Surface Defect Classification Research Articles

Quantifying the atomistic free-volume morphology of materials with graph theory

We introduce a new computational methodology for the identification and characterization of free volume within/around atomistic configurations. This scheme employs a three-stage workflow, by which spheres are iteratively grown inside of voxels, and ultimately converted to planar graphs, which are then characterized via a graph-based order parameter. Our approach is computationally efficient, physically intuitive, and universally transferable to any material system. Validation of our methodology is performed on several sets of materials problems: (1) classification of unique free volumes in various crystal phases, (2) autonomous detection and classification of complex surface defects during epitaxial growth simulations, (3) characterization of free volume defects in metals/alloys, and (4) quantification of the spatio-temporal behavior of nano-scale free volume morphologies as a function of both temperature and free-volume size. Our method accurately identifies and characterizes unique free volumes over a multitude of systems and length scales, indicating its potential for future use in understanding the relationship between free volume morphology and material properties under both static and dynamic conditions.

A nondestructive testing method for detecting surface defects of Si3N4-Bearing cylindrical rollers based on an optimized convolutional neural network

Aiming at solving the problems of low detection efficiency, poor accuracy rate, and low applicability of the traditional detection methods for surface defects on the silicon nitride (Si3N4) bearing cylindrical rollers. In this study, to detect the surface defects on Si3N4-bearing cylindrical rollers, a nondestructive testing (NDT) method based on an optimized convolutional neural network is proposed, which uses machine vision system to detect the surface defects. The optimized convolutional neural network is a two-stage network. It combines a semantic segmentation sub-network and a decision sub-network. The semantic segmentation sub-network performs an end-to-end learning based on the features of the original image. It completes defect feature extraction to segment the surface defect area from the normal area. The decision sub-network classifies the defects in the segmented surface defect area. The experimental results show that the detection time of surface defects on Si3N4-bearing cylindrical rollers by the proposed network was 72 ms. In addition, its Accuracy (Acc), Percision (Pre), Sensitivity (Sen), and Specificity (Spe) were 97.5%, 99.9%, 99.0%, 98.6%, respectively, which significantly improved the Acc and Pre of the detection of surface defects on Si3N4-bearing cylindrical rollers compared with the traditional detection method. On the other hand, its mIoU, mPA were 84.4%, 92.9%, respectively, meaning brilliant ability of image segmentation for this network. To sum up, the ability of the proposed network to detect and classify surface defects on Si3N4-bearing cylindrical rollers is excellent.

Cross-Domain Few-Shot Learning Approach for Lithium-Ion Battery Surface Defects Classification Using an Improved Siamese Network

It is difficult to detect the surface defects of a lithium battery with an aluminum/steel shell. The reflectivity, lack of 3D information on the battery surface, and the shortage of many datasets make the 2D detection method hard to apply in this field. In this paper, a cross-domain few-shot learning (FSL) approach for lithium-ion battery defect classification using an improved siamese network (BSR-SNet) is proposed. To obtain the critical 3D surface of the lithium-ion battery, a multiexposure-based structured light method is utilized. Then, the heights of the 3D cloud points are transferred to grayscale information and are saved as 8-bit 2D images. For the FSL task, the DAGM 2007 datasets are used as the source domain to pre-train the improved siamese model. To avoid negative mitigation in the target domain, batch spectral regularization (BSR) is added as a penalizer in the loss function. The accuracies of the experimental results are 93.3% for 10-shot batteries and 91.0% for 5-shot batteries, which means that our method can be used to classify the surface defects of lithium batteries well.

