Effective Defect Detection Research Articles

Advanced Defect Detection on Curved Aeronautical Surfaces Through Infrared Imaging and Deep Learning

Detecting defects on aerospace surfaces is critical to ensure safety and maintain the integrity of aircraft structures. Traditional methods often need more precision and efficiency for effective defect detection. This paper proposes an innovative approach that leverages deep learning and infrared imaging techniques to detect defects with high precision. The core contribution of our work lies in accurately detecting the size and depth of defects. Our method involves segmenting the size of the defect and calculating its centre to determine its depth. We achieve a more comprehensive and precise assessment of defects by integrating deep learning with infrared imaging based on the U-net model for segmentation and the CNN model for classification. The proposed model was rigorously tested on both a simulation dataset and an experimental dataset, demonstrating its robustness and effectiveness in accurately identifying and assessing defects on aerospace surfaces. The results indicate significant improvements in detection accuracy and computational efficiency, showing advancements over state-of-the-art methods and paving the way for enhanced maintenance protocols in the aerospace industry.

Pseudo- World: The Role of Augmented Reality and AI in Construction and Retrofitting

The construction industry is undergoing a revolution with the integration of augmented reality (AR) and artificial intelligence (AI). These technologies are transforming the way construction projects are planned and executed, leading to increased productivity, enhanced design visualization, and more informed decision-making. Our research focuses on developing Pseudo World, a platform that converts 2D house plans into interactive 3D models, allowing for real-time exploration and collaboration through AR. By combining machine learning techniques, pathfinding algorithms, and graph-based models, our approach optimizes spatial planning and retrofitting decisions. This innovative solution enables immersive visualization, enables more effective defect detection and management, and streamlines construction workflows, thereby positioning AR as a driver of innovation in construction planning.

RELEVANCE OF RESEARCH ON INNOVATIVE SOLUTIONS FOR DETECTING DEFECTS IN FLAT ROOFS

Problem Statement. In Ukraine, the most numerous buildings are those constructed between 1960–1990. As of today, half of them require major repairs. According to current Ukrainian regulatory documents, comprehensive inspections of the entire building should be conducted every 10 years, and at least once every 5 years for buildings or separate elements of buildings that operate under adverse conditions, including roofs. During the full-scale war on the territory of Ukraine, the safety and health of workers are of paramount importance. Especially during air raids, when being on the roof is most dangerous—posing a threat to the life and health of specialists inspecting the roof [1]. The issue of preserving life and health is particularly significant during the Covid-19 pandemic. For example, the International Code Council, the main institution for standardizing building systems in the USA, issued recommendations during the Covid-19 pandemic regarding remote inspection of building structures. The authorities of Los Angeles at the municipal level proposed using this method for building structure inspections [2]. Objective. The article aims to analyze the needs and challenges associated with roof inspections in Ukraine, particularly in the Dnipropetrovsk region, in the context of the ongoing full-scale war. It is necessary to determine the overall volume of roofs requiring inspection, the main defects that arise, and the risks that may occur due to the lack of timely inspections. Additionally, the article needs to outline the main stages of the roof inspection process, identify the necessary knowledge and skills required by qualified specialists for comprehensive roof inspections. Conclusions. Analyzing the total number of buildings and the norms determining the frequency of roof inspections, considering all preparation stages and the skills needed by inspection specialists, as well as the conditions of the full-scale war in which our country finds itself today, it can be concluded that the preparation of such specialists is resource-intensive and requires significant investments of time and effort. Unfortunately, according to IMF data, the population of Ukraine is showing a tendency to decrease. According to statistics, in 2022 the population decreased to 35 million, and by 2023 – to 33.2 million. This leads to a decline in the number of sufficiently qualified specialists who will be able to comprehensively engage in roof inspections. The general review of aspects showed the need to introduce innovative solutions and new approaches in the field of comprehensive roof inspections. This particularly concerns the effective detection of roof defects, the preparation of comprehensive reports, and estimates with maximum savings of time, financial, and human resources.

