophyll and Nitrogen Content of Maize Crops in the Framework of the Future CHIME Mission

引用

REMOTE SENSING 2022年第8期14卷 1792页

作者： Candiani, Gabriele Tagliabue, Giulia Panigada, Cinzia Verrelst, Jochem Picchi, Valentina Rivera Caicedo, Juan Pablo Boschetti, Mirco CNR Inst Electromagnet Sensing Environm I-20133 Milan Italy Univ Milano Bicocca Remote Sensing Environm Dynam Lab I-20126 Milan Italy Univ Valencia Image Proc Lab Valencia 46980 Spain Council Agr Res & Econ Res Ctr Engn & Agrofood Proc I-20133 Milan Italy CONACYT UAN Secretary Res & Postgrad Tepic 63000 Nayarit Mexico

In the next few years, the new Copernicus Hyperspectral Imaging Mission (CHIME) is foreseen to be launched by the European Space Agency (ESA). This mission will provide an unprecedented amount of hyperspectral data, enabling new research possibilities within several fields of natural resources, including the "agriculture and food security" domain. In order to efficiently exploit this upcoming hyperspectral data stream, new processing methods and techniques need to be studied and implemented. In this work, the hybrid approach (HYB) and its variant, featuring sampling dimensionality reduction through active learning heuristics (HAL), were applied to CHIME-like data to evaluate the retrieval of crop traits, such as chlorophyll and nitrogen content at both leaf (LCC and LNC) and canopy level (CCC and CNC). The results showed that HYB was able to provide reliable estimations at canopy level (R-2 = 0.79, RMSE = 0.38 g m(-2) for CCC and R-2 = 0.84, RMSE = 1.10 g m(-2) for CNC) but failed at leaf level. The HAL approach improved retrieval accuracy at canopy level (best metric: R-2 = 0.88 and RMSE = 0.21 g m(-2) for CCC;R-2 = 0.93 and RMSE = 0.71 g m(-2) for CNC), providing good results also at leaf level (best metrics: R-2 = 0.72 and RMSE = 3.31 mu g cm(-2) for LCC;R-2 = 0.56 and RMSE = 0.02 mg cm-2 for LNC). The promising results obtained through the hybrid approach support the feasibility of an operational retrieval of chlorophyll and nitrogen content, e.g., in the framework of the future CHIME mission. However, further efforts are required to investigate the approach across different years, sites and crop types in order to improve its transferability to other contexts.

关键词： spaceborne imaging spectroscopy radiative transfer modeling machine learning regression algorithm Gaussian process regression active learning chlorophyll content nitrogen content

来源：评论

学校读者我要写书评

暂无评论

Data-driven prediction for the number of distribution network users experiencing typhoon power outages

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2020年第24期14卷 5844-5850页

作者： Hou, Hui Yu, Jufang Geng, Hao Zhu, Ling Li, Min Huang, Yong Li, Xianqiang Wuhan Univ Technol Sch Automat Wuhan Peoples R China Guangdong Power Grid Co Ltd Guangzhou Peoples R China Guangdong Power Grid Co Ltd Elect Power Res Inst Guangzhou Peoples R China

Typhoons have substantial impacts on power systems and may result in major power outages for distribution network users. Developing prediction models for the number of users going through typhoon power outages is a high priority to support restoration planning. This study proposes a data-driven model to predict the number of distribution network users that may experience power outages when a typhoon passes by. To improve the accuracy of the prediction model, twenty six explanatory variables from meteorological factors, geographical factors and power grid factors are considered. In addition, the authors compared the application effect of five different machine learning regression algorithms, including linear regression, support vector regression, classification and regression tree, gradient boosting decision tree and random forest (RF). It turns out that the RF algorithm shows the best performance. The simulation indicates that the accuracy of the optimal model error within +/- 30% can reach up to 86%. The proposed method can improve the prediction accuracy through continuous learning on the existing basis. The prediction results can provide efficient guidance for emergency preparedness during typhoon disaster, and can be used as a basis to notify the distribution network users who are likely to lose power.

关键词： storms support vector machines regression analysis disasters power grids decision trees power system reliability power engineering computing random forests gradient methods pattern classification power system planning distribution networks distribution network users typhoon power outages data-driven model power grid factors data-driven prediction power systems restoration planning meteorological factors geographical factors machine learning regression algorithm linear regression support vector regression classification regression tree gradient boosting decision tree random forest

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：