Surface Defects Classification of Hot Rolled Strip Based on Few-shot Learning

Surface Defects Classification of Hot Rolled Strip Based on Few-shot Learning

Defect Detection and Classification Algorithm of Metal Nanomaterials Based on Deep Learning

With the rapid development of nanotechnology, researchers can prepare nanomaterials by various methods. The rapid development of nanotechnology has greatly promoted the wide application of nano materials in the field of detection and catalysis. Especially the metal nanomolecules have good biocompatibility, absorption of plasma surface resonance, enhanced Raman surface and other properties. Metal nanomolecules have good biocompatibility, absorption of plasma surface resonance and enhanced Raman surface Rice inspection and catalytic application have attracted wide attention. This paper mainly studies the defect detection and classification algorithm of metal nanomaterials based on deep learning. Through the experimental phenomena, we can understand and master the defect detection methods of metal nanomaterials, and review the problems and future development direction of the preparation of metal nanomaterials. Deep learning algorithm the first mock exam deep learning network model, metal defect multi-mode detection method and the classification of metal surface defects are investigated. The defect detection of metal nano materials based on deep learning is realized. The whole defect and the quantitative detection of metal defects are realized. The detection range of traditional single mode nondestructive testing technology is overcome. The deficiency of accurate quantitative detection is difficult. The results show that there are five characteristic parameters for metal nano surface defect detection. In the deep learning based defect detection and classification algorithm, the big data technology is used to analyze the complete defect data, environmental data and working intensity data to complete the prediction of the future development trend of defects, which can play an important role in the maintenance of materials It is also of great significance to the development of metal nano detection technology.

SDDA: a method of surface defect data augmentation of hot-rolled strip steel

The detection of surface defects in hot-rolled strip steel is an important step in the production process of hot-rolled strip steel, and it is closely related to the final quality. At present, many researchers have conducted many in-depth studies on the classification of strip steel surface defects and achieved fruitful results. However, current research has always focused on modifying the model; this approach has limited improvement in classification accuracy and often brings a reduction in model efficiency. A data augmentation method named SDDA, which can perform multiscale transformations on the images input to the deep learning models, is proposed and validated on X-SDD dataset by MixNet model. The test results show that after the SDDA data augmentation, the accuracy of the model reached 96.81%, which is 1.71% higher than the previous best result; meanwhile, since the improvement occurs on the data side, it only leads to an increase in training time and does not increase the inference time of the model. Through comparison experiments, it can be found that our data augmentation approach provides significant improvements in multiple metrics such as accuracy and F1 for a variety of deep learning models.

Surface Defect Classification in Silicon Wafer Manufacturing Using the Linear-Based Channeling and Rule-Based Binning Algorithms

Developing an accurate means of classifying defects, such as crystal-originated pits, surface-adhered foreign particles, and process-induced defects, using scanning surface inspection systems (SSIS) is of paramount importance because it provides the opportunity to determine the root causes of defects, which is valuable for yield enhancement. This report presents a novel defect classification approach developed by optimizing the linear-based channeling (LBC) and rule-based binning (RBB) algorithms that are applied to a commercially available SSIS (KLA-SP5), in combination with test sample selection including the signature defect patterns associated with the typical crystal growth process. The experimental results demonstrate that defect classification is possible with an accuracy and purity above 80% using the LBC algorithm and 90% using the RBB algorithm.

Fusion of multi-light source illuminated images for effective defect inspection on highly reflective surfaces

It is observed that a human inspector can obtain better visual observations of surface defects via changing the lighting/viewing directions from time to time. Accordingly, we first build a multi-light source illumination/acquisition system to capture images of workpieces under individual lighting directions and then propose a multi-stream CNN model to process multi-light source illuminated images for high-accuracy surface defect classification on highly reflective metal. Moreover, we present two effective techniques including individual stream deep supervision and channel attention (CA) based feature re-calibration to generate and select the most discriminative features on multi-light source illuminated images for the subsequent defect classification task. Comparative evaluation results demonstrate that our proposed method is capable of generating more accurate recognition results via the fusion of complementary features extracted on images illuminated by multi-light sources. Furthermore, our proposed light-weight CNN model can process more than 20 input frames per second on a single NVIDIA Quadro P6000 GPU (24G RAM) and is faster than a human inspector. Source codes and the newly constructed multi-light source illuminated dataset will be accessible to the public.

