Fault Detection Method Research Articles

Enhanced Deep Stacked CapsNet Ensemble Gazelle Neural Network for multi‐level fabric defect classification

AbstractFabric detection in the materials industry plays a vital role in the global economy, making effective quality control measures essential to ensure product value and reduce manufacturing waste. With the rise of Industry 4.0, manufacturing companies have been striving to develop automated fabric defect detection systems to overcome the limitations of traditional manual inspection. However, because of challenges in creating highly effective fabric defect detection methods with strong noise resistance, conventional systems often struggle to capture intricate fabric details and accurately distinguish between defect types. To address these challenges, this research introduces an innovative approach called the Enhanced Deep Stacked capsNet Ensemble Gazelle Neural Network (EDSEGNN) for multi‐level local and global defect classification. By incorporating the Window‐aware Guided Image Filtering technique, image quality and resolution are enhanced, enabling the detection of fine fabric details. Additionally, the Wavelet Packet Transform aids in segmenting fabric defects by identifying small patterns through varying frequency waves. In the final stage, the EDSEGNN model performs local defect identification and multi‐level global defect classification, distinguishing between normal and defective patterns while categorising defect types like discoloration, stains, foreign objects, cuts, holes, thread issues and metal contamination. The proposed method achieves impressive results, with a peak accuracy of 99.8%, along with high recall (99.5%) and F1‐score (99%), compared with existing methods. The proposed approach offers a highly accurate and robust solution to the challenges faced by traditional fabric defect detection systems, representing a valuable advance in automated quality control for the materials industry.

An Efficient and Lightweight Surface Defect Detection Method for Micro-Motor Commutators in Complex Industrial Scenarios Based on the CLS-YOLO Network

Existing surface defect detection methods for micro-motor commutators suffer from low detection accuracy, poor real-time performance, and high false detection and missed detection rates for small targets. To address these issues, this paper proposes a high-performance and robust commutator surface defect detection model (CLS-YOLO), using YOLOv11-n as the baseline model. First, a lightweight Cross-Scale Feature Fusion Module (CCFM) is introduced to integrate features from different scales, enhancing the model’s adaptability to scale variations and ability to detect small objects. This approach reduces model parameters and improves detection speed without compromising detection accuracy. Second, a Large Separable Kernel Attention (LSKA) module is incorporated into the detection head to strengthen feature understanding and capture, reducing interference from complex surface patterns on the commutator and significantly improving adaptability to various target types. Finally, to address issues related to the center point location, aspect ratio, angle, and sample imbalance in bounding boxes, SIoU Loss replaces the CIoU Loss in the original network, overcoming limitations of the original loss function and enhancing overall detection performance. Model performance was evaluated and compared on a commutator surface defect detection dataset, with additional experiments designed to verify the model’s effectiveness and feasibility. Experimental results show that, compared to YOLOv11-n, the CLS-YOLO model achieves a 2.08% improvement in mAP@0.5. This demonstrates that CLS-YOLO can accurately detect large defect targets while maintaining accuracy for tiny defects. Additionally, CLS-YOLO outperforms most YOLO-series models, including YOLOv8-n and YOLOv10-n. The model’s parameter count is only 1.860 million, lower than YOLOv11-n, with a detection speed increase of 8.34%, making it suitable for deployment on resource-limited terminal devices in complex industrial scenarios.

Investigating the Potential of Latent Space for the Classification of Paint Defects

Defect detection methods have greatly assisted human operators in various fields, from textiles to surfaces and mechanical components, by facilitating decision-making processes and reducing visual fatigue. This area of research is widely recognized as a cross-industry concern, particularly in the manufacturing sector. Nevertheless, each specific application brings unique challenges that require tailored solutions. This paper presents a novel framework for leveraging latent space representations in defect detection tasks, focusing on improving explainability while maintaining accuracy. This work delves into how latent spaces can be utilized by integrating unsupervised and supervised analyses. We propose a hybrid methodology that not only identifies known defects but also provides a mechanism for detecting anomalies and dynamically adapting to new defect types. This dual approach supports human operators, reducing manual workload and enhancing interpretability.

MAFF-Net: PCB defect detection via feature-enhancement fusion

Abstract Defect detection of printed circuit board (PCB) is of significant practical importance to ensure quality control in the production process. However, traditional defect detection methods suffer from limitations such as low detection accuracy and poor generalization ability. To tackle these issues, we propose a novel deep learning-based defect detection method for bare PCBs through multi-attention adaptive feature-enhancement fusion (AFF). First, we utilize ResNext101 as the backbone for feature extractor and embed a normalization-based attention mechanism in a residual structure, aiming at improving the feature extraction capability of the network. Second, we introduce an AFF module, which leverages multi-scale feature extraction and feature fusion to facilitate information interaction and enhance the correlation of feature information between channels. Finally, we incorporate the coordinate attention mechanism into AFF to highlight the target area for boosting detection accuracy. The experimental results demonstrate the effectiveness of the proposed method, which achieves a mean accuracy precision (mAP) of 99.01 % on a publicly available PCB defect dataset.

