Article
Automation & Control Systems
Van Doi Truong, Jiaping Xia, Yuhyeong Jeong, Jonghun Yoon
Summary: Hardwood flooring products are popular due to their aesthetics, durability, low maintenance requirements, and affordability. This study developed an automatic machine vision-based inspection system with a robust algorithm to detect small hardwood flooring defects. The algorithm utilized image-processing techniques and the YOLOv5 deep-learning algorithm for object detection, demonstrating its potential in practical situations with different colors and patterns.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Metallurgy & Metallurgical Engineering
Xiang Li, Linyi Cui, Sara Shonkwiler, Sara McMains
Summary: The microstructural characteristics of spherical metal powders are important for the quality of mechanical parts made through powder metallurgy processes. Identifying individual powder particles from their microscopic images is a convenient and cost-efficient method for analyzing powder characteristics. We propose an automatic algorithm to accurately identify spherical powder particles, especially those heavily overlapped, from microscope images. We validate the accuracy and efficiency of our algorithm using real-world scanning electron microscope images, outperforming other existing methods with precision and recall above 99%.
JOURNAL OF IRON AND STEEL RESEARCH INTERNATIONAL
(2023)
Article
Computer Science, Information Systems
Jakkrit Onshaunjit, Jakkree Srinonchat
Summary: This research proposes an algorithmic scheme that can detect and classify all 14-known PCB defect types, achieving high accuracy in defect detection and classification. The scheme also provides information on the location, area, and nature of defects, which is useful in identifying root causes and adjusting the manufacturing process. Additionally, it can be integrated into machine vision to improve PCB quality and reduce production costs.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Optics
Shaoyong Yu, Yang-Han Lee, Cheng-Wen Chen, Peng Gao, Zhigang Xu, Shunyi Chen, Cheng-Fu Yang
Summary: Various techniques were combined to optimize an optical inspection system for automatically detecting defects in manufactured paper bowls. A self-assembled system was used to capture images of defects, using an image sensor with a multi-pixel array and an infrared LED matrix panel. Enhancements such as Gaussian filtering, Sobel operators, binarization, and connected components were employed to improve defect inspections. The results showed that the machine vision system is an efficient method for inspecting defects in fabricated paper bowls.
Article
Computer Science, Information Systems
Xinyu Tong, Ziao Yu, Xiaohua Tian, Houdong Ge, Xinbing Wang
Summary: This paper proposes a machine learning based method to improve the accuracy of automated optical inspection (AOI). By utilizing a customized deep learning model to preprocess and classify the images taken by AOI machine, the method reduces the rate of misjudgment significantly. Experimental results demonstrate the importance of this method for practical production of PCBs.
FRONTIERS OF COMPUTER SCIENCE
(2022)
Article
Mathematics
Javier Martinez-Torres, Alicia Silva Pineiro, Alvaro Alesanco, Ignacio Perez-Rey, Jose Garcia
Summary: This study introduces an automatic method for characterizing psoriasis images, including image pre-processing, feature extraction, lesion classification, and parameter obtaining. Endorsed by a professional dermatologist, this methodology is suitable for monitoring different types of lesions.
Article
Computer Science, Interdisciplinary Applications
Kung-Jeng Wang, Hao Fan-Jiang, Ya-Xuan Lee
Summary: This study proposes a four-stage defect detection model using convolution neural networks (CNNs) to reduce error rates and offer informative quality messages. The model achieves high precision and velocity and reduces labor power.
COMPUTERS & INDUSTRIAL ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Dawei Li, Qian Xie, Xiaoxi Gong, Zhenghao Yu, Jinxuan Xu, Yangxing Sun, Jun Wang
Summary: Damage to metro tunnel surfaces often leads to accidents due to lack of maintenance. An automatic Metro Tunnel Surface Inspection System (MTSIS) is designed for efficient and accurate defect detection, with hardware and software components covering data collection and image processing for defect recognition. High precision defect detection methods have shown promising performance in practical experiments and successful application on multiple metro lines.
ADVANCED ENGINEERING INFORMATICS
(2021)
Article
Chemistry, Analytical
Pawat Chunhachatrachai, Chyi-Yeu Lin
Summary: Automated optical inspection (AOI) is crucial for quality control of contact lenses, and the authors propose a novel algorithm, CLensRimVision, for precise and automated detection of rim defects. The algorithm achieves exemplary performance and offers valuable insights for defect detection strategies in the contact lens domain.
