Fault Recognition Method Research Articles

Research on tire internal defect identification method based on deep learning

As an important part of automobile, the safety and durability of tire have attracted more and more attention. Tire defect detection is an important link to ensure tire quality, while traditional detection methods have problems such as low efficiency, high false detection rate and high labor intensity. Therefore, this study aims to develop an efficient and accurate tire defect identification and classification technique to improve the efficiency and accuracy of tire inspection. In this paper, based on YOLO (You Only Look Once) v5 algorithm, tire defect recognition and classification are studied. Firstly, the data sets containing various types of tire defects were collected and sorted out, and the data sets were preprocessed. Then, by constructing, training and optimizing the YOLOv5 tire defect recognition model, the fast and accurate recognition of tire defects was realized. Finally, the performance of the model was evaluated through experiments and compared with the existing methods. The experimental results show that the tire defect recognition and classification method based on YOLOv5 proposed in this study has high accuracy. Compared with traditional methods, this method has a significant improvement in detection speed and accuracy.

A novel boundary defect recognition method based on adaptive regularization-improved artificial gorilla troops optimizer

A novel boundary defect recognition method based on adaptive regularization-improved artificial gorilla troops optimizer

Optimization of steel plate quality inspection driven by PscSE and SPPFELAN

AbstractBased on the improved YOLOv8n, a steel plate defect detection and recognition method is proposed to address the high labor costs and workload of traditional tasks. SPPFELAN processes inputs in parallel to enhance computational efficiency by executing multiple pooling operations simultaneously. The parallel feature fusion module PscSE, using a mixed‐dimension SE attention mechanism (scSE), captures global and channel‐related information better, improving characterization capability. The EIOU loss function addresses the ambiguous aspect ratio definition of CIOU loss, enhancing detection accuracy and accelerating convergence. Results show the YOLOv8n‐PscSE‐SPPFELAN model achieves 76.9% mAP@0.5 on the Northeastern University steel plate dataset, a 4.6% improvement over the original YOLOv8n, with a computation amount of 7.7 GFLOPs, reducing resource usage and greatly improving detection speed.

A Convolutional Neural Network-Based Defect Recognition Method for Power Insulator

As the scale of the power grid rapidly expands, its operation becomes increasingly complex, with higher demands on personnel proficiency, grid stability, equipment safety, and operational efficiency. In this study, a novel power insulator defect detection method based on convolutional neural networks (CNNs) is proposed. This method innovatively combines the feature extraction advantages of deep learning to build an efficient binary classification model capable of accurately detecting defects in power insulators in complex backgrounds. To avoid the impact of a small dataset on model performance, transfer learning was employed during model training to enhance the model’s generalization ability. A combination of Grid Search and Random Search was used for hyperparameter tuning, and the Early Stopping strategy was introduced to effectively prevent the model from overfitting to the training set, ensuring generalization performance on the validation set. Experimental results show that the proposed method achieves an average accuracy of 98.6%, a recall of 96.8%, and an F1 score of 97.7% on the test set. Compared to traditional Faster RCNN and PCA-SVM methods, the proposed CNN model significantly improves detection accuracy and computational efficiency in complex backgrounds, exhibiting superior recognition precision and model generalization ability for efficiently and accurately identifying defective insulators.

Research on Nondestructive Testing Technology for Drilling Risers Based on Magnetic Memory and Deep Learning