Development of ultrasonic phased array technique for inspection of fir-tree type turbine blade root and disc-rim in nuclear power plant

ABSTRACT Steam turbines are crucial in both nuclear and thermal power plants, serving a key role in electricity generation. However, the operational lifespan of these turbines is often limited by failures in the turbine blade roots and disc rims due to fatigue, stress corrosion cracking and creep. Usage of reliable non-destructive technique during in-service inspection of turbine assembly is very important for decision making and safe operation of power plant. The conventional ultrasonic technique which is being employed currently suffers from access limitation, high inspection time and false calls during defect detection due to complex geometry of blade roots and disc rims. To address these issues, an advanced ultrasonic inspection technique using phased array technology was developed, specifically tailored for fir-tree type blade roots and disc rims. Ultrasonic Simulation studies were performed to determine the optimal parameters for phased array probes, ensuring the effective detection and precise sizing of crack-like defects. This manuscript presents the findings from these simulations, along with experimental results from phased array inspections of turbine blade root and disc rim mockup of turbine assembly in nuclear power plant.

FDADNet: Detection of Surface Defects in Wood-Based Panels Based on Frequency Domain Transformation and Adaptive Dynamic Downsampling

The detection of surface defects on wood-based panels plays a crucial role in product quality control. However, due to the complex background and low contrast of defects in wood-based panel images, features extracted by traditional deep learning methods based on spatial domain processing often contain noise and blurred boundaries, which severely affects detection performance. To address these issues, we have proposed a wood-based panel surface defect detection method based on frequency domain transformation and adaptive dynamic downsampling (FDADNet). Specifically, we designed a Multi-axis Frequency Domain Weighted Information Representation Module (MFDW), which effectively decoupled the indistinguishable low-contrast defects from the background in the transform domain. Gaussian filtering was then employed to eliminate noise and blur between the defects and the background. Additionally, to tackle the issue of scale differences in defects that led to difficulties in accurate capture, we designed an Adaptive Dynamic Convolution (ADConv) module for downsampling. This method flexibly compressed and enhanced features, effectively improving the differentiation of the features of objects of varying scales in the transform space, and ultimately achieved effective defect detection. To compensate for the lack of data, we constructed a dataset of wood-based panel surface defects, WBP-DET. The experimental results showed that the proposed FDADNet effectively improved the detection performance of wood-based panel surface defects in complex scenarios, achieving a solid balance between efficiency and accuracy.

DCW-YOLO: An Improved Method for Surface Damage Detection of Wind Turbine Blades

Wind turbine blades (WTBs) are prone to damage from their working environment, including surface peeling and cracks. Early and effective detection of surface defects on WTBs can avoid complex and costly repairs and serious safety hazards. Traditional object detection methods have disadvantages of insufficient detection capabilities, extended model inference times, low recognition accuracy for small objects, and elongated strip defects within WTB datasets. In light of these challenges, a novel model named DCW-YOLO for surface damage detection of WTBs is proposed in this research, which leverages image data collected by unmanned aerial vehicles (UAVs) and the YOLOv8 algorithm for image analysis. Firstly, Dynamic Separable Convolution (DSConv) is introduced into the C2f module of YOLOv8, allowing the model to more effectively focus on the geometric structural details associated with damage on WTBs. Secondly, the upsampling method is replaced with the content-aware reassembly of features (CARAFE), which significantly minimizes the degradation of image characteristics throughout the upsampling process and boosts the network’s ability to extract features. Finally, the loss function is substituted with the WIoU (Wise-IoU) strategy. This strategy allows for a more accurate regression of the target bounding boxes and helps to improve the reliability in the localization of WTBs damages, especially for low-quality examples. This model demonstrates a notable superiority in surface damage detection of WTBs compared to the original YOLOv8n and has achieved a substantial improvement in the mAP@0.5 metric, rising from 91.4% to 93.8%. Furthermore, in the more rigorous mAP@0.5–0.95 metric, it has also seen an increase from 68.9% to 71.2%.

