检索结果-内蒙古大学图书馆

43rd Chinese Control Conference, CCC 2024

作者： Zhou, Junjie Wang, Lin Wang, Xiaofan Meng, Qiang Shanghai Jiao Tong University School of Electronic Information and Electrical Engineering Shanghai202400 China Ministry of Education of China Key Laboratory of System Control and Information Process Shanghai202400 China National University of Singapore Department of Civil and Environmental Engineering Singapore117576 Singapore Shanghai Institute of Technology School of Electrical and Electronic Engineering Shanghai202400 China

ISBN: (纸本)9789887581581

Critical boundary scenarios play a vital role in the comprehensive testing of autonomous vehicles, as they can significantly expedite testing processes and reduce economic and time costs. To tackle the intricate, multidimensional, and diverse nature of intelligent driving scenarios, this paper proposes an innovative bi-level adaptive deep reinforcement learning (BADRL) approach aimed at generating authentic and diverse critical boundary scenarios. Leveraging naturalistic driving data, background agents are trained to exhibit naturalistic and realistic driving behaviors using a neural-based naturalistic driving behavior model. To address the intricacies of multi-interaction, high-dimensional environments, the scenario complexity model is introduced to evaluate the relative complexity between the traffic environment and the tested autonomous vehicle in real time. By integrating the scenario complexity model, the naturalistic driving behavior learning, intelligent driving testing, and critical boundary scenario generation are concatenated together to form a closed loop. BADRL facilitates the upper-level neural network in learning to adaptively increase the complexity of test scenarios, which are then fed into lower-level models to optimize the behavior of principal traffic participants, thereby generating naturalistic and critical boundary test scenarios. Extensive simulations were carried out to verify the efficacy of the BADRL technique in complex intersection environments. Results indicate that the BADRL approach boosts the efficiency of critical boundary scenario generation by approximately 10% compared to the state-of-the-art method. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

The 2022 record-breaking high temperature in China:Sub-seasonal stepwise enhanced characteristics,possible causes and its predictability

引用

Advances in Climate Change Research 2023年第5期14卷 651-659页

作者： Yuan-Yuan MA Yi-Ting CHEN Xiao-Xue HU Qian-Rong MA Tai-Chen FENG Guo-Ling FENG Di MA Key Laboratory of Land Surface Process and Climate Change in Cold and Arid Regions Northwest Institute of Eco-Environment and ResourcesChinese Academy of SciencesLanzhou 730000China School of Physical Science and Technology Yangzhou UniversityYangzhou 225127China College of Atmospheric Sciences Lanzhou UniversityLanzhou 730000China School of Atmospheric Sciences Key Laboratory of Tropical Atmosphere-Ocean SystemMinistry of EducationSun Yat-sen UniversityZhuhai 519082China Southern Marine Science and Engineering Guangdong Laboratory Zhuhai 519082China

In the summer of 2022,an unprecedented and long-lasting high temperature swept central-eastern China,causing significant societal ***,the sub-seasonal characteristics,causes and predictability of this extreme high temperature event are not well *** on the locations,intensities and causes of the high temperature,we divided it into three stages:early(13 June-3 July),sustained(4-28 July),and enhancement(29 July-30 August)*** high temperature during the early stage mainly occurred in north-central China with an anomaly of 2.5℃compared with climatology(1981-2010),while the last two stages occurred in the middle and lower Yangtze River Basin with anomalies of 2.8 and 3.8℃*** high temperature during the three stages were all regulated by the strengthening and westward extension of the western Pacific subtropical high(WPSH)but involved different physical *** the early stage,it was mainly caused by the anticyclones over the Mongolia and Northwest Pacific and enhanced by the minor impact of *** the sustained stage it was influenced by relatively more stronger WPSH and South Asia high(SAH)and the relatively minor impact of the anticyclone over the north-western South *** the enhancement stage,the high temperature was mainly caused by a combination of the record-breaking WPSH and SAH and the strong European blocking ***,the exceptionally powerful WPSH was well correlated with the sea surface temperature gradient induced by the developing La Niñ*** ECMWF and NCEP models reasonably predicted the location and intensity of the high temperature in the early stage,but poorly predicted that in the sustained and enhancement stages partly because of the failure prediction of the WPSH's enhancement and westward *** ECMWF model's more accurate prediction of the WPSH may contribute to its better forecasting of the heatwaves.

