Weak Defects Research Articles

An weak surface defect inspection approach using efficient multi-scale attention and space-to-depth convolution network

In the field of precision manufacturing, machine vision technology is gradually replacing traditional manual inspection methods as a key technology to improve product quality. In precision manufacturing companies, weak defects on the product surface are unacceptable. However, existing defect detection methods rarely focus on the weak surface defect detection task. To address this challenge, we acquire and build a dataset called USB-DET, which contains weak defect samples. Then, we propose an innovative lightweight deep learning model, SDIA-net, which integrates SPD-Conv, Dysample technique, and attention mechanism-iRMA, to improve the recognition and localization of weak defects effectively. On the USB-DET dataset, SDIA-net achieves 55.1% mAP, which is 3.2% higher than the existing SOTA models. The computational efficiency is 205.1 FPS, which satisfies real-time demands. SDIA-net’s advantages make it well-suited for deployment in resource-limited precision manufacturing environments, providing an effective technical solution for product surface quality control with significant practical application value.

Development of compact smart bearing and novel hybrid feature assessment for weak defect identification

ABSTRACT In this study, a compact smart bearing with self-sensing and condition monitoring function is proposed. A traditional bearing embedded in a piezoelectric transducer ring with a segmented electrode design is prototyped and tested under different working conditions. Its compact design ensures compatibility for integration with different systems. The segmented electrodes enable possible multidirectional data acquisition and piezoelectric energy generation, suggesting potential integration with Internet of Things (IoT) platforms. Utilizing the high sensitivity, fast response and high signal resolution of the piezoelectric material in conjunction with a novel design that enables close contact between the piezoelectric transducer and the bearing, the smart bearing demonstrates effective performance in detecting weak bearing defects signals. A novel feature characterising method is proposed, and a hybridised feature selection method is employed for reducing the dimension of feature subsets and ensuring defect identification accuracy. A classification model for the identification of defects is developed based on a Long Short-Term Memory (LSTM) network. The performance of the smart bearing and the method for identifying the defects are evaluated through experiments to demonstrate the potential for practical applications. A preliminary experiment for energy harvesting using the smart bearing has been conducted, and it proves the potential to sustain power.

A Dynamic Weights-Based Wavelet Attention Neural Network for Defect Detection.

Automatic defect detection plays an important role in industrial production. Deep learning-based defect detection methods have achieved promising results. However, there are still two challenges in the current defect detection methods: 1) high-precision detection of weak defects is limited and 2) it is difficult for current defect detection methods to achieve satisfactory results dealing with strong background noise. This article proposes a dynamic weights-based wavelet attention neural network (DWWA-Net) to address these issues, which can enhance the feature representation of defects and simultaneously denoise the image, thereby improving the detection accuracy of weak defects and defects under strong background noise. First, wavelet neural networks and dynamic wavelet convolution networks (DWCNets) are presented, which can effectively filter background noise and improve model convergence. Second, a multiview attention module is designed, which can direct the network attention toward potential targets, thereby guaranteeing the accuracy for detecting weak defects. Finally, a feature feedback module is proposed, which can enhance the feature information of defects to further improve the weak defect detection accuracy. The DWWA-Net can be used for defect detection in multiple industrial fields. Experiment results illustrate that the proposed method outperforms the state-of-the-art methods (mean precision: GC10-DET: 6.0%; NEU: 4.3%). The code is made in https://github.com/781458112/DWWA.

Research on weak appearance defect detection method for engine piston rings based on 3D vision

Abstract As a critical engine component, the appearance quality of piston rings directly affects engine performance and lifespan. Subtle defects like minor chipping, cracks, and scratches can significantly impact engine safety and durability. Traditional 2D image processing and AI-based methods struggle to detect these defects, being prone to interference and resulting in high false positive and negative rates. This paper introduces a 3D vision-based detection method, which captures detailed surface morphology to improve defect detection accuracy. Experimental results demonstrate that this approach effectively reduces false positives and negatives, significantly enhancing detection accuracy.