Article
Chemistry, Analytical
Paolo Brambilla, Chiara Conese, Davide Maria Fabris, Paolo Chiariotti, Marco Tarabini
Summary: Quality inspection in industrial production is benefiting from the combination of vision-based techniques and artificial intelligence algorithms. This paper discusses the defect identification problem for circularly symmetric mechanical components and compares the performances of a standard algorithm with a Deep Learning (DL) approach. The standard algorithm provides better results in terms of accuracy and computational time, but DL achieves high accuracy in identifying damaged teeth. The possibility of extending the methods and results to other circularly symmetrical components is also analyzed and discussed.
Article
Chemistry, Multidisciplinary
Hossam A. Gabbar, Abderrazak Chahid, Md. Jamiul Alam Khan, Oluwabukola Grace Adegboro, Matthew Immanuel Samson
Summary: In this paper, a new toolbox called CT-Based Integrity Monitoring System (CTIMS-Toolbox) is proposed for automated inspection of CT images and volumes in non-destructive testing for industrial tool quality and safety control. The toolbox consists of three main modules: database management, pre-processing, and defect inspection, utilizing computer vision and deep learning techniques.
APPLIED SCIENCES-BASEL
(2022)
Review
Engineering, Multidisciplinary
Koji Nakamae
Summary: This paper reviews the application of SEM-based electron microscopy in semiconductor inspection. It provides an overview of electron microscopy, discusses application areas such as mask inspection, and addresses future challenges.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2021)
Article
Engineering, Manufacturing
Weifeng Li, Bin Li, Shuanlong Niu, Zhenrong Wang, Miao Wang, Tongzhi Niu
Summary: This article proposes an end-to-end network to solve the problem of defect location and shape feature fusion. The location attention module enhances the perception of defect locations, while the shape detection module with feature difference loss strengthens the detection of defect shapes. In the decoding stage, the features of different scales are fused to obtain the final defect region. The experimental results confirm the effectiveness of the proposed location and shape detection modules in the intersection over union on four datasets.
JOURNAL OF MANUFACTURING PROCESSES
(2023)
Article
Construction & Building Technology
E. Aldao, L. Fernandez-Pardo, L. M. Gonzalez-deSantos, H. Gonzalez-Jorge
Summary: This work proposes and compares different methods for autonomously inspecting railway bolts and clips. A prototype autonomous data acquisition system was developed, using LiDAR and camera sensors to obtain information about the state of the railway track. The system was tested on a railway track at the University of Vigo, and images were processed using image segmentation algorithms and a neural network to detect the bolts and clips.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Engineering, Electrical & Electronic
Xiaojun Wu, LingTeng Qiu, Xiaodong Gu, Zhili Long
Summary: Automatic surface defect inspection (ASDI) is a critical issue in industry affecting production quality and efficiency. This study introduces a generic method that can effectively detect defects even with small training data sets. By utilizing a ResMask GAN framework and establishing new industrial defect data sets, the algorithm achieves state-of-the-art results in various data sets.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Engineering, Multidisciplinary
Ying-Jun Lei, Rui-Jun Li, Wen-Shu Jiang, Lian-Sheng Zhang, Peng-Hao Hu, Qiang-Xian Huang, Kuang-Chao Fan
Summary: The study introduces a high-precision 2D coplanar micro-vibration generator with a flexible decoupling mechanism, capable of planar motion with excellent motion stroke, resolution, and load-bearing capacity.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2021)
Article
Optics
Yuchao Fan, Zhifeng Lou, Yubin Huang, Kuang-Chao Fan
Summary: A self-compensation method for improving the accuracy of roll angle measurement of a linear stage caused by non-parallelism of dual-beam due to time-dependent mechanical deformation of the support is proposed. The method was integrated into a 5-DOF sensor and verified through experiments under different supporting forces and ambient conditions, showing an average improvement of about 95% in compensated P-V values of the roll angles. The effectiveness and robustness of the proposed measurement system in changing environments were confirmed.
Article
Engineering, Electrical & Electronic
Lian-Sheng Zhang, You Tang, He Luan, Rui-Jun Li, Qiang-Xian Huang, Kuang-Chao Fan
Summary: The scanning probes on micro/nano-CMMs can achieve 3D measurement within a specific range, but the interferometer signal may break when the lateral displacement of the probe is greater than 10 mu m. By using a 2D angle fine-tuning stage, the measurement range of the probe can be extended to +/- 30 mu m while keeping the interference signal stable and uninterrupted.
