检索结果-内蒙古大学图书馆

Progress in Fabric Defect Detection Based on Machine Learning

Journal of Shanghai Jiaotong University (Science) 2025年 1-19页

作者： Wu, Ying Li, Donghui Guo, Peiyao Liu, Yanping School of Electrical Automation and Information Engineering Tianjin University Tianjin300072 China School of Fashion Design & Engineering Zhejiang University of Technology Hangzhou310018 China

This paper presents a comprehensive review of the latest advancements in fabric defect detection leveraging machine learning techniques. It introduces the characteristics of textile defects and public datasets, and encapsulates the challenges encountered in defect detection. A total of 2 000 references spanning diverse time periods are utilized to cluster keywords, revealing that machine learning and deep learning have emerged as the top two. By employing the systematic literature review methodology, it explores the research question, search progress, inclusion and exclusion criteria, and eligibility standards on the basis of the two keywords (machine learning and deep learning). Machine learning algorithms are classified into traditional machine learning and deep learning. The selected references are systematically subdivided into supervised, unsupervised, and semisupervised methods in accordance with the labeled dataset. A thorough analysis of classical network architectures is conducted using public datasets and other datasets, and each network type is accompanied with illustrative examples. The methods are further evaluated on the basis of key metrics in terms of detection success rate, datasets used, detection methodologies, time efficiency, and hardware. This comprehensive evaluation highlights the strengths and limitations of machine learning, particularly deep learning, in textile defect detection. Potential future developments and research directions in this field are explored, offering valuable insights for researchers and engineers working in textile defect detection. © Shanghai Jiao Tong University 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Epoc-Based Electroencephalography Signals Analysis of Different Stress Levels 3rd

Epoc-Based Electroencephalography Signals Analysis of Differ...

引用

3rd International Conference on Computational Electronics for Wireless Communications, ICCWC 2023

作者： Singh, Jatinderpal Sharma, Anurag School of Engineering Design and Automation GNA University Punjab Dhak Khati India

ISBN: (纸本)9789819719457

The researches show that people experience more mental stress as a result of an increase in workload. Excitation or emotional excitation is considered a "stress" situation and indicates a certain psychological state that might be impacting a person's performance. Stress increases health issues in the human body if it’s experienced for a long time. People went through a variety of stresses during the current epidemic and lockdown, including financial loss in company, family relationships, and joblessness. The long period of stress may be the cause of mental disorders, diabetes, depression, and other kinds of diseases. In this paper, the electroencephalography (EEG) signals are recorded with different mind states like low stress and high stress. The recorded electrical waves are compared with normal state and Low/High stressed states. For this, the database is collected with EPOC X headset. It is a 14-channels headset that is placed in different positions on the scalp. The normal state and low-stress state have almost the same types of brain signals, but the high-stress state has large differences in the detected signals. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Liquid Biopsy Instrument for Ultra-Fast and Label-Free Detection of Circulating Tumor Cells

引用

Research 2025年第1期2024卷 803-814页

作者： Shu Zhu Zhixian Zhu Chen Ni Zheng Zhou Yao Chen Dezhi Tang Kefan Guo Shuai Yang Kang Liu Zhonghua Ni Nan Xiang School of Mechanical Engineering and Jiangsu Key Laboratory for Design and Manufacture of Micro-Nano Biomedical InstrumentsSoutheast UniversityNanjing 211189China School of Electrical and Automation Engineering and Jiangsu Key Laboratory of 3D Printing Equipment and ManufacturingNanjing Normal UniversityNanjing 210023China

Rapid diagnosis and real-time monitoring are of great important in the fight against ***,most available diagnostic technologies are time-consuming and labor-intensive and are commonly ***,we describe CytoExam,an automatic liquid biopsy instrument designed based on inertial microfluidics and impedance cytometry,which uses a deep learning algorithm for the analysis of circulating tumor cells(CTCs).In silico and in vitro experiments demonstrated that CytoExam could achieve label-free detection of CTCs in the peripheral blood of cancer patients within 15 *** clinical applicability of CytoExam was also verified using peripheral blood samples from 10 healthy donors and>50 patients with breast,colorectal,or lung *** differences in the number of collected cells and predicted CTCs were observed between the 2 groups,with variations in the dielectric properties of the collected cells from cancer patients also being *** ultra-fast and minimally invasive features of CytoExam may pave the way for new paths for cancer diagnosis and scientific research.

