检索结果-内蒙古大学图书馆

LFM-Chirp-Square pulse-compression thermography for debonding defects detection in honeycomb sandwich composites based on THD-processing technique

引用

NONDESTRUCTIVE TESTING AND EVALUATION 2024年第4期39卷 832-845页

作者： Liu, Guozeng Gao, Weicheng Liu, Wei Xu, Jianxun Li, Rui Bai, Weiliang Harbin Inst Technol Dept Astronaut Sci & Mech Harbin Peoples R China Harbin Univ Commerce Coll Light Ind Harbin Peoples R China

Honeycomb Sandwich Composites (HSCs) have been widely used in aerospace and aircraft industries because of their high temperature and corrosion resistance, etc. As defects and damage to HSCs are unavoidable, non-destructive testing (NDT) is essential to ensure the reliability of HSCs. A series of artificial flat-bottomed holes (FBHs) defects of HSCs were prepared for pulse thermography (PT) and LFM-Chirp-Square pulse-compression thermography (PuCT). LFM-Chirp-Square PuCT has the advantage of frequency modulation over PT to detect different depth ranges of FBHs defects. In order to improve the efficiency of defect detection, pulse phase thermography (PPT) and total harmonic distortion (THD) techniques were applied to process the infrared image sequences. The results show that THD processing technique outperforms the PPT processing technique in improving the signal-to-noise ratio (SNR) from feature images. The combination of LFM-Chirp-Square PuCT and THD techniques can be applied to improve the defect detection identification results in HSCs.

关键词： Honeycomb Sandwich Composites (HSCs) Total harmonic distortion (THD) defects detection LFM-Chirp-square pulse-compression thermography (PuCT) Signal-to-noise ratio (SNR)

来源：评论

学校读者我要写书评

暂无评论

Small target detection algorithm for printing defects detection based on context structure perception and multi-scale feature fusion

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2024年第1期18卷 657-667页

作者： Chen, Wenqian Zheng, Yuanlin Liao, Kaiyang Liu, Haiwen Miao, Yalin Sun, Bangyong Xian Univ Technol Coll Fac Printing Packaging Engn & Digital Media Technol Xian 710048 Peoples R China Key Lab Printing & Packaging Engn Shaanxi Prov Xian 710048 Peoples R China

Small target detection is an important research direction in the field of computer vision, which is widely used in popular fields such as industrial defect detection, satellite remote sensing image detection. However, in printing defects detection, due to the complex defect background and small target, it is difficult to extract multi-scale features, and the extracted features have less available information. Therefore, this paper improves YOLOv7 and proposes an end-to-end printing defects detection algorithm based on context structure perception and multi-scale feature fusion (CM-YOLOv7). CM-YOLOv7 is mainly composed of a Context Structure Awareness Module (CSAM), a Multi-scale Feature Interaction Module (MFIM) and a Feature Refinement Layer Module (FRLM). Firstly, the CSAM uses multiple convolution kernels of different sizes to obtain features of different receptive fields and enhance multi-scale feature extraction. Secondly, for the extracted multi-scale features, the MFIM adaptively fuses the features of adjacent layers to achieve mutual learning between coarse-grained information and fine-grained information and improves the expression ability of small target features lost after convolution. Finally, in order to refine the edge information of the defect target more effectively and enhance the feature expression ability of the image, an FRLM is designed in MFIM. In the experimental part, this paper utilizes the printing defects detection dataset and DOTA-V1.0 dataset in order to better evaluate the effect of the algorithm. The experimental results show that the CM-YOLOv7 model proposed in this paper has a more accurate detection effect on the small target of printing defects.

关键词： Object detection Multi-scale feature Receptive fields Context information defects detection

来源：评论

学校读者我要写书评

暂无评论

Novel intelligent defects detection of boiler water walls in thermal power plants based on OFM_SSD

引用

DISPLAYS 2024年 85卷

作者： Han, Yongming Wang, Lei Liu, Jintao Yuan, Liang Liu, Hongxu Ma, Bo Geng, Zhiqiang Beijing Univ Chem Technol Coll Informat Sci & Technol Beijing 100029 Peoples R China Chongqing Univ State Key Lab Mech Transmiss Adv Equipment Chongqing 400044 Peoples R China Natl Univ Def Technol Coll Syst Engn Changsha 410073 Peoples R China Shanghai Jiao Tong Univ Shanghai 200240 Peoples R China Beijing Univ Chem Technol Coll Mech & Elect Engn Beijing 100029 Peoples R China

