Research on defect recognition technology of transmission line based on visual macromodeling

With the explosive growth in seismic data acquisition and the successful application of deep convolutional neural networks (DCNN) to various image processing tasks within multidisciplinary fields, many researchers have begun to research DCNN based automatic seismic interpretation techniques. Due to the vast number of parameters considered in deep neural networks, deep learning methods usually require a large amount of data for training. However, collecting a large number of expert interpretations is very time consuming, so related research usually uses synthetic datasets and ignores the practical problems of field datasets. In this paper, we open-source a multi-gigabyte expert-labelled field dataset in response to the challenge of accessing large-scale expert-labelled field datasets. We show that 2D fault recognition within this dataset is an image segmentation or edge detection problem in the computer vision field, that can be expressed as a pixel-level fault/non-fault binary classification. Both types of DCNNs are compared, and we propose a novel fault recognition workflow, which involves processing and screening of seismic images and labels, training DCNNs and automatic numerical evaluation. We have also demonstrated for three case study datasets that effective image augmentation methods can reduce the required labelled crosslines while maintaining satisfactory performance. Our experimental results show that our workflow not only outperforms two state-of-the-art DCNN solutions but also achieves performance comparable to humans on an expert labelled image dataset, even predicting subtle faults that an expert interpreter did not annotate. We suggest that the proposed workflow could reduce the fault interpretation life cycle from months to hours and improve the quality, and define the confidence, of fault interpretation results.

A fault recognition method for transmission systems based on independent component analysis and convolutional neural networks

In order to achieve rapid and accurate recognition of a large number of images of transmission line, and improve the ability to detect defects, according to the characteristics of defects in transmission line, an improved multi-target defect recognition algorithm based on the Faster-RCNN was proposed in this study. The algorithm adopted bilinear interpolation method and selected alternating optimization training method of Faster-RCNN. ROI Pooling in convolutional neural network was improved to ROI Align regional feature aggregation. Using the target image datasets of 7 types of transmission line, the structure and parameters of VGG16, VGG_CNN_M1024 and ZF network models under the framework of Faster-RCNN were optimized, and by comparing the precision rate-recall rate of the three network models, the refined VGG16 was selected as the feature extraction network of Faster-RCNN. The mean Average Precision (mAP) of the network model for target recognition of transmission line was about 88.01%. Also, the loss curves of region proposal network (RPN) regression and classification, Fast-RCNN regression and classification showed that the effectiveness of the improved VGG16 network model is ideal. Further, the test results indicated that the improved Faster-RCNN for target recognition on transmission line had a recall rate of 0.8252 to 0.9869, with an average of 0.9254; an accuracy of 0.5400 to 0.8616, with an average of 0.7273; F1 value (F-measure) of 0.6618 to 0.9230, with an average of 0.8114; the average accuracy of this model was 86.57% and the average detection time was 0.307 s. Capitalizing on these study findings, the improved Faster-RCNN has high effectiveness and real-time performance for defect recognition of transmission line, and can provide intelligent and effective decision-making basis for the detection of transmission lines defects in actual line inspections.

Deep neural networks (DNNs), e.g., convolutional neural network (CNN), are able to learn effective features from wafer maps for dimensional reduction and feature extraction. However, very large image data are needed to train DNNs to obtain high generalization performance. It is still a difficult task due to the lack of sufficient labeled images with various defects. This article proposes a semisupervised deep transfer learning algorithm called joint feature and label adversarial network (JFLAN). JFLAN uses CNNs to extract transferable features of wafer maps and then introduces a multilayer domain adaptation and pseudolabel learning block based on the generative adversarial network (GAN). This effectively reduces the distribution discrepancy and the among-class distance of the transferable features. Finally, JFLAN transfers knowledge from wafer image source data collected offline and then achieves the goal of significantly improved accuracy of wafer defect recognition and realizes online adaptive defect recognition. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —The defect recognition on wafer maps plays a key role to recognize fault sources of the semiconductor manufacturing processes. Transfer learning is able to use the existing labeled data to assist in the classification of unlabeled data and is very effective to solve the problem of small samples and nonstationary generalization errors. In particular, the infusion of adversarial learning in transfer learning will provide a new idea for deep feature learning. This article provides a novel method based on transfer learning to implement wafer map defect recognition (WMDR) to quickly identify defect root causes for yield enhancement. This article provides a novel way for quality control of semiconductor manufacturing processes based on transfer and adversarial learning.

Aiming at the problem of objects in image recognition rectangle, but objects which are input into convolutional neural networks square, the object recognition model was put forward which was based on BING method to realize object estimate, used vectorization of convolutional neural networks to realize input square image in convolutional networks, therefore, built joint convolution neural networks, which achieve multiple size image input. Verified by experiments, the accuracy of multi-object image recognition was improved by 6.70% compared with single vectorization of convolutional neural networks. Therefore, image recognition method of joint convolutional neural networks can enhance the accuracy in image recognition, especially for target in rectangular shape.