关键词： High temperature Sub-seasonal characteristics Western Pacific subtropical high La Niña development phase Predictability

来源：评论

学校读者我要写书评

暂无评论

Slope stability calculation based on sparrow search algorithm and Monte Carlo simulation

引用

Arabian Journal of Geosciences 2023年第1期17卷 1-14页

作者： He, Li Zhao, Yong-ming Njamba, Bruno Liu, Yi-he Xiong, Hai-tao Hubei Key Laboratory of Metallurgical Process System Science Wuhan University of Science and Technology Hubei China Hubei Key Laboratory of Blasting Engineering Jiang Han University Wuhan China

Limit and numerical analyses are the two most commonly used methods for slope stability analysis. The former is simple and easy to understand and thus preferred to the latter. However, this method has limitations, including artificial definition of sliding surface, numerous calculations, and easily falling into local optima. To address these limitations, an objective function is established based on the simplified Bishop method principle, minimum factor of safety is taken as the fitness function, and sparrow search algorithm (SSA) is used to search for the center position of the most dangerous sliding surface on the slope. Furthermore, Monte Carlo method is used to simulate the law of cohesion, which follows a normal distribution, and internal friction angle. The maximum, minimum, and average factors of safety values of the slope are obtained through massive calculation; accordingly, an improved slope stability analysis method is established by introducing the failure probability. Finally, the established method is compared with the limit equilibrium, traditional finite element strength reduction, and double strength reduction methods combined with slope examples. The results show that the center position and factor of safety of the most dangerous sliding surface determined by the SSA are similar to those obtained by the limit equilibrium method; however, the factor of safety determined by the Monte Carlo method is smaller. The failure probability of the two examples is 0, which indicates that there is no risk of slope instability. Consequently, the proposed method is deemed suitable for slope stability analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on PV power fluctuation smoothing control strategy based on ESS 3

Research on PV power fluctuation smoothing control strategy ...

引用

3rd International Conference on Laser, Optics, and Optoelectronic Technology, LOPET 2023

作者： Sun, Bing Wang, Lichao Ma, Jian Wei, Xingyuan Electric Power Research Institute of State Grid Xinjiang Electric Power Co. Ltd Xinjiang Key Laboratory of Whole Process Simulation for Power System Urumqi830011 China Shandong University School of Electrical Engineering Jinan250012 China

ISBN: (纸本)9781510667624

Energy storage systems can effectively improve the inertia of PV systems and achieve power smoothing of PV power generation due to their fast and flexible power regulation capability. This study proposes a BESS charging and discharging control method with limited PV fluctuation smoothing for the capacity optimization of energy storage in high permeability PV grids. This method can reduce the number of times the BESS is charged and discharged and improve its service life while smoothing out large fluctuations in PV power output. © 2023 SPIE.

关键词： Energy storage

来源：评论

学校读者我要写书评

暂无评论

A Novel Cooperative Co-Evolutionary Framework for Large-Scale Overlapping Problems

A Novel Cooperative Co-Evolutionary Framework for Large-Scal...

引用

Congress on Evolutionary Computation

作者： Mingke Chen Wei Du Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education Engineering Research Center of Process System Engineering Ministry of Education East China University of Science and Technology Shanghai China

Large-scale overlapping problems are a type of challenging problems because of the special structure of the shared variables. In order to solve the large-scale overlapping problems effectively, the paper proposes a novel cooperative co-evolutionary framework for large-scale overlapping problems called the cooperative co-evolution algorithm with subgroup merging and resource allocation for overlapping problems (CCMRO). In CCMRO, a contribution-based subcomponent merging strategy is proposed to deal with the decomposition of the large-scale overlapping problem and reduce the interaction of subgroups. In addition, a new computational resource allocation strategy (CCRO) is designed to maintain a balance between the full allocation of computational resources and the stability of search speed. Finally, the effectiveness of the proposed CCMRO is verified by the large-scale overlapping benchmark functions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mean-Square Exponential Consensus of Nonlinear Multi-Agent systems via Distributed Random Impulsive Control 49

Mean-Square Exponential Consensus of Nonlinear Multi-Agent S...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Yu, Yi He, Wangli Yang, Yanping East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Processes Ministry of Education Shanghai China Engineering Research Center of Process System Engineering Ministry of Education East China University of Science and Technology Shanghai China College of Information Science and Technology and Engineering Research Center of Digitized Donghua University Shanghai China