High-performance surface defect detection of aluminum substrate based on event camera

Abstract Traditional industrial surface defect detection often employs CCD/CMOS cameras, but they are difficult to detect the minute defects on aluminum substrates in highly dynamic industrial scenes due to their nature. Event camera is a novel high-resolution vision sensor which measures per-pixel brightness changes in an asynchronous manner and outputs as event information flow (EIF). Small and weak defects on aluminum substrate can be captured by event camera effectively, but the EIF contain a large amount of noise, making it difficult to perform accurate and high-precision defect detection. To address this problem, we propose a frame aggregation method to realize good event information flow processing (EIFP), and then use an improved circle detection method to locate the aluminum substrate in each frame, removing abundant event information outside the aluminum substrate. Subsequently, we enhance the event signals under different frames based on optical flow tracking using multiple features, and construct a semi-supervised detector based on pseudo-labels to achieve high-precision defect localization. Finally, considering the small inter-class differences in defects on the surface of aluminum substrates, we construct a defect class corrector based on ensemble learning to enhance the ability to determine defect classes, achieving high-precision automatic quality inspection of aluminum substrate surfaces. The performance of our method is compared with other advanced methods based on event camera data of aluminum substrates in real industrial scenarios. The experimental results show that our method has improved the detection accuracy by about 10% and the classification accuracy by about 25% compared to the original state-of-the-art methods.

Is Public Participation Weak Environmental Regulation? Experience from China’s Environmental Public Interest Litigation Pilots

Previous studies have generally concluded that public participation lacks substantive constraints and has weak environmental regulation effects. Using China’s environmental public interest litigation (EPIL), implemented in 2015, as a quasi-natural experiment to verify the environmental effects of public participation under judicial norms, the difference-in-differences (DID) estimates in this paper show that industrial wastewater and industrial sulfur dioxide (SO2) emissions in the treated cities declined by an average of 2.76 million tons and 2.51 kilotons per year, respectively, which ultimately improved the city’s environmental quality. The results of the mechanism also show that the EPIL was able to mobilize all three parties: the public, government and enterprises. In the context of the environment as an externality product, where the interests of all the parties are difficult to coordinate, the EPIL has the advantage of overcoming conflicts of interest. Our study provides a quantitative justification for the environmental impact assessment of public litigation and contributes empirical references to overcome the weak binding defect of public participatory environmental regulation.

RAM-YOLOv8: A multi-fault detection method for photovoltaic module

ABSTRACT Given the constraints in fault type identification, localization precision, and detection efficiency inherent in current photovoltaic fault detection methodologies, this paper introduces an innovative detection approach integrating RAM-YOLOv8 with the Swin Transformer. To mitigate the limitations in model extraction capabilities during the detection process and circumvent the vanishing gradient issue encountered during backward information propagation, this study introduces a residual aggregation module as a substitute for the original C2F module, thereby augmenting feature extraction efficiency. Furthermore, within the feature fusion network, the Swin attention mechanism fusion module is designed by integrating the Swin Transformer’s architectural concept to minimize the loss of weak defect information and suppress irrelevant background interference. The model achieves a detection accuracy of 88.5% on the dataset, representing a 7% improvement over the original YOLOv8 algorithm, with a detection rate of 83.33 FPS on an RTX2080 GPU. This method offers a robust and efficient fault detection solution for PV systems, rendering it a practical approach for enhancing system performance and reducing maintenance costs.

Experimental Investigation Using Robust Deep VMD-ICA and 1D-CNN for Condition Monitoring of Roller Element Bearing

Abstract A rotor-bearing system experiences numerous vibrations during the operation that frequently degrade performance and endanger operational safety. Roller bearing failure has significant consequences, leading to downtime or even a complete outage of rotating machinery. It is crucial to detect and diagnose incipient bearing defects promptly to ensure optimal operation of the machinery and minimize potential disruptions to the process. Deep Independent Component Analysis is a necessity used in modern condition monitoring to detect bearing failure earlier than it occurs. To address this issue the feasibility of utilizing Deep Independent Component Analysis (ICA) method based on Variational Modal Decomposition (VMD) with one-dimensional convolutional neural network (1D-CNN) to diagnose incipient bearing defect. Fast Fourier Techniques are utilized to extract the vibration signatures of artificially damaged bearings on a newly built test bed. VMD addresses to minimize data noise, allowing data to decompose into various sub-datasets for extraction of incipient defect features. With weak defect characteristic signal and noise interference, the Deep VMD-ICA model and 1D-CNN simplicity improved the accuracy of diagnosis corresponding to the experimental results. Moreover, Deep VMD-ICA with 1D-CNN has additionally demonstrated strong performance in comparison to experimental results and is useful for monitoring the condition of industrial machinery. The results reveal that this fault diagnosis approach is reliable, with a diagnostic accuracy of 98.93% for bearing faults.