With the upgrading of mobile phone equipment, automatic detection of mobile phone film defects has been paid more and more attention in industrial production quality. Mobile phone film defect detection is a huge workload and challenging problem. Traditional methods can also detect some industrial id

Defects detection and recognition is very important to guarantee the welding quality. Many researches have done on this topic. However, most of them are too complex or limited in efficiency. Different from these researches, a method that is used to auto-recognize defects from the images of welding lines is put forward. Begin with the characteristics of the welding defects, the paper discusses an effective method to extract the features of the defects much simple algorithm which is based on perceptron model to recognize and classify the defects. Experimental results show that the pretreatment of the images of welding lines is very important to the feature extraction and defects recognition and the and method of recognition and classification of defects put forward is effective. It can much reduce the working effort of human being and increase the defect recognition efficiency.

Insulator fault diagnosis is a daily but key task for the power transmission system. Long-term exposure to complex natural environment will cause different insulator defects. As a common defects, missing-cap defects of insulators will not only affect the structural strength of power insulators, but also bring a certain effect to the stable power transmission. With the rapid development of machine learning, some machine learning-based defect recognition methods have been proposed for fast and high-precision power inspection. However, the handcrafted features could not effectively express the aerial images against complex inspection environment to affect detection performance of the shallow learning algorithms. And the detection precision of deep learning algorithms will be affected by the unbalanced small-scale defects. Therefore, the fast and high-precision power inspection still faces a certain challenge in the smart grid. To address the above issues, fusion with the deep convolutional neural network (DCNN) and transfer learning, a novel fault diagnosis algorithm of power insulators is proposed to provide a fast and accurate power inspection scheme. To remove complex backgrounds, a fast insulator location algorithm based on the lightweight YOLOV4 model is proposed which is served for the following defect recognition. On the basis, to imitate human vision, a defect recognition algorithm is proposed based on multi-feature fusion. Meanwhile, to ensure the feature expression ability of transfer learning on power insulators, a novel optimization strategy of transfer learning is proposed to improve the recognition precision. Experiments show that the proposed method could acquire a good recognition performance than other recognition models.

With the gradual improvement of the intelligence of power grid inspection, it is of great significance to apply image recognition technology based on deep learning to the intelligent inspection of transmission lines. This paper proposes an image recognition technology for transmission line equipment based on YOLOv2 network. It utilizes the powerful learning ability and fast recognition speed of YOLOv2 network to accurately learn different characteristics of multiple devices under the condition that the background of transmission lines is varied, and quickly complete the image recognition task. After conducting thorough training on the image of the transmission line obtained by inspection, the accuracy of the YOLOv2 network reached 90.9%, and the recognition speed reached 30 frames per second. The simulation results show that the image recognition technology based on YOLOv2 network balances the recognition accuracy and speed well, and it satisfies the requirements of real-time intelligent inspection.

Deep learning models have gained prominence in AI research due to their exceptional feature extraction capabilities. In fingerprint-based indoor localization, 1D and 2D convolutional neural networks (CNNs) are frequently utilized for their superior performance and minimal hardware requirements. However, these models primarily extract spatial features and often exhibit degraded real-time performance due to signal inconsistencies caused by shadowing, fading, and multipath effects. To address this, incorporating temporal variations through 3D CNNs can enhance outcomes, albeit with increased computational costs. This study proposes a knowledge distillation (KD) approach using 3D CNNs for indoor localization, to bridge the computational and performance gaps. The proposed KD framework employs a complex teacher model (TM) to train two simpler student models A (SM-A) and B (SM-B). We employ both response-based and feature-based KD methods to optimize the student models’ weights. The proposed techniques are evaluated using the UJILIB dataset collected from two floors of the University of Jaume I library. To enhance model performance, data augmentation is applied, yielding substantial improvements in test accuracy of 10.56% for TM, 16.19% for SM-A, and 16.93% for SM-B. The application of KD results in accuracy improvements of 5.45% for SM-A and 3.35% for SM-B, consequently reducing their average positioning errors (APEs) from 1.070 m and 1.030 m to 0.840 m and 0.944 m, respectively. Compared to KD-based SM-A, TM shows only 3.30% higher positioning accuracy, but with a 65.14% increase in computational complexity. Notably, the KD-enhanced SM-A also achieves a significantly lower APE of 0.84 m compared to the 2D CNN of 1.72 m.

