检索结果-内蒙古大学图书馆

defect detection of Primary Coil Spring of Heavy-Haul Locomotive by Dynamic Adaptive Parallel Fusion Residual Network

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Xiang, Junyue Chen, Shiqian Wang, Hongbing Wang, Kaiyun Zhai, Wanming Southwest Jiaotong Univ State Key Lab Rail Transit Vehicle Syst Chengdu 610031 Peoples R China

The damage of primary coil spring in heavy-haul locomotive poses a significant risk to the safety of railway transportation. However, the strong background noise caused by the complicated running environment usually drowns out the defect features of coil spring in the locomotive vibration response, which makes it challenging to detect the spring defect states in time. Considering the advantages of the efficient channel attention (ECA) and residual network (ResNet) in data mining, this article reports a novel dynamic adaptive parallel fusion residual network (DAPFRNet) for accurately detecting the defect degree of the coil spring of heavy-haul locomotive. The DAPFRNet begins by integrating a convolutional neural network (CNN) with ECA to autonomously extract sensitive features from the raw bogie frame acceleration signals. Then, a multiscale parallel residual network is constructed to deeply mine the multiscale latent features from the extracted information, which can effectively improve the feature learning capability by dynamically adjusting the scale of branches. Finally, an adaptive feature fusion module is designed to accurately integrate the branch features by enhancing the relationship awareness among distinct parallel branches, and thus achieves intelligent grading assessment of coil spring defects. Both dynamics simulations and field tests are carried out to show that the proposed method can effectively identify different degrees of defects in coil spring under different running speeds and damage locations.

关键词： defect detection efficient channel attention (ECA) heavy-haul locomotive parallel fusion residual network primary coil spring defect detection efficient channel attention (ECA) heavy-haul locomotive parallel fusion residual network primary coil spring

来源：评论

学校读者我要写书评

暂无评论

defect detection in Concrete Structures Based on Characteristics of Hammer Reaction Force and Apparent Stiffness of Concrete

引用

IEEE ACCESS 2025年 13卷 25325-25338页

作者： Shoda, Koki Kasahara, Jun Younes Louhi An, Qi Yamashita, Atsushi Univ Tokyo Grad Sch Frontier Sci Dept Human & Engn Environm Studies Chiba 2778563 Japan Univ Tokyo Grad Sch Engn Dept Precis Engn Tokyo 1138656 Japan

Concrete structures play a vital role in civil engineering. However, their deterioration poses a significant safety risk, making regular inspection essential. The impact method detects defects by analyzing characteristic reaction forces generated when striking areas with internal cavities, offering the advantage of being unaffected by acoustic noise and not requiring direct sensor contact. Traditional approaches, relying solely on reaction force signals, have struggled with low defect detection accuracy due to the similarity of signals between healthy and defective concrete and limited data quantity. To address this challenge, we propose a novel method that enhances defect discrimination accuracy by integrating statistical processing and physical property analysis within a machine learning framework designed for force signal characteristics. Our method employs wavelet transformation to convert short-duration force signals into high-resolution time-frequency features, capturing their non-stationary behavior in detail. For dimensionality reduction, we use Uniform Manifold Approximation and Projection to accurately embed data clusters near decision boundaries in a low-dimensional space. The embedded data is then clustered using Fuzzy c-means, and defect cluster identification is automated based on the apparent stiffness of the concrete. Experimental validation through field and laboratory tests confirmed the effectiveness of our method, demonstrating a significant improvement in defect detection accuracy. By advancing the precision and automation of the impact method, this study contributes a valuable tool for enhancing the safety and maintenance of concrete structures.

关键词： Force Accuracy Inspection Time-frequency analysis Wavelet transforms defect detection Feature extraction Dimensionality reduction Robustness Noise Non-destructive testing hammering test structural health monitoring concrete defect detection machine learning robustness against acoustic noise

来源：评论

学校读者我要写书评

暂无评论

defect detection in hot stamping process printed matter by beluga optimized support vector machine with opposition-based learning

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2025年第1期19卷 1-13页

作者： Ru, Xin Yao, Yingdong Li, Jianqiang Peng, Laihu Sun, Zhuocheng Zhejiang Sci Tech Univ Zhejiang Key Lab Modern Text Equipment Technol 9282 St Hangzhou 310018 Zhejiang Peoples R China Zhejiang Sci Tech Univ Longgang Res Inst 3FBldg 2Printing Ind Innovat Serv ComplexCentur Wenzhou 325000 Zhejiang Peoples R China

