Fault Detection Method Research Articles

A New Method for Rapid Detection of Surface Defects on Complex Textured Tiles

A New Method for Rapid Detection of Surface Defects on Complex Textured Tiles

A 3-D Forward Model of Metal Magnetic Memory Method for Quantitative Defect Detection

A 3-D Forward Model of Metal Magnetic Memory Method for Quantitative Defect Detection

An automatic defect detection and localization method using imaging geometric features for sewer pipes

Accurate longitudinal localization of defects in sewer pipes is crucial for efficient maintenance and renewal. However, traditional closed-circuit television (CCTV)-based localization methods have been inefficient and imprecise, impeding real-time inspection performance. In this paper, we firstly point out that the inaccuracy of CCTV-based localization methods stems from the oversight of monocular imaging geometry, which leads to a deviation in sewer defect localization. Then, we propose an automated framework for sewer defect detection and longitudinal localization based on a deep-learning algorithm and monocular imaging geometry. Specifically, structural defects are qualitatively analyzed to explore their intrinsic correlation with the pipe wall. Then, the imaging geometry is leveraged to establish the projection relationship between the defects and the pipe joints. The longitudinal localization correction model for structural defects is then developed using the pipe diameter as the actual size. Our experiments show that this framework enhances the mean average precision (mAP) for multi-defects by 7.2 % and achieves a theoretical mean absolute error of 0.2 m and a practical mean absolute error of 0.28 m for defect localization, surpassing current research. Finally, with the generated detection results and localization records, the proposed framework can promote the efficiency of the sewer investigation and accelerate the development of intelligent sewer systems.

A High-Impedance Fault Detection Method for Active Distribution Networks Based on Time–Frequency–Space Domain Fusion Features and Hybrid Convolutional Neural Network

Traditional methods for detecting high-impedance faults (HIFs) in distribution networks primarily rely on constructing fault diagnosis models using one-dimensional zero-sequence current sequences. A single diagnostic model often limits the deep exploration of fault characteristics. To improve the accuracy of HIF detection, a new method for detecting HIFs in active distribution networks is proposed. First, by applying continuous wavelet transform (CWT) to the collected zero-sequence currents under various operating conditions, the time–frequency spectrum (TFS) is obtained. An optimized algorithm, modified empirical wavelet transform (MEWT), is then used to denoise the zero-sequence current signals, resulting in a series of intrinsic mode functions (IMFs). Secondly, the intrinsic mode functions (IMFs) are transformed into a two-dimensional spatial domain fused image using the symmetric dot pattern (SDP). Finally, the TFS and SDP images are synchronized as inputs to a hybrid convolutional neural network (Hybrid-CNN) to fully explore the system’s fault features. The Sigmoid function is utilized to achieve HIF detection, followed by simulation and experimental validation. The results indicate that the proposed method can effectively overcome the issues of traditional methods, achieving a detection accuracy of up to 98.85% across different scenarios, representing a 2–7% improvement over single models.

Research on X-ray nondestructive defect detection method of tire based on dynamic Snake Convolution YOLO model

Tire X-ray nondestructive testing before leaving the factory is crucial for driving safety. Given the complexity of tire structures and the diversity of defect types, traditional manual visual inspections and machine learning methods face significant challenges in terms of accuracy and efficiency. This study proposes an innovative tire X-ray image nondestructive testing technique based on the YOLOv5 model, incorporating several advanced technologies to enhance detection performance. Specifically, we introduce Dynamic Snake Convolution (DSConv), which adaptively focuses on slender and curved features within tires. Additionally, we have designed a C3 module based on DSConv, specifically targeting slender defects such as cord-overlap and cord-cracking. To improve the detection accuracy of small defects, we redesigned the neck network structure and introduced the Scale sequence feature fusion module (SSFF) and the Triple feature encoding module (TFE) to integrate multi-scale information from different network layers. Furthermore, we developed the Convolution Block Attention Module, integrated into the SSFF, which effectively reduces the interference of complex backgrounds and focuses on defect recognition. In the post-processing stage, we employed the Soft-NMS algorithm to optimize the confidence of candidate detection boxes, enhancing the accuracy of box selection. The experimental results show that compared to the YOLOv5 benchmark model, the algorithm proposed in this study achieved a 5.9 percentage point increase in mAP0.5 and a 5.7 percentage point increase in mAP0.5:0.95, demonstrating superior detection accuracy compared to current mainstream object detection algorithms and effectively completing the nondestructive testing task of tire defects.

