检索结果-内蒙古大学图书馆

Research on landslide susceptibility prediction model based on LSTM-RF-MDBN

ENVIRONMENTAL science AND POLLUTION RESEARCH 2024年第1期31卷 1543-1561页

作者： Yang, Xiaoyi Fan, Xinyue Wang, Kai Zhou, Zhongli Chengdu Univ Technol Coll Math & Phys Chengdu 610059 Peoples R China Chengdu Univ Technol Coll Management Sci Chengdu 610059 Peoples R China

The occurrence of landslide disasters causes huge economic losses and casualties. Although many achievements have been made in predicting the probability of landslide disasters, various factors such as the scale and spatial location of landslide geological disasters should still be fully considered. Further research on how to quantitatively characterize the susceptibility of landslide geological disasters is necessarily important. To this end, taking the Wenchuan earthquake as the research area and extracting eight influencing factors, including terrain information entropy (Ht), lithology, distance from rivers, distance from faults, vegetation coverage (NDVI), distance from roads, peak ground motion acceleration (PGA), and annual rainfall, a landslide susceptibility prediction model was hereby established based on LSTM-RF-MDBN, a landslide susceptibility prediction map was drawn, and the spatial distribution characteristics of landslide disasters were analyzed. The results showed that (1) LSTM had good prediction results for the eight influencing factors, with an average prediction accuracy of 85%;(2) compared with models such as DNN and LR for predicting landslide disaster points, the AUC value of RF for predicting landslide point positions reached 0.88, presenting a higher accuracy compared to other models;(3) the AUC value of the landslide susceptibility prediction model based on LSTM-RF-MDBN reached 0.965, which had a high accuracy in predicting landslide susceptibility. Overall, the research results can provide a scientific basis for selecting the best strategy for landslide disaster warning, prevention, and mitigation.

关键词： Ten severely affected areas in Wenchuan Landslide susceptibility Dynamic prediction LSTM-RF-MDBN

来源：评论

学校读者我要写书评

暂无评论

Power Sharing and Storage-Based Regenerative Braking Energy Utilization for Sectioning Post in Electrified Railways

引用

IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION 2024年第2期10卷 2677-2688页

作者： Chen, Junyu Zhao, Yue Wang, Minghao Wang, Ke Huang, Yi Xu, Zhao Southwest Jiaotong Univ Sch Elect Engn Chengdu 611756 Peoples R China Hong Kong Polytech Univ Dept Elect & Elect Engn Hong Kong Peoples R China Inner Mongolia Elect Power Res Inst Co Ltd Hohhot 010020 Peoples R China Hong Kong Polytech Univ Res Inst Smart Energy Hong Kong Peoples R China

It is energy-efficient and grid-friendly to utilize regenerative braking energy (RBE) in electrified railways. However, considering the segmented structure of the railway power system (RPS), it is challenging to utilize the RBE between adjacent traction substations (TSSs). To this end, an RBE utilization method involving power sharing and storage is proposed in this article. The proposed method is implemented on a sectioning postenergy storage system (SPESS) to coordinate RBE utilization between adjacent TSSs. To provide real-time power management and control for the SPESS, a centralized power flow control strategy is developed. Specifically, a two-stage power dispatch algorithm-based power management strategy (PMS) is designed in the central controller. A nonlinear optimization function is formulated in the PMS to determine the active power commands to maximize the RBE utilization and shave the power demand. It also calculates the reactive power commands based on residual capacity to stabilize the catenary voltage. The power flow control is implemented in the local controllers as per the power commands from the central controller. The feasibility of the proposed method is verified through hardware-in-the-loop (HIL) experiments. The techno-economic superiority of the proposed method over literature methods is validated based on field load data-based comparison analysis.

