Detection Of Small Defects Research Articles

On Detecting Internal Coating Defects in Pipes using EMAT

Pipeline integrity is a must to maintain to ensure safe and smooth operation. Therefore, periodic inspection is required to make timely decisions for replacement or repair. One of the problems faced in a pipeline network, and targeted by this work is internal coating defect detection, whereby it is required to locate and characterize damage in the internal coating of the pipe. Current industry practice is to replace an entire set of pipelines or its large segment due to unknown defect location, implying significant wastage. A widely used NDT technology, electromagnetic acoustic transducer (EMAT) is employed in this laboratory-based work, however, it is a challenging task to extract internal coating damage information from the received acoustic signal as it has low SNR and is highly non-linear and non-stationary, thus warranting the use of sophisticated algorithms for data analysis. Artificial defects in the form of 100% tape-wrap coating removal are introduced with dimensions 100 x 100 mm2, 30 x 30 mm2, and 10 x 10 mm2 (square-shaped). The Carbon-Steel pipe sample has a 12” diameter and 10 mm wall thickness. The objectives are to externally inspect the pipe sample using commercially available hand-held EMAT sensors with Lamb modes, and develop and employ Singular Spectrum Analysis (SSA) algorithm to characterize the internal coating defects. Only the largest defect is detected, whereby A1 Lamb mode shows precise location and shape, and acceptable sizing accuracy compared with A0, S0, and S1. Moreover, the results are repeatable over several scans, thus showing the effectiveness of the adopted methodology. The main novelty lies in the fact that the methodology does not require any modifications to the hardware of the EMAT setup, thus increasing the capability of the available hand-held equipment. Current and future work is focused on the detection of smaller defects.

Improved MobileNetV2-SSDLite for automatic fabric defect detection system based on cloud-edge computing

Fabric defect detection is the important step of ensuring the quality and price of textiles. In order to make the automatic fabric defect detection system used in production sites, a cloud–edge collaborative fabric defect system is proposed. Firstly, real-time defect detection is performed on edge device, the accuracy of small defect detection is ensured by improved MobileNetV2-SSDLite. The channel attention mechanism is introduced in the network to highlight defect features and suppress background noise features. The loss function is redefined by Focal Loss to overcome the imbalance of the number of defects and background candidate boxes. Then, detection result storage and model update are carried out in the cloud. Experiments show that the accuracy of the system is improved while maintaining the faster detection speed, among which, the accuracy of the Camouflage dataset with small defects has increased by 10.03% and the detection speed reaches 14.19FPS on NVIDIA Jeston Nano.

ESDDNet: efficient small defect detection network of workpiece surface

Defect detection of a workpiece surface is a basic and essential task in the production of products. Although significant progress has been made in workpiece surface defect detection, traditional methods still find it difficult to detect small defects efficiently. To deal with this problem, we propose an efficient small defect detection network with a novel parallel convolution module, serial convolution module and feature fusion module. First, a lightweight backbone network is used to extract the preliminary defect features. Second, the parallel convolution module and serial convolution module are used to obtain the abundant defect features. Then, the feature fusion module is used to fuse the shallow features with deep features, to enhance the features of the small defects. Finally, the obtained features are put into the corresponding detection head to get the final prediction results. The experimental results on a local cable dataset and a public printed circuit board dataset show that our method achieves a remarkable performance in detecting small defects and achieves a favorable trade-off between accuracy, speed and model size, which meets the requirements of industrial applications.

Using ISU-GAN for unsupervised small sample defect detection

Surface defect detection is a vital process in industrial production and a significant research direction in computer vision. Although today’s deep learning defect detection methods based on computer vision can achieve high detection accuracy, they are mainly based on supervised learning. They require many defect samples to train the model, which is not compatible with the current situation that industrial defect sample is difficult to obtain and costly to label. So we propose a new unsupervised small sample defect detection model-ISU-GAN, which is based on the CycleGAN architecture. A skip connection, SE module, and Involution module are added to the Generator, enabling the feature extraction capability of the model to be significantly improved. Moreover, we propose an SSIM-based defect segmentation method that applies to GAN-based defect detection and can accurately extract defect contours without the need for redundant noise reduction post-processing. Experiments on the DAGM2007 dataset show that the unsupervised ISU-GAN can achieve higher detection accuracy and finer defect profiles with less than 1/3 of the unlabelled training data than the supervised model with the full training set. Relative to the supervised segmentation models UNet and ResUNet++ with more training samples, our model improves the detection accuracy by 2.84% and 0.41% respectively and the F1 score by 0.025 and 0.0012 respectively. In addition, the predicted profile obtained using our method is closer to the real profile than other models used for comparison.