Cross-domain fine grained strip steel defect detection method based on semi-supervised learning and Multi-head Self Attention coordination

The identification of steel strip defects plays a pivotal role in assessing steel quality and advancing production technology. However, the majority of intelligent defect recognition algorithms for steel strips, based on deep learning, primarily focus on supervised learning. These methods depend on a multitude of training samples, incurring additional manual labelling costs, and exhibit low recognition efficiency. In contrast to supervised learning, we integrate the fine-grained characteristics of strip defects. We propose a cross-domain, fine-grained strip defect detection method based on semi-supervised learning and Multi-head self-attention coordination, along with an improvement strategy, resulting in a novel network structure: Multi-head Self Attention and Semi-supervised collaborative detection network (MSD Net). This method initiates the cross-domain migration of defect samples through Cycle Generative Adversarial Networks (Cycle GAN), creating new semi-supervised training samples from source domain and target domain data to enhance data distribution diversity. The detection model is then constructed leveraging the advantages of Multi-head Self Attention (MSA) in augmenting the global receptive field of feature extraction. The proposed semi-supervised learning method employs a pseudo-label allocation strategy to guide the model in fully utilizing the distribution fitting of unlabeled samples. This allows the deep neural network to learn a more comprehensive multivariate data distribution within the training set, thereby enhancing the generalization ability of the semi-supervised model. Experimental results on the benchmark dataset for steel strip defect detection demonstrate that the cross-domain semi-supervised method achieves a test accuracy of 96.1 % on mAP@0.5, surpassing the supervised baseline model by 4.8 %. Our method also outperforms the baseline supervised model in the accuracy of small target recognition on PASCAL VOC 2007 datasets. Additionally, we have implemented a strip defect detection system based on edge computing for real-time deployment of the proposed algorithm. Testing in an actual industrial setting further validates the efficacy of our proposed method in practical applications. Our work encourages further exploration, the task of public datasets can be obtained at https://github.com/songzhiweiknight/NEU-DET-Datasets.git.

Fault detection method based on modified local gravity and its application in multimodal process

Fault detection method based on modified local gravity and its application in multimodal process

Fault Detection Algorithms in Medium-Voltage Direct-Current (MVDC) Grids

Developing reliable protection systems is critical for the advancement of medium-voltage direct-current (MVDC) grids. This paper highlights the significance of fault detection in MVDC grids, especially in ensuring the reliability and efficiency of renewable energy systems. This paper provides a comparative analysis of fault detection algorithms, including overcurrent, undervoltage, rate of change of current (ROCOC), rate of change of voltage (ROCOV), differential, and inductor voltage derivative methods. The performance of these algorithms is quantified by metrics such as the detection speed, accuracy, and sensitivity under diverse scenarios. The authors assess these algorithms within a multi-terminal MVDC grid designed for renewable hydrogen production, evaluating the detection speed across various fault types (bus and link faults) and conditions, including the variation in the fault location and resistance. The results reveal that the UV, ROCOC, ROCOV and LIVRD methods achieve detection speeds as high as 0.01 ms, outperforming other techniques under low-resistance fault conditions. By using uniform fault scenarios, we identify the most effective algorithms for rapid fault detection, aiming to enhance the protection strategies for MVDC grids. These findings underline critical performance differences between methods, guiding the design of tailored protection schemes that address specific fault challenges in renewable-powered grids. Additionally, the practical implications of these findings for designing resilient protection schemes in renewable-powered grids are discussed. Simulations are conducted using PSCAD/EMTDC V4.6 software, ensuring the consistency and accuracy of the performance comparison. The insights gained provide a concrete understanding of each algorithm’s trade-offs, enabling informed decisions when selecting optimal fault detection methods to ensure MVDC grid reliability.

