Article
Automation & Control Systems
Xiaoqing Zheng, Song Zheng, Yaguang Kong, Jie Chen
Summary: This paper presents the latest advances in surface defect inspection using deep learning, focusing on industrial products in semiconductor, steel, and fabric manufacturing processes. The research provides literature reviews, traditional surface defect inspection algorithms, and applications of deep learning-based inspection algorithms.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Swarit Anand Singh, Aitha Sudheer Kumar, K. A. Desai
Summary: Small and Medium Enterprises (SMEs) and Micro, Small, and Medium Enterprises (MSMEs) are considering integrating machine vision with high throughput manufacturing lines to ensure consistent quality. Pre-trained Convolutional Neural Networks (CNNs) can enhance machine vision capabilities compared to rule-based classical image processing algorithms. Lack of labeled datasets and model development expertise restricts their usage for SMEs and MSMEs. This study examines the practicality of using publicly available labeled datasets to develop surface defect detection algorithms using pre-trained CNNs for typical machined components. The results show that explicitly labeled image datasets offer better prediction abilities in specific cases, and EfficientNet-b0 outperforms other networks for surface defect detection.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Interdisciplinary Applications
Cai Luo, Leijian Yu, Jiaxing Yan, Zhongwei Li, Peng Ren, Xiao Bai, Erfu Yang, Yonghong Liu
Summary: By using an unmanned aerial vehicle to capture panoramic images, employing distortion augmentation methods, and training on VGG-16, the PADENet network effectively tackles the challenges of detecting surface damage in panoramic images.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Du-Ming Tsai, Po-Hao Jen
Summary: This paper evaluates the unsupervised autoencoder learning method for automated defect detection in manufacturing, and proposes a new CAE model with regularizations that significantly improves the detection performance based on the center of defect samples.
ADVANCED ENGINEERING INFORMATICS
(2021)
Article
Multidisciplinary Sciences
Yazid Saif, Yusri Yusof, Anika Zafiah M. Rus, Atef M. Ghaleb, Sobhi Mejjaouli, Sami Al-Alimi, Djamal Hissein Didane, Kamran Latif, Aini Zuhra Abdul Kadir, Hamood Alshalabi, Safwan Sadeq
Summary: In the context of Industry 4.0, manufacturing metrology plays a crucial role in machine inspection and measurement. This study investigates the use of MQTT protocol to enhance the performance of circularity measurement data transmission between cloud servers and round-hole data sources through Open CV. Accuracy in circularity measurement is vital for lubricant distribution, assemblies, and rotational force innovation. Vision inspection systems utilizing image processing techniques can detect quality concerns by analyzing the model's surface through circular dimension analysis. Experimental results showed a variation of 5 to 9.6 micrometers between non-contact-based 3SMVI system and contact-based CMM system for roundness evaluation. It is suggested that using a high-resolution camera and appropriate lighting conditions can further enhance result precision.
Review
Computer Science, Information Systems
Zhiqiang Chen, Jiehang Deng, Qiuqin Zhu, Hailun Wang, Yi Chen
Summary: This paper provides a systematic review of machine-vision-based leather surface defect inspection. It investigates and evaluates the performance of different detectors and machine learning methods for defect detection and identification. The challenges and future development trends of leather surface defect inspection are discussed, providing guidelines for designing and developing new solutions in this field.
Article
Chemistry, Analytical
Abdelrahman Allam, Medhat Moussa, Cole Tarry, Matthew Veres
Summary: Gears are crucial in many mechanical systems, including vehicle transmissions, but defects in their manufacturing process can lead to catastrophic failure. The current manual inspection process used by an automotive gear manufacturer in Guelph suffers from poor scalability and the risk of missing defects.
