scholarly journals Modal-based vibrothermography using feature extraction with application to composite materials

2019 ◽  
Vol 19 (4) ◽  
pp. 967-986 ◽  
Author(s):  
Xintian Chi ◽  
Dario Di Maio ◽  
Nicholas AJ Lieven
Keyword(s):  
Feature Extraction ◽  
Composite Materials ◽  
Damage Detection ◽  
Infrared Camera ◽  
Experimental Tests ◽  
Detection Algorithm ◽  
Modal Testing ◽  
Theoretical Development ◽  
Operational Environment ◽  
Practical Applications

This research focuses on the development of a damage detection algorithm based on modal testing, vibrothermography, and feature extraction. The theoretical development of mathematical models is presented to illustrate the principles supporting the associated algorithms, through which the importance of the three components contributing to this approach is demonstrated. Experimental tests and analytical simulations have been performed in laboratory conditions to show that the proposed damage detection algorithm is able to detect, locate, and extract the features generated due to the presence of sub-surface damage in aerospace grade composite materials captured by an infrared camera. Through tests and analyses, the reliability and repeatability of this damage detection algorithm are verified. In the concluding observations of this article, suggestions are proposed for this algorithm’s practical applications in an operational environment.

scholarly journals A object detection algorithm based on pyramid Convolutional Neural Networks (CNN) and feature map fusion model

2019 ◽  
Vol 1 ◽  
pp. 1-1
Author(s):  
Nu Wen ◽  
Biao He ◽  
Zhilu Yuan ◽  
Yong Fan
Keyword(s):  
Neural Networks ◽  
Feature Extraction ◽  
Object Recognition ◽  
Object Detection ◽  
Detection Algorithm ◽  
Small Object ◽  
Image Block ◽  
Feature Map ◽  
Practical Applications ◽  
Traffic Video

<p><strong>Abstract.</strong> The aim of this paper is to solve two problems: object detection of small objects and multi-view scenes. First, in practical applications, the collected traffic video is affected by the resolution, viewing angle, focal length and model of the front-end acquisition device. The object size, shape and attitude of the video to be detected are different, resulting in the overall detection performance of the algorithm recognition. In particular, for traffic intersections, the size of the vehicle is related to the distance between the vehicle and the camera, and the object resolution of the vehicle near the intersection is relatively high. As the relative distance increases, the resolution of the object gradually decreases, resulting in feature extraction of the detection object to be detected. And identification becomes more and more difficult, and the probability of the object being detected is greatly reduced. Secondly, there are usually many ways to collect traffic data, such as fixed-position camera, high-altitude camera, and cruising UAV (Unmanned Aerial Vehicle). These video sources collected at different viewing angles and locations pose challenges to the stability, robustness, and generalization capabilities of the detection algorithms. Therefore, design a new algorithm and optimizing model parameters and training samples of different source data is extremely important for multi-view object detection.</p><p>An object detection algorithm based on pyramid Convolutional Neural Networks (CNN) and feature map fusion method was proposed, and the deep learning technology and the object detection algorithm are used to detect and identify the video objects of multiple viewing angles and different resolution scenes in traffic field. By mixing the lower and deeper feature map model, the algorithm can detect a smaller object in multiple viewing angles and different resolution scenes. Meanwhile, an image block and multi-threading technology was used to avoid scale limit of input image. The experiments show that it can be more efficient and accurate in practical applications of traffic detection filed.</p><p>The method can be used for the existing network model (VGG16, ResNet101, etc.) to build the skeleton of the object detection algorithm. A new object detection algorithm is developed for these goals, which contain small object recognition and multi-view recognition of traffic video, and it can enable it to extract the lower features of the object and effectively realize multi-object recognition of different scenes. Using the pyramid CNN model, it is possible to effectively combine low-level features and high-level features to achieve feature extraction and fusion of the object, and to solve the problem of small object recognition accuracy to a certain extent. Meanwhile, in view of the shortcomings of the existing object detection algorithm to re-compress the image size, the image block and multi-threading technology are used to restore the original resolution of the image. By using this technology, the accuracy of image object to be detected can be improved.</p>

Lightweight detection algorithm for fine-grained surface defects of aerospace seal rings

2021 ◽  
pp. 1-18
Author(s):  
Hui Liu ◽  
Boxia He ◽  
Yong He ◽  
Xiaotian Tao
Keyword(s):  
Feature Extraction ◽  
Defect Detection ◽  
Surface Defect ◽  
Surface Defects ◽  
Detection Algorithm ◽  
Seal Ring ◽  
Fine Grained ◽  
Aerospace Applications ◽  
Surface Defect Detection ◽  
The Mean