Classification and Fast Few-Shot Learning of Steel Surface Defects with Randomized Network

Quality inspection is inevitable in the steel industry so there are already benchmark datasets for the visual inspection of steel surface defects. In our work, we show, contrary to previous recent articles, that a generic state-of-art deep neural network is capable of almost-perfect classification of defects of two popular benchmark datasets. However, in real-life applications new types of errors can always appear, thus incremental learning, based on very few example shots, is challenging. In our article, we address the problems of the low number of available shots of new classes, the catastrophic forgetting of known information when tuning for new artifacts, and the long training time required for re-training or fine-tuning existing models. In the proposed new architecture we combine EfficientNet deep neural networks with randomized classifiers to aim for an efficient solution for these demanding problems. The classification outperforms all other known approaches, with an accuracy 100% or almost 100%, on the two datasets with the off-the-shelf network. The proposed few-shot learning approach shows considerably higher accuracy at a low number of shots than the different methods under testing, while its speed is significantly (at least 10 times) higher than its competitors. According to these results, the classification and few-shot learning of steel surface defects can be solved more efficiently than was possible before.

Hybrid Architecture Based on CNN and Transformer for Strip Steel Surface Defect Classification

Strip steel surface defects occur frequently during the manufacturing process, and these defects cause hidden risks in the use of subsequent strip products. Therefore, it is crucial to classify the strip steel’s surface defects accurately and efficiently. Most classification models of strip steel surface defects are generally based on convolutional neural networks (CNNs). However, CNNs, with local receptive fields, do not have admirable global representation ability, resulting in poor classification performance. To this end, we proposed a hybrid network architecture (CNN-T), which merges CNN and Transformer encoder. The CNN-T network has both strong inductive biases (e.g., translation invariance, locality) and global modeling capability. Specifically, CNN first extracts low-level and local features from the images. The Transformer encoder then globally models these features, extracting abstract and high-level semantic information and finally sending them to the multilayer perceptron classifier for classification. Extensive experiments show that the classification performance of CNN-T outperforms pure Transformer networks and CNNs (e.g., GoogLeNet, MobileNet v2, ResNet18) on the NEU-CLS dataset (training ratio is 80%) with a 0.28–2.23% improvement in classification accuracy, with fewer parameters (0.45 M) and floating-point operations (0.12 G).

CASI-Net: A Novel and Effect Steel Surface Defect Classification Method Based on Coordinate Attention and Self-Interaction Mechanism

The surface defects of a hot-rolled strip will adversely affect the appearance and quality of industrial products. Therefore, the timely identification of hot-rolled strip surface defects is of great significance. In order to improve the efficiency and accuracy of surface defect detection, a lightweight network based on coordinate attention and self-interaction (CASI-Net), which integrates channel domain, spatial information, and a self-interaction module, is proposed to automatically identify six kinds of hot-rolled steel strip surface defects. In this paper, we use coordinate attention to embed location information into channel attention, which enables the CASI-Net to locate the region of defects more accurately, thus contributing to better recognition and classification. In addition, features are converted into aggregation features from the horizontal and vertical direction attention. Furthermore, a self-interaction module is proposed to interactively fuse the extracted feature information to improve the classification accuracy. The experimental results show that CASI-Net can achieve accurate defect classification with reduced parameters and computation.

A semi-supervised learning method for surface defect classification of magnetic tiles

A semi-supervised learning method for surface defect classification of magnetic tiles

The development of on-line surface defect detection system for jujubes based on hyperspectral images

• A hyperspectral system was built for collecting hyperspectral image data and performing skin defect detection of jujubes online. • Hyperspectral data of jujubes with common skin defects were obtained for training classification models. • Support vector machine and artificial neural network models were used for online skin defect detection of jujubes. • To reduce the computation time of online classification, spectral bands were selected with equal band interval method or the principal component analysis. • Experimental results showed that artificial neural network models using 14 bands can compromise the accuracy and speed for online classification of jujubes. This paper presents the development of an on-line surface defect system using hyperspectral images for jujubes. A push-broom hyperspectral system was built for collecting hyperspectral image data and detecting skin defects of jujube online. Hyperspectral images with an effective wavelength range of 468–950 nm were obtained for jujubes with normal surface or common skin defect types (i.e., russeting, decay, white fungus, black fungus and crack). Support vector machine (SVM) and artificial neural networks (ANN) models were used to classify surface defects of jujubes. The classification accuracies, with the use of full wavelength range, of ANN and SVM models for jujube skin defects are 96.5% and 96.3% respectively. The times required for processing one jujube face are about 25 and 320 s for ANN and SVM models respectively. To reduce the computation time of online classification tasks, spectral bands were selected from a wavelength range of 468–760 nm with equal band intervals or by the principal component analysis (PCA) method. Experimental results showed that the accuracy of SVM and ANN models using 14 bands (469, 491, 513, 535, 558, 580, 602, 624, 646, 668, 691, 713, 735 and 757 nm), selected by equal wavelength intervals, were 94.4% and 95% respectively. And the accuracies of ANN and SVM models with 14 bands (470, 493, 534, 555, 590, 623, 632, 654, 672, 674, 683, 696, 707 and 747) selected by PCA are 95% and 94.6% respectively. The classification time, with the use of 14 bands, of ANN and SVM models for jujube skin defects reduced to 16.6 and 30 s respectively. The online line scanning and classification hyperspectral imaging system can be used for surface defect detection of other fruits.