IEEE SENSORS JOURNAL
(2021)
Article
Automation & Control Systems
Yuchao Fan, Yubin Huang, Yejin Chen, Zhifeng Lou, Kuang-Chao Fan
Summary: This paper introduces a new volumetric error modeling method based on the vector transfer (VT) method, which simultaneously measures the geometric errors in each axis using developed multi-degree-of-freedom measuring systems (MDFMs) to reduce measurement time and uncertainty. Through experimental verification, the volumetric errors of the tested OMM were accurately assessed with an accuracy of 93%, demonstrating the effectiveness and applicability of the VT method.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2022)
Article
Optics
Ruijun Li, Shaohua Ma, Peng Xu, Qiaosheng Pan, Yongqing Wei, Kuang-Chao Fan
Summary: The high-sensitivity dual-axis optoelectronic level proposed in this paper utilizes a double-layer liquid refraction principle and silicone oil as a reference for precision angle measurement. Experimental results demonstrate its capability to meet the requirements of high-precision tilt measurements.
OPTICS AND LASERS IN ENGINEERING
(2021)
Article
Optics
Yindi Cai, Luhui Wang, Yang Liu, Chang Li, Kuang-Chao Fan
Summary: A compact, portable and easy installation six-degree-of-freedom geometric error measurement system is proposed in this study to improve the accuracy of linear stages. Two mirrors with special position and orientation are innovatively used as sensitive elements for roll error, and a set of combined focus lenses is integrated into the measurement system to enhance the resolution of roll error.
Editorial Material
Chemistry, Multidisciplinary
Kuang-Chao Fan, Peter Kinnell
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Yindi Cai, Yinghao Gao, Kedi Yin, Qin Fu, Kuangchao Fan
Summary: The proposed methods in this study aim to improve the measurement accuracy of a compact LD-based system by active shaping of the laser spot and compensating for laser beam drifts.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Multidisciplinary
Ya-Xiong He, Rui-Jun Li, Jie Li, Zhen-Ying Cheng, Qiao-Sheng Pan, Qiang-Xian Huang, Kuang-Chao Fan
Summary: A nanometer precision height gauge for measuring the depth of small holes with a high aspect ratio was developed in this study. The gauge showed a high resolution and measurement uncertainty after calibration and verification, making it suitable for measuring the depth of small holes.
PRECISION ENGINEERING-JOURNAL OF THE INTERNATIONAL SOCIETIES FOR PRECISION ENGINEERING AND NANOTECHNOLOGY
(2022)
Article
Automation & Control Systems
Zhifeng Lou, Jiyun Zhang, Rui Gao, Liang Xu, Kuang-Chao Fan, Xiaodong Wang
Summary: This research proposes a 3D passive laser tracker for measuring the spatial trajectory of a moving target. By simplifying the laser tracker structure, a 2D rotary stage and a linear telescopic mechanism are used to measure the target's position and obtain world coordinates through coordinate transformation. After accuracy calibration and error compensation, the measurement error of the instrument is 49.2 μm.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Engineering, Multidisciplinary
Wenkai Zhao, Rui-Jun Li, Liuhui Duan, Zhenying Cheng, Qiaosheng Pan, Qiangxian Huang, Kuang-Chao Fan
Summary: A high-precision radius and sphericity measurement method for the microsphere of the CMM probe tip is proposed in this paper. The method involves measuring different circumferences of the microsphere to obtain the true radius of any measuring point on the surface and evaluating the sphericity using the minimum zone sphere method. The proposed method and system have been verified through experiments and can be used for precision measurements and compensations in micro-CMMs and other related applications.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2023)
Article
Engineering, Multidisciplinary
Jiyun Zhang, Zhifeng Lou, Kuang-Chao Fan, Hanping Zhang, Jingjie Zhou
Summary: This study aims to establish a precision vertical planar stage to provide programmable planar references for field accuracy calibration of areal sensors. By modeling, measuring, and compensating the spatial positional errors, the real-time motion accuracy of the planar stage is improved. A new six-degree-of-freedom measurement system is proposed for simultaneous measurement of all geometric errors. Experimental verification shows that the developed vertical stage achieves 89.1% accuracy improvement after positional error compensation. This vertical planar stage can generate any shape of programmed trajectory for the calibration of industrial areal sensors.