YOLOv7-Rep: a re-parameterization method for surface defect detection in workpieces

YOLOv7-Rep: a re-parameterization method for surface defect detection in workpieces

Guaranteed Disturbance Compensation and Robust Fault Detection Based on Zonotopic Evaluation

ABSTRACTIn the context of model‐based fault detection, it is crucial to achieve strong robustness against disturbance and noise. However, the existing robust fault detection methods typically address disturbance and noise in a centralized manner to enhance robustness, which may cause some conservatism since the dynamic characteristics of disturbance and noise are considerably different. In addition, most of the existing model‐based fault detection method is implemented with constant thresholds, which may further introduce conservatism. In this context, this paper proposes a guaranteed disturbance compensation and robust fault detection method based on zonotopic evaluation for the discrete‐time systems subject to unknown but bounded disturbance and noise. To this end, a disturbance compensation controller is developed based on technology to obtain guaranteed control performance. Moreover, the control performances with or without disturbance compensation are analyzed based on zonotopes. By considering the disturbance dynamic characteristics, an extended fault detection observer (EFDO) is created to pursue robustness to disturbance, noise, and sensitivity to fault simultaneously. Meanwhile, a multi‐objective EFDO is devised by exploiting the index and index as the criteria within the finite‐frequency domain. Furthermore, the zonotopic residual evaluation is further deployed to generate the residual boundary, which helps to reduce the conservatism of fault detection. The superiority of the proposed method is theoretically analyzed. Simulation results also validate the effectiveness and superiority of the proposed method in disturbance compensation fault detection.

Fault detection observer design for T-S fuzzy systems based on membership function-dependent mixed H−/H∞ performance in the finite-frequency domain

This paper focuses on the design of a fault detection observer for T–S fuzzy systems with faults and unknown disturbances, based on a membership function-dependent [Formula: see text] performance index. Currently, common methods for disturbance suppression and fault detection are based on traditional [Formula: see text] performance criteria. Traditional [Formula: see text] performance indices impose the same constraints on the entire system, which does not align with the characteristic that T–S fuzzy systems do not operate continuously in all linear subsystems. Therefore, aiming to improve the performance of the linear subsystems where the system operates for long periods, this paper proposes a membership function-dependent [Formula: see text] performance index and designs a fault detection observer based on this performance index. In addition, considering that the frequency of actual system faults and disturbances is not across the entire frequency domain, the design of the fault detection observer based on the membership function-dependent [Formula: see text] performance index is achieved through the generalized Kalman-–Yakubovich-–Popov lemma in a finite-frequency domain.

Piecewise just-in-time data recovering and fault detection method for time-varying wind power generation process with missing data

Piecewise just-in-time data recovering and fault detection method for time-varying wind power generation process with missing data

HDFA-Net: A high-dimensional decoupled frequency attention network for steel surface defect detection

Accurately detecting surface defects is crucial for maintaining the quality of steel products. The existing methods often struggle with identifying small defects in complex scenes. To overcome this limitation, we propose a high-dimensional decoupled frequency attention network (HDFA-Net), which features a novel HDFA module. This module considers frequency domain feature information at both the channel and spatial levels and uniquely decouples feature representations into low-frequency components and high-frequency components, conveying global contextual information and highlighting local details, respectively. This innovative approach enables the network to apply distinct attention mechanisms to each frequency domain, significantly enhancing the ability to detect small defects. The HDFA-Net architecture comprises three main subnetworks: a backbone for feature extraction, a neck for multiscale feature interaction, and a head for precise defect localization. The experimental results demonstrate that HDFA-Net outperforms the state-of-the-art defect detection methods, highlighting the effectiveness of the HDFA module in improving the detection accuracy.