Drilling risers play a crucial role in deepwater oil and gas development, and any compromise in their integrity can severely hinder the progress of drilling operations. In light of this, efficient and accurate nondestructive testing of drilling risers is paramount. However, existing inspection equipment falls short in both efficiency and accuracy, posing challenges to the sustainability of deepwater oil and gas exploration and development. To effectively assess the damage conditions of deepwater drilling risers, this study developed an inspection robot based on metal magnetic memory and researched intelligent defect recognition methods using computer vision. The robot can perform in situ inspections on drilling risers and has been successfully deployed for field application on a deepwater drilling platform. The application results demonstrate that this detection robot offers significant advantages regarding high reliability and detection efficiency. Utilizing data collected on-site, we constructed a dataset containing 1100 images that cover five typical types of defects in drilling risers, including pitting, groove corrosion, and wear. Based on this dataset, we proposed and trained a novel image classification model, SK-ConvNeXt-KAN. By deeply optimizing the ConvNeXt convolutional network incorporating the introduced SK attention module and replacing traditional linear classification layers with the KAN module, this model significantly enhanced its feature extraction capabilities and efficiency in handling complex nonlinear problems. Experimental results show that this model achieved an accuracy rate of 95.4% in identifying defects in drilling risers, which is significantly better than traditional methods. This achievement has dramatically improved the efficiency and accuracy of deepwater drilling riser inspections, providing robust technical support for deepwater oil and gas exploration and development sustainability.

A Seismic Fault Recognition Method Based on Region Energy Algorithm

A Seismic Fault Recognition Method Based on Region Energy Algorithm

An interpretable multiscale lifting wavelet contrast network for planetary gearbox fault diagnosis with small samples

Previous deep learning-based fault diagnosis methods for planetary gearbox require numerous training samples and lack the necessary interpretability. Aiming at the problems of insufficient interpretability of deep models and the absence of feature mining capability with small samples, this study presents an interpretable multiscale lifting wavelet contrast network for planetary gearbox fault diagnosis. First, an interpretable multiscale lifting wavelet network is designed to achieve comprehensive and credible features mining from fault signals. Secondly, an interactive channel attention mechanism is constructed to choose feature maps with different frequency components. It can further confirm the interpretability of the lifting wavelet layer while improving the accuracy of the model. Finally, a time-frequency contrast loss is designed to simultaneously optimizing the distribution of time-frequency domain features. The effectiveness and interpretability of the model are analyzed through various visualization approaches. Experimental results on two planetary gearbox datasets indicate that our method is an interpretable and effective fault recognition method with small samples, and it holds a promising future for engineering applications.

Automated Defect Recognition Using Spline Interpolation

Existing infrastructure systems are aged and deteriorated rapidly, state agencies started searching for more advanced way to maintain their valuable assets to the acceptable level. One of them is the application of digital image processing. This problem proposes a digital image processing method to assess a steel bridge coating surface. The image processing method was developed based on B-Spline interpolation and can be used to recognizing the existence of bridge coating rust defects. An automated defect recognition method can make a decision whether a given digitized image contains defects by image comparison. Key Words:B-Spline interpolation, Digital Image Processing, Automated defect recognition method, Image comparision

Unveiling the potential of progressive training diffusion model for defect image generation and recognition in industrial processes

Industrial defect image generation is a crucial technique for augmenting defect image data, catering to fulfill the exigencies of training data necessary for defect recognition methods. In recent years, generative adversarial networks have seen widespread use in generating defect images. However, constrained by the scarcity of training data and the intricate variability in various defect categories, the existing methods are susceptible to issues such as training instability, a dearth of diversity, and suboptimal image quality. To overcome these challenges, this paper proposes a defect image generation framework based on a progressive training diffusion model (PTDM). Firstly, this study adopts a denoising diffusion model, supplanting traditional generative adversarial networks, to mitigate issues related to training instability and the dearth of diversity observed in generated images. Secondly, a novel progressive training strategy based on the self-designed image quality evaluator is developed to efficiently generate numerous defect images while maintaining quality. Finally, extensive experiments on a steel surface defect image dataset were conducted to validate the performance of the proposed framework in defect image generation and recognition tasks.