Fabric Defect Segmentation System Based on a Lightweight GAN for Industrial Internet of Things

Machine vision systems based on deep learning play an important role in the industrial Internet of things (IIoT) and Industry 4.0 applications, especially for product quality monitoring. Fabric defect detection is an important task in the industrial production of textiles and is crucial for product quality assurance. In actual production, the detection of many small and weak target defects remains challenging. Furthermore, industrial production requires high production rates and small model sizes in practice. This study proposes a lightweight segmentation system that meets real-time industrial production requirements. Herein, first, the defect sample image was repaired based on the image repair mechanism of the generative adversarial network model. Then, the difference between the defect sample and the repaired sample was obtained and subsequent processing, such as denoising and enhancement, was done. Finally, the defect areas were segmented. Our model was specifically designed for the segmentation of weak and small defects. This was achieved through adversarial training, optimization of an objective function, and image processing. Experimental comparisons show that the intersection over union of the three different datasets is 77.84%, 77.85%, and 73.6% and that our model is superior to the conventional semantic segmentation model. Furthermore, our model has good image restoration quality with a low mean absolute error and high structural similarity index. Additionally, our model is lightweight, has good real-time performance, and is suitable for applications in the IIoT and industrial production lines, such as embedded systems.

SOD‐YOLO: A Small Target Defect Detection Algorithm for Wind Turbine Blades Based on Improved YOLOv5

AbstractEarly and effective detection of wind turbine blade (WTB) surface defects can avoid complex and expensive repair problems and serious safety hazards. The traditional target detection methods have the problems of insufficient detection capability, long model inference time and low recognition accuracy for small targets and long strip defects in WTB datasets. This paper proposes a high‐precision model SOD‐YOLO for WTB surface defect detection based on UAVs image analysis of YOLOv5. First, the WTB images are preprocessed by foreground segmentation and Hough transform to build the WTB defect dataset. Then, a micro‐scale detection layer is added to the original YOLOv5, and the K‐means algorithm is used to re‐cluster anchors and add the CBAM attention mechanism to each feature fusion layer to reduce the loss of feature information for small target defects and other defects. In addition, to improve the detection efficiency, the channel pruning algorithm is used to reduce the model size. The experimental results show that the average accuracy (mAP) of the SOD‐YOLO algorithm on the WTB dataset reaches 95.1%, which is 7.82% better than YOLOv5, and the FPS is 28.3% better. Therefore, SOD‐YOLO is able to detect small target defects and other defects quickly and effectively.

Eddy Current Microsensor and RBF Neural Networks for Detection and Characterization of Small Surface Defects

Abstract The growing complexity of industrial processes and manufactured parts, the growing need for safety in service and the desire to optimize the life of parts, require the implementation of increasingly complex quality assessments. Among the various anomalies to consider, sub-millimeter surface defects must be the subject of particular care. These defects are extremely dangerous as they are often the starting point for larger defects such as fatigue cracks, which can lead to the destruction of the parts. Penetrant testing is now widely used for this type of defect, due to its good performance. Nevertheless, it should be abandoned eventually due to environmental standards. Among the possible alternatives, the use of eddy currents (EC) for conductive materials is a reliable, fast, and inexpensive alternative. The study concerns the design and modeling of eddy current probe structures comprising micro-sensors for non-destructive testing. The moving band finite element method is implemented for this purpose to take into account the movement of the sensor, experimental validations were conducted on a nickel-based alloy specimen. The real and imaginary parts of the impedance at every position of the sensor computed by experiments and simulations were in good agreement. The crack detection quality was quantified and the geometric characteristics of the defects were estimated using RBF NN (Radial Basis Function Neural Networks) that were designed and implemented on the acquired signals.