关键词： Rail transportation Load flow control Transportation Load flow Energy efficiency Costs Voltage control Electrified railway energy storage system (ESS) power flow control strategy real-time power management regenerative braking energy (RBE)

来源：评论

学校读者我要写书评

暂无评论

Aspect-level sentiment classification with fused local and global context

引用

JOURNAL OF BIG DATA 2023年第1期10卷 176页

作者： Feng, Ao Cai, Jiazhi Gao, Zhengjie Li, Xiaojie Chengdu Univ Informat Technol Chengdu Peoples R China

Sentiment analysis aims to determine the sentiment orientation of a text piece (sentence or document), but many practical applications require more in-depth analysis, which makes finer-grained sentiment classification the ideal solution. Aspect-level Sentiment Classification (ALSC) is a task that identifies the emotional polarity for aspect terms in a sentence. As the mainstream Transformer framework in sentiment classification, BERT-based models apply self-attention mechanism that extracts global semantic information for a given aspect, while a certain proportion of local information is missing in the process. Although recent ALSC models have achieved good performance, they suffer from robustness issues. In addition, uneven distribution of samples greatly hurts model performance. To address these issues, we present the PConvBERT (Prompt-ConvBERT) and PConvRoBERTa (Prompt-ConvRoBERTa) models, in which local context features learned by a Local Semantic Feature Extractor (LSFE) are fused with the BERT/RoBERTa global features. To deal with the robustness problem of many deep learning models, adversarial training is applied to increase model stability. Additionally, Focal Loss is applied to alleviate the impact of unbalanced sample distribution. To fully explore the ability of the pre-training model itself, we also propose natural language prompt approaches that better solve the ALSC problem. We utilize masked vector outputs of templates for sentiment classification. Extensive experiments on public datasets demonstrate the effectiveness of our model.

关键词： Aspect-level sentiment classification Local semantic feature extractor Adversarial training

来源：评论

学校读者我要写书评

暂无评论

Design of Ultraviolet Molecular Doppler Lidar for Wind Measurement at Altitudes of 0.1–20 km

引用

Current Optics and Photonics 2025年第2期9卷 108-119页

作者： Shen, Fahua Shu, Zhifeng Dong, Jihui Yang, Liangliang Zhu, Chengyun Xu, Hua Jiangsu Province Intelligent Optoelectronic Devices and Measurement-Control Engineering Research Center Department of Physics and Electronic Engineering Yancheng Teachers University Jiangsu Yancheng224007 China School of Atmospheric Physics Nanjing University of Information Science & Technology Nanjing210044 China Beijing Huairou Laboratory Beijing101400 China Lidar and Devices Laboratory Southwest Institute of Technical Physics Chengdu610041 China

Since aerosols are rare above the boundary layer, Mie Doppler lidar can generally only detect lowaltitude wind speed. Therefore, for wind-field detection at altitudes of 0.1–20 km a molecular Doppler lidar technology, using a fixed air-gap dual Fabry-Perot etalon as the frequency discriminator and a tunable ultra-violet (UV) laser as the emission source, is proposed. The Rayleigh-Brillouin scattering spectrum of atmospheric molecules is described by a three-Gaussian model, and the parameters of the dual Fabry-Perot etalon are optimized. Simulation results show that in the absence of dust and clouds, the inversion deviation of radial wind speed is less than 0.08 m/s within the radial-wind-speed dynamic range of ±10 m/s at 100 m of altitude;The deviation is less than 0.1 m/s within the radial-wind-speed dynamic range of ±50 m/s above 1.2 km of altitude. By using a 355-nm ultraviolet laser with a pulse energy of 400 mJ and repetition frequency of 50 Hz, and a telescope with a 300-mm aperture, vertical resolution of 26 m @ 0.06–10km and 78 m @ 10–20 km, and temporal resolution of 1 min, the system has an allday radial-wind-speed measurement error of less than 1.8 m/s between 0.1 to 20 km of altitude, and a radial-wind-speed error less than 0.54 m/s at 10 km of altitude. © 2025 Current Optics and Photonics.