Concept Drift Early Fault Detection in Wind Turbine Based on Distance Metric: A Systematic Literature Review

The Supervisory Control and Data Acquisition (SCADA) system in wind turbines generates substantial data that remains underutilized in terms of wind farm operation and maintenance (O&M). Numerous fault detection methods leveraging SCADA data are being extensively researched to reduce O&M costs. The detection methods are revolutionizing wind farm O&M strategies, shifting from scheduled passive detection to predictive active detection, with the potential to significantly reduce spare parts and labor costs. This paper presents a systematic review of wind turbine fault detection methods based on concept drift and distance metrics, employing the PRISMA methodology. The selected literature is analyzed from three perspectives: fault components, modeling methods, and data sources. Additionally, this review addresses research questions related to current trends, concept drift applications, and distance metric utilization in wind turbine fault detection. Lastly, it provides valuable insights for researchers and industry practitioners in wind energy engineering to explore future research and development in fault detection techniques for enhancing the reliability and efficiency of wind turbine operations.

Unsupervised defect detection for solar photovoltaic cells based on convolutional autoencoder

ABSTRACT Solar photovoltaic (PV) cells are inevitably subject to defects during the production process, affecting their power generation efficiency and life. Electroluminescence (EL) imaging is the mainstream non-destructive method for PV cell defect detection. Aiming at PV cell EL images, an unsupervised defect detection method was proposed. Specifically, an unsupervised convolutional autoencoder (CAE), the scale structure perception convolutional autoencoder (SSP_CAE), was constructed, whose Squeeze-and-Excitation Attention (SE Attention) and skip connections avoid the blurring of image structure information and the loss of pixel-level details in the encoding and decoding process. Furthermore, to balance the global and local information of the image, a scale perception loss function called SP_SSIM was proposed for model training. The defect segmentation was achieved by using Otsu thresholding method to binarize the obtained Mean Absolute Error (MSE) residual heat image in the testing stage of the model. Finally, the experiments were performed on the test dataset and the experimental results showed that the proposed SSP_CAE can effectively detect PV cell defects. The experimentally obtained defect detection performance metrics Precision, Recall, IoU, F1-score and AUROC values were 0.739, 0.886, 0.723, 0.764 and 0.841, respectively. Compared with other classical methods, the proposed SSP_CAE had a better comprehensive performance for defect detection.

Research on Textile Tiny Defective Targets Detection Method Based on YOLO-GCW

In the textile quality control system, textile defect detection occupies a central position. In order to solve the problems of numerous model parameters, time-consuming computation, limited precision, and accuracy of tiny features of textile defects in the defect detection process, this paper proposes a textile defect detection method based on the YOLO-GCW network model. First, in order to solve the problem of detection accuracy of tiny defective targets, the CBAM (Convolutional Block Attention Module) attention mechanism was incorporated to guide the model to focus more on the spatial localization information of the defects. Meanwhile, the WIoU (Weighted Intersection over Union) loss function was adopted to enhance model training as well as to improve the detection accuracy, which can also provide a more accurate measure of match between the model-predicted bounding box and the real target to improve the detection capability of tiny defect targets. Consequently, in view of the need for performance optimization and lightweight deployment, the Ghost convolution structure was adopted to replace the traditional convolution for compressing the model parameter scale and promoting the detection speed of complex texture features in textiles. Finally, numerous experiments proved the positive performance of the presented model and demonstrated its efficiency and effectiveness in various scenes.

Wind Turbine Blade Fault Detection Method Based on TROA-SVM

Wind turbines are predominantly situated in remote, high-altitude regions, where they face a myriad of harsh environmental conditions. Factors such as high humidity, strong gusts, lightning strikes, and heavy snowfall significantly increase the vulnerability of turbine blades to fatigue damage. This susceptibility poses serious risks to the normal operation and longevity of the turbines, necessitating effective monitoring and maintenance strategies. In response to these challenges, this paper proposes a novel fault detection method specifically designed for analyzing wind turbine blade noise signals. This method integrates the Tyrannosaurus Optimization Algorithm (TROA) with a support vector machine (SVM), aiming to enhance the accuracy and reliability of fault detection. The process begins with the careful preprocessing of raw noise signals collected from wind turbines during actual operational conditions. The method extracts vital features from three key perspectives: the time domain, frequency domain, and cepstral domain. By constructing a comprehensive feature matrix that encapsulates multi-dimensional characteristics, the approach ensures that all relevant information is captured. Rigorous analysis and feature selection are subsequently conducted to eliminate redundant data, thereby focusing on retaining the most significant features for classification. A TROA-SVM classification model is then developed to effectively identify the faults of the turbine blades. The performance of this method is validated through extensive experiments, which indicate that the recognition accuracy rate is 98.7%. This accuracy is higher than that of the traditional methods, such as SVM, K-Nearest Neighbors (KNN), and random forest, demonstrating the proposed method’s superiority and effectiveness.

