Defect Detection Scheme Research Articles

Fabric Defect Detection in Real World Manufacturing Using Deep Learning

Defect detection is very important for guaranteeing the quality and pricing of fabric. A considerable amount of fabric is discarded as waste because of defects, leading to substantial annual losses. While manual inspection has traditionally been the norm for detection, adopting an automatic defect detection scheme based on a deep learning model offers a timely and efficient solution for assessing fabric quality. In real-time manufacturing scenarios, datasets lack high-quality, precisely positioned images. Moreover, both plain and printed fabrics are being manufactured in industries simultaneously; therefore, a single model should be capable of detecting defects in all kinds of fabric. So training a robust deep learning model that detects defects in fabric datasets generated during production with high accuracy and lower computational costs is required. This study uses an indigenous dataset directly sourced from Chenab Textiles, providing authentic and diverse images representative of actual manufacturing conditions. The dataset is used to train a computationally faster but lighter state-of-the-art network, i.e., YOLOv8. For comparison, YOLOv5 and MobileNetV2-SSD FPN-Lite models are also trained on the same dataset. YOLOv8n achieved the highest performance, with a mAP of 84.8%, precision of 0.818, and recall of 0.839 across seven different defect classes.

Improved automatic defect detection from X-ray scans for aluminum conductor composite core wire based on modified Skip-GANomaly

The Aluminium Conductor Composite Core (ACCC) is a critical component of power transmission that needs automated nondestructive defect detection to prevent wire breaking accidents and ensure regular city operations. Unfortunately, the current supervised target detection scheme is limited in its generalization ability due to the diversity of defect morphology and the high cost of acquiring samples. To overcome these challenges, we propose an automatic defect detection method based on a modified Skip-GANomaly model using X-ray images of ACCC wires as input. We experiment with semi-supervised deep learning reconstruction methods to mitigate the lack of abnormal samples and improve the generalization ability of unknown defects. We also explore hierarchical reconstruction and Skip-Connection adjustment to enhance the reconstruction effect and defect identification based on Resnet50. The results show that our method can achieve high accuracy, recall, and precision levels of over 99 %, significantly highlighting the difference in defect morphology. Compared to existing supervised schemes, our Defect Detection Scheme with Hierarchical Reconstruction and Anomaly-Subtracted Image Discrimination (DHRAD) eliminates dependence on the number of abnormal samples and the diversity of defect types in the training set, and has the ability to detect defects with unknown morphology. Therefore, DHRAD provides an effective detection scheme for automatic nondestructive defect detection of ACCC in operation, based on computer vision and semi-supervised learning.

Defect detection of glassivation passivation parts wafer surface with random texture and different brightness

Automatic defect detection for glassivation passivation parts (GPP) wafer surface becomes an extremely challenging task, due to the interference of random texture, disturbance of low-contrast pseudo defects within the image, and difference of different brightness between images. In this paper, we propose a novel defect detection scheme for GPP wafer surface with random texture and different brightness. First, an automatic segmentation method center expansion idea-based for the region of interest (ROI) of die image is presented to eliminate the interference from edge background and improve the efficiency of defect detection. Then, a feature point set extraction method based on adaptive gain and error diffusion is proposed so that the defect feature between images with different brightness can be highlighted by adaptive gain, and the candidate defect feature point set under random texture feature is able to be extracted by error diffusion. Finally, the density-based spatial clustering of applications with noise considering grayscale constraint (GC-DBSCAN) is designed to identify the true defect clusters from the candidate defect feature point set and accomplish the detection of various types of surface defects. Experimental results show that the proposed method can completely implement the extraction of crack and dirty defects and eliminate the false detection caused by random texture and different brightness, which is very efficient and superior to other methods.

