检索结果-内蒙古大学图书馆

An Adaptive Physics-Informed Neural Network with Two-Stage Learning Strategy to Solve Partial Differential Equations

引用

numerical Mathematics(Theory,Methods and Applications) 2023年第2期16卷 298-322页

作者： Shuyan Shi Ding Liu Ruirui Ji Yuchao Han School of Automation and Information Engineering Xi‘an University of TechnologyXi‘an 710048P.R.China National&Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration Xi‘an 710048P.R.China Xi’an University of Technology Shannxi Key Laboratory of Complex System Control and Intelligent Information ProcessingXi‘an 710048P.R.China

Physics-Informed Neural Network(PINN)represents a new approach to solve Partial Differential Equations(PDEs).PINNs aim to solve PDEs by integrating governing equations and the initial/boundary conditions(I/BCs)into a loss ***,the imbalance of the loss function caused by parameter settings usually makes it difficult for PINNs to converge,*** they fall into local *** other words,the presence of balanced PDE loss,initial loss and boundary loss may be critical for the *** addition,existing PINNs are not able to reveal the hidden errors caused by non-convergent boundaries and conduction errors caused by the PDE near the ***,these problems have made PINN-based methods of limited use on practical *** this paper,we propose a novel physics-informed neural network,*** adaptive physics-informed neural network with a two-stage training *** algorithm adds spatio-temporal coefficient and PDE balance parameter to the loss function,and solve PDEs using a two-stage training process:pre-training and formal *** pre-training step ensures the convergence of boundary loss,whereas the formal training process completes the solution of PDE by balancing various loss *** order to verify the performance of our method,we consider the imbalanced heat conduction and Helmholtz equations often appearing in practical *** Klein-Gordon equation,which is widely used to compare performance,reveals that our method is able to reduce the hidden *** results confirm that our algorithm can effectively and accurately solve models with unbalanced loss function,hidden errors and conduction *** codes developed in this manuscript are publicy available at https://***/callmedrcom/ATPINN.

关键词： Physics informed neural networks partial differential equations two-stage learning scientific computing

来源：评论

学校读者我要写书评

暂无评论

Quasi-Parallel Resonant Switched Capacitor DC-DC Converter with Continuous Voltage Regulation Capability

Quasi-Parallel Resonant Switched Capacitor DC-DC Converter w...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Qi, Jingjing Wu, Xuezhi Xu, Wenzheng Sun, Kai Tsinghua University State Key Laboratory of Power System Operation and Control Department of Electrical Engineering Beijing China Beijing Jiaotong University National Active Distribution Network Technology Research Center Beijing China

ISBN: (纸本)9798350376067

Resonant switched capacitor converters have the advantages of small size, light weight and high efficiency, but have poor voltage regulation ability. To overcome this problem, a quasi-parallel resonant switched capacitor DC-DC converter is proposed in this paper, which mainly incorporates a resonant switched capacitor converter with soft-switching and variable voltage ratio and a Buck converter. Most of the power can be transmitted by the resonant switched capacitor converter, while the Buck converter is responsible for output voltage regulation. In addition, the voltage ratio of the resonant switched capacitor converter can be flexibly changed base on the input voltage, which is beneficial for Buck converter to always handle a small portion of power. Furthermore, input voltage feedforward control is incorporated to suppress the input voltage disturbance. The proposed converter can not only continuously regulate the voltage over a wide range, but also perform high efficiency and achieve rapid dynamic response. The operating principle of the converter is introduced, the circuit characteristic is analyzed, and the correctness of the theoretical analysis is verified by experiments. © 2024 IEEE.

关键词： Capacitor bank

来源：评论

学校读者我要写书评

暂无评论

Real-Time Traffic Management of High-Speed Trains: A Novel Approach Combining Optimization with Machine Learning

Real-Time Traffic Management of High-Speed Trains: A Novel A...

引用

2024 China Automation Congress, CAC 2024

作者： Li, Chong Yin, Jiateng Ma, Lin Tang, Tao State Key Laboratory of Advanced Rail Autonomous Operation Beijing Jiaotong University Beijing China National Engineering Research Center of Rail Transportation Operation and Control System Beijing Jiaotong University Beijing China

ISBN: (纸本)9798350368604

The real-time traffic control of high-speed trains (HSTs) is an important task in railway networks to reduce the delay time of trains in case of unexpected disruptions. Traditional approaches are based on mixed-integer programming (MILP) formulations to be solved by optimization methods such as branch-and-bound (B&B), which however require a very long time in real-world problems. Our study introduces a novel methodology that employs machine learning (ML) techniques to accelerate the optimization of MILPs. Specifically, our approach develops a feedforward network, which can be trained off-line, to predict the optimal MILP parameter configurations for the control of HSTs. Additionally, we develop a differential evolution (DE) algorithm, which fine-tunes these parameters in response to dynamic conditions. We conduct numerical experiments based on the real-world data of Beijing-Zhangjiakou high-speed railway (BZHR). The results demonstrate that our ML-accelerated approach significantly outperforms traditional optimization methods, improving the solution performance by 21.47%. © 2024 IEEE.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

Online Optimization Method for Virtually Coupled Train Operation Deviation from Reference Curve 21

Online Optimization Method for Virtually Coupled Train Opera...