关键词： analysis circulating tumor cells ctcs liquid biopsy liquid biopsy instrument impedance cytometrywhich diagnostic technologies vitro experiments deep learning algorithm inertial microfluidics

来源：评论

学校读者我要写书评

暂无评论

Research progress of shear-thickening polishing technology: A review

引用

Precision engineering 2025年 95卷 322-349页

作者： Sun, Baochen Wang, Zixuan Zhao, Yang Zhang, Qingchun Liu, Qi Wen, Lu Yu, Tianbiao Zhao, Ji School of Mechanical Engineering and Automation Northeastern University Shenyang110819 China Liaoning Provincial Key Laboratory of High-end Equipment Intelligent Design and Manufacturing Technology Shenyang110819 China

Shear-thickening polishing (STP) is an emerging precision polishing technology that dynamically adjusts the viscosity of polishing fluid by precisely controlling the shear rate, thereby enhancing material removal rate (MRR) and surface accuracy while effectively suppressing surface defects such as scratches and microcracks commonly found in conventional polishing methods. This expands its potential applications in high-tech fields such as precision manufacturing and microelectronics. Studies have shown that under optimized parameters (polishing speed: 70 rpm, polishing angle: 70°, abrasive particle concentration: 12 wt%), STP achieves an MRR of up to 813.63 nm/min on optical glass. Additionally, under conditions of 38 °C, abrasive particle size of 0.6 μm, polishing speed of 600 rpm, and abrasive particle concentration of 12 vol%, adaptive shear-gradient thickening polishing (AS-GTP) can reduce the subsurface damage depth and surface roughness (Ra) of lithium niobate (LN) crystals to below 1 nm. However, research on STP remains fragmented, and a comprehensive review is currently lacking. To bridge this gap, this article systematically reviews the primary types of shear-thickening polishing fluid based on the shear-thickening characteristics of non-Newtonian fluids and provides an in-depth discussion of the working mechanisms and process optimization strategies of different STP methods. Finally, the latest advancements in STP are summarized, and its future development trends and industrialization challenges are analyzed. © 2025 Elsevier Inc.

关键词： Non Newtonian liquids

来源：评论

学校读者我要写书评

暂无评论

Experiments and modeling of microstructural and mechanical behaviors of laser-welded Ni-based superalloy at high temperatures

引用

Chinese Journal of Aeronautics 2025年第1期38卷 99-114页

作者： Ting HOU Yong LI Degang WANG Yuelin WANG Marko VILOTIC School of Mechanical Engineering and Automation Beihang UniversityBeijing 100191China Department of Structure Shenyang Aircraft Designand Research InstituteShenyang 110000China Engineering Center Shenyang Aircraft CorporationShenyang 110000China Faculty of Technical Science University of Novi SadNovi Sad 21102Serbia

The performance of welded Ni-based superalloys at high temperatures is essential to be evaluated due to their particular service environment for aero-engines and high-speed *** tensile properties and related microstructural evolutions such as the carbide precipitate and grain of a laser-welded Ni-based alloy were experimentally and numerically investigated at different temperatures(20,300,500,800℃).The results show that at room temperature,the strength of the Base Material(BM)was slightly smaller,with a difference of less than 1%,than the Welded Material(WM),which can be attributed to the more uniformly distributed needle-shaped carbide precipitates in the WM than those nonuniformly coarser spherical ones in the *** at 300℃ and 500℃,the strength of WM decreased more obviously compared with that of BM due to the more apparent growth of grain:13.52%loss in yield strength in WM alloys as compared with BM alloys at 300℃,and 16.57% at 500℃.At 800℃,the strength of BM and WM both decreased to a similar level due to Dynamic Recrystallization(DRX).However,a much higher elongation was observed for the BM than WM(less than 50%of BM),which can be attributed to the enhanced dislocation accumulation capability of the large spherical carbides along grain boundaries on the fracture surface in ***,a unified model considering the welding effects on both microstructures(dislocation,carbides,and grain)and mechanical properties evolutions at different temperatures was developed and *** on this model,the key temperature ranges(20–600℃)where apparent weakening of strength and uniform plasticity occurs for welded structures were identified,providing a direct guidance for potential structure and process design.

