Defect Images Research Articles

A photovoltaic cell defect detection model capable of topological knowledge extraction

As the global transition towards clean energy accelerates, the demand for the widespread adoption of solar energy continues to rise. However, traditional object detection models prove inadequate for handling photovoltaic cell electroluminescence (EL) images, which are characterized by high levels of noise. To address this challenge, we developed an advanced defect detection model specifically designed for photovoltaic cells, which integrates topological knowledge extraction. Our approach begins with the introduction of a multi-scale dynamic context-based feature extraction method, capable of generating static context by thoroughly capturing the local texture and structural information of multi-scale defects. This static context is then combined with dynamic context to produce fine-grained local features. Subsequently, we developed a centralized feature pyramid structure, enhanced by spatial semantics, which models the explicit visual center. This structure effectively elucidates the relationship between local and global features in defect images, thereby improving the representation of defect characteristics. Finally, we implemented a feature enhancement strategy grounded in spatial semantic knowledge extraction. This strategy uncovers potential correlations among defect targets by constructing a spatial semantic topology of features, mapping these features to a higher-order representation, and ultimately delivering precise defect detection results.

Research on Welding Defect Classification Methods Based on Convolutional Neural Networks

To address the issues of low detection and identification rates and inaccurate classification of welding defects, this paper proposes a welding defect classification method based on convolutional neural networks. By modifying the ResNet101 backbone network and incorporating a multi-head attention mechanism (MHA), the method enhances the focus on regions of interest in welding defect images, thereby improving the ability to extract defect features. This approach reduces the chances of missed detections and false positives. By analyzing the effects of different optimizers and dynamic factors on recall (M) and precision (N), the optimal optimizer and dynamic factor are identified. The algorithm is validated on the JPEGWD dataset. Experimental results show that the recall (M) reaches 0.9634, representing a 4.88% improvement, and the precision (N) reaches 0.9875, representing a 3.81% improvement. The mean average precision (mAP) is 0.9817, reflecting a 5.98% improvement. These results effectively enhance the recognition rate of welding defects and reduce the probability of missed detections and false positives.

THE INFLUENCE OF THE QUALITY OF X-RAY IMAGES FROM TELEMEDICINE ON THE COLLECTIVE EFFECTIVE DOSE OF PATIENTS

Ensuring a quality of diagnostic radiology along with increasing efficiency is a key task for healthcare system for both municipal medical facilities and private medicine. When a defective X-ray image is obtained, there is a need to re-conduct a examination, which in turn entails reputational, temporary and economic losses for a medical facility. Repeated examination makes an additional contribution to the patient’s radiation exposure also. The paper shows that for facilities providing telemedicine services, implementation of a clinical audit for diagnostic examinations using information technology is efficient. In 2022 2059 error x-ray images were identified applying a similar system, which is 0.084% of the total number of telemedicine radiology examinations. A collective effective dose due to defective examinations was 3,613 man-Sv, which is less than 0.11% of the total collective dose.

Application of Generative Adversarial Networks in Semi-Annotated Defect Synthesis and Detection Under Limited Resources

Defect detection is a crucial technology that is extensively employed in the manufacturing industry to monitor and ensure the quality of output. Deep learning models have shown remarkable potential for defect detection. However, the success of these models heavily relies on voluminous training data. Collecting substantial amounts of defect data is challenging in practical settings, and the tedious process of pixel-level defect annotation further complicates the task. Among the common defects encountered in manufacturing, scratches are particularly significant. To address these challenges, this study proposes a two-phase generative adversarial network (GAN) approach for synthesizing defect images and generating semi-automatic pixel-wise labels for anomaly detection. The first phase primarily focuses on synthesizing images, while the second phase involves the pixel-wise labeling of the images. The synthesized paired images generated by the GANs serve as input to the semantic network. Notably, the proposed methodology requires only a few real defect samples for training and a small amount of annotated data, making it practical and computationally efficient for implementation in the manufacturing industry. Experimental results indicate the effectiveness of the proposed deep-learning solution in defect detection, specifically in identifying scratches on various textured and patterned surfaces. A notably high detection accuracy is achieved, validating the potential of the approach in real-world manufacturing scenarios.

