检索结果-内蒙古大学图书馆

Predicting Red Light Running Violation Using Machine Learning Classifiers 11th

学校读者我要写书评

暂无评论

Predicting Red Light Running Violation Using Machine Learnin...

11th International Conference on Green Intelligent Transportation Systems and Safety, 2020

作者： Zahid, Muhammad Jamal, Arshad Chen, Yangzhou Ahmed, Tufail Ijaz, Muhammad College of Metropolitan Transportation Beijing University of Technology Beijing100124 China Department of Civil and Environmental Engineering King Fahd University of Petroleum and Minerals KFUPM Box 5055 Dhahran31261 Saudi Arabia College of Artificial Intelligence and Automation Beijing University of Technology Beijing100124 China Agoralaan Diepenbeek3590 Belgium School of Transportation and Logistics Southwest Jiaotong University Chengdu610031 China

ISBN: (纸本)9789811654282

Red light Running (RLR) violation remains as an important road safety concern at urban intersections. Existing method have mostly used statistical regression-based methods to explore factors contributing to RLR. However, it is well-known that statistical methods are based on predefined associations among variables and are unable to capture latent heterogeneity. This study aims to classify and predict RLR using spatial analysis and machine learning (ML) methods. Georeferenced RLR violation data for the year 2016 was collected for the city of Luzhou, China. To identify violation hotpots, frequency-based clustering was carried out using collect event tool in ArcMap geographic information system (GIS). Prior to RLR prediction via ML, data imbalance problem was addressed using a random over-sampling technique. Two widely used ML algorithms, i.e., Random Forest (RF) and Gradient Boosted Decision Tree (GBDT), were then used for prediction and classification of RLR. The performance of these models was assessed with accuracy and Cohen's kappa. The results showed that GBDT had an overall accuracy of 96% outperformed the RF. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Machine learning

Research on Thermal Stratification Phenomenon at the Secondary Side of Steam Generator in Isolated Loop

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Hao, Jianli Liu, Xinxin Yu, Lei Chen, Wenzhen Nuclear Power Institute of China Chengdu610041 China College of Nuclear Science and Technology Naval University of Engineering Wuhan430033 China

For marine nuclear power plants with multiple loops, it can continue to maintain power operation by isolation methods when a loop fails. In this paper, thermal stratification has been found at the secondary side of the steam generator in the isolated loop. It causes the coolant temperature at the primary side of the steam generator to be lower than that in the primary loop, which will have a significant impact on the operational safety of the marine nuclear power plants. On the basis of the mechanism analysis of above problems, an experiment is designed to verify the existence of thermal stratification. And then the simulation analysis is performed by RELAP5/MOD3.2 program, from which the development laws of thermal stratification are obtained. The research has important guiding significance for improving the operational safety of the marine nuclear power plants. © 2022, The Authors. All rights reserved.

关键词： Steam

An evaluation method for nuclear radiation detection performance of glass scintillator

学校读者我要写书评

暂无评论

Radiation Detection technology and Methods 2024年第2期8卷 1107-1119页

作者： Zhehao Hua Sen Qian Hua Cai Dejing Du Ruirui Fan Jifeng Han Chen Hu Peng Hu Shan Liu Yong Liu Lishuang Ma Laishun Qin Jing Ren Ruiqiang Song Zexuan Sui Xilei Sun Xinyuan Sun Gao Tang Zhigang Wang Qi Wu Dong Yang Lirong Zheng Yao Zhu Institute of High Energy Physics Chinese Academy of SciencesBeijing 100049China State Key Laboratory of Particle Detection and Electronics Beijing 100049China China Building Materials Academy Beijing 100024China Spallation Neutron Source Science Center(SNSSC) Dongguan 523803China Institute of Nuclear Science and Technology Sichuan UniversityChengdu 610064China Shanghai Institute of Ceramics Chinese Academy of SciencesShanghai 201899China Beijing Glass Research Institute Beijing 101111China College of Materials and Chemistry China Jiliang UniversityHangzhou 310018China College of Physics and Optoelectronic Engineering Harbin Engineering UniversityHarbin 150001China Department of Physics Jinggangshan UniversityJi'an 343009China