引用

21st International Conference on Networking, Sensing and control, ICNSC 2024

作者： Lang, Yinghui Liu, Hongjie Liao, Yanli Li, Bosi Wang, Yihan Chai, Ming School of Automation and Intelligence Beijing Jiaotong University Beijing100044 China Beijing Jiaotong University National Engineering Research Center of Rail Transportation Operation and Control System Beijing100044 China Beijing Hollysys System Engineering Co. Ltd. Xi'an Branch Xi'an710061 China

ISBN: (纸本)9798350365221

Virtually coupled train set (VCTS) has become a popular research topic in the railway industry in recent years. It is considered one of the solutions to the uneven spatial and temporal distribution of passenger flow in urban rail transit. A VCTS consists of multiple train units (TUs). The overall operation of the VCTS relies on the coordinated efforts of each TU. A feasible approach involves pre-planning reference curves for the TUs, with the Automatic Train Operation (ATO) system tracking these curves. However, as the TUs operate at close intervals, the control strategy needs to ensure safety and precise control. Consequently, the reference curve of the TU is characterized by frequent changes in acceleration. As a result, the ATO system is prone to deviating from the curve. This paper builds a time-varying vehicle dynamics model and a controller performance model based on data learning. Using these models, we predict deviations and construct an online optimization model. A mesh adaptive direct search (MASD) algorithm is designed to solve for online adjustment curves, promptly correcting any deviations. Simulation experiments demonstrate the effectiveness of the proposed online optimization method when combined with PID and MPC alzorithms. © 2024 IEEE.

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

research on Abnormal Detection Method of Rail Fastener Based on Yolov5 8

Research on Abnormal Detection Method of Rail Fastener Based...

引用

8th International Conference on Electromechanical control Technology and Transportation, ICECTT 2023

作者： Huang, Xiaolong Fan, Lei Sun, Yongkui School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China National Engineering Research Center of Rail Transportation Operation and Control System Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9781510668331

The rapid development of rail transit has put forward higher requirements for the reliability testing of all components of rail lines. There are some drawbacks in relying on manual handheld device detection, so it is urgent to develop an intelligent and convenient rail fastener detection system. This paper introduces a rail fastener detection method based on YOLOV5, which can identify fasteners by training existing classified pictures, and continuously improve the accuracy of rail fasteners by modifying training documents and capturing frameworks. In this experiment, through training and training of the classified and labeled pictures, take 500 or 600 pictures as a group and 200 rounds as an experiment to improve the recognition accuracy of the experiment, so as to identify the position of the rail fastener with a suitable frame, and classify the identified fastener into its category. Through the analysis of the pr value of the experimental results, the experimental parameters are continuously modified to achieve the above effect. Finally, the pr value obtained from the experiment is about 0.6. © 2023 SPIE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Robust Global Exponential Stability of Fuzzy Neural Networks with Bis-Disturbances

Robust Global Exponential Stability of Fuzzy Neural Networks...

引用

2023 China Automation Congress, CAC 2023

作者： Si, Wenxiao Gao, Shigen Tian, Wanqi School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China National Engineering Research Center of Rail Transportation Operation and Control System Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9798350303759

This paper provides a sufficient criterion guaranteeing the robust global exponential stability (RGES) of fuzzy neural networks (FNN) with bis-disturbances, i.e., derivative contraction coefficients and piecewise constant arguments. By using the generalized Gronwall inequality and modular inequality, the upper bound of bis-disturbances is derived by solving the binary implicit transcendental equation as well as external spontaneous constraints respectively, ensuring the primitive stable FNN can be stable again in the presence of external bis-disturbances. Furthermore, the feasible boundary derived from the established criterion can guarantee that the mutual restraint and dynamic interconnection effects between the bis-disturbances that allow the system to be stable again can occur instead of being independent. Finally, the validity of the derived theoretical results is verified by simulation. © 2023 IEEE.

关键词： Fuzzy neural networks

来源：评论

学校读者我要写书评

暂无评论

Trajectory Prediction of High-Speed Train Group Tracking Based on LSTM-KF Hybrid Model 27

Trajectory Prediction of High-Speed Train Group Tracking Bas...