The existing seal ring surface defect detection methods for aerospace applications have the problems of low detection efficiency, strong specificity, large fine-grained classification errors, and unstable detection results. Considering these problems, a fine-grained seal ring surface defect detection algorithm for aerospace applications is proposed. Based on analysis of the stacking process of standard convolution, heat maps of original pixels in the receptive field participating in the convolution operation are quantified and generated. According to the generated heat map, the feature extraction optimization method of convolution combinations with different dilation rates is proposed, and an efficient convolution feature extraction network containing three kinds of dilated convolutions is designed. Combined with the O-ring surface defect features, a multiscale defect detection network is designed. Before the head of multiscale classification and position regression, feature fusion tree modules are added to ensure the reuse and compression of the responsive features of different receptive fields on the same scale feature maps. Experimental results show that on the O-rings-3000 testing dataset, the mean condition accuracy of the proposed algorithm reaches 95.10% for 5 types of surface defects of aerospace O-rings. Compared with RefineDet, the mean condition accuracy of the proposed algorithm is only reduced by 1.79%, while the parameters and FLOPs are reduced by 35.29% and 64.90%, respectively. Moreover, the proposed algorithm has good adaptability to image blur and light changes caused by the cutting of imaging hardware, thus saving the cost.

scholarly journals Concrete Crack Detection Based on Well-Known Feature Extractor Model and the YOLO_v2 Network

2021 ◽  
Vol 11 (2) ◽  
pp. 813
Author(s):  
Shuai Teng ◽  
Zongchao Liu ◽  
Gongfa Chen ◽  
Li Cheng
Keyword(s):  
Feature Extraction ◽  
Crack Detection ◽  
Computational Cost ◽  
Concrete Structures ◽  
Detection Algorithm ◽  
Computational Time ◽  
Image Size ◽  
Important Indicator ◽  
Feature Extractor ◽  
Model Training

This paper compares the crack detection performance (in terms of precision and computational cost) of the YOLO_v2 using 11 feature extractors, which provides a base for realizing fast and accurate crack detection on concrete structures. Cracks on concrete structures are an important indicator for assessing their durability and safety, and real-time crack detection is an essential task in structural maintenance. The object detection algorithm, especially the YOLO series network, has significant potential in crack detection, while the feature extractor is the most important component of the YOLO_v2. Hence, this paper employs 11 well-known CNN models as the feature extractor of the YOLO_v2 for crack detection. The results confirm that a different feature extractor model of the YOLO_v2 network leads to a different detection result, among which the AP value is 0.89, 0, and 0 for ‘resnet18’, ‘alexnet’, and ‘vgg16’, respectively meanwhile, the ‘googlenet’ (AP = 0.84) and ‘mobilenetv2’ (AP = 0.87) also demonstrate comparable AP values. In terms of computing speed, the ‘alexnet’ takes the least computational time, the ‘squeezenet’ and ‘resnet18’ are ranked second and third respectively; therefore, the ‘resnet18’ is the best feature extractor model in terms of precision and computational cost. Additionally, through the parametric study (influence on detection results of the training epoch, feature extraction layer, and testing image size), the associated parameters indeed have an impact on the detection results. It is demonstrated that: excellent crack detection results can be achieved by the YOLO_v2 detector, in which an appropriate feature extractor model, training epoch, feature extraction layer, and testing image size play an important role.

scholarly journals Unknown SAR Target Identification Method Based on Feature Extraction Network and KLD–RPA Joint Discrimination

2021 ◽  
Vol 13 (15) ◽  
pp. 2901
Author(s):  
Zhiqiang Zeng ◽  
Jinping Sun ◽  
Congan Xu ◽  
Haiyang Wang
Keyword(s):  
Feature Extraction ◽  
Position Angle ◽  
Automatic Target Recognition ◽  
Identification Accuracy ◽  
Training Dataset ◽  
Target Feature ◽  
Practical Applications ◽  
Feature Vectors ◽  
Identification Method ◽  
Leibler Divergence

Recently, deep learning (DL) has been successfully applied in automatic target recognition (ATR) tasks of synthetic aperture radar (SAR) images. However, limited by the lack of SAR image target datasets and the high cost of labeling, these existing DL based approaches can only accurately recognize the target in the training dataset. Therefore, high precision identification of unknown SAR targets in practical applications is one of the important capabilities that the SAR–ATR system should equip. To this end, we propose a novel DL based identification method for unknown SAR targets with joint discrimination. First of all, the feature extraction network (FEN) trained on a limited dataset is used to extract the SAR target features, and then the unknown targets are roughly identified from the known targets by computing the Kullback–Leibler divergence (KLD) of the target feature vectors. For the targets that cannot be distinguished by KLD, their feature vectors perform t-distributed stochastic neighbor embedding (t-SNE) dimensionality reduction processing to calculate the relative position angle (RPA). Finally, the known and unknown targets are finely identified based on RPA. Experimental results conducted on the MSTAR dataset demonstrate that the proposed method can achieve higher identification accuracy of unknown SAR targets than existing methods while maintaining high recognition accuracy of known targets.