Purpose Glass is a potential choice for the scintillator in Hadronic calorimetry(HCAL)of the *** requires sophisticated instruments and suitable methods to obtain scintillation properties of the glasses in the first *** is necessary to establish an evaluation method for nuclear radiation detection performance of glass *** The spectroscopy research of the glass includes transmission/absorption spectrum and emission *** time characteristics include rise time,scintillation decay time and *** scintillation properties include light yield,energy resolution and minimum ionizing particle(MIP)*** a new method for measuring the low light yield of glass scintillators is *** We have built a complete performance test system and evaluation method,which can evaluate the nuclear radiation detection performance of different glass *** By continuously improving the composition and preparation process of the glass,it can provide potential possibilities for the application in the high-energy physics experiment and nuclear radiation detection fields.

关键词： CEPC Calorimeter Glass scintillator Scintillation nuclear radiation detection

Effect of Pre-Existing Dislocations and Precipitates on Microstructure Evolution in W-0.5zrc Alloy During In-Situ He+ & H2+ Dual-Beam Synergistic Irradiation

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Huang, Jinchi Zhong, Qinghong Chen, Zhe Cao, Ziqi Ding, Yifan Zhou, Zhehui Ma, Yan Ran, Guang College of Energy Xiamen University Xiamen361102 China Fujian Provincial Nuclear Energy Engineering Technology Research Center Xiamen361102 China Southwestern Institute of Physics Chengdu610000 China School of Nuclear Science and Engineering North China Electric Power University Beijing102206 China

Bubble evolution in different defect sinks has a crucial effect on the properties of materials for fusion reactor. Here, transmission electron microscopy (TEM) was used to in-situ investigate bubble evolution in different defect sinks, including pre-existing dislocations and precipitates in W-0.5ZrC alloy during He+ & H2+ dual-beam synergistic irradiation at 900 °C. The average size and volume number density of bubbles with increasing irradiation dose were obtained, revealing not only the significant effect of different types of defect sinks, but also the obvious impact of the same type of defect sinks in different states. It was found that linear pre-existing dislocations promoted bubble growth while inhibited nucleation. Pre-existing dislocations characterized by curved form exhibited strong inhibition effect on bubble nucleation, while pre-existing dislocations with staggered-mesh form, not only inhibited bubble growth but also suppressed nucleation compare to the linear pre-existing dislocations. ZrC precipitates had minimal effect on the bubble growth, but could decrease the bubble nucleation. Dispersed small precipitates could better reduce the bubble nucleation sites in the early stage of irradiation. Once the absorption capacity of small precipitate was saturated, bubble growth might accelerate sharply. The presence of hydrogen made the linear pre-existing dislocation maintain high mobility. The current research results are of great significance for understanding the irradiation behavior of tungsten alloys and optimizing preparation process. © 2024, The Authors. All rights reserved.

关键词： Helium

An Order-Invariant and Interpretable Hierarchical Dilated Convolution Neural Network for Chemical Fault Detection and Diagnosis

学校读者我要写书评

暂无评论

arXiv

arXiv 2023年

作者： Li, Mengxuan Peng, Peng Wang, Min Wang, Hongwei The College of Computer Science and Technology Zhejiang University Hangzhou310013 China Zhejiang University The University of Illinois Urbana-Champaign Institute Haining314400 China The School of Automation Engineering University of Electronic Science and Technology of China Chengdu611731 China