An weak surface defect inspection approach using efficient multi-scale attention and space-to-depth convolution network

In the field of precision manufacturing, machine vision technology is gradually replacing traditional manual inspection methods as a key technology to improve product quality. In precision manufacturing companies, weak defects on the product surface are unacceptable. However, existing defect detection methods rarely focus on the weak surface defect detection task. To address this challenge, we acquire and build a dataset called USB-DET, which contains weak defect samples. Then, we propose an innovative lightweight deep learning model, SDIA-net, which integrates SPD-Conv, Dysample technique, and attention mechanism-iRMA, to improve the recognition and localization of weak defects effectively. On the USB-DET dataset, SDIA-net achieves 55.1% mAP, which is 3.2% higher than the existing SOTA models. The computational efficiency is 205.1 FPS, which satisfies real-time demands. SDIA-net’s advantages make it well-suited for deployment in resource-limited precision manufacturing environments, providing an effective technical solution for product surface quality control with significant practical application value.

Near-Surface defect detection in ultrasonic testing using Domain-Knowledge-Informed self-supervised learning

Recently, significant research efforts have been made to enhance ultrasonic testing (UT) by employing artificial intelligence (AI). However, collecting an extensive amount of labeled data across various testing environments to train the AI model poses significant challenges. Moreover, conventional UT typically focuses on detecting deep-depth defects, which limits the effectiveness of such methods in detecting near-surface defects. To this end, this paper proposes a novel near-surface defect detection method for ultrasonic testing that can be employed without collecting labeled data. We propose a self-supervised anomaly detection model that incorporates domain knowledge. First, synthetic faulty samples are generated by fusing the measured UT signals with the back-wall UT reflection signals, to simulate real faulty features. Unlike the CutPaste method used for computer vision applications, this synthesis method adds the back-wall echo signal to random locations by incorporating the physical principles of the superposition of ultrasonic signals. Next, a de-anomaly network is devised to isolate subtle defect features within the measured UT signals. The presence of defects was determined using the three-sigma rule of the mean absolute value of the residual output. The defect depth is determined by a time-of-flight calculation from the residual output. The effectiveness of the proposed method was evaluated through the UT of aluminum blocks with near-surface defects of varying depths under different surface conditions. Both qualitative and quantitative comparison studies demonstrated that the proposed method outperformed existing methods in detecting the presence and depth of near-surface defects.

A Brief Analysis of the Progress and Trends in Software Defect Prediction Methods

Software defect detection is particularly important for modern society, as it is a crucial step in ensuring the quality and reliability of software systems. With the emergence of artificial intelligence (AI), research in software defect detection has evolved from traditional methods to more complex approaches that utilize deep learning and large language models (LLMs). The advent of LLMs has fundamentally changed the paradigm of software development and defect detection, bringing new challenges and confusion to the field of software defect prediction research. To address these issues, we compare software defect detection methods based on traditional techniques, deep learning approaches, and LLMs through a literature review. We analyze the changes brought about by the introduction of LLMs to software development and propose new insights. Additionally, we examine the progress and trends in software defect prediction to provide inspiration for subsequent research.

A method for signal components identification in acoustic signal with non-Gaussian background noise using clustering of data in time-frequency domain

This paper presents a novel method for fault detection in vibration/acoustic signals contaminated with non-Gaussian noise, specifically addressing the challenge of random impulsive and wideband disturbances in industrial measurements. While damage detection in Gaussian noise environments is well understood, high-amplitude non-cyclic impulsive disturbances arising from random aspects of industrial processes, such as non-uniform operations and random impacts, pose significant analytical challenges.The proposed method analyzes the distribution densities of spectral vectors derived from spectrograms. It considers a simple additive model consisting of the signal of interest (SOI) and Gaussian and non-Gaussian noise. Using the density-based spatial clustering algorithm (DBSCAN), the method isolates distinct classes of spectral vectors from the spectrogram, effectively separating different signal behaviors and extracting fault-related information. The effectiveness of the proposed method was validated using an envelope spectrum-based indicator (ENVSI) and successfully demonstrated on real signals from an industrial machine with a faulty bearing.