A three-stage framework for accurate detection of high-speed train body paint film defects

Detecting paint film defects on high-speed train (HST) body is a crucial step towards zero-defect manufacturing (ZDM). The effectiveness of defect detection in industrial environments, however, is significantly impacted by factors such as high reflection noise, weak defect features, small defect size, and various defect scales, resulting in unsatisfactory detection accuracy. To address these challenges, this paper proposes a technical framework for the accurate detection of paint film defects on HST body, encompassing three stages. A reflection detection removal method that takes into account the reflection transition region as well as the preservation of defect features is at first used to reduce reflection noise interference. Then a lightness-weighted adaptive image enhancement algorithm based on the fractional order differentiation is utilized to enhance the features of paint film defects while avoiding the introduction of reflection noise. Finally, an improved YOLOv5 algorithm, incorporating attention mechanism feature extraction and multi-scale feature fusion, is employed to detect and classify paint film defects. Experimental results demonstrate that the proposed framework effectively reduces the reflection in paint film images, and enhances the contrast between paint film defects and the background, with a mean average precision (mAP) for defect detection reaching up to 90.13%. This work serves as a valuable reference for the automated detection of defects arising in the painting process of HST body.

Study on ultrasonic lamb wave testing technology of honeycomb sandwich structures

Abstract Honeycomb sandwich composite panels have complex structures, large sizes, many types of defects, and significant sound attenuation, which lead to low efficiency and poor sensitivity of ultrasonic non-destructive testing. In the study, a non-linear ultrasonic lamb wave testing technique for honeycomb sandwich composite panels is proposed. Firstly, the anisotropic propagation characteristics and modal structure of lamb waves in honeycomb sandwich composite panels are analyzed, and the lamb wave modes with non-linear ultrasonic accumulation are excited. Secondly, the data extraction method and imaging algorithm of non-linear ultrasonic lamb wave imaging testing are proposed. Finally, an enhanced imaging algorithm is proposed to improve image quality based on the sliding window algorithm. Based on the comparative analysis of air-coupled ultrasonic testing images and metallographic tests, it can be seen that non-linear ultrasonic lamb wave testing signals can be used to characterize the damage distribution characteristics of honeycomb sandwich composite panels, display debonding and weak debonding defects, and have the advantages of being able to perform on the same side testing and high efficiency, which can be used for non-destructive testing of honeycomb sandwich composite panels.

EfficientNet-ECA: A lightweight network based on efficient channel attention for class-imbalanced welding defects classification

Welding defects recognition is crucial for ensuring weldment quality in robot arc welding. Nevertheless, due to unbalanced data distributions, limited computing resources in factory, as well as intraclass variability and interclass similarity among different welding defects, it is difficult to extract the most discriminative defect features from welding molten pool images on site, resulting in weak class-imbalanced defect recognition performance. To address the above issue, a novel lightweight network named EfficientNet-ECA is proposed for recognizing and classifying welding defects according to molten pool images of robot arc welding. Firstly, the EfficientNet-ECA network based on Efficient Channel Attention (ECA) is designed to extract the most discriminative features of different defects from molten pool images, where ECA is employed to enhance cross-channel information interactions. Secondly, a dynamic equalized focal loss function is proposed to both rebalance the loss contribution of class-imbalanced data of different defects and improve defects recognition accuracy. Subsequently, a class-imbalanced dataset containing eight typical welding defects is constructed to evaluate the EfficientNet-ECA model. Finally, the proposed model is comprehensively analyzed through ablation studies and compared with the existing state-of-the-art lightweight models, and results show that the proposed method exhibits better effectiveness and generalizability in classifying class-imbalanced defects across different welding scenarios, achieving the highest accuracy of 95.84% on a self-constructed AL5083 dataset and 96.50% on a publicly available SS304 dataset. Moreover, with fewer parameters and less complexity, the proposed method is more suitable for online welding quality monitoring in factory.

DMWMNet: A novel dual-branch multi-level convolutional network for high-performance mixed-type wafer map defect detection in semiconductor manufacturing

Wafer map defect detection plays an important role in semiconductor manufacturing by identifying root causes and accelerating process adjustments to ensure product quality and reduce unnecessary expenditures. However, existing methods have some limitations, such as low accuracy in mixed-type defect detection and poor recognition of similar defects and weak features. In this article, a novel dual-branch multi-level convolutional network (DMWMNet) is proposed for high-performance mixed-type wafer map defect detection. By fully considering the interrelationships between basic defects, defect number, and defect type, the network is designed to include two efficient parallel Branches and a Fusion classifier. Detecting defect types using basic defect discrimination and defect number detection is helpful for ameliorating problems with high complexity and low accuracy caused by multiple defect categories and feature overlaps. Furthermore, a composite loss function based on focal loss is employed to improve the network’s capacity to recognize weak features and similar defects. Experimental results on the MixedWM38 dataset show that DMWMNet has favorable mixed-type defect detection performance compared to other methods, with accuracy, precision, recall, F1 score, and MCC of 98.99%, 98.94%, 99.03%, 98.98%, and 98.97%, respectively.