Yolo Based Defects Detection Algorithm for EL in PV Modules with Focal and Efficient IoU Loss

Considering the defect detection issues in electroluminescence (EL) of photovoltaic (PV) cell systems, lots of factors result in performance degradation, including defect diversity, data imbalance, scale difference, etc. Focal-EIoU loss, an effective defect detection solution for EL, is proposed based on the improved YOLOv5. Firstly, by analyzing the detection background and scale characteristics of EL defects, a binary classification is carried out in the system. Subsequently, a cascade detection network based on YOLOv5 is designed to further extract features from the binary-classified defects. The defect localization and classification are achieved in this way. To address the problem of imbalanced defect samples, a loss function is designed based on EIoU and Focal-F1 Loss. Experimental results are illustrated to show the effectiveness. Compared with the existing CNN-based deep learning approaches, the proposed focal loss calculation-based method can effectively improve the performance of handling sample imbalance. Moreover, in the detection of 12 types of defects, the Yolov5 algorithms can always obtain higher MAP (mean average precision) even with different parameter levels (Yolov5m: 0.791 vs. 0.857, Yolov5l: 0.798 vs. 0.862, Yolov5x: 0.802 vs. 0.867, Yolov5s: 0.793 vs. 0.865).

PCB Defect Detection Based on Improved Deep Learning Model

Printed circuit boards (PCBs) play a critical role in electronic products. Ensuring these products’ long-term reliability and consistent performance requires effective PCB defect detection. Although existing deep learning models for PCB defect detection are not highly accurate, they often neglect capability considerations. This paper introduces a precise, fast, and lightweight defect detection model, CCG-YOLO, based on an enhanced YOLOv5 model to address this issue. The enhancements in CCG-YOLO can be summarized as follows: (1) Improved Backbone network: The feature extraction ability of the Backbone network is enhanced by introducing a C3HB module, which fosters spatial interaction capabilities. (2) Lightweight feature fusion network: A lightweight convolution structure called Ghost-Shuffle Convolution is incorporated in the feature fusion network, remarkably reducing model parameters while maintaining performance. (3) Efficient residual networking: To enhance model performance further, a CNeB module is introduced based on the ConvNeXt network, which replaces the C3 module in the Neck. CNeB improves model detection accuracy and reduces the number of model parameters. The combination of these enhancements results in impressive performance. CCG-YOLO achieves mean average precision (mAP@0.5) of 99.5% and 88.75% in mAP@0.5:0.95 on the TDD-Net public dataset. Compared with the original YOLOv5s algorithm, CCG-YOLO offers a 4.24% improvement in mAP@0.5:0.95, a 1[Formula: see text]MB reduction in model size, a 0.472[Formula: see text]M decrease in the number of parameters, a 0.6G floating point operation reduction in computational complexity, and a 120 frames per second real-time inference speed. These experimental results underscore that the proposed model excels in accuracy and speed and has a compact size for PCB defect detection. Moreover, CCG-YOLO is easily deployable on low-end devices, making it well-suited for meeting the real-time requirements of industrial defect detection.

Extraction and empirical evaluation of GUI-level invariants as GUI Oracles in mobile app testing