Built-in Self-prevention (BISP) for runtime ageing effects of TSVs in 3D ICs

The adoption of Through-Silicon-Vias (TSVs) in Three-Dimensional Integrated Circuits (3D ICs) is gaining momentum in the industry, thanks to the numerous advantages it offers over traditional 2D ICs. However, TSVs are susceptible to defects during their formation, die stacking, and operational lifespan, leading to reliability issues in 3D ICs. While existing approaches have focused on addressing assembly and stacking yield losses, the runtime failure caused by Electro-migration (EM) remains a significant challenge in commercializing TSV-based 3D ICs. Detecting and monitoring TSV defects require an expensive on-chip sensor network, making it crucial to implement a cost-effective TSV defect prevention and detection scheme. This paper introduces a runtime Built-in Self-prevention (BISP) scheme that significantly extends TSV lifetime. The proposed method employs a repair circuit to rectify post-manufacturing TSV defects, resulting in minimal hardware costs. Furthermore, the combined repair and prevention solution introduces a delay overhead of less than 0.5 ns, ensuring compliance with timing constraints.

Real-Time Defect Detection Scheme Based on Deep Learning for Laser Welding System

Laser welding, as an important material processing technology, has been widely used in various fields of industry. In most industrial welding production and processing, high precision is required for welding parameters and fixed work pieces. However, in the process of laser welding, serious heat transfer effect will bring unpredictable welding deviations, and even a small deviation will lead to serious welding defects, which will affect the quality of the welded products. Traditional non-destructive testing methods have been widely used, but they have been proved to have some limitations. Existing laser welding defect detection schemes are mainly focused on the detection of post-weld defects, which requires a large amount of data, and the real-time detection cannot be guaranteed. In this paper, we propose a data acquisition system for collecting changes in physical characteristics during laser welding with the aids of multiple sensors. Based on the data originating from sensors’ system, an efficient laser welding defect detection model has been designed and investigated based on the MSCNN (multi-scale convolutional neural network), BiLSTM (bidirectional long short-term memory), and AM (attention mechanism). The final proposed MSCNN-BiLSTM-AM fusion detection model can achieve 99.38% detection accuracy, which make the laser welding system more efficient and more suitable.

Remanent magnetization of steel plates after being magnetized by moving magnets

Inconsistent initial magnetization of ferromagnetic specimens may result in low signal-to-noise ratio and poor consistency in detecting defects and stress anomalies of magnetic methods. One of the solutions to the problem is to magnetize specimen in advance and make it magnetized uniformly. Via theoretical analysis, finite element simulation and experiment verification, the distribution of remanent magnetization and remanent flux density of steel plates after being magnetized by moving single and dual magnets is studied. The results show that the remanent magnetization of the steel plate becomes uniform and in the same tangential direction of the magnet moving. The remanent magnetization inside the steel plate is layered, and the magnetization between different layers may be opposite. However, the magnetization of each layer is uniform, and the tangential remanent magnetization is large, while the normal remanent magnetization is small. The longer the length of the steel plate specimen, the longer the flat area of the magnetic flux density near the surface after magnetization, and the value of the flat area is closer to zero. The research results provide important guidance for the magnetization method and the defect detection scheme design.

Defect Detection Scheme of Pins for Aviation Connectors Based on Image Segmentation and Improved RESNET-50

In this paper, a new detection method of pin defects based on image segmentation and ResNe-50 is proposed, which realizes the defect detection of faulty pins in many aviation connectors. In this paper, a new dataset image segmentation method is used to segment many aviation connectors in a single image to generate a dataset, which reduces the tedious work of manually labeling the dataset. In the defect detection model, based on ResNet-50, a ResNet-B residual structure is introduced to reduce the loss of features during information extraction; a continuously differentiable CELU is used as the activation function to reduce the neuron death problem of ReLU; a new deformable convolution network (DCN v2) is introduced as the convolution kernel structure of the model to improve the recognition of aviation connectors with prominent geometric deformation pin recognition. The improved model achieved 97.2% and 94.4% accuracy for skewed and missing pins, respectively, in the experiments. The detection accuracy improved by 1.91% to 96.62% compared to the conventional ResNet-50. Compared with the traditional model, the improved model has better generalization ability.