关键词： Ni-based superalloy Microstructure Mechanical properties Constitutive model High temperature

来源：评论

学校读者我要写书评

暂无评论

Substrate bias effects in p-channel GaN-on-Si transistors

引用

Science China(Information Sciences) 2025年第1期68卷 404-405页

作者： Mengyao ZHAO Jie MA Lanlan YANG Chuanqi PAN Denggui WANG Jianjun ZHOU Sheng LI Jiaxing WEI Long ZHANG Siyang LIU Weifeng SUN National ASIC System Engineering Research Center School of Integrated Circuits Southeast University National Center of Technology Innovation for Electronic Design Automation Southeast University National Key Laboratory of Solid-State Microwave Devices and Circuits

The drain current （ID） of the n-channel GaN field-effecttransistor （n-FET） is influenced by the substrate-to-source bias voltage (VBS)（substrate bias effect）[1].Actually,nonzero VBSis also likely to occur in p-FET in real application,because the source electrode of p-FET is usually connected to high *** study reports the dependency between IDand VBSin p-FET for the first time,and analyzes the underlying mechanisms from the perspective of vertical electric field （EF） distribution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Resilience of IEC 61131-3 Software With Online Reconfigurations for Fault Handling

引用

IEEE Transactions on automation Science and engineering 2025年 22卷 12436-12454页

作者： Wilch, Jan Vogel-Heuser, Birgit Sax, Florian Ruth, Simon Oeckl, Ulrich Wohlschlager, Bernhard Hsieh, Yu-Ming Cheng, Fan-Tien Institute of Automation and Information Systems Technical University of Munich School of Engineering and Design Garching85748 Germany Hawe Hydraulik Se Freising85356 Germany Institute of Manufacturing Information and Systems National Cheng Kung University Tainan701401 Taiwan

In automated production, resilience describes a system's capacity to absorb disturbances by reconfiguring itself, thus retaining its Overall Equipment Effectiveness at least partially. This includes online behavior reconfiguration to automatically recover from or prevent faults, collectively called fault handling. Promising research exists for fault handling in automated Production Systems. In process engineering, fault diagnosis and automatic parameter adaptions are already industrially available. However, handling faults in discrete manufacturing requires a series of distinct operations, which cannot be achieved by parameter changes alone. Further, core requirements must remain fulfilled by automatic fault handling approaches, including real-time control and extra-functional requirements like changing operation modes, monitoring interlocks, and an alarming and communication system. This article proposes a concept for reconfigurable IEC 61131-3 software for automatic fault handling, validated by a public reference implementation for a demonstrator, an industrial production system, and a modified industrial test rig. Eight experiments were successfully conducted, showcasing four use cases of the concept: The prevention of faults by avoiding anomalous components, the recovery from a fault state to automatic operation, the definition of previously undefined state variables, and the monitoring of global interlocks to trigger a controlled stop. All mentioned extra-functional requirements are fulfilled. Note to Practitioners - Identification, reporting, diagnosis, and recovery of faults in automated production incur substantial effort. Project-specific code is required for diagnosis, and the recovery and re-initialization are often performed manually. To our knowledge, automatic recovery approaches from scientific literature are not widely used in discrete manufacturing. Reasons may include a frequent disregard of extra-functional requirements mentioned above. Further, s

关键词： Solar power plants

来源：评论

学校读者我要写书评

暂无评论

Relative Localizability and Localization for Multirobot Systems

引用

IEEE Transactions on Robotics 2025年 41卷 2931-2949页

作者： Chen, Liangming Liang, Chenyang Yuan, Shenghai Cao, Muqing Xie, Lihua Southern University of Science and Technology School of System Design and Intelligent Manufacturing Guangdong Provincial Key Laboratory of Fully Actuated System Control Theory and Technology Shenzhen518055 China Harbin Institute of Technology School of Mechanical Engineering and Automation Shenzhen518055 China Southern University of Science and Technology School of System Design and Intelligent Manufacturing Shenzhen518055 China Nanyang Technological University School of Electrical and Electronic Engineering 639798 Singapore Carnegie Mellon University Robotics Institute PittsburghPA15213 United States