ISBN: (纸本)9798350331820

This paper aims to study mean-square exponential consensus of nonlinear leader-following multi-agent systems (MASs) in the presence of noise via distributed random impulsive control. The noise is driven by a second-order moment process with bounded mean power. A distributed random impulsive controller whose impulses occur at random moments is designed to ensure the desired consensus performance while enhancing security of the system. Sufficient conditions in terms of the network topology and impulsive parameter are derived, using the Lyapunov-based approach and properties of stochastic process. Finally, a numerical example is presented to demonstrate the effectiveness of our theoretical results. © 2023 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Factors affecting land dissection density in geomorphological regions of China

引用

Journal of Mountain Science 2024年第4期21卷 1372-1387页

作者： SUN Xiaolin ZHAO Yinjun PENG Peihao CHENG Weiming WEI Yongping YANG Ronghao LI Jiaxu College of Earth Sciences Chengdu University of TechnologyChengdu 610059China School of Civil Engineering Guangxi Polytechnic of ConstructionNanning 530001China Key Laboratory of Environment Change and Resources Use in Beibu Gulf Ministry of EducationNanning Normal UniversityNanning 530001China Key Laboratory of Earth Surface Process and Intelligent Simulation(Guangxi) Nanning Normal UniversityNanning 530001China State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources ResearchCASBeijing 100101China School of Earth and Environmental Sciences The University of QueenslandBrisbane 4702Australia School of Geography and Planning Nanning Normal UniversityNanning 530001China

Land dissection density(LDD)provides morphological evidence regarding prior intense soil erosion and quantifies the distribution of land dissections.A comprehensive understanding of the potential factors influencing the spatial pattern and value of the LDD is vital in geological disasters,soil erosion,and other related *** dissection phenomena in China affects large areas with different morphological,pedological,and climatic *** studies have focused on the potential factors influencing the LDD at a watershed ***,these results are insufficient to reflect the status quo of dissection development and its primary influencing factors on a national ***’s spatial patterns and the dominant factors at a regional scale in millions of square kilometers remain to be *** study used the geomorphon-based method and the geographical detector model to quantify the spatial pattern of LDD over China and identify the dominant factors affecting this pattern in China’s six first-order geomorphological regions(GR1~GR6).The results yield the following findings:(1)LDD in China ranges from 0~4.55 km/km^(2),which is larger in central and eastern regions than in other regions of China;(2)dominant factors and their dominant risk subcategories vary with each geomorphological region’s primary internal and external forces;(3)the influence of natural factors is more significant on the large regional scale in millions of square kilometers compared to anthropogenic factors;relief degree of land surface(RDLS)is dominant in GR1,GR2,and GR5;the slope is dominant in GR6,soil type is dominant in GR3 and GR4,and lithology plays a critical role in the dominant interactions of GR3,GR4,and GR6;(4)the interactions between factors on LDD’s spatial pattern have a more significant effect than individual factors.

关键词： Land dissection density Influencing factors Regional scale Spatial pattern Geographical detector model Geomorphon-based method China

来源：评论

学校读者我要写书评

暂无评论

An optimal configuration method of new generation and high-capacity synchronous condenser for enhancing the power grid voltage support 8

An optimal configuration method of new generation and high-c...

引用

8th International Symposium on Advances in Electrical, Electronics, and Computer engineering, ISAEECE 2023

作者： Xiaoxiao, Qi Yongjun, Yu Xiaoyun, Wang Yue, Ma Jing, Cheng Xinjiang Key Laboratory of Whole Process Simulation for Power System Urumqi Xinjiang830011 China State Grid Xinjiang Electric Power Co. Ltd. Urumqi Xinjiang830011 China School of Electrical Engineering Xinjiang University Urumqi Xinjiang830017 China

ISBN: (纸本)9781510666290

Aiming at the weak voltage support of the long-chain power grid, an optimal configuration method of condensers considering system stability constraints is proposed. To add condensers to key buses to improve the voltage support strength of the power grid. The basic data of Southern Xinjiang Power Grid in winter operation mode was collected, and statistical prediction and analysis of load and power surplus were made. After preliminarily selecting the location for the 750kV backbone grid, the location of the condenser was determined. Further, the weak area of 220kV bus voltage stability to achieve the accurate location of the condenser was determined. With the stability of the power grid as the constraint and economic optimization as the goal, the condenser capacity configuration is realized. The power grid model is built on the PSASP software platform, and the power flow calculation and voltage stability analysis are carried out. The results show that the proposed method can effectively improve the voltage support strength of the power grid, and promote the increase of new energy access ratio and consumption level. © 2023 SPIE. All rights reserved.

