检索结果-内蒙古大学图书馆

Computer Vision, Image and Deep Learning (CVIDL), International Conference on

作者： Yuanye Xu Yuanhao Liu Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Key Laboratory of Networked Control System Shenyang Institute of Automation Chinese Academy of Sciences Shenyang Institute of Automation University of Chinese Academy of Sciences Shenyang China

ISBN: (数字)9798350373820

ISBN: (纸本)9798350373837

Detecting surface defects in carbon fiber-reinforced composites (FRCs) during prepreg stacking is crucial for ensuring product quality. Traditional methods using horizontal bounding boxes (HBBs) for defect detection often lead to overlapping boxes and inaccurate results. This paper proposes an Aspect-Ratio and Scale Aware Detector network (ARSADet) specifically designed for rotated defect detection in FRCs. The network incorporates a Gabor convolutional network for feature extraction, an aspect-ratio and scale-aware label assignment method, and a newly established FRCs Oriented Defect Detection dataset (FODD). Evaluation on the FODD dataset demonstrates superior performance compared to existing methods.

关键词： Deep learning Stacking Detectors Optical fiber networks Feature extraction Product design Quality assessment

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-based Fault Detection and Diagnosis: Towards Application in a Chemical Process

Artificial Intelligence-based Fault Detection and Diagnosis:...

引用

Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS), CAA Symposium on

作者： Yiqi Liu Zhi Li Hongtian Chen Key Laboratory of Autonomous Systems and Networked Control Ministry of Education The School of Automation Science & Engineering South China University of Technology Guangzhou China Department of Automation Shanghai Jiao Tong University Shanghai China

As the chemical processes become more and more complicated, it is crucial but also difficult to detect and diagnose faults in the system than ever. With the development of machine learning algorithms and cloud computing, to monitor chemical processes completely with the help of big data become true. However, most machine learning methods suffer from unexplainable problem. By employing Explainable Artificial Intelligence(XAI) techniques, this paper applies two kinds of unsupervised machine learning methods, One-Class Support Vector Machine and Depth-based Isolation Forest Feature Importance, to detect and diagnosis faults in a chemical process. By combining two different fault explanation methodologies, accuracy and reliability of the fault diagnosis results can be achieved by the validation in a simulated continuous stirred tank reactor.

关键词：

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

Chinese Automation Congress (CAC)

作者： Chong Li Jiateng Yin Lin Ma Tao Tang 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: (数字)9798350368604

ISBN: (纸本)9798350368611

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%.

关键词： Heuristic algorithms Microscopy Optimization methods Machine learning Traffic control Programming Feature extraction Prediction algorithms Real-time systems Rail transportation

来源：评论

学校读者我要写书评

暂无评论

Combining Transformer and Convolutional Neural Network for Smoke Detection 9th

Combining Transformer and Convolutional Neural Network for...

引用

9th International Forum on Digital Multimedia Communication, IFTC 2022

作者： Gong, Yafei Lian, Xinkang Ma, Xuanchao Xia, Zhifang Zhou, Chengxu Faculty of Information Technology Beijing University of Technology Beijing China Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing China Beijing Laboratory of Smart Environmental Protection Beijing China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing China Beijing Artificial Intelligence Institute Beijing China National Information Center Beijing China School of Electronic and Information Engineering Liaoning University of Technology Liaoning Jinzhou China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian China

ISBN: (纸本)9789819908554

Smoke detection plays a crucial role in the safety production of petrochemical enterprises and fire prevention. Image-based machine learning and deep learning methods have been widely studied. Recently, many works have applied the transformer to solve problems faced by computer vision tasks (such as classification and object detection). To our knowledge, there are few studies using the transformer structure to detect smoke. In order to research the application potential and improve the performance of the transformer in the smoke detection field, we propose a model consisting of two transformer encoders and a convolutional neural network (CNN) module. The first transformer encoder can be used to establish the global relationship of an image, and the CNN structure can provide additional local information to the transformer. The fusion of global information and local information is conducive to the second transfer encoder to make better decisions. Experiments results on large-size dataset for industrial smoke detection illustrate the effectiveness of the proposed model. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Smoke

来源：评论

学校读者我要写书评

暂无评论

Point-Plane Better than Point-Point – for Embedding-based USAD 8

Point-Plane Better than Point-Point – for Embedding-based U...