Defect Detection Scheme for Key Equipment of Transmission Line for Complex Environment

Aiming at the difficulty in detecting defects of key equipment of transmission lines in small samples and complex environments, and the problems of low accuracy and unreliability in one-time detection using traditional deep learning-based methods, an image detection scheme combining optimized deep convolutional neural networks and Kalman filtering is proposed. The convolutional neural network architecture is based on Faster Region-based Convolutional Neural Networks (R-CNNs). First, the model backbone network is constructed by MobileNet, which effectively reduces the computational cost. Secondly, a soft nonmaximum suppression algorithm is integrated to solve the occlusion problem of target parts, and the context-aware ROI pooling layer replaces the original pooling layer, maintaining the original structure of small-sized components. Finally, the detection results are corrected twice by Kalman filtering to further improve the detection accuracy and reliability. The experimental results show that this method can realize the accurate detection of components in complex transmission line equipment, the mean Average Precision (mAP) reaches 91.10%, which is 11.05% higher than the original model, and the detection time of each picture is only 0.05 s. Compared with other detection algorithms under the same conditions, the comprehensive performance of the proposed method can be improved by 20%.

PCA-based sub-surface structure and defect analysis for germanium-on-nothing using nanoscale surface topography

Empty space in germanium (ESG) or germanium-on-nothing (GON) are unique self-assembled germanium structures with multiscale cavities of various morphologies. Due to their simple fabrication process and high-quality crystallinity after self-assembly, they can be applied in various fields including micro-/nanoelectronics, optoelectronics, and precision sensors, to name a few. In contrast to their simple fabrication, inspection is intrinsically difficult due to buried structures. Today, ultrasonic atomic force microscopy and interferometry are some prevalent non-destructive 3-D imaging methods that are used to inspect the underlying ESG structures. However, these non-destructive characterization methods suffer from low throughput due to slow measurement speed and limited measurable thickness. To overcome these limitations, this work proposes a new methodology to construct a principal-component-analysis based database that correlates surface images with empirically determined sub-surface structures. Then, from this database, the morphology of buried sub-surface structure is determined only using surface topography. Since the acquisition rate of a single nanoscale surface micrograph is up to a few orders faster than a thorough 3-D sub-surface analysis, the proposed methodology benefits from improved throughput compared to current inspection methods. Also, an empirical destructive test essentially resolves the measurable thickness limitation. We also demonstrate the practicality of the proposed methodology by applying it to GON devices to selectively detect and quantitatively analyze surface defects. Compared to state-of-the-art deep learning-based defect detection schemes, our method is much effortlessly finetunable for specific applications. In terms of sub-surface analysis, this work proposes a fast, robust, and high-resolution methodology which could potentially replace the conventional exhaustive sub-surface inspection schemes.

A novel insulator defect detection scheme based on Deep Convolutional Auto‐Encoder for small negative samples

This paper presents a novel insulator defect detection scheme based on Deep Convolutional Auto-Encoder (DCAE) for small negative samples. The proposed DCAE scheme combines the advantages of supervised learning and unsupervised learning. In order to reduce the high cost of training Deep Neural Networks, this paper pre-trained the Convolutional Neural Networks (CNN) through open labelled datasets. Through transferring learning, the encoder part of the traditional Convolutional Auto-Encoder was replaced by the first three layers of the CNN, and a small number of defect samples were used to fine-tune the parameters. A threshold discrimination scheme was designed to evaluate the model detection, realising the self-explosion detection of insulator by judging the residual result and abnormal score. The experimental results show that compared with the existing insulator self-explosion detection schemes, the proposed scheme can reduce the model training time by up to 40%, and the recognition accuracy can reach 97%. Moreover, this model does not need a large number of insulator labelled data and is especially suitable for small negative sample application.

Automated defect detection and classification for fiber-optic coil based on wavelet transform and self-adaptive GA-SVM.

The quality monitoring of fiber-optic coil (FOC) in winding systems is usually done manually. Aiming at the problem of inefficient and low accuracy of manual detection, this article is dedicated to researching a defect detection framework based on machine vision, which provides a reliable method for automatic defect detection of FOC. For this purpose, a defect detection scheme that integrates wavelet transform and nonlocal means filtering is proposed to accurately locate the defect region. Then, based on the features constructed by wavelet coefficients, a support vector machine (SVM) is used as the classifier. Additionally, a self-adaptive genetic algorithm is proposed to optimize the parameters of the SVM to form the final classifier. Through experiments on the data set obtained by our designed imaging system, the results show that our method has good defect detection performance and high classification accuracy, which provides an optimal solution for the automatic detection of FOC.