In-line imaging and recognition of flip chip fabrication defects by real-time photoacoustic remote sensing system

Microscopic defects in flip chips, originating from manufacturing, significantly affect performance and longevity. Post-fabrication sampling methods ensure product functionality but lack in-line defect monitoring to enhance chip yield and lifespan in real-time. This study introduces a photoacoustic remote sensing (PARS) system for in-line imaging and defect recognition during flip-chip fabrication. We first propose a real-time PARS imaging method based on continuous acquisition combined with parallel processing image reconstruction to achieve real-time imaging during the scanning of flip-chip samples, reducing reconstruction time from an average of approximately 1134 ms to 38 ms. Subsequently, we propose improved YOLOv7 with space-to-depth block (IYOLOv7-SPD), an enhanced deep learning defect recognition method, for accurate in-line recognition and localization of microscopic defects during the PARS real-time imaging process. The experimental results validate the viability of the proposed system for enhancing the lifespan and yield of flip-chip products in chip manufacturing facilities.

Partial discharge fault identification method for GIS equipment based on improved deep learning

AbstractAiming at the problems of large consumption of computational resources and insufficient data feature extraction in the current partial discharge fault identification process of GIS equipment, a partial discharge fault identification method of GIS equipment based on improved deep learning is proposed. Firstly, the audio information of GIS equipment is filtered by a simple power normalised cepstral coefficient (SPNCC). Secondly, the spatial correlation between audio data streams is obtained by a convolutional neural network, the temporal correlation of audio is obtained and the next time slice data stream is predicted by using bi‐directional long short‐term memory (BiLSTM) network, and the attention mechanism is designed to extract deeper data features. Finally, the partial discharge fault identification model of GIS equipment based on improved SPNCC‐CNN‐BiLSTM‐Multi‐att is established, which improves the accuracy of the partial discharge identification method of GIS equipment. Experiments show that when the number of iterations is 100, the accuracy, recall, and F1 value of the proposed GIS equipment partial discharge fault recognition method on the dataset are 0.876, 0.812, and 0.843, respectively.

Defect Recognition Method for Magnetic Leakage Detection in Oil and Gas Steel Pipes Based on Improved Neural Networks

The aging infrastructure of petroleum and natural gas pipelines poses a threat to national economies, necessitating precise defect detection for safety and efficiency. To enhance the accuracy of predicting pipeline defect sizes, this study introduces a magnetic leakage detection system, employing Backpropagation (BP) neural networks optimized with genetic algorithms. Traditional BP networks face challenges, including parameter determination and slow convergence, addressed through genetic algorithms' global search capabilities. Simulated data are generated using ANSYS software by using models of semi-circular defects in steel pipes, producing magnetic leakage signals of varying intensities. MATLAB was used to construct both standard BP and genetically optimized BP neural networks. Results show that the latter significantly reduces computational errors, demonstrating improved accuracy in defect dimension prediction. The approach contributes to overcoming non-uniqueness in the recognition process and the complex nonlinear relationship between magnetic signals and defect size parameters. The study offers a guided approach for selecting BP neural network parameters, enhancing practicality. Simulations validate the method's effectiveness, indicating low workload and high reliability. This research provides a meaningful advancement in the detection of defects in long-distance pipelines, impacting the safety and efficiency of petroleum and natural gas transportation.

Insulator Defect Detection Based on YOLOv8s-SwinT

Ensuring the safety of transmission lines necessitates effective insulator defect detection. Traditional methods often need more efficiency and accuracy, particularly for tiny defects. This paper proposes an innovative insulator defect recognition method leveraging YOLOv8s-SwinT. Combining Swin Transformer and Convolutional Neural Network (CNN) enhances the model’s understanding of multi-scale global semantic information through cross-layer interactions. The improved BiFPN structure in the neck achieves bidirectional cross-scale connections and weighted feature fusion during feature extraction. Additionally, a new small-target detection layer enhances the capability to detect tiny defects. The experimental results showcase outstanding performance, with precision, recall, and mAP reaching 95.6%, 95.3%, and 97.7%, respectively. This boosts detection efficiency and ensures high accuracy, providing robust support for real-time detection of tiny insulator defects.