The boiler is a critical component of conventional thermal power systems, where surface flaws in boiler water walls can significantly compromise safety and availability, potentially leading to substantial loss of life and property. Traditional detection methods, whether manual or based on machine learning, often prove costly, inefficient and time-consuming, failing to meet the stringent requirements for water wall inspection. Therefore, a novel surface defect detection model integrating an improved single shot multibox detector (SSD) with the optical flow method (OFM) (OFM_SSD) is proposed. The OFM enhances data sample diversity by augmenting the dataset derived from thermal power plants, while the incorporation of deconvolution techniques improves the model receptive field, thereby enhancing its ability to detect and classify small defects. Comprehensive experiments demonstrate that the OFM_SSD outperforms several existing models including the SSD model based on traditional expanded datasets (T_SSD), you only look once (YOLO), ordinary SSD, Regions with the CNN(R_CNN), and Deconvolution-only SSD (DSSD) in terms of accuracy in defect localization and classification. This advancement of the OFM_SSD not only reduces operational costs but also enhances detection capabilities, ultimately contributing to safer and more efficient operations within thermal power plants.

关键词： Optical flow method Single shot multibox detector defects detection Boiler water wall Thermal power plants

来源：评论

学校读者我要写书评

暂无评论

DefectGAN: Synthetic Data Generation for EMU defects detection With Limited Data

引用

IEEE SENSORS JOURNAL 2024年第11期24卷 17638-17652页

作者： Liu, Scarlett Ni, Hai Li, Chao Zou, Yukang Luo, Yiping Cent South Univ Sch Traff & Transportat Engn Changsha 410075 Hunan Peoples R China

Deep learning (DL)-based defect detection provides various robust automated solutions for maintaining the daily operations of electric multiple units (EMUs). However, a sophisticated detection model typically requires extensive, high-quality data. Therefore, effective detection of certain low-frequency defects can be challenging because it is impractical to collect a sufficient amount of data. To address the lack of targeted training data, a novel synthetic dataset generation method for defect detection of EMUs is proposed based on generative adversarial networks (GANs) and a 3-D CRH380A model. By using synthetic data, defect detection accuracy is significantly improved, even when the scope of real data is limited. The synthetic dataset is employed in this article to train three DL detection models (YOLO v5, Mask R-CNN, and TOOD), and comprehensive experiments are conducted to verify the proposed DefectGAN. The experimental results illustrate that the mixed dataset (synthetic and real data) can significantly improve defect detection accuracy for EMUs with limited data. With a few dozen real images, only mixing the synthetic images generated by the proposed DefectGAN into training datasets can increase the F1 score from 0 to 0.8. This work will significantly improve the accuracy of defect detection of existing trouble of moving EMU detection system (TEDS) during data scarcity, facilitate automated operation and maintenance of EMUs, and reduce overall operating costs.

关键词： Data models Three-dimensional displays Training Solid modeling Defect detection Generative adversarial networks Feature extraction CycleGAN data augmentation defects detection electric multiple unit (EMU) maintenance trouble of moving EMU detection system (TEDS)

来源：评论

学校读者我要写书评

暂无评论

A defects detection Method of Buried Liquid-Filled Pipes Based on T(0,1) Guided Waves

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Liu, Fulu Li, Zhiying Huang, Xiaofei Ma, Linhui Li, Jiyao Pu, Hang Long, Jun Xu, Lijun Xie, Yuedong Beihang Univ Sch Instrument & Optoelect Engn Beijing 100191 Peoples R China China Acad Space Technol Beijing Inst Space Mech & Elect Beijing 100094 Peoples R China China Acad Space Technol Beijing Inst Control Engn Beijing 100094 Peoples R China

In this article, we propose a method using T(0,1) guided waves combined with coil coding technique to detect defects in buried liquid-filled pipes implemented by an electromagnetic acoustic transducer (EMAT). Due to its non-dispersive properties and the fact that there is no energy loss in nonviscoelastic fluids, the T(0,1) mode is selected for pipe defects detection. The electromagnetic device that generates the circumferential magnetic field is optimized to excite the pure T(0,1) mode. To realize energy enhancement and defect location identification, the electromagnetic acoustic coil is spatially encoded by 11-bit Barker code and the receiver coil is multiplexed consisting of a spatial coded coil and a unit coil. The defect detection is accomplished through time-of-flight (TOF) time-frequency analysis, and the defect location identification is achieved by digital signal processing methods (cross correlation and convolution). The feasibility of this method is verified by the finite element (FE) model and experimental analysis, indicating the defect locating error in a liquid-filled pipes is less than 1%. Overall, the proposed method achieves a high-precision flaw detection and location identification.