Article
Engineering, Electrical & Electronic
Ya-Xiong He, Rui-Jun Li, Jie Li, Wen-Kai Zhao, Zhen-Ying Cheng, Qiang-Xian Huang, Kuang-Chao Fan
Summary: This study proposes a global volumetric error compensation model for micro-coordinate measuring machines (CMMs) based on the Abbe and Bryan principles. By measuring geometric errors and offsets, and using these parameters for error compensation, the standard deviations of length measurements were significantly reduced.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Engineering, Electrical & Electronic
Wenkai Zhao, Ruijun Li, Liuhui Duan, Zhenying Cheng, Rongjun Cheng, Qiangxian Huang, Kuang-Chao Fan
Summary: A new method and system for radius and roundness measurement of microspheres have been proposed and developed in this article. Experimental results show that they can be used in the precision contact measurements of parts with microcircular characteristics.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Engineering, Electrical & Electronic
Wenkai Zhao, Ruijun Li, Xin Li, Yaxiong He, Zhenying Cheng, Liansheng Zhang, Qiaosheng Pan, Qiangxian Huang, Kuang-Chao Fan
Summary: A proposed analog electronic method effectively reduces nonlinear errors in interferometry measurements using designed circuits, as demonstrated by significant improvements across different frequency and amplitude ranges in experimental results.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Materials Science, Characterization & Testing
Bin Ma, Qingzhao Kong, Yewei Ding, Lin Chen, Weihang Gao
Summary: This study proposes an end-to-end damage detection framework that integrates emphasized channel attention, propagation, and aggregation-time-delay neural network (ECAPA-TDNN) with percussion techniques. The framework effectively detects internal damage within timber structures and distinguishes between different sizes of damage.
NDT & E INTERNATIONAL
(2024)
Article
Materials Science, Characterization & Testing
Zhiyuan Zhao, Lishuai Liu, Wen Liu, Da Teng, Yanxun Xiang, Fu-Zhen Xuan
Summary: The total focusing method (TFM) is a standard technique in ultrasonic phased array imaging and plays a crucial role in industrial non-destructive testing (NDT). This paper presents an improved TFM approach by formulating its imaging principle as a Boolean matrix and establishing a discretized tensor-based model. By employing sparse regularization strategy and a non-negative constraint solution algorithm, the proposed approach demonstrates superior capabilities in defect characterization and noise suppression compared to the traditional TFM.
NDT & E INTERNATIONAL
(2024)
Article
Materials Science, Characterization & Testing
Dongsoo Lee, Jung-Doung Yu, Seokgyu Jeong, Geunwoo Park, Jong-Sub Lee
Summary: This study suggests a more accurate method for evaluating the integrity of drilled shafts using electromagnetic waves propagating through transmission lines. The experimental results show that the location and size of sound and defect segments can be more clearly identified with the use of connectors on the transmission line.
NDT & E INTERNATIONAL
(2024)
Article
Materials Science, Characterization & Testing
Lu-Nan Dai, Chen-Yin Ni, Kai-Ning Ying, Ling Yuan, Zhi Yang, Wei-Wei Kan, Zhong-Hua Shen
Summary: A laser ultrasonics based frequency domain synthetic aperture focusing technology has been developed for imaging internal horizontal hole defects in bimetallic composites with a diameter of approximately 1.0 mm. The results show that this technology can improve imaging quality and locating capability, with a low testing error.
NDT & E INTERNATIONAL
(2024)
Article
Materials Science, Characterization & Testing
Guillermo Cosarinsky, Jorge F. Cruza, Mario Munoz, Jorge Camacho
Summary: This study develops an ultrasound imaging method for industrial and structural components, which can automatically detect the surface and estimate the probe position and orientation. By fitting the parametric models based on measured surface echoes, the method achieves the measurement of surface echoes and estimation of probe position and orientation. Validation experiments show that this method can accurately detect defects in the component under different probe positions and orientations.
NDT & E INTERNATIONAL
(2024)
Article
Materials Science, Characterization & Testing
L. Gahleitner, G. Thummerer, G. Mayr, G. Mayr, P. Burgholzer, U. Cakmak
Summary: This study presents a one-dimensional photothermal method using the virtual wave concept to estimate subsurface interface parameters and demonstrates its application in layered materials. Experimental results validate the accurate estimation of interfacial parameters for the analyzed samples.