A novel rotor-stator rub-impact fault and locations recognition method

Rub-impact fault is a kind of typical secondary fault encountered by large-sized rotation machinery. When it happens, the fault information contained is often weak, complicated and compound. This makes it difficult to correctly identify a rub-impact fault and affected part. Signals captured by sensors vary greatly in terms of energy, stability and complexity before and after a rub-impact fault occurs and when affected part is different. Graph indexes are sensitive to the variation of energy, stability and complexity in graph signal. Based on this, the paper has raised a method based on graph indexes to identify rub-impact fault and its locations and graph indexes are used to describe different running status of equipment. Firstly, to reduce the influence of noise components, vibration signals are given an auto-correlation analysis. Secondly, each auto-correlation function is converted to graph signals and five graph indexes of each graph signal are calculated. Thirdly, when running state of equipment is the same, an analysis is given to the consistency of graph indexes of signals from the same sensor, as well as the difference of graph indexes of each signal from different sensors. Fourthly, when running state of equipment is different, the difference of graph indexes of signals from the same sensor is analyzed. Fifthly, an analysis is given to the effectiveness and sensibility of graph indexes of signals from different sensors to running state. Finally, by the excellent consistency and difference shown by graph indexes, it is treated as a feature vector and according to two classical classification algorithms, rub-impact fault and location is identified. The result indicates that the mean identification rate of proposed method for rub-impact fault and locations can reach to 96%; graph indexes can serve as fault feature index to effectively represent a rub-impact fault and locations and has very excellent robustness.

An imbalanced small sample slab defect recognition method based on image generation

The surface quality of slabs has a profound impact on the subsequent performance and quality of steel. Accurate detection and classification of surface defects are crucial for improving steel quality. However, online visual inspection in the steel industry faces challenges such as sparse data, unclear features, sample imbalances, and impeding the application of deep learning in slab defect detection. To address these challenges, this paper introduces a novel approach utilizing the Slab Defect Generation (SDG) network to generate additional images by training on imbalanced small samples of slab defects, thereby constructing a comprehensive defect database. This methodology significantly enhances the efficiency and accuracy of deep learning in slab defect detection. Furthermore, an improved loss function is proposed specifically for the You Only Look Once version 5 (YOLOv5) model to augment the training of challenging samples. Experimental validation confirms the superiority of our method in terms of both image generation quality and defect-recognition compared to State-Of-The-Art (SOTA) models. The accuracy achieved by our approach is 98.6 %, outperforming the second-ranking model with an accuracy of 90.1 %.Index Terms—Data Enhancement, Deep Learning, Defect Recognition, Machine Vision, Neural Networks, Small sample learning.

Rolling bearing fault diagnosis based on the fusion of sparse filtering and discriminative domain adaptation method under multi-channel data-driven

Currently, the diagnostic performance of many deep learning algorithms may drop dramatically when the distribution of training data is significantly different from that of the test data. Moreover, the fault diagnosis approaches based on single-channel data may suffer problems such as large precision fluctuation, low reliability, and incomplete expression of fault features. To overcome the above deficiencies, a novel multi-channel data-driven fault recognition method based on the fusion of sparse filtering (SF) and discriminative domain adaptation (MSFDDA) is proposed in this article. Firstly, inspired by attention mechanisms and information fusion methods, a spectrum-based weighted multi-channel data fusion strategy is designed to fully utilize the data collected by sensors to obtain a more comprehensive representation of fault features. Then, the joint probability-based discriminative maximum mean discrepancy algorithm is introduced into the SF method to strengthen the capability of extracting the domain invariant features. Finally, two bearing datasets are employed to verify the validity of the MSFDDA method, which proved to be superior to other current domain adaptation methods.