关键词： system stability

来源：评论

学校读者我要写书评

暂无评论

Multi-scale feature fused stacked autoencoder and its application for soft sensor modeling

引用

Chinese Journal of Chemical engineering 2025年 81卷 241-254页

作者： Li, Zhi Xia, Yuchong Long, Jian Liu, Chensheng Zhang, Longfei State Key Laboratory of Industrial Control Technology East China University of Science and Technology Shanghai 200237 China Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education East China University of Science and Technology Shanghai200237 China Huzhou Institute of Industrial Control Technology Huzhou313099 China Engineering Research Center of Process System Engineering Ministry of Education East China University of Science and Technology Shanghai200237 China

Deep Learning has been widely used to model soft sensors in modern industrial processes with nonlinear variables and uncertainty. Due to the outstanding ability for high-level feature extraction, stacked autoencoder (SAE) has been widely used to improve the model accuracy of soft sensors. However, with the increase of network layers, SAE may encounter serious information loss issues, which affect the modeling performance of soft sensors. Besides, there are typically very few labeled samples in the data set, which brings challenges to traditional neural networks to solve. In this paper, a multi-scale feature fused stacked autoencoder (MFF-SAE) is suggested for feature representation related to hierarchical output, where stacked autoencoder, mutual information (MI) and multi-scale feature fusion (MFF) strategies are integrated. Based on correlation analysis between output and input variables, critical hidden variables are extracted from the original variables in each autoencoder's input layer, which are correspondingly given varying weights. Besides, an integration strategy based on multi-scale feature fusion is adopted to mitigate the impact of information loss with the deepening of the network layers. Then, the MFF-SAE method is designed and stacked to form deep networks. Two practical industrial processes are utilized to evaluate the performance of MFF-SAE. Results from simulations indicate that in comparison to other cutting-edge techniques, the proposed method may considerably enhance the accuracy of soft sensor modeling, where the suggested method reduces the root mean square error (RMSE) by 71.8%, 17.1% and 64.7%, 15.1%, respectively. © 2025 Chemical Industry and engineering Society of China, and Chemical Industry Press Co., Ltd.

关键词： Frequency estimation

来源：评论

学校读者我要写书评

暂无评论

Physics-informed neural networks for parameter learning of wildfire spreading

arXiv

引用

arXiv 2024年

作者： Vogiatzoglou, Konstantinos Papadimitriou, C. Bontozoglou, V. Ampountolas, K. System Dynamics Laboratory Department of Mechanical Engineering University of Thessaly Volos38334 Greece Transport Processes & Process Equipment Laboratory Department of Mechanical Engineering University of Thessaly Volos38334 Greece Automatic Control & Autonomous Systems Laboratory Department of Mechanical Engineering University of Thessaly Volos38334 Greece

Wildland fires pose a terrifying natural hazard, underscoring the urgent need to develop datadriven and physics-informed digital twins for wildfire prevention, monitoring, intervention, and response. In this direction of research, this work introduces a physics-informed neural network (PiNN) designed to learn the unknown parameters of an interpretable wildfire spreading model. The considered modeling approach integrates fundamental physical laws articulated by key model parameters essential for capturing the complex behavior of wildfires. The proposed machine learning framework leverages the theory of artificial neural networks with the physical constraints governing wildfire dynamics, including the first principles of mass and energy conservation. Training of the PiNN for physics-informed parameter identification is realized using synthetic data on the spatiotemporal evolution of one- and two-dimensional firefronts, derived from a high-fidelity simulator, as well as empirical data (ground surface thermal images) from the Troy Fire that occurred on June 19, 2002, in California. The parameter learning results demonstrate the predictive ability of the proposed PiNN in uncovering the unknown coefficients of the wildfire model in one- and two-dimensional fire spreading scenarios as well as the Troy Fire. Additionally, this methodology exhibits robustness by identifying the same parameters even in the presence of noisy data. By integrating this PiNN approach into a comprehensive framework, the envisioned physics-informed digital twin will enhance intelligent wildfire management and risk assessment, providing a powerful tool for proactive and reactive strategies. Copyright © 2024, The Authors. All rights reserved.

关键词： Risk assessment

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：