Detection and Localization of Small Defects in Large Glass-ceramics by Hybrid Macro and Micro Vision in Large Glass-ceramics by Hybrid Macro and Micro Vision

Detection and Localization of Small Defects in Large Glass-ceramics by Hybrid Macro and Micro Vision in Large Glass-ceramics by Hybrid Macro and Micro Vision

Small Visible Defect Detection of Small Sample based on the Fusion of Multiple Features

Computer-Aided Design and Applications is an international journal on the applications of CAD and CAM. It publishes papers in the general domain of CAD plus in emerging fields like bio-CAD, nano-CAD, soft-CAD, garment-CAD, PLM, PDM, CAD data mining, CAD and the internet, CAD education, genetic algorithms and CAD engines. The journal is aimed at all developers and users of CAD technology to ptovide CAD solutions for various stages of design and manufacturing. The journal publishes all about Computer-Aided Design and Computer-Aided technologies.

An Improved Algorithm for Wind Turbine Blade Defect Detection

With the increase in wind power generation, wind turbine blades require regular inspections to ensure they continue to operate safely. You only look once (YOLO) is one of the most widely used object detection algorithms and is easy to deploy into drone devices. To enhance the real-time detection of small target defects in wind turbine blades, this paper proposes an improved attention and feature balanced YOLO (AFB-YOLO) algorithm based on YOLOv5s. Specifically, AFB-YOLO improves the feature pyramid network by using weighted feature fusion and cross-scale connections. The improved feature pyramid network solves the problem that most previous feature pyramid networks treat all input features equally, and obtains more feature information. Furthermore, the coordinate attention (CA) module is introduced into the network to augment the representations of the objects of interest. Finally, the paper redesigned the loss function through efficient intersection over union (EIoU) loss to make the model obtain a better localization effect. The experimental results on the imagery of wind turbine blade defects indicate that our method shows significant gains in performance. The mean average precision (mAP50) of AFB-YOLO is 83.7% and the detection accuracy is improved by 4.0% compared to the original YOLOv5s model. The experiments in this paper demonstrate that AFB-YOLO is more effective and robust than state-of-the-art detectors.

ELCNN: A Deep Neural Network for Small Object Defect Detection of Magnetic Tile

Automatic detection of magnetic tile surface defects is an important and challenging task, especially for small objects such as cracks. To address this problem, we propose a novel framework called feature enhancement and loop-shaped fusion convolutional neural network (ELCNN), which enhances shallow features and fuses features with a loop-shaped feature pyramid structure. First, our network focuses on shallow features and maximizes their extraction and enhancement. We believe that if the shallow features cannot be completely extracted and effectively propagated, any further improvements will be futile. Second, inspired by the mechanism of <i>looking and thinking twice</i>, we propose a loop-shaped feature pyramid network (LFPN), which not only applies top-down and bottom-up multiscale feature fusion but also connects features recursively to the left and right, creatively constructing a loop-shaped feature pyramid structure. The structure enables features to be propagated and fused in all directions, making each layer more directly connected. Just like the shortcut in ResNet, the loop structure is like a loop-shortcut in the feature pyramid, which can make feature fusion more efficient and comprehensive. Also, the loop-shortcut can improve the flow of information and gradients throughout the network, making them easy to train. The proposed ELCNN is validated on the production line, and the results demonstrate that our network can significantly improve detection accuracy and meet real-time requirements. We also built a new large-scale dataset MT-SOD for the detection of small defects in magnetic tile and proved its effectiveness in practical applications.

Online recognition of magnetic tile defects based on UPM-DenseNet

The detection of surface defects of magnetic tile has a crucial impact on the quality of the motor; however, owing to the large difference in the scale of the surface defects of magnetic tile and the complex background texture, it is difficult for the convolutional neural network to extract the characteristics of the defect itself, and the phenomenon that small defects easily lose features in forward propagation further increases the difficulty of extracting features from the network model. As a result, the accuracy and robustness of surface defect detection based on machine vision are low. Aiming at the above problems, this paper proposes a UPM-DenseNet two-stage detection model. First, the original image data are generated through the positioning network to generate areas where defects may exist, and the influence of complex backgrounds is eliminated to a feasible extent. Then, the obtained feature map is used as the input of the classification network. Finally, the online recognition of the magnetic tile defect is completed through the classification network. To enhance the neural network’s ability to recognize regions of interest for defects of different scales, a plug-and-play feature restoration module is further proposed. The experimental results on the defective set of magnetic tiles show that UPM-DenseNet was effective for different kinds of defects. Under normal, out-of-focus and, noise conditions, the sparse classification accuracy of this method was 96.385%, 95.107%, and 84.47%, respectively. Compared with mainstream network frameworks, it increased by 1.037%, 0.83%, and 1.531%, respectively. The average area under the curve of various defects reached 0.9863, and the average detection speed was 11.109 FPS, both of which meet the accuracy and speed requirements for the detection of small defects on the surface of the magnetic tile in industrial production.