Research on steel surface defect detection system based on YOLOv5s-SE-CA model and BEMD image enhancement

ABSTRACT The nondestructive testing capability of steel surface defects has a significant impact on quality of industrial production. However, the single-stage detection network YOLOv5s model for steel surface defect detection is of insufficient feature extraction ability and susceptibility to noise interference in extracting surface defect images. Accordingly, a steel surface defect detection system based on YOLOv5s-SE-CA model and bi-dimensional empirical mode decomposition (BEMD) image enhancement is proposed. Firstly, the BEMD is used for image threshold denoising to improve the quality of surface defect images and achieve preprocessing of the dataset. Secondly, the squeeze and excitation network (SENet) attention mechanism is introduced into the backbone network of YOLOv5s model to adaptively adjust weights of each feature channel. Meanwhile, the coordinate attention (CA) attention mechanism is integrated to improve network model’s ability to focus on surface defects. Therefore, the YOLOv5s-SE-CA model is designed to enhance detection capability of steel surface defects. Experimental verification was carried out using the NEU-DET noisy dataset with specific evaluation indicators of image enhancement detection system. Results showed the proposed system has superior performance when compared to traditional models trained on noisy and denoising datasets and achieved more accurate detection of surface defects in steel.

Soldering Defect Segmentation Method for PCB on Improved UNet

Despite being indispensable devices in the electronic manufacturing industry, printed circuit boards (PCBs) may develop various soldering defects in the production process, which seriously affect the product’s quality. Due to the substantial background interference in the soldering defect image and the small and irregular shapes of the defects, the accurate segmentation of soldering defects is a challenging task. To address this issue, a method to improve the encoder–decoder network structure of UNet is proposed for PCB soldering defect segmentation. To enhance the feature extraction capabilities of the encoder and focus more on deeper features, VGG16 is employed as the network encoder. Moreover, a hybrid attention module called the DHAM, which combines channel attention and dynamic spatial attention, is proposed to reduce the background interference in images and direct the model’s focus more toward defect areas. Additionally, based on GSConv, the RGSM is introduced and applied in the decoder to enhance the model’s feature fusion capabilities and improve the segmentation accuracy. The experiments demonstrate that the proposed method can effectively improve the segmentation accuracy for PCB soldering defects, achieving an mIoU of 81.74% and mPA of 87.33%, while maintaining a relatively low number of model parameters at only 22.13 M and achieving an FPS of 30.16, thus meeting the real-time detection speed requirements.

Real-time visual intelligence for defect detection in pharmaceutical packaging

Defect detection in pharmaceutical blister packages is the most challenging task to get an accurate result in detecting defects that arise in tablets while manufacturing. Conventional defect detection methods include human intervention to check the quality of tablets within the blister packages, which is inefficient, time-consuming, and increases labor costs. To mitigate this issue, the YOLO family is primarily used in many industries for real-time defect detection in continuous production. To enhance the feature extraction capability and reduce the computational overhead in a real-time environment, the CBS-YOLOv8 is proposed by enhancing the YOLOv8 model. In the proposed CBS-YOLOv8, coordinate attention is introduced to improve the feature extraction capability by capturing the spatial and cross-channel information and also maintaining the long-range dependencies. The BiFPN (weighted bi-directional feature pyramid network) is also introduced in YOLOv8 to enhance the feature fusion at each convolution layer to avoid more precise information loss. The model's efficiency is enhanced through the implementation of SimSPPF (simple spatial pyramid pooling fast), which reduces computational demands and model complexity, resulting in improved speed. A custom dataset containing defective tablet images is used to train the proposed model. The performance of the CBS-YOLOv8 model is then evaluated by comparing it with various other models. Experimental results on the custom dataset reveal that the CBS-YOLOv8 model achieves a mAP of 97.4% and an inference speed of 79.25 FPS, outperforming other models. The proposed model is also evaluated on SESOVERA-ST saline bottle fill level monitoring dataset achieved the mAP50 of 99.3%. This demonstrates that CBS-YOLOv8 provides an optimized inspection process, enabling prompt detection and correction of defects, thus bolstering quality assurance practices in manufacturing settings.