Liquid concentration sensing via weakly coupled point defects in a phononic crystal

A pair of weakly coupled point defects in a liquid–solid phononic crystal are employed for liquid concentration sensing. An exemplary case of methanol in ethanol is investigated. As the physical and chemical properties of the two constituents are very similar, sensing is a rather difficult task by other analytical means. The defects are formed by thin-walled polyethylene tubing filled with either the reference liquid (ethanol) or the mixture in a square phononic crystal composed of cylindrical steel rods in water. Finite-element method simulations for the dual defect system, which has a small form factor comparable to the acoustic wavelength in water, revealed that two sharp transmission peaks corresponding to the even and odd modes arising from symmetry lifting due to weak defect interaction behave in different manners as the methanol concentration is varied. Specifically, the even mode frequency exhibits a linear dependence on the concentration, whereas the odd mode is associated with a quadratic shift. Besides, a simple coupled mass-spring model is employed to analyze the observed peak behavior as a function of methanol concentration in ethanol. Accordingly, when the acoustic properties of the two liquids in a binary mixture vary in a parallel manner with temperature, the ratio of the resonance frequencies depends only on the concentration, thus offering a sensing scheme immune to temperature fluctuations. Furthermore, it is shown for a number of water-miscible liquids that the even and odd mode frequencies are representative of the dominant contents of the reference and the sample cells.

Optimization of Weak Ultrasonic Defect Signal Detection of Carbon Fiber Composites Based on Double-Sided Pulse Reflection Scanning

Optimization of Weak Ultrasonic Defect Signal Detection of Carbon Fiber Composites Based on Double-Sided Pulse Reflection Scanning

RADDA-Net: Residual attention-based dual discriminator adversarial network for surface defect detection

Surface defect detection is a critical yet challenging task in the product production process, mainly because of the complex background texture on the material surface, the large intra-class defect differences, and the weak texture defect regions. To address this problem, a Residual Attention-based Dual Discriminator Adversarial Network (RADDA-Net) is developed to accurately detect various types of texture defect regions. Specifically, a residual network-based feature extraction module integrating multi-channel attention mechanism and multi-scale convolutional layers is designed to improve the detection ability of abnormal defects. Besides, to deeply excavate material surface texture information, the pixel attention-based up-sampling blocks are also incorporated into RADDA-Net to enhance the extraction of shallow features. To further improve the detection performance of RADDA-Net, a dual discriminant adversarial training strategy and a comprehensive measurement method are introduced to assist the developed network to identify defects from both macroscopic structure and microscopic edges. Finally, the six evaluation indexes of our proposed method outperformed other state-of-the-art methods on the four defect datasets, among which the highest detection precision, recall, and F-measure are 0.926, 0.916, 0.920, respectively. Therefore, the experimental results consistently verify the detection accuracy and effectiveness of RADDA-Net.

Neurexin drives Caenorhabditis elegans avoidance behavior independently of its post-synaptic binding partner neuroligin.

Neurexins and their canonical binding partners, neuroligins, are localized to neuronal pre-, and post-synapses, respectively, but less is known about their role in driving behaviors. Here, we use the nematode C. elegans to show that neurexin, but not neuroligin, is required for avoiding specific chemorepellents. We find that adults with knockouts of the entire neurexin locus exhibit a strong avoidance deficit in response to glycerol and a weaker defect in response to copper. Notably, the C. elegans neurexin (nrx-1) locus, like its mammalian homologs, encodes multiple isoforms, α and γ. Using isoform-specific mutations, we find that the γ isoform is selectively required for glycerol avoidance. Next, we used transgenic rescue experiments to show that this isoform functions at least partially in the nervous system. We also confirm that the transgenes are expressed in the neurons and observe protein accumulation in neurites. Furthermore, we tested whether these mutants affect the behavioral responses of juveniles. We find that juveniles (4th larval stages) of mutants knocking out the entire locus or the α-isoforms, but not γ-isoform, are defective in avoiding glycerol. These results suggest that the different neurexin isoforms affect chemosensory avoidance behavior in juveniles and adults, providing a general principle of how isoforms of this conserved gene affect behavior across species.