Defect detection in pipes using Van der Pol systems based on ultrasonic guided wave

The sensitivity of small defect detection and the location of small defect in pipes are the main difficulties of the present ultrasonic guided wave inspection technology. A Van der Pol (VdP) chaotic system's sensitivity to initial conditions and capability of being immune to noise was used to establish the relationship between local defect positions and chaos damage factors in this paper. Simulation studies of phase trajectory and Lyapunov exponents based on damping ratio detection of a Van der Pol system were performed. Five kinds of oblique defects with inclined angles of 0°, 30°, 45°, 60°, and 90° were investigated by experiment and analyzed using the location method of a Van der Pol chaotic system. Both the simulated and experimental results show that the proposed method could be used to inspect weaker guided waves and locate tiny defects.

Research on Surface Defect Detection of Rare-Earth Magnetic Materials Based on Improved SSD

In order to overcome the limitation of manual visual inspection of surface defects of rare-earth magnetic materials and increase production efficiency of traditional rare-earth enterprises, a detection method based on improved SSD (Single Shot Detector) is proposed. The SSD model is improved from two aspects for better performance in the detection of small defects. First of all, the multiscale receptive field module is embedded into the backbone network of the algorithm to improve the feature extraction ability of the model. Secondly, the interlayer feature fusion strategy of bidirectional feature pyramid in PANet (path aggregation network) is integrated into the model. In order to enhance the detection ability of the model, the high-level semantic information is strengthened by an efficient channel attention mechanism. The detection speed of the improved SSD algorithm is 55FPS, and the mAP (mean Average Precision) is up to 83.65%, which is 3.41% higher than of the original SSD algorithm, and the ability to identify small defects is significantly improved.

Vector coherence imaging for enhancement of small omni-directional scatterers and suppression of geometric reflections

Ultrasonic imaging with full-matrix capture (FMC) datasets using the total focusing method (TFM) has been demonstrated to improve the detection, sizing and characterization of small defects in the area of Nondestructive Evaluation (NDE). Despite the general improvements in resolution and signal to noise ratio (SNR) offered by FMC/TFM, detection of small flaws remains challenging - particularly when flaws are in immediate proximity to the bounding surfaces of a test piece. In this paper, it is shown that by retaining only phase information during the application of the TFM algorithm, it is possible increase the image intensity of small omni-directional reflectors with respect to large specular reflectors (i.e. backwall/frontwall). The proposed algorithm, called Vector Coherence Imaging, is derived from the Vector Coherence Factor phase coherence metric and represents the amount of statistical (Shannon) information in favour of the presence of a coherent scatterer everywhere in the imaging domain. The VCI algorithm is shown to aid in detection of small defects located close to the boundaries of the specimen. Notably, VCI is seen to facilitate detection tip diffraction/scattering originating from surface connected fatigue cracks (less than 2 ultrasonic wavelengths in height) and early stage high temperature hydrogen attack (HTHA) damage (void nucleation and micro-fissuring).

High-Frequency Guided Wave Propagation and Scattering in Silicon Wafers

Abstract Thin monocrystalline silicon wafers are employed for the manufacturing of solar cells with high conversion efficiency. Micro-cracks can be induced by the wafer cutting process, leading to breakage of the fragile wafers. High-frequency guided waves allow for the monitoring of wafers and detection and characterization of surface defects. The material anisotropy of the monocrystalline silicon leads to variations of the guided wave characteristics, depending on the guided wave mode and propagation direction relative to the crystal orientation. Selective excitation of the first antisymmetric A0 wave mode at 5 MHz center frequency was achieved experimentally using a custom-made wedge transducer. Strong wave pulses with limited beam skewing and widening were measured using noncontact laser interferometer measurements. This allowed the accurate characterization of the Lamb wave propagation and scattering at small artificial surface defects with a size of less than 100 µm. The surface extent of the defects of varying size was characterized using an optical microscope. The scattered guided wave field was evaluated, and characteristic parameters were extracted and correlated with the defect size, allowing in principle detection of small defects. Further investigations are required to explain the systematic asymmetry of the guided wave field in the vicinity of the indents.