Fault detection and diagnosis is significant for reducing maintenance costs and improving health and safety in chemical processes. Convolution neural network (CNN) is a popular deep learning algorithm with many successful applications in chemical fault detection and diagnosis tasks. However, convolution layers in CNN are very sensitive to the order of features, which can lead to instability in the processing of tabular data. Optimal order of features result in better performance of CNN models but it is expensive to seek such optimal order. In addition, because of the encapsulation mechanism of feature extraction, most CNN models are opaque and have poor interpretability, thus failing to identify root-cause features without human supervision. These difficulties inevitably limit the performance and credibility of CNN methods. In this paper, we propose an order-invariant and interpretable hierarchical dilated convolution neural network (HDLCNN), which is composed by feature clustering, dilated convolution and the shapley additive explanations (SHAP) method. The novelty of HDLCNN lies in its capability of processing tabular data with features of arbitrary order without seeking the optimal order, due to the ability to agglomerate correlated features of feature clustering and the large receptive field of dilated convolution. Then, the proposed method provides interpretability by including the SHAP values to quantify feature contribution. Therefore, the root-cause features can be identified as the features with the highest contribution. Computational experiments are conducted on the Tennessee Eastman chemical process benchmark dataset. Compared with the other methods, the proposed HDLCNN-SHAP method achieves better performance on processing tabular data with features of arbitrary order, detecting faults, and identifying the root-cause features. Copyright © 2023, The Authors. All rights reserved.

关键词： Convolution

Research on properties of hollow glass microspheres/epoxy resin composites applied in deep rock in-situ temperature-preserved coring

学校读者我要写书评

暂无评论

Petroleum Science 2022年第2期19卷 720-730页

作者： Zhi-Qiang He Yang Yang Bo Yu Jian-Ping Yang Xiang-Biao Jiang Bo Tian Man Wang Xi-Yuan Li Si-Qing Sun Hui Sun State Key Laboratory of Hydraulics and Mountain River Engineering MOE Key Laboratory of Deep Earth Science and EngineeringCollege of Water Resource and HydropowerSichuan UniversityChengdu 610065SichuanChina Guangdong Provincial Key Laboratory of Deep Earth Sciences and Geothermal Energy Exploitation and Utilization Institute of Deep Earth Sciences and Green EnergyCollege of Civil and Transportation EngineeringShenzhen UniversityShenzhen 518060GuangdongChina Shenzhen Key Laboratory of Deep Underground Engineering Sciences and Green Energy Shenzhen UniversityShenzhen 518060GuangdongChina School of Mechanical Engineering Sichuan UniversityChengdu 610065SichuanChina College of Polymer Science and Engineering Sichuan UniversityChengdu 610065SichuanChina Changsha High tech Automation Equipment Co. LTD Changsha 410100HunanChina Jinshi Drilltech co. LtdTangshan 063000HebeiChina State Key Laboratory of Coking Coal Exploitation and Comprehensive Utilization Institute of Coal Mining and UtilizationPingdingshan Tianan Coal Mining Co.LTD.Pingdingshan 467000China Xi’an Research Institute China Coal Technology&Engineering Group CorpXi’an 710077China

Deep petroleum resources are in a high-temperature ***,the traditional deep rock coring method has no temperature preserved measures and ignores the effect of temperature on rock porosity and permeability,which will lead to the distortion of the petroleum resources reserves ***,the hollow glass microspheres/epoxy resin(HGM/EP)composites were innovatively proposed as temperature preserved materials for in-situ temperature-preserved coring(ITP-Coring),and the physical,mechanical,and temperature preserved properties were *** results indicated that:As the HGM content increased,the density and mechanical properties of the composites gradually decreased,while the water absorption was deficient without hydrostatic *** composites with 50 vol%HGM,when the hydrostatic pressure reached 60 MPa,the water absorption was above 30.19%,and the physical and mechanical properties of composites were *** the hydrostatic pressure was lower than 40 MPa,the mechanical properties and thermal conductivity of composites were almost ***,the composites with 50 vol%HGM can be used for ITPCoring operations in deep environments with the highest hydrostatic pressure of 40 ***,to further understand the temperature preserved performance of composites in practical applications,the temperature preserved properties were *** unsteady-state heat transfer model was established based on the test results,then the theoretical change of the core temperature during the coring process was *** above tests results can provide a research basis for deep rock in-situ temperature preserved corer and support accurate assessment of deep petroleum reserves.