A SURVIVAL ANALYSIS ON PATTERN CLASSIFIER AND DETECTION TECHNIQUES FOR DEFECTIVE IMAGE ANALYSIS

Image based defect detection becomes a demanding task in estimating the quality of intermediate and end products in fabric and granite manufacturing, pipeline installation in heavy industries. A fabric defect detection scheme improves the quality for image defect detection and achieves higher accuracy to detect images. But, the image detection is complex in noisy applications. When the image size is large, it provides the false positive detection. The automated fabric defect classification techniques were used to analyze the ability of classifiers that employed in defect inspection systems with geometrical features. But in defect classification technique, level of accuracy is not satisfactory and real-time constraints needs to be addressed. Fabric defect detection is a significant problem in fabric quality control processing, and need to develop fast, efficient, reliable and real-time defect detection through image analysis techniques. Our research work on filtering, pattern classification and pattern detection aims to identify normal and defective image patterns from trained class patterns of the training image dataset.

Defect detection method for rail surface based on line-structured light

• A novel rail defect detection scheme before welding is designed. • A registration algorithm based on feature points is presented to align data. • A dynamic defect detection algorithm is proposed for real-time detection. • Results show that the proposed method has higher accuracy and practicability. Based on intensive study on rail surface defect, a rail surface defect inspection scheme is proposed in this paper. With high-precession structured laser sensors, the original data are collected by industrial control computer and transformed into dimensional point cloud pattern. According to analysis of the specific feature of rail surface, a registration method is proposed to re-construct the digital rail surface. To achieve a high-precision detection result, a novel curve fitting model is established and accordingly a dynamic defect detection algorithm is improved to adapt to the successive production process based on the former study. Within the detailed study process, for each single frame data, a judge method is developed for noise elimination and specific feature defect detection. Finally, by studying successive frames of data points (actually cloud points), multiple frames data are dynamically computed to judge if there is a defect area on rail surface. In this paper, to avoid the random influence of minor factors, a probability threshold is introduced to judge defect points in the algorithm, which increases the anti-interference and decreases instability in the defect detection process. To verify the effect of proposed method, an experimental bench is developed in research process. Experimental results show that the detection method has reliable stability and anti-interference possibly influenced by minor factors like oxygen layer detection and characters area detection on rail surface. Compared with traditional two dimensional defect detection methods, the algorithm proposed in this paper is less computationally intensive and more suitable for online detection on rail surface.

Morphological Detection and Extraction of Rail Surface Defects

Rail inspection by means of a visual system has been a subject of a number of publications in recent years. The main requirements with regard to such a system are that it has to be fast, nondestructive, and accurate. This article presents a system for rail defect detection and shape extraction utilizing morphological operations. The proposed system is evaluated using publicly available rail surface discrete defects (RSDDs) data sets of Type-I and Type-II. Several versions of the system are compared, and the best one is reduced to just 17 basic morphological operations implementing defect detection, defect extraction, and false-positive (FP) reduction scheme. Two evaluation methods are considered, which is a pixel-level method and a defect-level method. 70% precision and 79% recall were obtained at the defect level for Type-I RSDD. Similarly, 82% precision and 89% recall were obtained at the defect level for Type-II RSDD. Experiments showed that the FP reduction scheme is effective for type II RSDD when considering defect-level results, and it increases precision by 7%–9% while maintaining the recall almost intact. The execution time of the morphological operations of the detection algorithm together with FP reduction is in the order of 50 ms on a usual laptop.

Road Tunnel Detection Robot and Method Based on Laser Point Cloud

The maintenance of road tunnels is more important, and there are problems such as water seepage, surface cracking and falling off. If it cannot be detected and handled in time, it will pose a major threat to the driving safety of road vehicles. Therefore, this paper proposes a road tunnel defect detection scheme based on laser point cloud. Firstly, a robot for road detection is developed. Secondly, a road defect detection method based on laser point cloud is developed. Laser SLAM technology is used to reconstruct dense point clouds in road tunnel scenes. Finally, through the automatic detection of the three-dimensional reconstruction scene of the tunnel, the defects such as cracks and spalling of the road tunnel are automatically identified. Compared with the visual detection scheme, this method does not depend on the problem of ambient light and has better robustness and practicability.