引用

8th International Conference on Video and Image Processing, ICVIP 2024

作者： Zhao, Zhirong Zhang, Yuanhao Yu, Zujun Zhu, Liqiang Science and-Technology Department Guoneng Shuohuang Railway Development Co Ltd. Cangzhou Cangzhou062350 China Frontiers Science Center for Smart High-Speed Rail System Beijing Jiaotong University Beijing100044 China State Key Laboratory of Advanced Rail Autonomous Operation Beijing Jiaotong University Beijing100044 China School of Mechanical Electronic and Control Engineering Beijing Jiaotong University Beijing100044 China

ISBN: (数字)9781510689244

ISBN: (纸本)9781510689237

As deep neural networks (DNNs) have advanced, high-quality pre-trained models have provided excellent feature extraction methods for embedding-based unsupervised anomaly detection (EUSAD). However, when calculating anomaly scores, common EUSAD models often rely on point-to-point distance computations between test features and reference features. This approach not only fails to fully utilize the carefully integrated reference feature library but may also increase pixel-level false positives due to the incorrect selection of reference points. To address this issue, this paper adopts the least squares method, evaluating anomalies by calculating the distance between test feature points and the reference feature plane. Experimental results demonstrate that this method not only performs well in global image detection but also significantly reduces pixel-level false positives, showing strong performance across many anomaly detection datasets. © 2025 SPIE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Utilizing EEG to explore the mental states involved in the occurrence of different levels design fixation 41

Utilizing EEG to explore the mental states involved in the o...

引用

41st Computers and Information in Engineering Conference, CIE 2021, Held as Part of the ASME 2021 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC-CIE 2021

作者： Cao, Juan Zhao, Wu Guo, Xin Wu, Tingting School of Mechanical Engineering Sichuan University Chengdu China Innovation Method and Creative Design Key Laboratory of Sichuan Province Chengdu China Key Laboratory of Networked Control System Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9780791885376

Design fixation, which is a form of cognitive bias, is commonly reported to unconsciously occur when designers take the path of least resistance during the fulfillment of a design task. It's thought to be easy and effortless. Nonetheless, the mental states such as mental effort and mental fatigue that accompany the occurrence of different levels of design fixation are still unknown. In the present study, an experiment using electroencephalography (EEG) was conducted to examine the mental effort and mental fatigue involved in the occurrence of different levels of design fixation during creative idea generation. Fluency, flexibility, the degree of copying, and the time spent generating ideas were used to evaluate the design performance and fixation level of each participant, and the task-related power changes of theta, alpha, and beta bands of participants with higher and lower levels of fixation during creative idea generation process were compared and analyzed separately. The comparison results revealed that participants with higher levels of design fixation made the less mental effort and showed higher levels of mental fatigue during the ideation process compared to those with lower levels of design fixation. These results provide additional evidence for the mental states involved in the occurrence of design fixation and could contribute to a deeper understanding of design fixation from the neuroscience perspective. Copyright © 2021 by ASME

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Aerodynamic and aeroacoustic impact of the axial distance upon contra-rotating rotors during hovering condition

Aerodynamic and aeroacoustic impact of the axial distance up...

引用

AIAA Aviation and Aeronautics Forum and Exposition, AIAA AVIATION Forum 2023

作者： Li, Pengyu Yang, Yannian Zhang, Haoyu Liu, Yu Li, Qingxi Noack, Prof. Bernd Department of Mechanics and Aerospace Engineering Southern University of Science and Technology Shenzhen Key Laboratory of Complex Aerospace Flows Guangdong Shenzhen518055 China Key Laboratory of Autonomous Systems and Networked Control Ministry of Education Unmanned Aerial Vehicle Systems Engineering Technology Research Center of Guangdong School of Automation Science and Engineering South Guangdong510640 China Department of Mechanics and Aerospace Engineering Southern University of Science and Technology Shenzhen Key Laboratory of Complex Aerospace Flows Guangdong Shenzhen518055 China AVIC General Aircraft Research Institute Zhuhai Shenzhen Key Laboratory of Complex Aerospace Flows Guangdong519040 China School of Mechanical Engineering and Automation Harbin Institute of Technology Guangdong Shenzhen518055 China

ISBN: (数字)9781624107047

ISBN: (纸本)9781624107047

Contra-rotating rotors have the advantage of compactness and redundancy, which can be observed in many unmanned aerial vehicles. One significant installation parameter for the contra-rotating rotors is the axial distance between the upper and lower rotors, which influences both the time-averaged and unsteady loading of the rotors, as well as the aeroacoustic noise emission. Through experimental methods, each rotor is mounted to a six-component balance to study the impact of the axial distance on the two rotors, and an microphone arc-array is used to study the noise emission and directivity in an anechoic chamber. Two rotors are set at the same rotational speed for all axial distance settings. The results indicate that the increase of axial distance is advantageous for the aerodynamic performance increase and noise reduction, especially in the axial range of 0.1 diameter. The recovery of aerodynamic performance is due to the fully developed slipstream which reduces the mutual influence between the two rotors. The noise reduction is mainly due to the reduced velocity fluctuation alleviates the inter actiontonal noise, although the broadband noise becomes larger as the axial distance increases. © 2023, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

A Novel Trajectory Tracking controller for UAV with Uncertainty Based on RBF and Prescribed Performance Function 3rd

A Novel Trajectory Tracking Controller for UAV with Uncert...