ContextMobile apps (software) are used in almost all aspects of daily life by billions of people. Given the widespread use of mobile apps in various domains, the demand for systematic testing of their Graphical User Interfaces (GUI) is crucial. Despite the significant advances in automated mobile app testing over the last decade, certain challenges remain, most notably the app-specific GUI test-oracle problem, which can significantly hinder the effective detection of defects in mobile apps. In this study, we introduce the use of GUI-level invariants, referred to as GUI invariants, as app-specific GUI oracles in GUI test cases to address this challenge. MethodsWe propose a semi-automatic solution to extract GUI invariants and use them as app-specific GUI oracles in test cases. We use the mutation testing technique to evaluate the (fault detection) effectiveness of the GUI oracles used. In addition, we evaluate their quality aspects, namely correctness, understandability, and compatibility, from the perspective of human experts using a questionnaire survey. ResultsThe empirical results show that the GUI oracles used are effective and helpful, as they improved the fault-detection effectiveness of the empirical test suites ranging from 18% to 32%. These results also highlight the efficacy of GUI oracles used in identifying various defects, including crashing and non-crashing functional issues, and surpassing the performance of existing tools in fault-detection rates. Additionally, the questionnaire survey outcomes indicate that the GUI oracles used are correct, understandable, and compatible. ConclusionsBased on the empirical results, we can conclude that using GUI invariants as GUI oracles can be useful and effective in mobile app testing.

Stochastic Defect Localization for Cooperative Additive Manufacturing Using Gaussian Mixture Maps

Abstract Robotic additive manufacturing (RAM) offers significant improvements in maximum build volume compared to conventional bounded designs (e.g., gantry) by leveraging high degrees-of-freedom machines and multi-robot cooperation. However, cooperative RAM suffers from the same defect generation challenges as conventional systems, necessitating improvements in the detection and prevention of flaws within fabricated components. Quality assurance can be further bolstered through the integration of AM models, which utilize sensor feedback to localize defects, vastly reducing false positives. This research explores defect localization through a novel dynamic defect model created from simulated sensing data. In particular, two cooperative robots are simulated to estimate defect parameters, while observing the workspace and accurately classifying different regions of the part, generating a Gaussian mixture map that identifies and assigns appropriate actions based on defect types and characteristics. The experimental result shows that the implementation of the dynamic defect model and selective reevaluation achieved an effective defect detection accuracy of 99.9%, an improvement of 9.9% without localization. The proposed framework holds potential for application in domains that utilize high degrees-of-freedom machines and collaborative agents, offering scalability, improved fabrication speeds, and enhanced mechanical properties.

Edge detection in x-ray images of drill mast welds based on an improved Scharr operator

Rotary drilling rigs are extensively used in foundational construction, with main components including the mast, drill rods, drill bits, power head, and cockpit. The mast, a critical component, must be of high quality to ensure operational reliability. To ensure the reliability of the mast during operation, it is necessary to detect defects in the most stress-prone areas. Based on finite element analysis and practical engineering experience, the welds on the large circular disc of the drill mast are identified as the most vulnerable to damage. Accordingly, this paper prepared test specimens specifically from these weld locations and conducted X-ray inspections, obtaining images for analysis. Given the inevitable presence of noise due to objective conditions, the images first underwent median filtering. For effective subsequent defect detection, edge detection was performed on the images. Among various edge detection operators, the Scharr operator was found to be highly effective. To further enhance the edge detection performance, this paper introduces an improved Scharr edge detection algorithm that incorporates dynamic thresholds and Markov Random Field (MRF) techniques. The enhanced algorithm was evaluated using signal-to-noise ratio and edge localization accuracy as metrics, and it was found to significantly improve performance.

Design of Staggered Halbach EMAT to Generate SH Guided Wave in Pipe Structures

This research investigates the application of Staggered Electromagnetic Acoustic Transducer (EMAT), mainly focusing on the beam steering capabilities of Shear Horizontal (SH) Guided Waves in pipe structures. As a specific case of EMAT, Staggered EMAT introduces a lateral movement in the magnet rows so that the wave propagation occurs at an angle. A three-dimensional model of double row Staggered Halbach EMAT is developed and a finite element analysis is carried out in an aluminium pipe with high radius to thickness ratio. To obtain better signal-to-noise ratio (SNR), the size of the magnets and the number of magnets in a row are optimized by studying multiple cases. For all the configurations, the in-plane surface displacement is studied keeping the wavelength of the transducer constant. The corresponding frequency is derived from the dispersion curve for SH0 wave mode. The results shows that there is significant increase in the amplitude of the in-plane surface displacement with the increase in magnet height and the number of magnets in a row, ultimately leading to the signal with higher amplitude and better SNR. The study then analyses Staggered Halbach EMATs where the second row of magnets is displaced by the maximum value of half of the wavelength. The interference between the waves generated from the two magnet rows resulted in the directivity change of the guided wave, thereby achieving the steering of the SH wave by the maximum value of 27°. The finding of this study shows the enhanced beam steering capabilities of Staggered EMATs, particularly in the field of pipeline monitoring and can lead to more precise and effective detection of structural defects. Keywords: Staggered Halbach EMAT, Beam Steering, SH Guided Wave, Pipeline Inspection