关键词： Fabry-Perot interferometers

来源：评论

学校读者我要写书评

暂无评论

An extended Kalman filter based SOC estimation method for Li-ion battery

引用

ENERGY REPORTS 2022年 8卷 81-87页

作者： Cui, Zhenjie Hu, Weihao Zhang, Guozhou Zhang, Zhenyuan Chen, Zhe Univ Elect Sci & Technol China Sch Mech & Elect Engn Sichuan Prov Key Lab Power Syst Wide Area Measure Chengdu Peoples R China Aalborg Univ Dept Energy Technol Aalborg Denmark

In recent years, the global environmental pollution and energy crisis are becoming more and more serious. The Li-ion battery is widely used in vehicles due to long cycle life and high energy density. The state of charge (SOC) of Li-ion battery is an important indicator. The accurate estimation of SOC can ensure the safe operation of Li-ion battery. However, the traditional estimation method, the ampere-hour integration method, has a cumulative error and cannot maintain good results for a long time in an operating environment with the Gaussian noise. To this end, this paper firstly applies Thevenin equivalent circuit model of a battery to establish estimation model, and it can reflect the working state of the battery. Then, the extended Kalman filtering algorithm is employed to solve the estimation error caused by Gaussian noise. Finally, the test system is built in MATALAB/Simulink to investigate the performance of the proposed method. Simulation results show that the proposed method achieves better performance, and it has higher estimation accuracy in comparison with traditional methods under different working conditions. (c) 2022 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/). Peer-review under responsibility of the scientific committee of the The 2nd International Conference on Power Engineering, ICPE, 2021.

关键词： Li-ion battery State of charge Estimation Extended Kalman filtering algorithm

来源：评论

学校读者我要写书评

暂无评论

Solid-Liquid Phase Equilibria of the Aqueous Ternary System Containing Lithium Borate and Calcium Borate at T = (298.2, 323.2, and 348.2 K)

引用

JOURNAL OF CHEMICAL AND ENGINEERING DATA 2024年第6期69卷 2358-2368页

作者： Feng, Xia Zhang, Shengtai Wu, Changhao Yang, Yousheng Li, Qi Yao, Zhihao Zhao, Zhixing Zeng, Ying Yu, Xudong Chengdu Univ Technol Coll Mat & Chem & Chem Engn Chengdu 610059 Peoples R China Qinghai Salt Lake Ind Co Ltd Golmud 816099 Peoples R China

Phase equilibria and diagrams can provide essential theoretical data for the enrichment and extraction of elements in the development and utilization of brines. For the composition of boron- and calcium-rich brines, the solid-liquid equilibria of the ternary system Li+, Ca2+// Borate-H2O at 298.2, 323.2, and 348.2 K were studied. In this work, calcium borate CaB6O105H(2)O was synthesized by a hydrothermal method for phase equilibria experiments, the structure and phase analyses of CaB6O105H(2)O were performed by X-ray diffractometer (XRD), scanning electron microscope (SEM), and Fourier transform infrared (FTIR) spectrometer, and the purity of CaB6O105H(2)O was determined by chemical analysis. Meanwhile, the solubility of CaB6O105H(2)O at 273.2-348.2 K was determined, which showed that it increases first and then decreases with the rise in temperature. The solubility, density, refractive index, and pH of the system Li+, Ca2+// Borate-H2O at 298.2, 323.2, and 348.2 K were measured, and the corresponding phase diagrams and physicochemical properties versus composition diagrams were constructed. The system Li+, Ca2+// Borate-H2O is a simple system at 298.2, 323.2, and 348.2 K;two crystalline regions correspond to CaB6O105H(2)O and Li2B4O73H(2)O (CaB6O105H(2)O > Li2B4O73H(2)O) and with the increase in temperature, the crystallization region of CaB6O105H(2)O increases.