Strip Steel Surface Defects Classification Based on Generative Adversarial Network and Attention Mechanism

In a complex industrial environment, it is difficult to obtain hot rolled strip steel surface defect images. Moreover, there is a lack of effective identification methods. In response to this, this paper implements accurate classification of strip steel surface defects based on generative adversarial network and attention mechanism. Firstly, a novel WGAN model is proposed to generate new surface defect images from random noises. By expanding the number of samples from 1360 to 3773, the generated images can be further used for training classification algorithm. Secondly, a Multi-SE-ResNet34 model integrating attention mechanism is proposed to identify defects. The accuracy rate on the test set is 99.20%, which is 6.71%, 4.56%, 1.88%, 0.54% and 1.34% higher than AlexNet, VGG16, ShuffleNet v2 1×, ResNet34, and ResNet50, respectively. Finally, a visual comparison of the features extracted by different models using Grad-CAM reveals that the proposed model is more calibrated for feature extraction. Therefore, it can be concluded that the proposed methods provide a significant reference for data augmentation and classification of strip steel surface defects.

Surface defect detection and classification of Si3N4 turbine blades based on convolutional neural network and YOLOv5

Due to the influence of mechanical vibration, high temperature creep and other factors, Si3N4 turbine blades are prone to surface defects. Besides, traditional algorithms are incapable to detect and classify surface defects simultaneously. Aiming at solving these problems, an algorithm for defect detection and classification of Si3N4 turbine blades based on convolutional neural network is proposed. The detection and classification network of this algorithm is optimized based on YOLOv5 network, the PAN structure and FPN structure of YOLOv5 are replaced by BiFPN structure. We establish the dataset of Si3N4 turbine blades, which is expanded by data enhancement. For the purpose of achieving a higher level of feature fusion, the PAN and FPN structures of the Neck part are replaced by BiFPN structure. As a result, the accuracy of detecting and classifying the surface defects by this algorithm is as high as 97.4%, and the detection speed is as low as 16ms. This optimized algorithm is able to solve the problems of traditional detection methods such as heavy workload, long time consuming and low accuracy. The algorithm provides a feasible approach for the quality detection of Si3N4 turbine blades and has certain engineering application value.

Classification of Surface Defects on Steel Strip Images using Convolution Neural Network and Support Vector Machine

Classification of Surface Defects on Steel Strip Images using Convolution Neural Network and Support Vector Machine

Defect Detection on LED Chips Based on Position Pre-Estimation and Feature Enhancement

Light-emitting diode (LED) chips have disordered arrangement and defects with characteristics of low contrast, for which traditional segmentation methods cannot classify surface defects effectively. In this paper, a chip segmentation method based on position pre-estimation and a modified Normalized Correlation Coefficient (NCC) matching algorithm, as well as feature enhancement methods are proposed. The position pre-estimation method is used to avoid the interference introduced by the disordered chip arrangement and the large missing area. By modifying the NCC algorithm, matching speed is improved by eight times compared to traditional NCC while matching result is not affected by brightness change. Furthermore, feature enhancement schemes with higher speed and accuracy were designed to identify low-contrast defects. The experimental results showed that the average accuracy reached 99.54%, improved by 0.66% compared to the state-of-the-art method while the inspection missing rate was 0.03%. In addition, the detection time of a single chip was approximately 1.098 ms, which meets the requirements of online detection, and the smallest defect that could be detected was 2 µm. In summary, the methods proposed in this study meet the requirements of industrial online detection regardless of accuracy, efficiency, or extensibility.