Method for rail surface defect detection based on neural network architecture search

Abstract This study addresses the inherent limitations of implementing neural network architecture search algorithms for rail surface defect detection, including low search efficiency and the oversight of edge features on the rail surface. A sophisticated multi-level neural network architecture search framework is proposed that integrates and emphasizes rail surface edge features. The framework utilizes the Z-Score normalization method to quantify the edge concern of rail surface defect samples, combined with an Edge-Loss function to enhance edge feature recognition capabilities. Furthermore, acknowledging the sensitivity of defect features to spatial resolution changes, a multi-level neural network architecture search space is meticulously designed. In the cell-level search space, a method combining partial channel sampling with operation pruning is employed to enhance model search efficiency and regularization. In the network-level search space, optimal paths for resolution change are established, allowing for the screening and aggregation of defect features at various levels to facilitate the adaptive extraction of multi-scale edge defect features. Experimental outcomes indicate that this method significantly reduces computational resource usage by approximately 75% and increases mIOU by 2.6% relative to traditional architecture search methods. Moreover, it demonstrates robust capability in accurately recognizing defective edges on rail surfaces, thereby substantiating the method’s effectiveness.

Detection of Defects in Warp Knitted Fabrics Based on Local Feature Scale Adaptive Comparison

In order to improve the accuracy and detection effect of fabric defect detection, a fabric defect detection method based on local similarity comparison is proposed in this paper. This method first takes each pixel in the image as the central pixel, selects a specific window as the region size, and then uses the similarity between the central region and the surrounding neighborhood to find the neighborhood most similar to the central region to complete the estimation of the central pixel. Finally, the target image is obtained by the principle of background difference, so as to detect fabric defects. The results show that this method is superior to the traditional detection method, which can not only detect the defect image under the complex background, but also have good detection results for the fabric defect image under the influence of different organization and lighting factors. The detection accuracy rate under factory conditions can reach 98.45%, which has a high applicability and detection rate, and also demonstrates certain anti-interference performance.

Detection of Defects in Polyethylene and Polyamide Flat Panels Using Airborne Ultrasound-Traditional and Machine Learning Approach

This paper presents the use of noncontact ultrasound for the nondestructive detection of defects in two plastic plates made of polyamide (PA6) and polyethylene (PE). The aim of the study was to: (1) assess the presence of defects as well as their size, type, and orientation based on the amplitudes of Lamb ultrasonic waves measured in plates made of polyamide (PA6) and polyethylene (PE) due to their homogeneous internal structure, which mainly determined the selection of such model materials for testing; and (2) verify the possibilities of building automatic quality control and defect detection systems based on ML based on the results of the above-mentioned studies within the Industry 4.0/5.0 paradigm. Tests were conducted on plates with generated synthetic defects resembling defects found in real materials such as delamination and cracking at the edge of the plate and a crack (discontinuity) in the center of the plate. Defect sizes ranged from 1 mm to 15 mm. Probes at 30 kHz were used to excite Lamb waves in the slab material. This method is sensitive to the slightest changes in material integrity. A significant decrease in signal amplitude was observed, even for defects of a few millimeters in length. In addition to traditional methods, machine learning (ML) was used for the analysis, allowing an initial assessment of the method’s potential for building cyber-physical systems and digital twins. By training ML models on ultrasonic data, algorithms can distinguish subtle differences between signals reflected from normal and defective areas of the material. Defect types such as voids, cracks, or weak bonds often produce distinct acoustic signatures, which ML models can learn to recognize with high accuracy. Using techniques like feature extraction, ML can process these high-dimensional ultrasonic datasets, identifying patterns that human inspectors might overlook. Furthermore, ML models are adaptable, allowing the same trained algorithms to work on various material batches or panel types with minimal retraining. This combination of automation and precision significantly enhances the reliability and efficiency of quality control in industrial manufacturing settings. The achieved accuracy results, 0.9431 in classification and 0.9721 in prediction, are comparable to or better than the AI-based quality control results in other noninvasive methods of flat surface defect detection, and in the presented ultrasonic method, they are the first described in this way. This approach demonstrates the novelty and contribution of artificial intelligence (AI) methods and tools, significantly extending and automating existing applications of traditional methods. The susceptibility to augmentation by AI/ML may represent an important new property of traditional methods crucial to assessing their suitability for future Industry 4.0/5.0 applications.