The high surface reflectivity and concave-convex of hot stamping process printed matters lead to poor defect detection accuracy. To solve this problem, this paper proposes a defect detection model (OBL-BWO-SVM) for hot stamping process printed matters based on oppositional learning (OBL) beluga optimized (BWO) support vector machine (SVM). First, in terms of image acquisition, a new light source illumination method is proposed for the own characteristics of hot stamping, the gray level covariance matrix (GLCM) is applied to extract the image information to build a dataset, and principal component analysis (PCA) is applied to reduce the dimensionality of the dataset. Then, SVM is used as the base model and the category weights of SVM are adjusted for the sample data category imbalance problem. Then, the C and gamma parameters of SVM are optimized using OBL-BWO. Finally, 14400 images are used as the dataset, in which the proportions of defect-free samples and defective samples are 48.9% and 51.1%, respectively, and are divided into the training set and the test set according to the ratio of 7:3. The models in this paper and the commonly used models are tested on this dataset. The experimental results show that the accuracy of the model proposed in this paper is 96.11%, precision is 94.61%, recall is 95.75%, and F1 score is 95.18%. Compared with the commonly used methods, the method proposed in this paper has higher classification accuracy and can improve the accuracy of printed matter defect detection during hot stamping printing.

关键词： Hot stamping process defect detection Printed matter Support vector machine

来源：评论

学校读者我要写书评

暂无评论

defect detection infused deposition modelling using lightweight convolutional neural networks

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 141卷

作者： Kuriachen, Basil Jeyaraj, Rathinaraja Raphael, Deepak Ashok, P. Sundari, P. Shanmuga Paul, Anand Natl Inst Technol Calicut Calicut 673601 Kerala India Univ Houston Victoria Victoria TX 77901 USA Symbiosis Int Pune 412115 Maharashtra India SRM Inst Sci & Technol Coll Allied Hlth Sci Trichy 621105 Tamil Nadu India LSU Hlth Sci Ctr New Orleans New Orleans LA 70112 USA

Early detection of defects in additive manufacturing (AM) processes has significant benefits such as reducing material waste and improving production time, which results in an increase in overall productivity. Existing methods for defect detection in AM lacks in generalizability, takes more time for training, and finds difficulty in identifying complex defects in the vertical plane in real-time. In addition, there are no datasets freely available for active research. Considering this, in this article, we propose an algorithm that uses simple convolutional neural networks (CNNs), which is an artificial intelligence (AI) technique, to detect major defects in layers during fused deposition modelling (FDM) in real-time. It analyses AM infill patterns to identify irregularities such as staircase, overfill, and void defects. The proposed model is trained using the dataset that has been collected manually and augmented at different scales for building a robust model. The results show that the proposed model is very effective and provides over 97.77% accuracy on real-time images. Furthermore, our proposed model uses fewer convolution layers than popular models, such as visual geometry group (VGG) 19, mobile neural network (MobileNet) V2, residual network (ResNet) 50, and densely connected convolutional network (DenseNet) 121. In addition, we open source the custom-generated datasets that contain staircase, overfill, and void defects images. For future research, we plan to expand dataset diversity and employ real-time adaptive learning.

关键词： Additive manufacturing Application of artificial intelligence Convolutional neural networks defect detection Fused deposition modelling

来源：评论

学校读者我要写书评

暂无评论

defect detection in Industrial Soldering Processes Using Machine Learning: A Critical Literature Review

引用

IEEE ACCESS 2025年 13卷 41533-41558页

作者： Eisentraut, Luca Hosch, Johanna Roytenberg, Maksym Benecke, Amelie Penava, Pascal Buettner, Ricardo Helmut Schmidt Univ Univ Fed Armed Forces Hamburg Chair Hybrid Intelligence D-22043 Hamburg Germany

As electrical devices take on more life-critical roles, such as in autonomous driving, ensuring the quality of solder joints during production becomes increasingly important. Recently, there has been a growing interest in using machine learning techniques for this purpose. However, current research lacks a comprehensive overview that categorizes and analyzes relevant studies based on their specific intervention points within the production process. This literature review aims to examine and evaluate research coverage along three dimensions: intervention points in the process, non-destructive testing methods, and machine learning techniques employed. For this review, 112 conference papers and journal articles published since 2010 were selected from three databases using the PRISMA methodology. These publications were classified into the three dimensions previously mentioned, summarized, and analyzed. Furthermore, the literature core is critically evaluated to identify research gaps and limitations. The analysis shows that most studies focus on solder joint control, with few addressing intervention points in solder paste and component placement. Visual imaging and neural networks are the dominant techniques for non-destructive testing and machine learning, respectively. Despite a variety of literature that uses high-performance neural networks, meeting industrial detection standards often requires tolerating high false alarm rates. The findings contribute to structuring existing research and identifying research needs, particularly in validating these systems and integrating data from various testing methods and intervention points.