引用

3rd International Conference on Neural Computing for Advanced Applications, NCAA 2022

作者： Qi, Xuelei Li, Chen Ma, Hongjun College of Information Science and Engineering Northeastern University Shenyang110819 China School of Automation Science and Engineering South China University of Technology Guangzhou510641 China Key Laboratory of Autonomous Systems and Networked Control Ministry of Education Unmanned Aerial Vehicle Systems Engineering Technology Research Center of Guangdong Guangzhou China

ISBN: (纸本)9789811961410

This paper proposes a novel trajectory tracking controller based on RBF neural network and fractional-order sliding mode control (FO-SMC). First, the prescribed performance control (PPC) is introduced into the system to make the tracking error converge to the predefined set. Then, the fractional-order calculus is introduced into SMC to alleviate the chattering of the system. Considering that RBF neural network can compensate for the uncertainty of the UAV motion model, RBF is introduced into the design of the controller. Besides, the Lyapunov theorem proves the stability of the system, and all signals in the closed-loop system are stable. Finally, a case study is carried out through simulation. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Chlorine-Substituent Regulation in Dopant-Free Small-Molecule Hole-Transport Materials Improves the Effi ciency and Stability of Inverted Perovskite Solar Cells

引用

Transactions of Tianjin University 2024年第4期30卷 314-323页

作者： Xinyi Liu Xiaoye Zhang Zhanfeng Li Jinbo Chen Yanting Tian Baoyou Liu Changfeng Si Gang Yue Hua Dong Zhaoxin Wu Key Laboratory of Advanced Transducers and Intelligent Control System Ministry of Education and Shanxi ProvinceTaiyuan University of TechnologyTaiyuan 030024China School of Electrical Engineering University of South ChinaHengyang 421001China College of Physics and Optoelectronics Taiyuan University of TechnologyTaiyuan 030024China Ningxia Hui Autonomous Region Screen Display Organic Materials Engineering Technology Research Center Ningxia Sinostar Display Material Co.Ltd.Yinchuan 750003China Organic Semiconductor Centre EaStCHEM School of ChemistryUniversity of St AndrewsFife KY169STUK Key Laboratory of Photonics Technology for Information School of Electronic and Information Engineering Xi’an Jiaotong UniversityXi’an 710049China

Although doped hole-transport materials(HTMs)off er an effi ciency benefi t for perovskite solar cells(PSCs),they inevi-tably diminish the ***,we describe the use of various chlorinated small molecules,specifi cally fl uorenone-triphenylamine(FO-TPA)-x-Cl[x=para,meta,and ortho(p,m,and o)],with diff erent chlorine-substituent positions,as dopant-free HTMs for *** chlorinated molecules feature a symmetrical donor-acceptor-donor structure and ideal intramolecular charge transfer properties,allowing for self-doping and the establishment of built-in potentials for improving charge *** effi cient hole-transfer interfaces are constructed between perovskites and these HTMs by strategi-cally modifying the chlorine ***,the chlorinated HTM-derived inverted PSCs exhibited superior effi ciencies and air ***,the dopant-free HTM FO-TPA-o-Cl not only attains a power conversion effi ciency of 20.82% but also demonstrates exceptional stability,retaining 93.8%of its initial effi ciency even after a 30-day aging test conducted under ambient air conditions in PSCs without *** fi ndings underscore the critical role of chlorine-substituent regulation in HTMs in ensuring the formation and maintenance of effi cient and stable PSCs.

关键词： Hole-transport materials Inverted perovskite solar cells Chlorinated small molecules Donor–acceptor–donor structure

来源：评论

学校读者我要写书评

暂无评论

Characteristics of the partial discharge in oil-paper cavity under the valve voltage waveform of converter transformer 3

Characteristics of the partial discharge in oil-paper cavity...

引用

3rd International Conference on Electrical Materials and Power Equipment, ICEMPE 2021

作者： Sun, Weidong Yang, Lijun Xu, Zhiren Wei, Yiheng Ministry of Education College of Automation Chongqing University of Posts and Telecommunications Key Laboratory of Industrial Internet of Things and Networked Control Chongqing China Chongqing University State Key Laboratory of Power Transmission Equipment System Security and New Technology Chongqing China

ISBN: (纸本)9781665418409

In this paper, the partial discharge (PD) in oil-paper insulation cavity is conducted under the voltage of AC,YΔ connection and Y/Y connection, respectively. The low-amplitude and high-repetition PD under the AC voltage is observed, the high-amplitude and a low-repetition PD is acquired under the given valve voltages. The discharge mainly occurs at the rising edge of the valve voltage waveforms. The Qmax of the discharge of YΔ and Y/Y connections is 2 and 2.5 times the Qmax under the AC voltage, respectively. The average discharge Qmean of Y/Δ and Y/Y connections is 3 and 2 times Qmean obtained under the AC voltage, respectively. The total discharge Qtatol of both valve voltage waveforms is higher than that under the AC voltage. The test results also show that the PD is severely affected by the voltage waveform as the voltage distortion is observed in the experiment. This work may provide a reference for the improvement of insulation design and the factory test of converter transformers. © 2021 IEEE.

关键词： Partial discharges

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：