BD-YOLOv8s: enhancing bridge defect detection with multidimensional attention and precision reconstruction

The YOLO (You Only Look Once) series has recently demonstrated remarkable effectiveness in the domain of object detection. However, deploying these networks for concrete bridge defect detection presents multiple challenges, such as insufficient accuracy, missed detections, and false positives. These complications arise chiefly from the complex backgrounds and the significant variability in defect characteristics observed in bridge imagery. This study presents BD-YOLOv8s, an advanced methodology utilizing YOLOv8s for bridge defect detection. This approach augments the network’s adaptability to a broad spectrum of bridge defect images through the integration of ODConv into the second convolutional layer, processing information within a four-dimensional kernel space. Furthermore, incorporating the CBAM module into the first two C2F architectures leverages spatial and channel attention mechanisms to focus on critical features, thus enhancing the accuracy of detail detection. CARAFE replaces traditional upsampling methods, improving feature map reconstruction and significantly reducing blurs and artifacts. In performance assessments, BD-YOLOv8s attained 86.2% mAP@0.5 and 56% mAP@0.5:0.95, surpassing the baseline by 5.3% and 5.7%. This signifies a considerable decrease in both false positives and missed detections, culminating in an overall improvement in accuracy.

AEDN-YOLO: an efficient one-stage detection network for strip steel surface defects

Steel surface defect detection is one of the key tasks in industrial production and quality control. Research on defect detection using deep learning algorithms has shown promising results. However, due to the complex backgrounds, large differences in defect sizes, and diverse defect types present in steel strip surface defect images, existing deep learning algorithms struggle to achieve precise detection. To address these challenges, this paper proposes an efficient detection model named AEDN-YOLO. Firstly, an adaptive feature extraction (AFE) module is designed, embedded into C2f to better capture irregularly shaped objects. Secondly, the Triplet Attention module is incorporated into the bottom layer of the backbone network to enhance the model’s ability to locate defect features accurately. Additionally, replace the standard convolution in the neck network with GSConv, which not only accelerates feature fusion to improve detection speed but also enlarges the model’s receptive field to enhance detection accuracy. Finally, add a small target detection layer to enhance the detection capability for tiny defects. The model achieves mAP of 81.7% and 72.7% on the NEU-DET and GC10-DET datasets, respectively, with a detection speed of 72.1 FPS. Compared to mainstream defect detection algorithms, the proposed algorithm enables accurate and efficient detection of steel surface defects.

High-resolution defect imaging of composites using delay-sum-and-square beamforming algorithm

Abstract High-resolution ultrasonic imaging for defects in anisotropic multilayer carbon fiber reinforced polymers (CFRPs) is challenging because of the severe ultrasonic attenuation and the low signal-to-noise ratio (SNR) of echoes. The existing delay-multiply-and-sum (DMAS) beamforming outperforms delay-and-sum (DAS) beamforming in resolution, but with high computational complexity and energy loss. This paper presents a novel delay-sum-and-square (DSAS) beamforming algorithm. It takes full advantage of spatial coherence of captured data in the receiving and transmitting apertures. The non-coherent components caused by background noise are suppressed during the imaging. The back-wall reflection method (BRM) is used to correct the direction-dependent velocity. Full-matrix data is experimentally captured and processed on three different CFRP samples. Compared with DAS and DMAS, DSAS has a significant improvement in resolution, SNR and contrast. It demonstrates excellent defect characterization and noise suppression capability with only 17.4% computation time of DMAS.

Trans-DCN: A High-Efficiency and Adaptive Deep Network for Bridge Cable Surface Defect Segmentation