关键词： Deep rock in-situ temperature-preserved coring(ITP-Coring) Hollow glass microspheres/epoxy resin composites Hydrostatic pressure Unsteady-state heat transfer model

Effect of N2/Ar Pressure Ratio On Microstructure, Mechanical Properties, Corrosion Properties and High Temperature Steam Oxidation Performance of Alticrnita High Entropy Alloy Nitride Coatings for Atf

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Zhao, Sha Liu, Chunhai Li, Zhuo Zhang, Wei Xiang, Yang He, Hengji He, Linxin Yang, Hongyan Liu, Ning Yang, Yuanyou Liao, Jiali Chang, Hong Yang, Jijun Key Laboratory of Radiation Physics and Technology of Ministry of Education Institute of Nuclear Science and Technology Sichuan University Chengdu610064 China College of Materials and Chemistry & Chemical Engineering Chengdu University of Technology Chengdu610059 China Science and Technology on Reactor Fuel and Materials Laboratory Nuclear Power Institute of China Chengdu610213 China College of Materials Science and Engineering Sichuan University of Science and Engineering Zigong643000 China Chengdu Qixing Vacuum Coating Technology Co. Ltd Chengdu610000 China

The (AlTiCrNiTa)N high entropy alloy (HEA) coatings with different ratios of N 2 /Ar were successfully prepared on Zr-4 alloy by radio frequency magnetron sputtering. The effect of different ratios of N 2 /Ar on the microstructure, mechanical properties, wettability properties, high-temperature corrosion properties and steam oxidation resistance of (AlTiCrNiTa)N coatings were systematically investigated. Autoclave tests and steam oxidation resistance tests showed that the (AlTiCrNiTa)N HEA coating with N 2 /Ar ratios of 1/8 had excellent corrosion properties and steam oxidation performance than other coatings. Moreover, the oxidation mechanism was evaluated in detail. © 2022, The Authors. All rights reserved.

关键词： Magnetron sputtering

Microstructure and Performance Analysis of Cr1-Xalx Coatings with Different Low Al Content and Evolution of Al Element During Steam Oxidation

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Liu, Chunhai Li, Zhuo Zhao, Sha Liu, Sujuan Zhang, Wei He, Linxin Chang, Hong Long, Jianping Yang, Jijun College of Materials and Chemistry & Chemical Engineering Chengdu University of Technology Chengdu610059 China Key Laboratory of Radiation Physics and Technology of Ministry of Education Institute of Nuclear Science and Technology Sichuan University Chengdu610064 China Science and Technology on Reactor Fuel and Materials Laboratory Nuclear Power Institute of China Chengdu610213 China College of Materials Science and Engineering Sichuan University of Science and Engineering Zigong643000 China Chengdu Qixing Vacuum Coating Technology Co. Ltd Chengdu610000 China

The Cr1-xAlx coatings with different low Al content were prepared on Zr alloy by magnetron sputtering. The influence of Al content on the microstructure, mechanical properties, surface wettability and oxidation resistance of Cr1-xAlx coating were systematically evaluated. Air oxidation results showed that Cr91.4Al8.6 coating had better air oxidation resistance. After steam oxidation tests, the Cr2O3-rich and Al2O3 -rich double oxide layer structure was formed in the Cr91.4Al8.6 coating. The Al2O3-rich layer can prevent Zr from consuming the surface Cr2O3 layer. Moreover, the diffusion evolution mechanism of the Al element during steam oxidation of Cr91.4Al8.6 coating was analyzed in detail. © 2022, The Authors. All rights reserved.

关键词： Magnetron sputtering

Microstructure and Performance Analysis of Cr1-Xalx Coatings with Different Low Al Content and Evolution of Al Element During Steam Oxidation

学校读者我要写书评

暂无评论

SSRN 2022年

关键词： Magnetron sputtering