An Image Classification Method of Unbalanced Ship Coating Defects Based on DCCVAE-ACWGAN-GP

Affected by the improper operation of the workers, environmental changes during drying and curing or the quality of the paint itself, diverse defects are produced during the process of ship painting. The traditional defect recognition method relies on expert knowledge or experience to detect defects, which is not conducive to ensuring the effectiveness of defect recognition. Therefore, this paper proposes an image generation and recognition model which is suitable for small samples. Based on a deep convolutional neural network (DCNN), the model combines a conditional variational autoencoder (DCCVAE) and auxiliary conditional Wasserstein GAN with gradient penalty (ACWGAN-GP) to gradually expand and generate various coating defect images for solving the overfitting problem due to unbalanced data. The DCNN model is trained based on newly generated image data and original image data so as to build a coating defect image classification model suitable for small samples, which is conducive to improving classification performance. The experimental results showed that our proposed model can achieve up to 92.54% accuracy, an F-score of 88.33%, and a G mean value of 91.93%. Compared with traditional data enhancement methods and classification algorithms, our proposed model can identify various defects in the ship painting process more accurately and consistently, which can provide effective theoretical and technical support for ship painting defect detection and has significant engineering research value and application prospects.

Inception meets Swin Transformer: A Novel Approach for Metal Defect Recognition

The detection of metal defects with high precision and efficiency is a significant challenge in modern industry. Existing machine learning methods for recognizing common metal surface defects heavily rely on expert knowledge for manual feature extraction. Conventional deep learning methods face challenges in capturing global feature information from defect images or defect detection signals.To address this issue, we proposed a metal defect recognition method based on an Inception-fused Swin Transformer model. The method combines the adaptive local feature extraction capability of the Inception structure with the advantage of the Swin Transformer in capturing global feature information from defect signals. Additionally, it utilizes the Channel-Coordinate Attention module (CoordAttention) to highlight important feature channels. Experimental results demonstrate the effectiveness of the proposed method on the Ultrasonic Defect Grayscale Image dataset (ULFSL-DET) and the publicly available Image-based Metal Defect dataset (NEU-CLS), achieving recognition accuracies of 98.1% and 99.8%, respectively. The method exhibits high effectiveness in recognizing metal defect signals in grayscale images, and it demonstrates strong generality for image-based metal defect recognition.

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

Accurate recognition of transmission line (TL) faults plays a vital role in protection systems, avoiding misoperations and false trips. Several studies in this area have revealed the limitations of existing algorithms, particularly when considering more complex electrical power systems (EPS), where some expected operations (capacitor and load switching, for example) can be misinterpreted as fault events. This work addresses the critical issue of fault recognition (FR) in TLs with a special focus on distinguishing faults from other types of disturbances. The primary objective of this study is to introduce an approach based on Convolutional Neural Networks (CNN) and Continuous Wavelet Transform (CWT) for FR in EPS. This method relies only on voltage signals acquired with a reasonable sampling frequency. The proposed method is enhanced with an Independent Component Analysis (ICA)-based preprocessing, making it robust and versatile in handling different types of disturbances, such as adjacent line faults, load switching and capacitor switching. The evaluation of the proposed method is done considering two different EPS, achieving an accuracy up to 99 %, showing the robustness of the method against different scenarios such as fault events and switching operations.

Research on an Online Monitoring Device for the Powder Laying Process of Laser Powder Bed Fusion.

Improving the quality of metal additive manufacturing parts requires online monitoring of the powder bed laying procedure during laser powder bed fusion production. In this article, a visual online monitoring tool for flaws in the powder laying process is examined, and machine vision technology is applied to LPBF manufacture. A multiscale improvement and model channel pruning optimization method based on convolutional neural networks is proposed, which makes up for the deficiencies of the defect recognition method of small-scale powder laying, reduces the redundant parameters of the model, and enhances the processing speed of the model under the premise of guaranteeing the accuracy of the model. Finally, we developed an LPBF manufacturing process laying powder defect recognition algorithm. Test experiments show the performance of the method: the minimum size of the detected defects is 0.54 mm, the accuracy rate of the feedback results is 98.63%, and the single-layer laying powder detection time is 3.516 s, which can realize the effective detection and control of common laying powder defects in the additive manufacturing process, avoids the breakage of the scraper, and ensures the safe operation of the LPBF equipment.