关键词： Magnetic liquids Magnetic fields Soil Magnetostriction Acoustics Attenuation Ultrasonic imaging defects detection electromagnetic acoustic transducer (EMAT) guided waves liquid-filled pipe location identification

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based defects detection in Keyhole TIG Welding with Enhanced Vision

引用

MATERIALS 2024年第15期17卷 3871页

作者： Zhang, Xuan Zhao, Shengbin Wang, Mingdi Soochow Univ Sch Mech & Elect Engn Suzhou 215137 Peoples R China

Keyhole tungsten inert gas (keyhole TIG) welding is renowned for its advanced efficiency, necessitating a real-time defect detection method that integrates deep learning and enhanced vision techniques. This study employs a multi-layer deep neural network trained on an extensive welding image dataset. Neural networks can capture complex nonlinear relationships through multi-layer transformations without manual feature selection. Conversely, the nonlinear modeling ability of support vector machines (SVM) is limited by manually selected kernel functions and parameters, resulting in poor performance for recognizing burn-through and good welds images. SVMs handle only lower-level features such as porosity and excel only in detecting simple edges and shapes. However, neural networks excel in processing deep feature maps of "molten pools" and can encode deep defects that are often confused in keyhole TIG. Applying a four-class classification task to weld pool images, the neural network adeptly distinguishes various weld states, including good welds, burn-through, partial penetration, and undercut. Experimental results demonstrate high accuracy and real-time performance. A comprehensive dataset, prepared through meticulous preprocessing and augmentation, ensures reliable results. This method provides an effective solution for quality control and defect prevention in keyhole TIG welding process.

关键词： keyhole TIG welding deep learning defects detection

来源：评论

学校读者我要写书评

暂无评论

Edge Intelligence for Smart EL Images defects detection of PV Plants in the IoT-Based Inspection System

引用

IEEE INTERNET OF THINGS JOURNAL 2023年第4期10卷 3047-3056页

作者： Tang, Wuqin Yang, Qiang Hu, Xiaochen Yan, Wenjun Zhejiang Univ Coll Elect Engn Hangzhou 310027 Peoples R China

Given the huge installed capacity of photovoltaic (PV) worldwide, the traditional defect detection system for PV plants is infeasible, especially for large-scale plants. In this article, unmanned aerial vehicles (UAVs) mounted with several sensors and a computer in the cloud are used cooperatively to establish an Internet of Things-based cloud-edge computing infrastructure, which can automatically detect defects with low latency, low cost, and high accuracy. The pretrained models trained in the cloud server are embedded into the processor in UAVs to implement online detection. Specifically, given the characteristic of defects in electroluminescence images, a two-stage algorithm is proposed to identify the defects with high performance. In the first stage, cells, the basic unit in the PV module, are extracted using an encoder-decoder network. Then, a vision-based incremental defect classification algorithm is proposed for defect detection that integrates deep learning with prior knowledge to maximize computing efficiency. The performance of the proposed system is evaluated through extensive experiments.

关键词： Inspection Cloud computing Internet of Things Image edge detection Servers Computer architecture Hardware Cloud-edge deep learning defects detection Internet of Things (IoT)

来源：评论

学校读者我要写书评

暂无评论

Barker Code Thermography Inspection and Reliability Evaluation for CFRP defects detection

引用

RUSSIAN JOURNAL OF NONDESTRUCTIVE TESTING 2023年第10期59卷 1083-1092页

作者： Bu, Chiwu Liu, Tao Zhao, Bo Li, Rui Harbin Univ Commerce Sch Light Ind Harbin 150028 Peoples R China Donghua Univ Coll Informat Sci & Technol Shanghai 201620 Peoples R China Dalian Maritime Univ Coll Marine Engn Dalian 116026 Peoples R China