A Systematic Review of Lithium Battery Defect Detection Techniques and Technologies

This systematic review aims to explore and synthesize the existing literature on defect detection methods in lithium batteries. With the increasing demand for reliable and efficient lithium batteries in various applications, ensuring their safety and performance through effective defect detection is critical. This review categorizes and evaluates different detection techniques, including electrochemical, non-destructive testing (NDT), electrical, acoustic emission, optical methods, and machine learning. The primary objective is to provide a comprehensive understanding of the current state of defect detection technologies, assess their effectiveness, and identify key challenges and future research directions. The review covers various defect types, including manufacturing, operational, and environmental defects, and discusses the methodologies used for defect detection, including their sensitivity, accuracy, speed, cost, and practicality. Additionally, the review highlights real-world applications, case studies, and the integration challenges of these technologies with Battery Management Systems (BMS). By examining these aspects, the review aims to offer valuable insights for researchers, manufacturers, and practitioners in the field of lithium battery technology. Key findings suggest that while significant advancements have been made, there remain substantial challenges, particularly in the areas of data acquisition, standardization, and integration with existing battery management systems. Future research should focus on improving the robustness, scalability, and cost-effectiveness of defect detection methods, as well as developing comprehensive regulatory frameworks to ensure the safe deployment of lithium batteries.

Detection of Train Wheelset Tread Defects with Small Samples Based on Local Inference Constraint Network

Due to the long-term service through wheel-rail rolling contact, the train wheelset tread will inevitably suffer from different types of defects, such as wear, cracks, and scratches. The effective detection of wheelset tread defects can provide critical support for the operation and maintenance of trains. In this paper, a new method based on a local inference constraint network is proposed to detect wheelset tread defects, and the main purpose is to address the issue of insufficient feature spaces caused by small samples. First, a generative adversarial network is applied to generate diverse samples with semantic consistency. An attention mechanism module is introduced into the feature extraction network to increase the importance of defect features. Then, the residual spine network for local input decisions is constructed to establish an association between sample features and defect types. Furthermore, the network’s activation function is improved to obtain higher learning speed and accuracy with fewer parameters. Finally, the validity and feasibility of the proposed method are verified using experimental data.

CNN-based defect detection and classification of PV cells by infrared thermography method

ABSTRACT As a crucial component of the photovoltaic (PV) power generation system, effective defect detection of PV cells can help to ensure the power generation efficiency and the system safety. The photo-thermal-radiation infrared thermography experimental system has been built, and the infrared images of normal and defective PV cells were collected by an IR camera. An effective convolutional neural network (CNN) based model with the residual architecture is designed here to detect and classify the defects. An offline date augmentation method is performed to overcome the insufficient image dataset in the step of dataset establishment, so as to improve the defects classification capability of the designed CNN model. The defects classification accuracy of the proposed model is obtained as 96.96% with 3-class. In order to verify the defect classification ability of the designed CNN model, other four models were adopted for comparative analysis. The results indicate that the proposed CNN model has advantages in defect classification of PV cells. The completed work can provide meaningful exploration in the industrial application of defect detection of PV cells.