引用

27th IEEE International Conference on Intelligent Transportation systems, ITSC 2024

作者： Yang, Boyu Lv, Jidong Liu, Hongjie Chai, Ming Zhang, Qinglong Tang, Tao Lv, Jiahui National Engineering Research Center of Rail Transportation Operation and Control System Beijing Jiaotong University Beijing China School of Civil and Resource Engineering University of Science and Technology Beijing China Beijing Jiaotong University The Associate Director of the Rail Traffic Control and Safety State Key Laboratory China

ISBN: (纸本)9798331505929

Operating multiple trains as a group under Train-to-Train communication is an efficient way in sparse railway networks. However, it is a barrier to accurate tracking for follower trains with the uncertain status of the preceding trains under communication delay. Therefore, we proposed a train trajectory prediction approach, aiming to obtain an accurate state of preceeding trains in a long time horizon. Firstly, we established a hybrid prediction model combined Long Short-Term Memory (LSTM) with the Kalman Filter (KF) and using the sliding window mechanism to enhance future prediction accuracy. Secondly, to fusion LSTM prediction data and the Kalman calculation model, we proposed the Hybrid Train Trajectory Prediction algorithm by adopting real-time calculation of the covariance matrix using real data and predicted data. Finally, we apply an experiment considering network characteristics in Western China. The result shows that the Mean Absolute Error (MAE) of series prediction in the longer time domain is 44% of the Recurrent Neural Network (RNN) model and 88% of the traditional LSTM model. © 2024 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Rail Surface Anomaly Detection Based on Deep Learning 8

Rail Surface Anomaly Detection Based on Deep Learning

引用

8th International Conference on Electromechanical control Technology and Transportation, ICECTT 2023

作者： Shi, Lei Wu, Junjie Sun, Yongkui School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China National Engineering Research Center of Rail Transportation Operation and Control System Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9781510668331

The role of the rail is to directly bear the weight of the train and its load transmitted by the wheels, and to guide the direction of the train. Prolonged train travel can cause unavoidable defect to the rails;however, China's railways are developing at a high speed, and rail damage will also increase. In order to ensure the safety of railway operation, the detection of rail damage must be fast and efficient. So, a method is needed to quickly and accurately detect the type of rail defect. Due to the superiority of machine vision detection, a rail surface anomaly detection method based on deep learning is proposed. Firstly, the image data features are extracted through the image annotation tool labeling. After that, the YOLO v5 deep learning network is trained by the training set. Finally, the accuracy of the trained network is checked, and the relevant parameters are modified to adjust the accuracy to the best. The overall rail defect detection accuracy reaches 97%, indicating the feasibility and effectiveness of the proposed method. © 2023 SPIE.

关键词： Surface defects

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis of On-board Equipment in CTCS-3 Based on CNN-LSTM Model

Fault Diagnosis of On-board Equipment in CTCS-3 Based on CNN...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Zhang, Daqian Cao, Yuan Zhang, Miao Chai, Ming Lv, Jidong Beijing Jiaotong University National Engineering Research Center of Rail Transportation Operation and Control System Beijing China China Academy of Railway Sciences Corporation Limited National Research Center of Railway Intelligence Transportation System Engineering Technology Beijing China

ISBN: (纸本)9781665465335

Data-driven methods based on deep learning have achieved remarkable results of fault diagnosis of train control system due to their superiority in feature extraction. However, it still faces uneven data distribution problem, which afects the detection accuracy of fault diagnosis. In this paper, by considering different failures both in system and subsystem level of train control system, we propose a novel two-stages fault diagnosis method based on a combination of Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM). Firstly, samples are obtained by segmenting and vectorizing the text form faulty data set, and fed into the proposed CNN-LSTM model. Then, in the first stage, the features of the processed data are extracted through the CNN layer, whereas the correlation between the sample data are derived through the LSTM layer. Thus, the classification of first-level faults, respect as system level, are realized with high accuracy of diagnosis. Finally, in the second stage, to solve the problem of data imbalance, we reconsider part of data from the CNN layer, and put them into the new LSTM layer for secondary faults diagnosis. We apply this method on a real CTCS-3 On-board equipment and the experimental results show that the accuracy rate of our proposed model reaches 96.7% and the accuracy of small data faults is also higher when compare with other neural network models,such as TextCNN, ANN, LSTM and RNN. © 2022 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Progress in models for coupled human and natural systems

引用

Science China Earth Sciences 2024年第11期67卷 3631-3637页

作者： Tianxiang YUE Chenchen WU Wenjiao SHI Yongzhong TIAN Qing WANG Yimin LU Lili ZHANG State Key Laboratory of Resources and Environment Information System Institute of Geographical Sciences and Natural Resources ResearchChinese Academy of SciencesBeijing 100101China College of Resources and Environment University of Chinese Academy of SciencesBeijing 101408China School of Geographical Sciences Southwest UniversityChongqing 400715China National Institute of Environmental Health Chinese Center for Disease Control and PreventionBeijing 100021China National Engineering Research Center of Geospatial Information Technology Fuzhou UniversityFuzhou 350108China The Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China

1. Introduction Malthus (1798) was one of the earliest researchers to propose a coupled human-natural system (CHANS) model, particularly in his analysis of the relationship between population growth and food supply. He argued that while population grows geometrically, food supply increases only arithmetically, suggesting that this imbalance could eventually lead to a food crisis due to diminishing per capita food availability (Malthus, 1798).

关键词： Malthus eventually population

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：