Bioinspired chitin/gelatin composites with enhanced mechanical property

AbstractThe defensive tissues such as insect epidermis and crustacean exoskeleton in nature displayed characteristics of high strength and high toughness via multi‐level structure, which shed light on the designation of natural polymer‐based composites with enhanced mechanical property. Herein, a bioinspired strategy was used to prepare chitin/gelatin composite with improved mechanical property. Chitin hydrogels were first prepared by dissolution in NaOH/urea via freezing–thawing and then regeneration in sodium propionate, to form a heterogeneous nanofibrous structure. After coating gelatin on the chitin nanofibers, a hierarchical structure was obtained, leading to more compact and homogenous morphology. The coating process significantly strengthened the chitin nanofibrous structure and reduced the weak defect, which enhanced the tensile strength and toughness of the composite. The present work not only supplies a chitin/gelatin composite with high mechanical property but also offers a facile approach to prepare strengthening and toughening materials based on natural polymers.

Progressive Frequency-Guided Depth Model with Adaptive Preprocessing for Casting Defect Detection

This article proposes a progressive frequency domain-guided depth model with adaptive preprocessing to solve the problem of defect detection with weak features based on X-ray images. In distinct intuitive surface defect detection tasks, non-destructive testing of castings using X-rays presents more complex and weak defect features, leading to lower accuracy and insufficient robustness on the part of current casting defect detection methods. To address these challenges, the proposed method establishes four specialized mechanisms to improve model accuracy. First, an adaptive image contrast enhancement method is proposed to enhance the features of defects in casting images to promote subsequent feature extraction and prediction. Second, a subtle clue mining module based on frequency domain attention is proposed to fully extract the discriminative features of casting defects. Third, a feature refinement module based on progressive learning is proposed to achieve a balance between feature resolution and semantic information. Finally, a refined deep regression supervision mechanism is designed to improve defect detection accuracy under strict intersection-to-union ratio standards. We established extensive ablation studies using casting defect images in GDXray, conducted detailed comparative experiments with other methods, and performed experiments to analyze the robustness of the resulting models. Compared with other X-ray defect detection methods, our framework achieves an average +4.6 AP. Compared to the baseline, our proposed refined deep regression supervision mechanism results in an improvement of 5.3 AP.

High resolution magnetic field imaging probe with two rows of TMR sensors for small defects inspection

It is still a challenging problem to detect small defects for eddy current array probes, which requires the probes to possess excellent sensitivity, as well as high spatial resolution. This paper presents a novel high-resolution magnetic field imaging probe with two rows of tunneling magnetoresistance (TMR) array sensors. The bare die sensors are integrated on a printed circuit board by golden wire bonding technology. The two rows of sensors are placed staggered with each other. The data of the two arrays are merged into a matrix, in which way the image pixel pitch is increased to 0.25 mm. The probe employs a differential scheme to suppress the noise, so as to detect the weak signal of small defects. To highlight the weak defect indications, feature extraction and segmentation algorithms are developed. The experimental results confirm that the proposed method can inspect a small defect with dimensions 1 mm (length) × 0.1 mm (width) × 0.1 mm (depth) on a stainless-steel sample.

Integrating binary organic phosphonic acid into nanofiltration membrane for high precision separation of mono-/divalent anions

Nanofiltration membrane (NF) have become increasingly crucial in ion separation. However, traditional polyamide (PA) NF suffers from poor selectivity for mono-/divalent anions due to weak charges and structure defects. Thus, a novel binary organic phosphonic acid, alendronic acid (AA), was firstly used as an aqueous co-monomer via interfacial polymerization (IP) to create negatively charged nanofiltration membranes with both higher charge density and pore size homogeneity for the separation of mono-/divalent anions. Both structure characterization and performance tests demonstrated the successful introduction of AA in the separation layer. Compared with pristine membrane, the NaCl/Na2SO4 selectivity of membrane incorporated with AA was four times improved, while the permeability exhibited no decline. Simultaneously, the separation efficiency of Cl-/SO42- was tested in NaCl/Na2SO4 binary mixed solutions with varying total concentrations and different mass ratios, and the separation factor consistently exceeded 500 across a concentration range of 1 g/L to 20 g/L. Moreover, the AA-integrated membrane exhibited excellent chlorine resistance after 20000 ppm·h of chlorine treatment, which is promising for high efficiency separation of mono-/divalent anions in industrial applications.