The leather industry plays a crucial role in the production of high-quality leather products to remain competitive in the market. Due to various reasons such as material handling and turning, leather defects can appear at different stages of the production process. This paper proposed deep learning techniques, specifically transfer learning, deep convolutional neural networks (D-CNN), and ensemble learning for automating leather defect detection and classification. The dataset was taken from the open source Kaggle. The dataset was preprocessed from the beginning. However, we performed Error Level Analysis (ELA) to detect possible changes or fraud in the image. We also used data augmentation techniques (resizing, rescaling, flipping, rotation, zooming, and contrasting) on the dataset to improve the model performance. This study investigated deep learning architectures for automatic leather defect detection, comparing them with seven deep convolutional neural networks (D-CNN) models and transfer learning architectures. Furthermore, we introduce and evaluate two novel ensemble models: MER built on transfer learning architecture (MobileNetV2, EfficientNetB0, and ResNet50) and AZL built on D-CNN architecture (AlexNet, ZfNet, and LeNet). A key contribution of this study is the demonstration of significant performance improvements achieved by strategically integrating squeeze and excitation and label smoothing techniques into transfer learning, D-CNN, and ensemble frameworks. Our proposed MER ensemble method achieves a state-of-the-art of 96.39% for leather defect detection. The proposed model was evaluated using performance metrics including precision, recall, F1-score, AUC, ROC, and Matthews Correlation Coefficient (MCC). Additionally, Grad-CAM was employed for explainable AI to visualize and interpret the model’s decision-making process. Comparative analysis against separate transfer learning and D-CNN models fails to establish the superior performance of our MER ensemble, which highlights the potential to significantly advance automated quality inspection in leather production. This study provides insights into evaluating the best deep learning techniques for leather defect classification, paving the way for more accurate, efficient, and reliable industrial applications. Proposes a robust deep learning-based framework for automated leather defect detection using transfer learning, deep CNNs, and two novel ensemble models (MER and AZL), enhanced with squeeze-and-excitation and label smoothing techniques. Achieves state-of-the-art performance with the proposed MER ensemble model, achieve 96.39% accuracy, and demonstrates superior results across precision, recall, F1-score, AUC–ROC, and MCC. Integrates Error Level Analysis (ELA), extensive data augmentation, and Grad-CAM–based explainable AI to ensure data reliability, improve generalization, and provide transparent visual interpretation of defect regions for industrial quality inspection.

The classification method of steel surface defects with high performance and easy to be embedded in the detection equipment is one of the keys to ensure the quality of hot rolled strip. However, the development of deep convolutional neural networks (CNNs) in many real-world applications is largely hindered by their high computational cost, especially in industrial production, although it has good classification accuracy compared with machine learning-based methods in image recognition. Therefore, in this work, we present a lightweight network FCCNet based on the convolutional neural network to facilitate its application in the detection system. To compensate for the accuracy loss caused by the network downsizing, a knowledge distillation (KD) method using a larger trained network (teacher network) to teach a smaller network (student network) is adopted to improve the performance of our model. As a result, our method achieves a classification accuracy of 99.44%, precision of 99.46%, recall of 99.45%, and an F1 score of 99.45% on the NEU-CLS dataset, using only 0.03 MB parameters. These results show that the FCCNet is lighter than other existing classic CNNs with good performance for surface defects classification of hot-rolled steel strip, and it has the potential to be applied in the actual production line.

For defense applications, rapid X-ray inspection of propellant samples is essential for the identification and assessment of defects. Automation of this process using artificial intelligence is possible by properly training a neural network model. Convolution Neural Networks (CNNs) have recently demonstrated excellent success in both the tasks of image recognition and localisation using an adequate amount of data. In real-world, it’s not an easy task to produce the correct amount of experimental data required for the deep neural network to operate. In this work, we propose a method for producing synthetic radiographic data that is supported by ray tracing based radiographic simulations for the deep learning algorithms to automatically detect anomaly in X-ray images. The simulation results, which are then supplemented by noise extracted from the experimental data, show a good comparison with the measurements. This Simulation assisted Automatic Defect Recognition (Sim-ADR) system simultaneously perform defect detection and defect instance segmentation. The accuracy of the defect detection system is more than 87% on a testing set included 416 images.

An Uncertainty-Aware Deep Learning Framework for Defect Detection in Casting Products

Medical image processing has become an integral part of disease diagnosis, where technological advancements have brought significant changes to this approach. In this review, a comprehensive comparison between Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) in processing medical images is conducted. Automated medical analysis is becoming increasingly important due to issues of subjectivity in manual diagnosis and potential treatment delays. This research aims to compare the performance of Machine Learning (ML) in medical contexts using MRI, CT scan, and X-ray data. The comparison includes the accuracy rates of CNN and SVM algorithms, sourced from various studies conducted between 2018 and 2022. The results of the comparison show that CNN has higher average accuracy in processing MRI and X-ray data, with average values of 98.05% and 97.27%, respectively. On the other hand, SVM exhibits higher average accuracy for CT scan data, reaching 91.78%. However, overall, CNN achieves an average accuracy of 95.58%, while SVM's average accuracy is at 94.72%. These findings indicate that both algorithms perform well in processing medical data with high accuracy. Although based on these average accuracy rates, CNN demonstrates slightly better capabilities than SVM. Further research and development of more complex models are expected to continue improving the effectiveness of both approaches in disease diagnosis and patient care in the future.