关键词： Systematic literature review Soldering defect detection Testing Quality control Visualization Production Process control Inspection Databases Critical literature review defect detection machine learning solder joint

来源：评论

学校读者我要写书评

暂无评论

defect detection of Photovoltaic Panels to Suppress Endogenous Shift Phenomenon

引用

IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING 2025年第1期38卷 83-95页

作者： Chen, Haiyong Zhang, Yaxiu Zhang, Yan Yan, Xingwei Zhang, Xin Zou, Kunlin Hebei Univ Technol Coll Artificial Intelligence & Data Sci Tianjin 300130 Peoples R China Tianjin Adv Technol Res Inst Intelligent Ubiquitous Percept Collaborat Innovat Tianjin 300387 Peoples R China Natl Univ Def Technol Coll Elect Sci Changsha 410073 Hunan Peoples R China

Efficient and intelligent surface defect detection of photovoltaic modules is crucial for improving the quality of photovoltaic modules and ensuring the reliable operation of large-scale infrastructure. However, the scenario characteristics of data distribution deviation make the construction of defect detection models for open world scenarios such as photovoltaic manufacturing and power plant inspections a challenge. Therefore, we propose the Gather and Distribute Domain shift Suppression Network. It adopts a single domain generalized method that is completely independent of the test samples to address the problem of distribution shift. Using a one-stage network as the baseline network breaks through the limitations of traditional domain generalization methods that typically use two-stage networks. It not only balances detection accuracy and speed but also simplifies the model deployment and application process. The network first employs the DeepSpine module to capture a wider range of contextual information. By concatenating and aligning multi-scale channel features, it effectively suppresses background style shifts. Building upon this, the Gather and Distribute Module performs cross layer interactive learning on multi-scale channel features. The multi-level features and semantic dependencies learned enhance the localization and recognition ability of target defects, thereby achieving the suppression of defect instance shift. Furthermore, we utilizes normalized Wasserstein distance for similarity measurement, reducing measurement errors caused by bounding box position deviations. We conducted a comprehensive evaluation of our network on the Electroluminescence Endogenous Shift Dataset and Photovoltaic Inspection Infrared Dataset. In scenarios with three production lines and four heights on two datasets, the detection accuracy of GDDS reached 91.2%, 82.3%, 79.9%, and 92.8%, 82.7%, 77.2%, and 69.2%, respectively. The experimental results showed that our method can a

关键词： Solar power generation Photovoltaic systems Inspection Production defect detection Feature extraction Manufacturing Data models Accuracy Solar panels defect detection of photovoltaic panels endogenous shift phenomenon single-domain generalized object detection photovoltaic manufacturing unmanned aerial vehicle photovoltaic inspection

来源：评论

学校读者我要写书评

暂无评论

defect detection in impeller parts utilising local geometric feature analysis

引用

INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH 2025年

作者： Wang, Rui Du, Wei Jiang, Qingchao Cao, Zhixing East China Univ Sci & Technol MOE Key Lab Smart Mfg Energy Chem Proc 130 Meilong Rd Shanghai Peoples R China East China Univ Sci & Technol State Key Lab Bioreactor Engn Shanghai Peoples R China

Impeller blades in aero-engines, vital for both military and civilian use, significantly impact operational efficiency through their surface quality. Surface defects like scratches can lead to severe consequences, including engine failures. Efficient defect detection in these blades is crucial. Traditional two-dimensional imaging methods fall short due to the blades' complex geometry and hidden defect areas. Currently, manual inspection methods dominate, leading to increased costs and reduced efficiency in industrial settings. Addressing these challenges, our paper introduces a three-dimensional point cloud-based defect detection method for impeller blades. This approach involves segmenting the blades using point clouds, employing normal vectors for data extraction, and reducing computational load through voxel down-sampling. It features a unique local feature extraction technique, combining normal vector aggregation with Fast Point Feature Histograms (FPFH) and fuzzy C-means clustering, to accurately identify blade defects. This method integrates both low-dimensional and high-dimensional features using a clustering algorithm to enhance scratch defect detection in complex impeller parts. The experimental results demonstrate that compared to existing leading methods, our approach achieves a defect detection rate that is more than 5% higher and the computational efficiency is increased up to 3 times compared to traditional solutions.