Novel Feature Fusion Module-Based Detector for Small Insulator Defect Detection

The failure of an insulator may compromise the safety of the entire power transmission system. Therefore, insulator defect detection is vital for the safe operation of power systems. However, insulator defects in an insulator image may have varying sizes, and several currently available methods do not have satisfactory detection accuracy for small defects. To address this issue, we propose an improved detection network for small insulator defects with a batch normalization convolutional block attention module (BN-CBAM) and a feature fusion module. The BN-CBAM is designed to better exploit channel information and enhance the effect of different channels on the feature map. In addition, we propose a feature fusion module that fuses multi-scale features from different layers to improve small object detection performance. Moreover, to address the scarcity of aerial images, a data augmentation method based on the fusion of the target segment and background is introduced. Experiments demonstrate that the proposed method achieves better small insulator defect detection performance than other state-of-the-art approaches. In addition, data augmentation methods enrich sample diversity and enhance the generalizability of the network.

Damage detection technique using ultrasonic guided waves and outlier detection: Application to interface delamination diagnosis of integrated circuit package

This paper presents the development of a robust data-driven damage diagnosis technique to accurately detect sealant delamination in an integrated circuit (IC) package. A sealant is used to bond the integrated heat spreader (IHS) to the substrate of IC packages for effective thermal dissipation. Delamination of the sealant causes significant reduction in heat management capability of the package, which leads to degradation of processor performance and component reliability. In this work, non-destructive evaluation (NDE) using ultrasonic guided wave (UGW) is performed to interrogate the integrity of the IC package. The advantage of using UGW is its large area inspection capability and small defect detection sensitivity. Ultrasonic tests using a pitch-catch active sensing method with removable piezoelectric (PZT) tranducers are performed with a wide range of excitation frequencies to classify various delamination scenarios in the IC package. Data preprocessing and Hilbert transform-based feature extraction method are also performed on the collected UGWs to extract dominant UGW features. Pattern analysis using a density-based spatial clustering of applications with noise (DBSCAN) algorithm is conducted on the UGW feature space to classify the damage indicators. These damage indicators (outliers) are then used to identify the IC packages with sealant delamination. The proposed technique is validated by comparing it to dye-and-pry tests, delamination metrics, and detection method using a multivariate Gaussian model. The results demonstrate that the proposed diagnosis technique has the potential to be a part of the industrial quality assurance process for IC packages for its capability to detect manufacturing defects with high accuracy.

Measurement of Small Defect Testing Accuracy in Additive Manufacturing Alloy Using Industrial CT Method

This article is based on the application of industrial CT testing in additive manufacturing parts. Based on the existing industrial X-ray CT inspection equipment, it aims to solve the problem of identifying small defects under the uncertainty of test results. Under the premise of removing artifacts, this paper studies the measurement methods of small defects, and analyzes the uncertainty of the test results by designing a comparison test block. This paper combines theoretical analysis and experimental research, and compares the test results with the half-width method to study the accuracy of the test method. In order to improve the accuracy of industrial CT quantitative non-destructive detection of small defects, this paper closely studies the engineering application and combines the practical application of industrial CT to solve the basic problems of key research work.

Ultrasonic C-scan techniques for the evaluation of impact damage in CFRP

Abstract In the present work, different ultrasonic C-scan approaches were used to evaluate Carbon Fiber Reinforced Polymers (CFRP) submitted to impacts of low energy, in order to evaluate their effectiveness for the detection and characterization of small defects. In particular, as to the question how useful could be the air-coupled C-scan approach, using low frequencies, for in-service application. For that goal, several samples with different stacking sequences and thicknesses were impacted with 1.5 and 3 J. Then, ultrasonic C-scan images were produced by immersion pulse-echo (in amplitude and time-of-flight (TOF)) and immersion through-transmission, and also by air-coupling through-transmission. The immersion C-scan images were produced using 5, 10 and 20 MHz probes and the air-coupled C-scan was made using two 400 kHz probes. The obtained images for the considered samples show that all used methods are able to detect the defects and give acceptable information about their size and shape. However, if the way of delamination evolving over thickness is of interest, the images by TOF should be used. As expected, good image resolution with sharp contour defects require high frequencies. Nevertheless, the air-coupled C-scan demonstrated similar capabilities to detect defects, with the advantage that the coupling medium is air, thus widening the range of applications, such as real-time damage monitoring of composite structures. As a disadvantage, the air C-scan system requires high power emission signals, and also great amplification of the received signals, to face the considerable attenuation in the air.