Cables are vital load-bearing components of cable-stayed bridges. Surface defects can lead to internal corrosion and fracturing, significantly impacting the stability of the bridge structure. The detection of surface defects from bridge cable images faces numerous challenges, including shadow disturbances due to uneven lighting and difficulties in addressing multiscale defect features. To address these challenges, this paper proposes a novel and cost-effective deep learning segmentation network, named Trans-DCN, to detect defects in the surface of the bridge cable. The network leverages an efficient Transformer-based encoder and integrates multiscale features to overcome the limitations associated with local feature inadequacy. The decoder implements an atrous Deformable Convolution (DCN) pyramid and dynamically fuses low-level feature information to perceive the complex distribution of defects. The effectiveness of Trans-DCN is evaluated by comparing it with state-of-the-art segmentation baseline models using a dataset comprising cable bridge defect images. Experimental results demonstrate that our network outperforms the state-of-the-art network SegFormer, achieving a 27.1% reduction in GFLOPs, a 1.2% increase in mean Intersection over Union, and a 1.5% increase in the F1 score. Ablation experiments confirmed the effectiveness of each module within our network, further substantiating the significant validity and advantages of Trans-DCN in the task of bridge cable defect segmentation. The network proposed in this paper provides an effective solution for downstream cable bridge image analysis.

Automatic Defect Detection Instrument for Spherical Surfaces of Optical Elements

In order to realize automatic surface defect detection for large aperture precision spherical optical elements, an automatic surface defect detection instrument has been designed. The instrument consists of a microscopic imaging system, illumination system, motion scanning system, and a software algorithm system. Firstly, a multi-angle channel illumination source and a coaxial illumination source were designed. Bright and dark field images of surface defects were captured by cooperating with an automatic zoom microscope. Then, algorithms for scanning trajectory planning, image stitching, and intelligent defect recognition were designed to achieve full-aperture surface image acquisition and defect quantification detection. The automated defect detection process of the instrument is summarized and introduced. Finally, the experimental platform was constructed, which can work well for the optical elements with a maximum diameter of 400 mm and a relative aperture R/D value of 1. It takes about 15 min to detect an optical element with a diameter of 200 mm in dark-field imaging mode. As a result, the minimum line width of scratch detectable is 2 μm and the minimum diameter of pitting detectable is 4 μm. Clearly, the instrument can realize the automatic detection of surface defects of spherical optical elements, and has the advantages of a high efficiency, stability, reliability, quantification, and data traceability.

Biosafety and osteogenic properties of a new type of absorbable magnesium-based amorphous alloy

The treatment of bone defects has always been a difficult problem in orthopedic clinical practice, and research on new materials is currently a hot topic. In this study, the biological safety and bone induction ability of a new magnesium-based amorphous alloy (Mg66Zn30Ca3Sr1) and zinc–magnesium powder were verified and compared in animal experiments. Thirty Sprague–Dawley rats were randomly divided into three groups, and a bone defect was made in the lateral condyle of the femur of the left hind limb. The blank group closed the wound after establishing the bone defect model, the control group added zinc–magnesium powder and chondroitin sulfate gel, and the experimental group added magnesium–zinc–calcium–strontium alloy and chondroitin sulfate gel with the same volume. Peripheral venous blood of rats was collected at 4, 8, and 12 weeks postoperatively, and alanine aminotransferase (ALT), aspartate transferase, creatinine, blood urea nitrogen, magnesium ion, and zinc ion levels were evaluated. The expression levels of bone morphogenetic protein 2 (BMP-2), osteoprotegerin (OPG), osteopontin (OPN), core binding factor α1 (RUNX2), and alkaline phosphatase (ALP) were detected using enzyme-linked immunosorbent assay (ELISA). After the rats were euthanized, samples were taken. X-rays and micro-computed tomography (CT) images of the bone defect were obtained, and hematoxylin and eosin and Masson staining were performed. This study shows that amorphous magnesium–zinc–calcium–strontium alloy is a biodegradable metal with good biocompatibility and bone induction and has good application prospects in treating bone defects.

Effect of light source wavelength on surface defect imaging in deep-water concrete dams

This study explores the relationship between surface defect imaging in deep-water concrete dams and the wavelength of the light source, aiming to improve concrete defect image quality by varying the wavelength. The underwater optical imaging model of concrete dam surfaces was developed by applying the principle of object reflection and the underwater optical propagation model. This model reflects the effect of different light wavelengths on underwater concrete defect imaging. Through a self-designed underwater optical darkroom test platform, defect image acquisition tests were conducted under various color light conditions. The results reveal the significant influence of light source wavelength on images captured in both air and water. Furthermore, under the same initial illuminance, blue light significantly enhanced the average gray value, sharpness, contrast, and the number of feature points in underwater defect images, exhibiting increments of 2.97 times, 0.48 times, 2.70 times, and 2.95 times, respectively, compared to white light. These findings can serve as a reference for the selection of color-light for the non-destructive testing of surface defects in actual underwater concrete dams.