关键词： Point cloud local geometric feature defect detection industrial production line impeller blade

来源：评论

学校读者我要写书评

暂无评论

defect detection of Photovoltaic Cells Based on an Improved YOLOv8

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2025年第3期16卷 495-503页

作者： Li, Zhihui Wang, Liqiang Tianjin Univ Technol & Educ Tianjin 300222 Peoples R China Tianjin Engn Res Ctr Fieldbus Control Technol Tianjin 300202 Peoples R China

Currently defect detection in photovoltaic (PV) cells faces challenges such as limited training data, data imbalance, and high background complexity, which can result in both false positives and false negatives during the detection process. To address these challenges, a defect detection network based on an improved YOLOv8 model is proposed. Firstly, to tackle the data imbalance problem, five data augmentation techniques-Mosaic, Mixup, HSV transformation, scale transformation, and flip-are applied to improve the model's generalization ability and reduce the risk of overfitting. Secondly, SPD-Conv is used instead of Conv in the backbone network, enabling the model to better detect small objects and defects in low-resolution images, thereby enhancing its performance and robustness in complex backgrounds. Next, the GAM attention mechanism is applied in the detection head to strengthen global channel interactions, reduce information dispersion, and enhance global dependencies, thereby improving network performance. Lastly, the CIoU loss function in YOLOv8 is replaced with the Focal-EIoU loss function, which accelerates model convergence and improves bbox regression accuracy. Experimental results show that the optimized model achieves a mAP of 86.6% on the augmented EL2021 dataset, representing a 5.1% improvement over the original YOLOv8 model, which has 11.24 x 10<^>6 parameters. The improved algorithm outperforms other widely used methods in photovoltaic cell defect detection.

关键词： Photovoltaic cells defect detection YOLOv8 loss function

来源：评论

学校读者我要写书评

暂无评论

defect detection in EBSM components through selective box fusion of modern object detection

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-17页

作者： Han, Rui Wang, Chenwei Wang, Yuzhong Zhang, Yihui Guo, Wenhua Zi, Yanyang Zhao, Jiyuan Xi An Jiao Tong Univ State Key Lab Mfg Syst Engn Xian 710049 Peoples R China Beijing Informat Sci & Technol Univ Sch Automat Beijing 100192 Peoples R China

Additive Manufacturing (AM) technology has gained widespread application across various industries due to its capability to directly produce products from computer-aided design models. Among AM techniques, the Electron Beam Selective Melting (EBSM) process has attracted significant attention, particularly in aerospace and automotive industries, owing to its high precision, speed, and excellent material properties. However, various defects, especially internal defects that inevitably arise during the manufacturing process, significantly limit the performance of EBSM parts. In this study, X-ray computed tomography (CT) was utilized to scan EBSM parts, and cross-sectional images were employed to train several state-of-the-art modern object detection models for evaluating their effectiveness in detecting internal defects. Sparse R-CNN demonstrated the best overall performance, while the YOLO series excelled in specific metrics. To further capitalize on the strengths of different detection models, a model ensemble approach, Selective Box Fusion (SBF) is proposed. This approach employs voting and weighted fusion of detection boxes to mitigate errors inherent in individual models. Experimental results show that the SBF ensemble method effectively integrates the advantages of multiple detection models, leading to improvements across various evaluation metrics compared to individual models and other ensemble methods.

关键词： Additive manufacturing Electron beam selective melting Computed tomography defect detection Model ensemble

来源：评论

学校读者我要写书评

暂无评论

A Transformer and YOLOv5-Integrated Visual defect detection Method for Mechanic Parts

引用

JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS 2025年第6期34卷

作者： Han, Susu Gao, Xintao Yellow River Conservancy Tech Inst Sch Informat Engn Kaifeng 475003 Peoples R China Henan Vocat Coll Light Ind Fdn Teaching Dept Zhengzhou 450000 Peoples R China

The defect detection of mechanical parts is a key link in industrial production, but traditional manual detection methods are inefficient and difficult to meet the needs of modern manufacturing. To overcome this challenge, this paper proposes a mechanical part visual defect detection method based on deep vision sensing technology, which integrates Transformer and YOLOv5 models. First, the YOLOv5 model has improved its ability to extract part features. Subsequently, a new detection model was constructed by combining the pre-trained transformer structure with the improved YOLOv5. To validate the performance of the proposed method, we selected two real datasets for experimentation. First, we evaluated the improvement of key elements in the model and found that the improvement of certain elements can significantly improve the average detection accuracy. Next, we compared the proposed model with several typical detection methods, including SSD, Faster R-CNN and RetinaNet. The experimental results show that under the same dataset and measurement standards, the performance of this scheme is superior to the comparative methods, with higher detection accuracy and faster detection speed. The contribution of this paper lies in proposing an innovative visual defect detection method for mechanical parts, which combines the advantages of Transformer and YOLOv5 to achieve efficient and accurate detection of mechanical part defects. This method not only improves detection efficiency, but also provides strong technical support for quality control in industrial production.

关键词： Deep vision sensing defect detection mechanical parts industrial electronics

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：