关键词： Boron Calcium Light absorption Salts Solubility

来源：评论

学校读者我要写书评

暂无评论

CircZmMED16 delays plant flowering by negatively regulating starch content through its binding to ZmAPS1

引用

Journal of Integrative Plant Biology 2025年第04期 1142-1161页

作者： Xin Tang Xiaoju Feng Yang Xu Bo Yang Yi Wang Yang Zhou Qi Wang Yan Mao Wubing Xie Tianhong Liu Qi Tang Yaxi Liu Yao Wang Jie Xu Yanli Lu State Key Laboratory of Crop Gene Exploration and Utilization in Southwest China Sichuan Agricultural University Maize Research Institute Sichuan Agricultural University College of Chemistry and Life Sciences Chengdu Normal University

Circular RNAs(circ RNAs), a type of head-to-tail closed RNA molecules, have been implicated in various aspects of plant development and stress responses through transcriptome sequencing; however, the precise functional roles of circ RNAs in plants remain poorly understood. In this study, we identified a highly expressed circular RNA, circZm MED16, derived from exon 8 of the mediator complex subunit 16(ZmMED16) across different maize(Zea mays L.) inbred lines using circ RNA-seq analysis. This circ RNA is predominantly expressed in maize tassels and functions in the cytoplasm. Overexpression of circ ZmMED16 resulted in increased expression of Zm MED16/At MED16 and delayed flowering in both maize and Arabidopsis thaliana,compared with that in wild-type plants. In contrast,overexpression of the parent gene ZmMED16 did not alter the flowering time of transgenic plants in Arabidopsis, suggesting that circ ZmMED16 plays a specific role in regulating flowering, distinct from that of linear ZmMED16. To further understand the mechanisms underlying the regulation of flowering time by circ ZmMED16, we performed RNA pulldown, dual-luciferase, RNA interference(RNAi), and ribonuclease protection assays(RPA). These results indicate that circ Zm MED16 interacts with small subunit 1 of ADP-glucose pyrophosphorylase(APS1)m RNA in both maize and Arabidopsis. The knockdown of circ Zm MED16 increased the expression of ZmAPS1, whereas the overexpression of circZmMED16 led to the downregulation of Zm APS1RNA and protein. By affecting ZmAPS1 expression,circ ZmMED16 reduced ADP-glucose pyrophosphorylase(AGPase) activity and led to delayed *** results revealed a novel regulatory mechanism for circ RNAs in flowering time and shed light on their functional and regulatory roles in plants.

关键词：

来源：评论

学校读者我要写书评

暂无评论

In Situ Multicolor Imaging of Photocatalytic Degradation Process of Permanganate on Single Bismuth-Based Metal-Organic Frameworks

引用

INORGANIC CHEMISTRY 2024年第7期63卷 3221-3228页

作者： Li, Yanhao Ye, Wenyou Yu, Haili He, Yi Southwest Univ Sci & Technol Sch Nucl Sci & Technol Natl Collaborat Innovat Ctr Nucl Waste & Environm Mianyang 621010 Peoples R China

Bismuth-based metal-organic frameworks (Bi-MOFs) have emerged as important photocatalysts for pollutant degradation applications. Understanding the photocatalytic degradation mechanism is key to achieving technological advantage. Herein, we apply dark-field optical microscopy (DFM) to realize in situ multicolor imaging of the photocatalytic degradation process of permanganate (MnO4-) on single CAU-17 Bi-MOFs. Three reaction kinetic processes such as surface adsorption, photocatalytic reduction, and disproportionation are revealed by combining the time-lapsed DFM images with optical absorption spectra, indicating that the photocatalytic reduction of purple MnO4- first produces beige red MnO42- through a one-electron pathway, and then MnO42- disproportionates into yellow MnO2 on CAU-17. Meanwhile, we observe that the deposition of MnO2 cocatalysts enhances the surface adsorption reaction and the photocatalytic reduction of MnO4- to MnO42-. Unexpectedly, it is found that isopropanol as a typical hole scavenger can stabilize MnO42-, avoiding disproportionation and causing the alteration of the photocatalytic reaction pathway from a one-electron avenue to a three-electron (1 + 2) process for producing MnO2 on CAU-17. This research opens up the possibility of comprehensively tracking and understanding the photocatalytic degradation reaction at the single MOF particle level.