Fault Detection of Permanent Magnet Synchronous Machines: An Overview

These days, as the application of permanent magnet synchronous machines (PMSMs) and drive systems becomes popular, the reliability issue of PMSMs gains more and more attention. To improve the reliability of PMSMs, fault detection is one of the practical techniques that enables the early interference and mitigation of the faults and subsequently reduces the impact of the faults. In this paper, the state-of-the-art fault detection methods of PMSMs are systematically reviewed. Three typical faults, i.e., the inter-turn short-circuit fault, the PM partial demagnetization fault, and the eccentricity fault, are included. The existing methods are firstly classified into signal-, model-, and data-based methods, while the focus of this paper is laid on the signal sources and the signatures utilized in these methods. Based on this perspective, this paper intends to provide a new insight into the inherent commonalities and differences among these detection methods and thus inspire further innovation. Furthermore, comparison is conducted between methods based on different signatures. Finally, some issues in the existing methods are discussed, and future work is highlighted.

Aluminum Reservoir Welding Surface Defect Detection Method Based on Three-Dimensional Vision

Welding is an important process in the production of aluminum reservoirs for motor vehicles. The welding quality affects product performance. However, rapid and accurate detection of weld surface defects remains a huge challenge in the field of industrial automation. To address this problem, we proposed a 3D vision-based aluminum reservoir welding surface defect detection method. First of all, a scanning system based on laser line scanning camera was constructed to acquire the point cloud data of weld seams on the aluminum reservoir surface. Next, a planar correction algorithm was used to adjust the slope of the contour line according to the slope of the contour line in order to minimize the effect of systematic disturbances when acquiring weld data. Then, the surface features of the weld, including curvature and normal vector direction, were extracted to extract holes, craters, and undercut defects. For better extraction of the defect, a double-aligned template matching method was used to ensure comprehensive extraction and measurement of defect areas. Finally, the detected defects were categorized according to their morphology. Experimental results show that the proposed method using 3D laser scanning data can detect and classify typical welding defects with an accuracy of more than 97.1%. Furthermore, different types of defects, including holes, undercuts, and craters, can also be accurately detected with precision 98.9%.

Control and islanding fault detection method of distributed photovoltaic EPG based on deep learning

ABSTRACT Distributed photovoltaic power generation system has many advantages, such as low production cost, rich raw material resources, environmental protection and pollution-free, long service life of power generation equipment, high energy efficiency conversion rate, etc., as an important supplement to centralized power supply mode, distributed photovoltaic power generation system has broad development space and great application value today when fuel resources are increasingly exhausted and the power load increases sharply during the peak period of power consumption. Because solar energy has great advantages, photovoltaic power generation technology is the most direct way to use solar energy in our country effectively. Solar energy has a good energy storage effect, wide distribution and no pollution. These advantages have caused photovoltaic power generation technology to get more attention, especially application of distributed photovoltaic power generation in small and medium-power roof photovoltaic systems. Due to the increasing shortage of traditional energy, the problem of environmental pollution needs to be improved, and public’s awareness of environmental protection needs to be awakened. Renewable energy, such as solar, wind, and bioenergy, has gradually developed into an alternative to traditional fossil energy. We can get better solutions and detection methods through in-depth learning and analysis of this method.

Power Insulator Defect Detection Method Based on Enhanced YOLOV7 for Aerial Inspection

Power Insulator Defect Detection Method Based on Enhanced YOLOV7 for Aerial Inspection

A Review: Methods of Fault Detection, Identification and Location in Conventional and Active AC Power Distribution System

A Review: Methods of Fault Detection, Identification and Location in Conventional and Active AC Power Distribution System

Deep learning-based defect detection in film-coated tablets using a convolutional neural network.