Article
Computer Science, Artificial Intelligence
Yi Liu, Changsheng Zhang, Xingjun Dong
Summary: In recent years, deep learning methods have been widely used in various industrial scenarios, promoting industrial intelligence. Real-time surface defect inspection of industrial products is one of the research focuses in industry. Surface defect inspection methods based on deep learning show great advantages and make it possible to detect defects in real time with high accuracy.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Computer Science, Artificial Intelligence
Benyi Yang, Zhenyu Liu, Guifang Duan, Jianrong Tan
Summary: This paper proposes a pixel-based defect inspection method for metal surface, which combines different depth Unet branches with dense skip connections, utilizes residual shape adaptive modules, and introduces a multi-branch training method. The method achieves accurate defect detection and localization.
PATTERN RECOGNITION
(2024)
Article
Chemistry, Multidisciplinary
Hongjun Wang, Xiujin Xu, Yuping Liu, Deda Lu, Bingqiang Liang, Yunchao Tang
Summary: Due to surface defects, inadequate contrast, and resemblance between noise and defects, edge detection is challenging in dimensional error detection. This research proposes a combined approach using the YOLOv6 deep learning network and metal lock body parts for accurate and rapid defect detection. An enhanced Canny-Devernay algorithm is used for size measurement.
APPLIED SCIENCES-BASEL
(2023)
Article
Chemistry, Multidisciplinary
Chaoquan Tang, Erfei Gao, Yingming Li, Menggang Li, Deen Bai, Hongwei Tang, Gongbo Zhou
Summary: The coal mine wind shaft is an important ventilation channel in coal mines, and its long-term safety is crucial. However, the current manual inspection of wind shafts has low reliability and high risk. The two main problems in shaft wall detection are the high humidity and dust concentration in the ventilation shafts, making imaging difficult, and the long and irregular cracks on the shaft wall. To address these issues, experiments were conducted to determine the mapping analysis between water vapor and dust concentration and image definition. A robot was designed to move along the axial and circumferential directions to approach the shaft wall, and a crack parameter detection method based on deep learning was used to control the robot's movement direction according to the crack direction.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Electrical & Electronic
Jiaxu Zhang, Jiong Zhang, Jiejun Chen, Shengchun Wang, Liang Wang
Summary: Current state-of-the-art railway surface defect inspection systems face the dilemma of false alarm and miss detection. To address this challenge, a bimodal detection scheme using feature-level fusion and decision-level fusion is designed. An improved evidential fusion algorithm with a three-branched evidential weight structure and the Transferable Belief Model is proposed, achieving outstanding performance in effectiveness and robustness analysis. The efficiency of the hybrid fusion-based detection scheme in solving rail surface defect problems is validated through theoretical justifications and experimental results.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Multidisciplinary
Jiangang Lin, Dongxing Wang, Hongzhi Tian, Zhaocai Liu
Summary: A one-shot machine-vision method based on texture orientation histogram is proposed for detecting defects in the surface texture of metal parts. Utilizing an improved Mean-C local threshold method to extract skeleton texture, statistical information is used for pre-processing texture direction, followed by a novel angle region growth method for detecting main texture clusters and abnormal texture clusters.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2021)
Article
Computer Science, Information Systems
Dejene M. Sime, Guotai Wang, Zhi Zeng, Bei Peng
Summary: The use of machine vision and deep learning in intelligent industrial inspection is important, but deep learning-based defect segmentation has not been widely studied. Existing state-of-the-art methods need further analysis when applied to unknown or defect segmentation datasets. We conducted an experimental study on recent deep learning-based segmentation methods for steel surface defect segmentation using two public datasets. We also proposed and trained a hybrid transformer-based encoder with CNN-based decoder head, achieving state-of-the-art results with high Dice scores.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Huangyuan Wu, Bin Li, Lianfang Tian, Zhengzheng Sun, Chao Dong, Wenzhi Liao
Summary: Visual inspection technology based on deep learning has achieved great success in surface defect inspection tasks. However, most existing methods transfer knowledge from natural datasets, which is suboptimal due to dataset gap and misalignment of task objectives. To address these issues, a contrastive and restorative self-supervised learning framework (CoRe) is proposed. Experimental results demonstrate that our method outperforms existing self-supervised learning methods, supervised pretraining, and specific defect inspection methods.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Multidisciplinary
Sicheng Jiao, Shixiang Wang, Minge Gao, Min Xu
Summary: This paper presents a non-contact method of thickness measurement for thin-walled rotary shell parts based on a chromatic confocal sensor. The method involves using a flip method to obtain surface profiles from both sides of the workpiece, measuring the decentration and tilt errors of the workpiece using a centering system, establishing a unified reference coordinate system, reconstructing the external and internal surface profiles, and calculating the thickness. Experimental results show that the method can accurately measure the thickness of a sapphire spherical shell workpiece and is consistent with measurements of other materials.