Imaging method of surface defect using leaky Rayleigh wave with ultrasonic phased array

ABSTRACT Leaky Rayleigh wave testing has the advantages of non-contact, high sensitivity, and good beam directivity. However, current leaky Rayleigh wave testing mostly uses monolithic transducers and is seriously affected by acoustic wave attenuation and diffusion, resulting in poor image quality, limited detection range and low imaging efficiency. In this paper, a novel leaky Rayleigh wave testing method using an ultrasonic phased array is developed, and the total focusing method (TFM) is used to achieve high-quality imaging of defects. To improve imaging efficiency, the root-mean-square velocity (RMSV) model is utilised to rapidly acquire an approximate analytical solution for the time of flight of the acoustic wave. To obtain more accurate defect images further, the amplitude of the total focusing imaging signal is calibrated. The experimental results demonstrate that the proposed method achieves a 48% improvement in the imaging accuracy of a 1 mm hole, compared to the traditional Synthetic Aperture Focusing Technique (SAFT) imaging method. The proposed method achieves an 92% reduction in imaging time compared to the conventional TFM. The proposed method provides a new non-contact approach for high-accuracy and high-efficiency defect imaging using leaky Rayleigh wave.

Towards to Theory of the X-ray Diffraction Tomography of Crystals with Nano-Sized Defects

X-ray diffraction tomography is an innovative method that is widely used to obtain 2D-phase-contrast diffraction images and their subsequent 3D-reconstruction of structural defects in crystals. The most frequent objects of research are linear and helical dislocations in a crystal, for which plane wave diffraction images are the most informative, since they do not contain additional interference artifacts unrelated to the images of the defects themselves. In this work the results of modeling and analysis of 2D plane wave diffraction images of a nano-dimensional Coulomb-type defect in a Si(111) thin crystal are presented based on the construction of numerical solutions of the dynamic Takagi-Taupin equations. An adapted physical expression for the elastic displacement field of the point defect, which excludes singularity at the defect location in the crystal, is used. A criterion for evaluating the accuracy of numerical solutions of the Takagi-Taupin equations is proposed and used in calculations. It is shown that in the case of the Coulomb-type defect elastic displacement field, out of the two difference algorithms for solving the Takagi-Taupin equations used in their numerical solution, only the algorithm for solving the Takagi-Taupin equations where the displacement field function enters in exponential form is acceptable in terms of the required accuracy-duration of the calculations.

Inspection of aluminum sheets using a multi-element eddy current sensor: 2d and 3d imaging of surface defects of various sizes and internal defects at various depths

In the industrial sector, ensuring reliability and durability is of paramount importance. Our research aims to advance beyond conventional non-destructive testing methods by focusing on thorough defect detection and imaging. We utilize advanced, sensor-enhanced eddy current testing, featuring multiple elements arranged in a cutting-edge serial array. This innovative configuration addresses the issue of magnetic repulsion between sensor elements, thereby speeding up the testing process and ensuring precise results through both 3D and 2D imaging. This sophisticated approach allows us to more effectively characterize defects of varying sizes and depths in aluminum sheets. By meticulously collecting and analyzing data from the sensors, we can identify the appearance and nature of these defects with greater clarity. Our findings introduce a pioneering method for defect detection, highlighting the efficacy of our advanced testing technique. Our research underscores the potential of multi-element eddy current sensors in revolutionizing the inspection process. The ability to produce detailed 3D and 2D images of surface and internal defects represents a significant leap forward in non-destructive testing. This comprehensive imaging capability not only accelerates the detection process but also enhances the accuracy and reliability of defect characterization. By employing this state-of-the-art technology, we can detect even the smallest and most deeply embedded defects that traditional methods might miss. The precise imaging provided by our approach ensures that defects of various sizes and depths are accurately identified and characterized. This level of detail is crucial for maintaining the structural integrity and performance of aluminum sheets used in industrial applications. Our research demonstrates a groundbreaking approach to defect detection in aluminum sheets, leveraging the advanced capabilities of multi-element eddy current sensors. The innovative use of a serial array of sensors, combined with sophisticated data analysis techniques, allows for rapid, accurate, and detailed imaging of defects. These findings pave the way for improved reliability and durability in industrial applications, setting a new standard for non-destructive testing.