Film-coating is a critical step in pharmaceutical manufacturing. Traditional visual inspections for film-coated tablet defect assessment are subjective, inefficient, and labor-intensive. We propose a novel approach utilizing machine learning and image analysis to address these limitations. Here, defects of four types- chipping, breaking, color non-uniformity and speckling, were manually induced in red-orange film-coated placebo tablets. Utilizing a 3-D printed tray and a unique segmentation approach, images of good and defective tablets were collected. A convolutional neural network (CNN) was employed to quantitatively analyze the defects. The model was trained on a comprehensive dataset of 25,200 images of tablets, augmented through various transformations to improve robustness. The CNN's performance was evaluated using metrics such as accuracy, precision, recall, and F1-score. The multi-class classification model demonstrated an accuracy of 99.7% in detection of defects in film-coated tablets, clearly outperforming static rule-based method which had 45%, 45% and 70% error in detecting dimensions- major axis, minor axis, and surface area of the tablets, respectively. This work demonstrates a valuable tool for pharmaceutical manufacturers, providing a standardized, objective, and efficient method for defect detection in tablets and presents a promising solution for ensuring product quality and accelerating the development of new pharmaceutical products.

DCFE-YOLO: A novel fabric defect detection method.

Accurate detection of fabric defects is crucial for quality control in the textile industry. However, the task of fabric defect detection remains highly challenging due to the complex textures and diverse defect patterns. To address the issues of inaccurate localization and false positives caused by complex textures and varying defect sizes, this paper proposes an improved YOLOv8-based fabric defect detection method. First, Dynamic Snake Convolution is introduced into the backbone network to enhance sensitivity to elongated and subtle defects, improving the extraction of edge and texture details. Second, a Channel Priority Convolutional Attention mechanism is incorporated after the Spatial Pyramid Pooling layer to enable more precise defect localization by leveraging multi-scale structures and channel priors. Finally, the feature fusion network integrates Partial Convolution and Efficient Multi-scale Attention, optimizing the fusion of information across different feature levels and spatial scales, which enhances the richness and accuracy of feature representations while reducing computational complexity. Experimental results demonstrate a significant improvement in detection performance. Specifically, mAP@0.5 increased by 2.9%, precision improved by 3.5%, and mAP@0.5:0.95 rose by 2.3%, highlighting the model's superior capability in detecting complex defects. The project is available at https://github.com/lilian998/fabric.

Research on ultrasonic detection method for weld defects based on complex synergetic convolutional calculation

Research on ultrasonic detection method for weld defects based on complex synergetic convolutional calculation

Broken Rotor Bar Fault Detection in Induction Motor Based on Spectral Analysis

Three-phase induction motors are among the most frequently used motors in industrial areas due to their simple structure, low cost, power specifications, etc. Electric energy consumption from these motors accounts for 68% of the energy used by all motors. The faults that occur in these motors over time decrease motor efficiency and result in significant energy consumption. In this study, a new method based on spectral subtraction (SS) was suggested for determining broken rotor bar (BRB) faults in these motors. The traditional method of motor current signature analysis via Fast Fourier Transform (FFT) is hard to use to diagnose BRB faults because the sideband characteristics used as a fault indicator are also seen in the healthy state at low amplitude levels. In the proposed fault detection method, the FFT of both healthy case and faulty case current signals were calculated and then the SS signal is obtained by subtracting the FFT of the healthy motor from the faulty motor for each time step. In the residual SS signal, fault detection was performed by examining the amplitude levels of the harmonic component of the BRB fault. Experimental results indicate that BRB faults can be successfully detected in squirrel-cage rotor induction motors using the suggested method.

Power Converter Fault Detection Using MLCA–SpikingShuffleNet

With the widespread adoption of electric vehicles, the power converter, as a key component, plays a crucial role. Traditional fault detection methods often face challenges in real-time performance and computational efficiency, making it difficult to meet the demands of electric vehicle power converters for efficient and accurate fault diagnosis. To address this challenge, this paper proposes a novel fault detection model—SpikingShuffleNet. This paper first designs an efficient SpikingShuffle Unit that integrates grouped convolutions and channel shuffle techniques, effectively reducing the model’s computational complexity by optimizing feature extraction and channel interaction. Next, by appropriately stacking SpikingShuffle Units and refining the network architecture, a complete lightweight diagnostic network is constructed for real-time fault detection in electric vehicle power converters. Finally, the Mixed Local Channel Attention mechanism is introduced to address the potential limitations in feature representation caused by grouped convolutions, further enhancing fault detection accuracy and robustness by balancing local detail preservation and global feature integration. Experimental results show that SpikingShuffleNet exhibits excellent accuracy and robustness in the fault detection task for power converters, fulfilling the real-time fault diagnosis requirements for low-power embedded devices.

A Time–Frequency Composite Recurrence Plots-Based Series Arc Fault Detection Method for Photovoltaic Systems with Different Operating Conditions

A Time–Frequency Composite Recurrence Plots-Based Series Arc Fault Detection Method for Photovoltaic Systems with Different Operating Conditions

A model mismatch method for gas turbine fault detection

A model mismatch method for gas turbine fault detection