NDT & E INTERNATIONAL
(2024)
Article
Materials Science, Characterization & Testing
Pengxiang Ji, Yiming Jiang, Ruobing Zhao, Jing Zou
Summary: Computed laminography (CL) is a non-destructive imaging technique for plate-like samples that has challenges in exact reconstruction. Fusion laminography (FL) combines Fourier information from CL and CT to achieve precise reconstruction, showing superiority in artifact removal and edge preservation, particularly for irregular sample structures.
NDT & E INTERNATIONAL
(2024)
Article
Materials Science, Characterization & Testing
Guangzhi Chen, Odile Abraham, Damien Pageot, Olivier Durand, Mathieu Chekroun, Vincent Tournat
Summary: This paper investigates the application of Nonlinear Coda Wave Interferometry (NCWI) method in evaluating the nonlinear interface areas in highly heterogeneous materials. An experimental protocol is proposed and validated through numerical simulation and experimental results. The findings demonstrate that NCWI can be used to quantitatively analyze the nonlinear interface effects in complex media.
NDT & E INTERNATIONAL
(2024)
Article
Materials Science, Characterization & Testing
Ronghua Xu, Raul Enrique Beltran-Gutierrez, Max Kaeding, Alexander Lange, Steffen Marx, Joern Ostermann
Summary: This study compares the signal response of four different couplant materials in acoustic emission analysis and ultrasonic testing, and analyzes their impact on the signal response of a piezoelectric sensor. The results indicate that acrylic adhesive pads and hot glue demonstrate more reliable signal transmission in certain frequency ranges, while honey and vaseline perform better in other frequency ranges. Acrylic adhesive pads and honey are considered the preferred couplant materials.
NDT & E INTERNATIONAL
(2024)
Article
Materials Science, Characterization & Testing
Yong-Ho Kim, Jung-Ryul Lee
Summary: An artificial intelligence system for phased-array ultrasonic testing (PAUT) was developed in this study using a newly configured training dataset and neural network. Three experiments were conducted to verify its performance, showing improved classification accuracy of signals and successful data evaluation, benefiting the PAUT experts.
NDT & E INTERNATIONAL
(2024)
Article
Materials Science, Characterization & Testing
Shaun Mcknight, S. Gareth Pierce, Ehsan Mohseni, Christopher Mackinnon, Charles Macleod, Tom 'Hare, Charalampos Loukas
Summary: This work proposes four synthetic data generation methods to address the issue of limited training data in Non-Destructive Ultrasonic Testing. Experimental results demonstrate that these methods significantly improve the classification performance of real experimental images.
NDT & E INTERNATIONAL
(2024)
Article
Materials Science, Characterization & Testing
Xintao Xu, Zhixuan Chang, Eryong Wu, Shiwei Wu, Jian Chen, Keji Yang, Haoran Jin
Summary: This paper proposes a novel nozzle-side inspection method based on the data fusion of multi-view plane wave imaging (PWI) for ultrasonic non-destructive testing of nozzle-to-pipe welds. Experiments demonstrate the capability of sensitivity mappings to optimize the inspection configuration and serve as filters to fuse multi-view images. The proposed method enables accurate defect characterization and detection of slag, cracks, and lack of penetration in nozzle specimens.
NDT & E INTERNATIONAL
(2024)
Article
Materials Science, Characterization & Testing
Kai Wang, Zechen Luo, Shuang Xu, Wenxin Lai, Ruiqi Guan, Qijian Liu, Menglong Liu, Jing Rao, Xinlin Qing
Summary: In this study, an analytical framework is proposed to interpret the formation of defect-induced LDR in multilayered structures. By analyzing the reflections of Lamb waves at defect boundaries and obtaining the phase shift of reflected waves, the relationship between LDR frequency components and defect size is determined. Experimental validations are performed to improve the precision of defect characterization using LDR.
NDT & E INTERNATIONAL
(2024)
Article
Materials Science, Characterization & Testing
Shijie Jin, Chengjun Di, Jiakai Su, Siqi Shi, Zhongbing Luo
Summary: This paper proposes a mirrored composite-mode total focusing method (CTFM) for the quantitative detection and profile characterization of priori unknown irregular planar defects. Multiple views and normalization are used to achieve accurate imaging results.
NDT & E INTERNATIONAL
(2024)