In this paper, Barker code thermography is used to detect delamination defects incarbon fiber reinforced polymer (CFRP). detection capability of this imaging technique is assessed through quantitative analysis of the signal-to-noise ratio (SNR) in the acquired feature images. An infrared thermography experimental system has been developed to implement the Barker code modulation for pulse compression excitation signals. A reference CFRP specimen with different diameter-to-depth ratio defects was tested. Three thermal wave imaging algorithms, namely principal component analysis (PCA), fitting correlation coefficient (FCC) and total harmonic distortion (THD), have been applied to process the acquired infrared images sequences, and determine SNR values characterizing the processing results. The experimental results show that Barker code thermography has the advantages of simple modulation and easy implementation. Also, the PCA algorithm outperforms the techniques of FCC and THD in terms of the SNR to enable effective identification defects in CFRP.

关键词： Barker code thermography CFRP defects detection thermal wave imaging algorithms SNR analysis principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Recent advances in machine learning for defects detection and prediction in laser cladding process

NEXT MATERIALS

引用

NEXT MATERIALS 2025年 7卷

作者： Ji, X. C. Chen, R. S. Lu, C. X. Zhou, J. Zhang, M. Q. Zhang, T. Yu, H. L. Yin, Y. L. Shi, P. J. Zhang, W. Foshan Univ Sch Mechatron Engn & Automat Foshan 528225 Peoples R China Acad Mil Sci Res Inst Chem Def Beijing 102205 Peoples R China Army Acad Armored Forces Natl Key Lab Remfg Beijing 100072 Peoples R China Chengdu State Owned Jinjiang Machine Factory Chengdu 610043 Peoples R China

As a fundamental component of artificial intelligence, machine learning has gained considerable prominence within the domain of laser cladding in recent years. By employing algorithms to analyze data, discern patterns and regularities, rendering predictions and decisions, machine learning has significantly influenced various aspects of laser cladding processes. The emergence of defects during the cladding procedure poses substantial challenges for the quality and performance of the cladding layers. Addressing the reliability and reproducibility of cladding quality is a paramount concern within laser cladding technology. Leveraging data-driven machine learning algorithms enables the monitoring and detection of defects throughout the laser cladding process. Moreover, these algorithms offer avenues for feedback regulation of the cladding process, optimizing parameters, and mitigating cladding defects, thereby establishing this as a research frontier. This paper presents an overview of the typologies and formation mechanisms of defects encountered during laser cladding, elucidates the signal characteristics and expounds upon monitoring principles and methodologies employed within the laser cladding process. Additionally, it synthesizes advancements in machine learning methodologies for signal feature extraction, defect classification, and predictive modeling within the laser cladding process. Furthermore, it encapsulates prevalent machine learning models and algorithms employed for defect detection. The findings highlight the efficacy of machine learning algorithms in detecting defects within laser cladding coatings, while concurrently establishing correlations between feature signals, coating defects, and cladding processes. Presently, supervised learning algorithms dominate the landscape of research, yet the potential of unsupervised and semi-supervised learning algorithms, with their diminished data annotation requirements, garners increasing attention within the rea

关键词： Laser cladding Machine learning defects detection Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

TSDD: A Two-Step defects detection Algorithm in Power Line Inspection

TSDD: A Two-Step Defects Detection Algorithm in Power Line I...

引用

IEEE-Power-and-Energy-Society General Meeting (PESGM)

作者： Wang, Jiangwei Tang, Zefan Hall, Elizabeth Zhao, Junhui Eversource Energy Berlin CT 06037 USA

ISBN: (纸本)9798350381849;9798350381832

Imagery-based inspection, with its small size, affordability, high-resolution imaging capability, and mobility, has become a preferred method in power line inspections. Meanwhile, artificial intelligence (AI)-enabled defects detection has been extensively studied to further improve the efficiency and accuracy of inspection tasks. However, traditional defect detection methods exhibit a high rate of false detections when applied to real-world utility data, impeding their widespread adoption. In this paper, we propose a two-step defects detection (TSDD) algorithm to mitigate these issues. During the first step, power components are located and classified, followed by removing the background. In the subsequent second step, defects within the power component region are detected. Our experiments demonstrate significant improvements in detecting small defects like broken bells and woodpecker holes, enhancing the accuracy and efficiency of power line inspections.

关键词： Artificial intelligence power line inspection defects detection

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：