Construction of defect detection scheme using static electricity distribution

Construction of defect detection scheme using static electricity distribution

Structure-aware-based crack defect detection for multicrystalline solar cells

Automatic crack defect detection for multicrystalline solar cells is a challenging task, owing to inhomogeneously textured background, disturbance of crystal grains pseudo defects, and low contrast between crack defect and background. In this paper, a novel structure-aware-based crack defect detection scheme (SACDDS) is proposed. Firstly, the structure features of crack defect and randomly distributed crystal grains are analyzed, and corresponding mathematical models are used to represent two structure features. Secondly, according to Hessian eigenvalues of the above mathematical models, the identification functions of linear-structure and blob-structure are obtained. Then, a novel structure similarity measure (SSM) function is designed by using the identification functions of two structures, which can highlight crack defect, suppress crystal grains simultaneously. It significantly weakens the interference of inhomogeneous texture and obtains uniform background. Further, in order to overcome non-uniform response of crack region and extract crack defect, a tensor voting-based non-maximum suppression (TV-NMS) method is developed. It improves the uniformity of crack defect response and extracts candidate crack defect pixels. Finally, an effective morphological operation is applied to remove non-crack pixels and complete crack defect can be located in the EL images. Experimental results show that the proposed method can completely extract crack defect in the inhomogeneously textured background, which is well effective and outperforms the previous methods.

Correction to: Vibration Suppression and Defect Detection Schemes in 1D Linear Spring-Mass Systems

This contains corrections to typographical errors in the paper “Vibration Suppression and Defect Detection Schemes in 1D Linear Spring-Mass Systems”.

An Efficient Fabric Defect Prediction Based on Modular Neural Network Classifier with Alternative Hard C-Means Clustering

In India, textile industry has been mainly focused because it increased the economy day by day. But, it has some problem in the field of quality control. At present, it is mainly solved visually through skilled workers. Though, due to the human errors and eye fatigue, the system reliability has been restricted. So, in this research has been focused automatic fabric defect detection scheme. Here, Modular Neural Network (MNN) is proposed for fabric defect detection and classification with low cost and high accurate rate via using image processing schemes in the woven fabrics. At first, the images are collected from the machine and then preprocessed by using Enhanced Directional Switching Median Filter (EDWF) to reduce the impulse and stationary noise. To attain high accurate prediction, the preprocessed image has been segmented by using Alternative Hard C-Means (AHCM) cluster. After clustering, the images are converted to binary image. Then, the first order features has been extracted from the image. The extracted features are given as input to MNN, which classifies the fabric defects. In MNN, the weight factors are calculated by using back propagation algorithm and generate the output. The simulation results show that the proposed MNN attained high accuracy rate of 96.7% when compared to existing Artificial Neural Network (ANN) than Support Vector Machine with Genetic Algorithm (SVM-GA) classification algorithms.

Health assessment of tree trunk by using acoustic-laser technique and sonic tomography

An innovative tree defect detection scheme, which combines acoustic-laser technique and sonic tomography, is studied. A new sensor distribution can be adopted based on the near-surface response detected by acoustic-laser technique, and a more reliable image of the tree trunk can be observed by sonic tomography. By using such hybrid detection scheme, the near-surface defects (bark detachment, cracks, decay) can be revealed at the early stages of defect development. The accuracy of defect detection during advanced tree risk assessment is therefore highly improved. As a newly developed detection technique for detecting the near-surface defect in tree trunk, the measurement results of acoustic-laser technique in tree trunk are comprehensively discussed, especially toward the detectable depth beneath the tree surface. The experimental results demonstrated that the acoustic-laser technique can identify the presence of near-surface defects in a tree trunk that are normally overlooked by the conventional sonic tomography measurements with random distribution of sensors.