Inter-robot relative positions are crucial for executing various multirobot missions, such as formation maneuvering and collaborative inspection. However, the current sensing technology usually provides part of relative position information, such as inter-robot distances, bearings and angles. This prompts the study of determining inter-robot relative positions, i.e., relative localization, from these partial measurements. Based on the existing results of static networks' localizability and mobile robots' relative localization, we propose a novel concept, relative localizability to describe whether a multirobot system is relatively localizable. Given each robot's self-displacement measurements and inter-robot partial measurements in d (d ≤ 4) sampling instants, we show that a multirobot system's relative localization can be achieved in a purely algebraic and distributed manner, in which the multirobot system is said to be d-step relatively localizable. To make the results more general, we consider that the multirobot system consists of landmarks, leaders, and followers, and that the inter-robot measurements can be distances, bearings or angles. When robots' coordinate frames have different orientations, we show that the given local measurements can be used to determine robots' relative positions and their coordinate frames' relative orientations simultaneously. Simulations and experiments of relative localization for ground robots are conducted to validate the obtained results. © 2004-2012 IEEE.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Development of a Novel Displacement-Sensitive Magnetorheological Damper for Vehicle Suspension with High-Speed Stability and Impact Resistance

Development of a Novel Displacement-Sensitive Magnetorheolog...

引用

International Conference on Applied Nonlinear Dynamics, Vibration and Control, ICANDVC 2024

作者： Tao, Zhu Gong, Ning Pan, Liyan Yu, Xiaotao Yang, Jian Sun, Shuaishuai CAS Key Laboratory of Mechanical Behaviour and Design of Materials School of Engineering Science University of Science and Technology of China Anhui Hefei230026 China School of Electrical Engineering and Automation Anhui University Anhui Hefei230039 China

ISBN: (纸本)9789819633166

With the ongoing enhancement of ride comfort standards, variable damping coefficient dampers are increasingly utilized in automobile suspensions. Among these, magnetorheological dampers (MRD) and continuous damping control dampers (CDC) are the most commonly used. MRD adjusts the damping coefficient by altering the magnetic field intensity, while CDC adjusts it by altering the flow channel size. However, due to the inherent delay of tens to hundreds of milliseconds in their damping coefficient adjustment, their effectiveness in suppressing high-frequency vibrations, particularly impacts, is limited. This paper introduces a novel displacement-sensitive MR damper (NDS-MRD). This damper controls its damping coefficient based on the position of the piston and the current amplitude. It offers a zero-delay adjustment of the damping coeffic.0ient, ensuring a substantial range of adjustable damping coefficients. Furthermore, the MTS force-displacement test and quarter-car model simulations confirm the distinct advantages of the NDS-MRD over conventional MR Damper and passive damper in terms of isolation from high-frequency vibrations and impact resistance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Vehicle suspensions

来源：评论

学校读者我要写书评

暂无评论

MSD-Det: Masonry structures damage detection dataset for preventive conservation of heritage

引用

Journal of Cultural Heritage 2025年 73卷 358-370页

作者： Long, Lingege Gan, Zhenkun Liu, Zhaoyi Zhao, Benyun Li, Qingxiang School of Art and Design Beijing Institute of Fashion Technology Beijing 100029 China School of Architecture and Urban Planning Beijing University of Civil Engineering and Architecture Beijing 100044 China Architecture Design and Research Institute of BUCEA CO LTD Beijing 100044 China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong China

For large and complex heritage masonry structures, preventive conservation reduces structural deterioration, reinforces cultural features, and enhances heritage value. Inspection and monitoring are the first steps of preventive conservation. However, the traditional manual visual inspection has limitations in terms of time and labor costs. Deep learning-based visual defect detection methods can provide an accurate and efficient solution for inspection and monitoring. The need for high-quality object-level datasets limits the application of deep learning in the preventive conservation of heritage masonry structures. Therefore, this study develops and releases a large-scale, high-resolution, multi-scene inspection MSD-Det dataset for heritage masonry damage detection. MSD-Det has 1082 high-resolution images, covering a wide range of heritage masonry structure types and including 7 common damage categories (cracks, fabric loss of masonry units, surface dissolution, efflorescence, discoloration, plant and moss). 17 deep learning object detection algorithms are applied to evaluate the accuracy, speed, and robustness of the dataset to validate the feasibility of the dataset, and real experiments on the Great Wall of Beijing's Panglong Mountain are conducted to confirm the practicality of MSD-Det dataset further. Compared with the existing datasets, MSD-Det extends the data quantity, improves the data quality, and encompasses a broader range of damage categories, contributing to a large-scale open detection dataset, which lays a solid foundation for advancing preventive preservation techniques and methods for heritage masonry structures. © 2025 Elsevier Masson SAS

关键词： Dataset Deep learning Heritage masonry structures Object detection Preventive conservation

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：