A Novel Adversarial Deep Learning Method for Substation Defect Image Generation.

The presence of defects in substation equipment is a major factor affecting the safety of power transmission. Therefore, timely and accurate detection of these defects is crucial. As intelligent inspection robots advance, using mainstream object detection models to diagnose surface defects in substation equipment has become a focal point of current research. However, the lack of defect image data is one of the main factors affecting the accuracy of supervised deep learning-based defect detection models. To address the issue of insufficient training data for defect images with complex backgrounds, such as rust and surface oil leakage in substation equipment, which leads to the poor performance of detection models, this paper proposes a novel adversarial deep learning model for substation defect image generation: the Abnormal Defect Detection Generative Adversarial Network (ADD-GAN). Unlike existing generative adversarial networks, this model generates defect images based on effectively segmented local areas of substation equipment images, avoiding image distortion caused by global style changes. Additionally, the model uses a joint discriminator for both overall images and defect images to address the issue of low attention to local defect areas, thereby reducing the loss of image features. This approach enhances the overall quality of generated images as well as locally generated defect images, ultimately improving image realism. Experimental results demonstrate that the YOLOV7 object detection model trained on the dataset generated using the ADD-GAN method achieves a mean average precision (mAP) of 81.5% on the test dataset, and outperforms other image data augmentation and generation methods. This confirms that the ADD-GAN method can generate a high-fidelity image dataset of substation equipment defects.

Efficient and lightweight layer-wise in-situ defect detection in laser powder bed fusion via knowledge distillation and structural re-parameterization

Powder bed quality is critical in Laser Powder Bed Fusion (LPBF) as defects in the powder bed will affect the quality of the forming parts. Recently, numerous powder bed defect detection methods based on semantic segmentation algorithms have been developed. However, due to the computational resource constraints and real-time requirements in industry scenarios, these heavy models face challenges in deploying into the LPBF process monitoring system. Meanwhile, existing lightweight models struggle to achieve sufficient performance on industrial data due to their limited feature extraction capabilities. To address the challenges in industrial deployment, this paper proposes a lightweight and efficient LPBF layer-wise defect detection paradigm to achieve a balance between performance and efficiency. Aiming at improving the performance of the lightweight model, this paper proposes a structured Knowledge Distillation framework, in which a pre-trained high-performance segmentation model (UNet++) is used to guide the training process of a lightweight model. To address the impact of model discrepancies on the effectiveness of Knowledge Distillation and further improve the inference speed, this paper constructs a specific lightweight model and applies Structural Re-parameterization to deeply compress the model. Moreover, we created a dataset comprising 406 images of powder-bed defects, with each image annotated at the pixel level. Massive experiments based on the dataset demonstrate the effectiveness of the proposed paradigm, with an excellent trade-off in performance and efficiency. The speed of the proposed model is approximately 5 times faster than that of high-performance models while maintaining comparable performance.

A Study on GAN-Based Car Body Part Defect Detection Process and Comparative Analysis of YOLO v7 and YOLO v8 Object Detection Performance

The main purpose of this study is to generate defect images of body parts using a GAN (generative adversarial network) and compare and analyze the performance of the YOLO (You Only Look Once) v7 and v8 object detection models. The goal is to accurately judge good and defective products. Quality control is very important in the automobile industry, and defects in body parts directly affect vehicle safety, so the development of highly accurate defect detection technology is essential. This study ensures data diversity by generating defect images of car body parts using a GAN and through this, compares and analyzes the object detection performance of the YOLO v7 and v8 models to present an optimal solution for detecting defects in car parts. Through experiments, the dataset was expanded by adding fake defect images generated by the GAN. The performance experiments of the YOLO v7 and v8 models based on the data obtained through this approach demonstrated that YOLO v8 effectively identifies objects even with a smaller amount of data. It was confirmed that defects could be detected. The readout of the detection system can be improved through software calibration.