A proposed hybrid model of ANN and KNN for solar cell defects detection and temperature prediction using fuzzy image segmentation

This paper presents a novel hybrid model employing Artificial Neural Networks (ANN) and Mathematical Morphology (MM) for the effective detection of defects in solar cells. Focusing on issues such as broken corners and black edges caused by environmental factors like broken glass cover, dust, and temperature variations. This study utilizes a hybrid model of ANN and K-Nearest Neighbor (KNN) for temperature prediction. This hybrid approach leverages the strengths of both models, potentially opening up new avenues for improved accuracy in temperature forecasting, which is critical for solar energy applications. The significance lies in the interconnectedness of temperature fluctuations and solar cell efficiency, leading to defects. The proposed model aims to predict temperatures accurately, providing insights into potential solar cell efficiency problems. Subsequently, this work studies the transitions to defect detection using Fuzzy C-Means (FCM) clustering and MM techniques. The hybrid model demonstrates accurate temperature prediction with Mean Absolute Percentage Error (MAPE) values of 0.92 %, 0.72 %, and 1.3 % for average, maximum, and minimum temperatures, respectively. The defect detection process yields a detection accuracy (CR) of 96 % and sensitivity of detection (SD) of 89 %. This work is validated compared to the literature work done and by using K-fold cross validation technique. The proposed work emphasizes the improvement in defect detection accuracy and the overall quality enhancement of solar cells.

Fusing spectral and spatial features of hyperspectral reflectance imagery for differentiating between normal and defective blueberries

Effective defect detection of blueberries is important to ensuring supplies of high-quality products to the fresh market. In this study, hyperspectral reflectance imaging with machine learning was evaluated for discriminating between defective and normal blueberries. Fresh blueberries hand-harvested were scanned in the wavelength range of 400–1000 nm. An image analysis pipeline was developed to segment individual blueberries and extract mean spectra and spatial features. Defective blueberries were found to have lower near-infrared reflectance than sound samples, and spectral features produced a better separation between defective and sound samples than the spatial features in the scattering plots of their first two principal components. Nine types of machine learning models were built for classifying defective and sound samples using the spectral and spatial features separately as well as their concatenation. The regularized linear discriminant analysis (RLDA) model trained on the spectral features achieved the best overall accuracy of 95.7 %, as opposed to the best accuracy of 85.3 % based on spatial features, which was obtained by LDA. Simply concatenating spectral and spatial features did not improve over modeling using spectral or spatial features alone. A model ensemble strategy integrating the spectral features-based RLDA and the spatial features-based LDA resulted in a statistically significant improvement in the overall accuracy to 96.6 %. Model-level feature integration offers an effective means for improving the discrimination between defective and normal blueberries. Both the hyperspectral data11https://doi.org/10.5281/zenodo.11200576. and the software programs22https://github.com/vicdxxx/Blueberry-Defect-Detection-by-Hyperspectral-Imaging. of this study are made publicly available.

Evaluation of the Bond Quality of Metal-Clad Plates Using Laser Ultrasonic Local Resonance

The effective detection of delamination defects, especially sub-millimeter delamination defects, in metal-clad plates is of great significance in improving product quality. In this work, the laser ultrasonic (LU) local resonance method is used to locate and characterize the sub-millimeter defects in stainless/carbon steel-clad plates. The influence of the delamination radius on the amplitude and resonant frequency of the laser ultrasound was investigated using 2D axisymmetric finite element (FE) simulations. The simulation results show that both the amplitude and the first resonance frequency (FRF) are effective features for detecting large-scale delamination defects, but the FRF is a better feature for detecting tiny delamination defects. A 304/Q235/304-clad plate specimen was made through a hot rolling bonding process, which contained a large number of self-forming delamination defects. The laser ultrasonic signals of different composite states collected in the experiment have good consistency with the simulated waveforms. The experimental results show that the laser ultrasonic local resonance method is a high-resolution imaging method, which can locate and characterize the sub-millimeter delamination defects in stainless/carbon steel-clad plates.

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.

Learning the Color Space for Effective Fabric Defect Detection

Learning the Color Space for Effective Fabric Defect Detection