关键词： Adsorption Degradation Optical imaging Photocatalysis Photocatalysts

来源：评论

学校读者我要写书评

暂无评论

Separative and Comprehensive Effects of Grain Coarsening and Grain Refinement of Ni-38Cr-3.8Al Alloy during Thermal Deformation Process

引用

MATERIALS 2024年第9期17卷 1965页

作者： Quan, Guozheng Zhao, Yifan Deng, Qi Quan, Mingguo Yu, Yanze Wu, Daijian Chongqing Univ Sch Mat Sci & Engn Chongqing Key Lab Adv Mold Intelligent Mfg Chongqing 400044 Peoples R China Jiangsu Yutaida Ind Technol Co Ltd Taizhou 225300 Peoples R China Huan Ding Intelligent Technol Suzhou Co Ltd Suzhou 215000 Peoples R China Sichuan Polytech Univ Sichuan Lab Adv Mfg Technol Press Engine Deyang 618000 Peoples R China

During thermal deformation, grain coarsening due to grain growth and grain refinement resulting from dynamic recrystallization (DRX) collectively influence the deformed grain size. To investigate the separative and comprehensive effects of the two mechanisms in the Ni-38Cr-3.8Al alloy, grain growth experiments and isothermal compression tests were conducted. Kinetics models for grain growth and DRX behaviors were established based on the experimental data, which were integrated with finite element (FE) techniques to simulate the evolution of grain size throughout the entire thermal compression process. The effects of grain coarsening and grain refinement during this process were separated and quantified based on the simulation data. The results revealed that grain coarsening predominated during the heating and holding stages, with a longer holding time and higher holding temperatures intensifying this effect. However, during the compression stage, grain coarsening and grain refinement co-existed, and their competition was influenced by deformation parameters. Specifically, grain refinement dominated at strain rates exceeding 0.1 s(-1), while grain coarsening dominated at lower strain rates (<0.1 s(-1)) and higher deformation temperatures (>1373 K). The simulated grain sizes closely matched the experimental observations.

关键词： nickel-based alloy grain growth dynamic recrystallization grain coarsening grain refinement kinetics model

来源：评论

学校读者我要写书评

暂无评论

Dynamic Impedance and Chaotic Behavior Modeling Featured Novel Robust Arc Fault Identification Approach

引用

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS 2024年第2期60卷 2480-2490页

作者： Ren, Jie Zhang, Zhenyuan Tang, Xiaotian Jing, Shi Liao, Kaiji Lee, Wei-Jen Univ Elect Sci & Technol China Mech & Elect Engn Chengdu 611731 Peoples R China Univ Elect Sci & Technol China Sch Mech & Elect Engn Chengdu 611731 Sichuan Peoples R China State Grid Sichuan Elect Power Corp Metering Ctr Chengdu 610041 Peoples R China Univ Texas Arlington Elect Engn Arlington TX 76019 USA

Accurate and reliable electric arc fault identification ensures the safety of personnel and equipment through in-field operations and maintenance work. However, due to the application scenarios and nonlinear arc dynamics, the distortion degree of the detectable signals is influenced by network/circuit structure, system parameter, operation manner, etc., the salience of the fault signatures may change significantly, which poses challenges to develop the "generic scheme" in arc faults identification. To address such issues, this paper proposed a robustness-improved arc fault identification approach that incorporates the modeling of dynamic impedance and chaotic behavior in faulting systems. For describing the "unique" nonlinear characteristics of arc faults among different operation scenarios, the HT-based dynamic impedance (HTDI) representation method is developed to extract the "signatures" of arc faults, and the mechanism of how system parameters impact the presentation form of arc fault features are also revealed. Meanwhile, for quantitively extracting the signatures, the chaotic behavior of arcing fault system has been analyzed in phase space in detail, with a series of chaos indicators. Additionally, HTDI and chaos indicators implemented LSTM classifier has been designed to achieve accurate and rapid arcing fault identification with time-series inputs. With the series of actual arc fault cases and simulation cases under different configurations, the effectiveness and robustness of the proposed method have been thoroughly validated.

关键词： Arc faults chaotic behavior dynamic impedance Hilbert transform robust identification

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：