Article
Engineering, Multidisciplinary
Rajeev Kumar, Sajal Agarwal, Sarika Pal, Alka Verma, Yogendra Kumar Prajapati
Summary: This study evaluated the performance of a CaF2-Ag-MXene-based surface plasmon resonance (SPR) sensor at different wavelengths. The results showed that the sensor achieved the maximum sensitivity at a wavelength of 532 nm, and higher sensitivities were obtained at shorter wavelengths at the expense of detection accuracy.
Article
Engineering, Multidisciplinary
Attilio Di Nisio, Gregorio Andria, Francesco Adamo, Daniel Lotano, Filippo Attivissimo
Summary: Capacitive sensing is a widely used technique for a variety of applications, including avionics. However, current industry standard Capacitive Level Sensors (CLSs) used in helicopters perform poorly in terms of sensitivity and dynamic characteristics. In this study, novel geometries were explored and three prototypes were built and tested. Experimental validation showed that the new design featuring a helicoidal slit along the external electrode of the cylindrical probe improved sensitivity, response time, and linearity.
Article
Engineering, Multidisciplinary
Kai Yang, Huiqin Wang, Ke Wang, Fengchen Chen
Summary: This paper proposes an effective measurement method for dynamic compaction construction based on time series model, which enables real-time monitoring and measurement of anomalies and important construction parameters through simulating motion state transformation and running time estimation.
Article
Engineering, Multidisciplinary
Hui Fu, Qinghua Song, Jixiang Gong, Liping Jiang, Zhanqiang Liu, Qiang Luan, Hongsheng Wang
Summary: An automatic detection and pixel-level quantification model based on joint Mask R-CNN and TransUNet is developed to accurately evaluate microcrack damage on the grinding surfaces of engineering ceramics. The model is effectively trained on actual micrograph image dataset using a joint training strategy. The proposed model achieves reliable automatic detection and fine segmentation of microcracks, and a skeleton-based quantification model is also proposed to provide comprehensive and precise measurements of microcrack size.
Review
Engineering, Multidisciplinary
Sang Yeob Kim, Da Yun Kwon, Arum Jang, Young K. Ju, Jong-Sub Lee, Seungkwan Hong
Summary: This paper reviews the categorization and applications of UAV sensors in forensic engineering, with a focus on geotechnical, structural, and water infrastructure fields. It discusses the advantages and disadvantages of sensors with different wavelengths and addresses the challenges of current UAV technology and recommendations for further research in forensic engineering.
Article
Engineering, Multidisciplinary
Anton Nunez-Seoane, Joaquin Martinez-Sanchez, Erik Rua, Pedro Arias
Summary: This article compares the use of Mobile Laser Scanners (MLS) and Aerial Laser Scanners (ALS) for digitizing the road environment and detecting road slopes. The study found that ALS data and its corresponding algorithm achieved better detection and delimitation results compared to MLS. Measuring the road from a terrestrial perspective negatively impacted the detection process, while an aerial perspective allowed for scanning of the entire slope structure.
