相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Longxin Zhang et al.
Summary: A novel one-stage object detection method based on YOLOv4, called the MSSIF-Net, is proposed for the fault detection of freight train parts. It achieves high detection accuracy and speed, outperforming other traditional methods. Furthermore, the MSSIF-Net demonstrates favorable anti-interference ability.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Zhilong Yu et al.
Summary: This paper presents a lightweight and efficient network for tiny defect detection. It introduces the Diagonal Feature Pyramid and a multi-scale neck network, as well as an adaptive localization loss function, to improve the performance and accuracy of tiny defect detection.
APPLIED INTELLIGENCE
(2023)
Article
Automation & Control Systems
Anurag Choudhary et al.
Summary: This paper presents a vibro-acoustic fusion technique for accurate fault diagnosis of induction motors (IMs) under varying working conditions. The proposed method utilizes the Multi Input-Convolutional Neural Network (MI-CNN) to fuse the features of vibration and acoustic signals. Experimental results show that the suggested methodology is accurate and reliable for IMs and other rotating machine components.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Engineering, Electrical & Electronic
Longxin Zhang et al.
Summary: This study proposes a lightweight train image fault detection network (FDNet) under an edge computing environment. The network makes improvements in design and optimization, achieving high detection accuracy while maintaining a high detection speed.
IEEE SENSORS JOURNAL
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Chien-Yao Wang et al.
Summary: Real-time object detection is an important research topic in computer vision, and the development of new approaches in architecture optimization and training optimization has led to two related research topics. To address these topics, a trainable solution combining flexible and efficient training tools, proposed architecture, and compound scaling method is proposed. YOLOv7 outperforms all known object detectors in terms of speed and accuracy, achieving the highest AP accuracy of 56.8% among real-time object detectors with 30 FPS or higher on GPU V100.
2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR
(2023)
Article
Engineering, Multidisciplinary
V. S. Bharath Kurukuru et al.
Summary: This paper proposes an automatic defect detection mechanism using texture feature analysis and supervised machine learning method for classifying failures in photovoltaic modules. The proposed technique combines infrared thermography, fuzzy-based edge detection, and gray level co-occurrence matrix to extract texture features and uses a support vector machine classifier for classification. The results demonstrate high accuracy and early failure detection advantages of the developed algorithm.
INTERNATIONAL JOURNAL OF SYSTEM ASSURANCE ENGINEERING AND MANAGEMENT
(2022)
Article
Engineering, Electrical & Electronic
Syed Sahil Abbas Zaidi et al.
Summary: This article introduces the task of object detection and explores recent developments in deep learning-based object detectors. The article also provides a concise overview of benchmark datasets, evaluation metrics, and prominent backbone architectures used in detection, as well as lightweight classification models used on edge devices. Lastly, the article compares the performances of these architectures on multiple metrics.
DIGITAL SIGNAL PROCESSING
(2022)
Article
Computer Science, Artificial Intelligence
Xin Liu et al.
Summary: Improving detection accuracy is essential for industrial processes like producing printed circuit boards (PCBs). This paper introduces a method using a new loss function called Gaussian intersection of union (GsIoU) to enhance accuracy, achieving significant improvements over existing methods on the PCBC dataset.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Hardware & Architecture
Mengjiao Li et al.
Summary: During the production and processing of steel strips, surface defects can negatively impact their integrity and functionality. Traditional defect detection methods are insufficient, so we propose an improved YOLOv4 algorithm for steel strip surface defect detection.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Engineering, Electrical & Electronic
Ihor Konovalenko et al.
Summary: This study explores the issue of neural network architecture selection for detecting surface defects on metal structures, and proposes ResNet and DenseNet models with the best generalizing properties. The U-Net model with a ResNet152 backbone achieves the highest recognition accuracy.
Article
Computer Science, Information Systems
Longxin Zhang et al.
Summary: In this paper, a object detection model called BD-YOLO is proposed for automatic fault detection of freight train image. The model consists of four steps which includes feature extraction, multi-scale feature fusion, prediction across scale modules, and decoding of prediction. The model is trained using mosaic data enhancement and K-means clustering algorithm to improve detection accuracy and speed. Experimental results demonstrate that BD-YOLO model outperforms state-of-the-art object detection models with an average improvement of 17.57% in mean average precision on four types of datasets. The BD-YOLO model can accurately detect three typical faults of freight trains.
Article
Engineering, Electrical & Electronic
Ihor Konovalenko et al.
Summary: This study investigates the impact of illumination level on the quantitative indicators of mechanical damage of rolled metal strips. Through a physical model experiment and analysis using a neural network model, the study identifies the differences in damage recognition under different illumination levels and provides insights for further adjustments of industrial systems.
Article
Computer Science, Artificial Intelligence
Huan Zhang et al.
Summary: In this study, a novel cost-sensitive residual convolutional neural network model (CS-ResNet) was proposed to optimize PCB cosmetic defect detection by adding a cost-sensitive adjustment layer. Experimental results showed that CS-ResNet outperformed in multiple aspects.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Automation & Control Systems
Yang Zhang et al.
Summary: This article proposes a lightweight framework for real-time fault detection in freight trains, using a novel lightweight network and multi-region proposal network to improve accuracy and efficiency while reducing computational costs. Experimental results demonstrate significant improvements in accuracy with high real-time performance and lower computational burden on both public benchmark datasets and six fault datasets.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Automation & Control Systems
Kanghui Zhang et al.
Summary: This study introduces a convolutional neural network (CNN) with attention modules to accurately segment foreign objects in coal, aiming to improve the efficiency and safety of clean coal production. By incorporating attention mechanisms, the network is able to recognize and extract foreign objects while avoiding interference from the background and surrounding objects. Experimental results demonstrate that the model correctly identified 97% of foreign objects in the test image sets, achieving a mean intersection over union (MIOU) of 91.24% and a real-time detection speed exceeding 15 fps/s, meeting the real-time requirement.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Article
Engineering, Multidisciplinary
Yingying Xu et al.
Summary: This paper proposes a novel tunnel defect inspection method based on Mask R-CNN, with detailed studies on PAFPN and the edge detection branch, showing their robustness and accuracy in tunnel defect detection and segmentation.
Article
Computer Science, Information Systems
Cen Chen et al.
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
(2020)
Article
Computer Science, Artificial Intelligence
Runwei Ding et al.
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY
(2019)
Article
Engineering, Civil
Gabriel Krummenacher et al.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2018)
Article
Computer Science, Artificial Intelligence
Shaoqing Ren et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2017)