Non-contact detection of railhead defects and their classification by using convolutional neural network

Railhead defects must be detected and classified intelligently in order for railway transportation systems to operate safely. Rail defect identification and categorization can be automated by using machine learning models to process rail image data (acquired using cameras). However, such an automated method has significant drawbacks: it cannot detect subsurface defects, picture data requires a high-end GPU with a long computational time, and machine learning model training can be influenced by image quality, which is dependent on light intensity and shooting altitude. Rayleigh waves are a potential candidate for rail inspection because they can detect both surface and subsurface defects and travel long distances on curved surfaces (like a rail) at high speed. This article looks into the possibility of combining fully non-contact laser ultrasonic technology (LUT) and a deep learning approach for intelligent detection and classification of railhead surface and subsurface defects. The fully non-contact LUT was used to actuate and capture laser-generated Rayleigh wave signals on railhead specimens in order to create a database of A-scan signals from healthy, surface, subsurface, and edge defect railheads. The classification capabilities of a support vector machine (SVM), a fully connected deep neural network (DNN), and a convolutional neural network (CNN) were examined after they were applied to the preprocessed signals without extracting any statistical/signal processing-based characteristics. The comparative analysis demonstrates that CNN is robust in classifying railhead defects. As a result, when combined with CNN, the laser ultrasonic technology may ensure automatic defection and classification of railhead surface and subsurface flaws.

Surface defect detection and prediction in carbide cutting tools treated by lasers

Laser surface engineering of cutting tools is used to improve the performance of cutting processes via altering the material interaction between the tool surface and workpiece. Laser processing applied to cemented carbide cutting tools can induce various thermal and mechanical surface defects including porosity, splatter, cracks, balling, spherical pores, voids, and dissociation. Those defects could be detrimental to the integrity of the tool, therefore parametric optimization is crucial to limit and control possible post-processing defects. This study aimed to identify and classify surface defects in post laser processed carbides to better understand the relationship between parameters and resultant surface integrity. A region convolutional neural network (R-CNN) was trained for identification and classification of these surface defects using scanning electron microscopy images (SEM) as inputs. The R-CNN provided a quantitative analysis of each defect with an average accuracy of 91%. Using the data from the R-CNN matched with the laser parameters, a back propagation neural network (BPNN) was trained to act as a predictive network. The network predicts the number and proportion of defects when the tool grain size, roughness and laser parameters are entered. The accuracy of this predictive network was 96.6%. The effect of individual laser parameters on the surface integrity is estimated by this method, enabling the optimization of laser processing in cutting tools. For the first time this can be used to predict tool performance based on tool’s surface integrity.

An Overview of Deeply Optimized Convolutional Neural Networks and Research in Surface Defect Classification of Workpieces

Currently, the development of industry is becoming increasingly rapid. Technicalization, informatization and industrialization give the fundamental impetus for industrial development and progress. Nevertheless, there are numerous problems that are hindering industrial progress and threatening human security in the industrial field. The surface defects of the workpieces are one of the primary problems. Moreover, defects of multi-type, mixed and unapparent characteristics presented by workpieces make the detection and classification of workpiece more difficult. Deep convolutional neural networks (DCNN) show strong ability of feature extraction and mines deeper essential features of data because of its features of unique receptive field structure and weights of shared. It can represent original data information well and obtain results more accurately than the traditional methods. But there also remains a problem that conventional DCNN has a huge number of parameters and computation, which brings great pressure to the equipment in terms of computing power, memory, speed and so on. Based on this situation, the optimization methods of CNNs model in the aspects of data, structure, algorithm are summarized. Related lightweight structures and networks are also summarized in this paper. The purpose of these work is to reduce the number of parameters and computation and improve the training performance. At the same time, the research on defect classification of workpieces based on traditional machine learning and deep learning model is reviewed, and the research on defect classification of workpieces based on deeply optimized CNNs is referred and prospected.