Article
Engineering, Multidisciplinary
Nur Luqman Saleh, Aduwati Sali, Raja Syamsul Azmir Raja Abdullah, Sharifah M. Syed Ahmad, Jiun Terng Liew, Fazirulhisyam Hashim, Fairuz Abdullah, Nur Emileen Abdul Rashid
Summary: This study introduces an enhanced signal processing scheme for detecting mouth-click signals used by blind individuals. By utilizing additional band-pass filtering and other steps, the detection accuracy is improved. Experimental results using artificial signal data showed a 100% success rate in detecting obstacles. The emerging concepts in this research are expected to benefit radar and sonar system applications.
Article
Engineering, Multidisciplinary
Jiqiang Tang, Shengjie Qiu, Lu Zhang, Jinji Sun, Xinxiu Zhou
Summary: This paper studies the magnetic noise level of a compact high-performance magnetically shielded room (MSR) under different operational conditions and establishes a quantitative model for magnetic noise calculation. Verification experiments show the effectiveness of the proposed method.
Review
Engineering, Multidisciplinary
Krzysztof Bartnik, Marcin Koba, Mateusz Smietana
Summary: The demand for miniaturized sensors in the biomedical industry is increasing, and optical fiber sensors (OFSs) are gaining popularity due to their small size, flexibility, and biocompatibility. This study reviews various OFS designs tested in vivo and identifies future perspectives and challenges for OFS technology development from a user perspective.
Article
Engineering, Multidisciplinary
Yue Wang, Lei Zhou, Zihao Li, Jun Wang, Xuangou Wu, Xiangjun Wang, Lei Hu
Summary: This paper presents a 3-D reconstruction method for dynamic stereo vision of metal surface based on line structured light, overcoming the limitation of the measurement range of static stereo vision. The proposed method uses joint calibration and global optimization to accurately reconstruct the 3-D coordinates of the line structured light fringe, improving the reconstruction accuracy.
Article
Engineering, Multidisciplinary
Jaafar Alsalaet
Summary: Order tracking analysis is an effective tool for machinery fault diagnosis and operational modal analysis. This study presents a new formulation for the data equation of the second-generation Vold-Kalman filter, using separated cosine and sine kernels to minimize error and provide smoother envelopes. The proposed method achieves high accuracy even with small weighting factors.
Article
Engineering, Multidisciplinary
Tonglei Cao, Kechen Song, Likun Xu, Hu Feng, Yunhui Yan, Jingbo Guo
Summary: This study constructs a high-resolution dataset for surface defects in ceramic tiles and addresses the scale and quantity differences in defect distribution. An improved approach is proposed by introducing a content-aware feature recombination method and a dynamic attention mechanism. Experimental results demonstrate the superior accuracy and efficiency of the proposed method.
Article
Engineering, Multidisciplinary
Qinghong Fu, Yunxi Lou, Jianghui Deng, Xin Qiu, Xianhua Chen
Summary: Measurement and quantitative characterization of aging-induced gradient properties is crucial for accurate analysis and design of asphalt pavement. This research proposes the composite specimen method to obtain asphalt binders at different depths within the mixture and uses dynamic shear rheometer tests to measure aging-induced gradient properties and reveal internal mechanisms. G* master curves are constructed to investigate gradient aging effects in a wide range. The study finds that the composite specimen method can effectively restore the boundary conditions and that it is feasible to study gradient aging characteristics within the asphalt mixture. The study also observes variations in G* and delta values and the depth range of gradient aging effects for different aging levels.
Article
Engineering, Multidisciplinary
Min Li, Kai Wei, Tianhe Xu, Yali Shi, Dixing Wang
Summary: Due to the limitations of ground monitoring stations in China for the BDS, the accuracy of BDS Medium Earth Orbit (MEO) satellite orbits can be influenced. To overcome this, low Earth orbit (LEO) satellites can be used as additional monitoring stations. In this study, data from two LEO satellites were collected to improve the precise orbit determination of the BDS. By comparing the results with GPS and BDS-2/3 solutions, it was found that including the LEO satellites significantly improved the accuracy of GPS and BDS-2/3 orbits.