Investigation of Sensor Placement in Lamb Wave-Based SHM Method

2012 ◽  
Vol 518 ◽  
pp. 174-183 ◽  
Author(s):  
Pawel Malinowski ◽  
Tomasz Wandowski ◽  
Wiesław M. Ostachowicz
Keyword(s):  
Wave Propagation ◽  
Damage Detection ◽  
Guided Waves ◽  
Sensor Placement ◽  
Detection Algorithm ◽  
Piezoelectric Sensors ◽  
Optimal Placement ◽  
Laser Vibrometer ◽  
Contact Method ◽  
Monitoring Method

In this paper the investigation of a structural health monitoring method for thin-walled parts of structures is presented. The concept is based on the guided elastic wave propagation phenomena. This type of waves can be used in order to obtain information about structure condition and possibly damaged areas. Guided elastic waves can travel in the medium with relatively low attenuation, therefore they enable monitoring of extensive parts of structures. In this way it is possible to detect small defects in their early stage of growth. It is essential because undetected damage can endanger integrity of a structure. In reported investigation piezoelectric transducer was used to excite guided waves in chosen specimens. Dispersion of guided waves results in changes of velocity with the wave frequency, therefore a narrowband signal was used. Measurement of the wave field was realized using laser scanning vibrometer that registered the velocity responses at points belonging to a defined mesh. An artificial discontinuity was introduced to the specimen. The goals of the investigation was to detect it and find optimal sensor placement for this task. Determination of the optimal placement of sensors is a very challenging mission. In conducted investigation laser vibrometer was used to facilitate the task. The chosen mesh of measuring points was the basis for the investigation. The purpose was to consider various configuration of piezoelectric sensors. Instead of using vast amount of piezoelectric sensors the earlier mentioned laser vibrometer was used to gather the necessary data from wave propagation. The signals gather by this non-contact method for the considered network were input to the damage detection algorithm. Damage detection algorithm was based on a procedure that seeks in the signals the damage-reflected waves. Knowing the wave velocity in considered material the damage position can be estimated.

Development of high-speed optical wavelength interrogation system for damage detection in composite materials

2005 ◽  
Author(s):  
Shinji Komatsuzaki ◽  
Seiji Kojima ◽  
Akihito Hongo ◽  
Nobuo Takeda ◽  
Takeo Sakurai
Keyword(s):  
Composite Materials ◽  
Damage Detection ◽  
High Speed ◽  
Optical Wavelength

Damage‐sensitive feature extraction with stacked autoencoders for unsupervised damage detection

2021 ◽  
Vol 28 (5) ◽  
Author(s):  
Moisés Felipe Silva ◽  
Adam Santos ◽  
Reginaldo Santos ◽  
Eloi Figueiredo ◽  
João C.W.A. Costa
Keyword(s):  
Feature Extraction ◽  
Damage Detection ◽  
Stacked Autoencoders

SELECTION OF CONTROLLABLE PARAMETERS OF THE BINARY DATA ARRAY DETECTION ALGORITHM IN THE INTEGRATED MANAGEMENT SYSTEM

2021 ◽  
Vol 4 (3) ◽  
pp. 11-18
Author(s):  
Khakimjon Zaynidinov ◽  
◽  
Odilbek Askaraliyev
Keyword(s):  
Management System ◽  
Binary Data ◽  
Integrated Management ◽  
Research Work ◽  
Hash Functions ◽  
Experimental Tests ◽  
Detection Algorithm ◽  
Identification Algorithm ◽  
Solution Algorithms ◽  
Selection Of

The article discusses the selection of parameters for the algorithm for determining binary data arrays included in the control system, developed by the authors using independent substitution methods. Based on the analysis of the algorithms of non-cryptographic hash functions, the hash function based on the linear matching method was selected as the basis for independent substitution methods. Simplified schemes of algorithms developed for creating and comparing identifiers using a set of basic hash functions are given. An array of binary data was selected and based on the appropriate values for the size of the divisible blocks and the number of basic hashfunctions used for independent substitutions. The selection of binary data arrays in information systems integrated into the management system was done for the purpose of intellectual processing of incoming data. The properties of the array of data entering integrated systems are studied. The authors conducted experimental tests in the selected direction and presented the results of similarity assessment measurements for various parameters of the identification algorithm. In addition, the article conductedexperiments on the object of study using the selected mathematical model, based on the analytical conclusions. Initiator elements are studied and analyzed using a set of hash functions. An algorithm for comparison of selected identifiers has been developed. A generation algorithm has been developed to demonstrate and test the proposed solution. Algorithms based on analysis and experiments, and methods for selecting binary data arrays using the ash function have been experimentally tested. Based on the results, the indicators are shown. Based on the results obtained, the analytical conclusions and problem solutions of the research work were recognized

Sign in / Sign up

Export Citation Format

Share Document