scholarly journals A Deep Learning Method for the Impact Damage Segmentation of Curve-Shaped CFRP Specimens Inspected by Infrared Thermography

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 395
Author(s):  
Ziang Wei ◽  
Henrique Fernandes ◽  
Hans-Georg Herrmann ◽  
Jose Ricardo Tarpani ◽  
Ahmad Osman
Keyword(s):  
Neural Network ◽  
Infrared Thermography ◽  
Deep Neural Network ◽  
Impact Damage ◽  
Weight Ratio ◽  
Advanced Materials ◽  
Destructive Testing ◽  
Cfrp Laminates ◽  
Long Wave ◽  
The Impact

Advanced materials such as continuous carbon fiber-reinforced thermoplastic (CFRP) laminates are commonly used in many industries, mainly because of their strength, stiffness to weight ratio, toughness, weldability, and repairability. Structural components working in harsh environments such as satellites are permanently exposed to some sort of damage during their lifetimes. To detect and characterize these damages, non-destructive testing and evaluation techniques are essential tools, especially for composite materials. In this study, artificial intelligence was applied in combination with infrared thermography to detected and segment impact damage on curved laminates that were previously submitted to a severe thermal stress cycles and subsequent ballistic impacts. Segmentation was performed on both mid-wave and long-wave infrared sequences obtained simultaneously during pulsed thermography experiments by means of a deep neural network. A deep neural network was trained for each wavelength. Both networks generated satisfactory results. The model trained with mid-wave images achieved an F1-score of 92.74% and the model trained with long-wave images achieved an F1-score of 87.39%.

Validating the impact of accounting disclosures on stock market: A deep neural network approach

2021 ◽  
Vol 170 ◽  
pp. 120903
Author(s):  
Prajwal Eachempati ◽  
Praveen Ranjan Srivastava ◽  
Ajay Kumar ◽  
Kim Hua Tan ◽  
Shivam Gupta
Keyword(s):  
Neural Network ◽  
Stock Market ◽  
Deep Neural Network ◽  
Network Approach ◽  
Neural Network Approach ◽  
Accounting Disclosures ◽  
The Impact

Damage Development in CFRP Laminates under Impact Loading

2006 ◽  
Vol 326-328 ◽  
pp. 1833-1836 ◽  
Author(s):  
Seung Min Jang ◽  
Tadaharu Adachi ◽  
Akihiko Yamaji
Keyword(s):  
Impact Damage ◽  
Stacking Sequence ◽  
Absorbed Energy ◽  
Damage Development ◽  
Damage Resistance ◽  
Cfrp Laminates ◽  
Impact Tester ◽  
Weight Impact ◽  
The Impact ◽  
Delamination Area

The development characteristics of impact-induced damage in carbon-fiber-reinforcedplastics (CFRP) laminates were experimentally studied using a drop-weight impact tester. Five types of CFRP laminates were used to investigate the effect of stacking sequences and thicknesses. The efficiency of absorbed energy to impact energy was different for CFRP laminates with different stacking sequences or thicknesses. The DA/AE ratio of delamination area (DA) to absorbed energy (AE) was almost the same for CFRP laminates with the same stacking sequence regardless of the thickness. We found that the DA/AE ratio could be used as a parameter to characterize the impact damage resistance in CFRP laminates with different stacking sequences.

Experimental and simulation investigation on BVID and CAI behaviors of CFRP laminates manufactured by RTM technology

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Fang Chen ◽  
Weixing Yao ◽  
Wen Jiang
Keyword(s):  
Compressive Strength ◽  
Impact Damage ◽  
Projection Area ◽  
Element Analysis ◽  
Mechanical Fracture ◽  
Content Type ◽  
Explicit Finite Element ◽  
Compression Load ◽  
Cfrp Laminates ◽  
The Impact

Purpose The purpose of this paper is to synthetically investigate the impact damage responses of carbon fiber reinforced polymer (CFRP) and its influence on the compression mechanical responses of CFRP laminates, including damage distribution, residual compressive strength and fracture morphology. Design/methodology/approach A progressive damage simulation model is developed to analyze the complicated damage responses of CFRP laminates that are manufactured by resin transfer method (RTM) technology. Based on the ABAQUS/explicit finite element analysis solver, a VUMAT code is proposed to descript the composite materials’ damage behaviors under both impact and compression load. Adopting this proposed model, the primary mechanical indicators of four groups’ 5284RTM/U3160 CFRP laminates with different stacking sequences are predicted. Moreover, impact and compression after impact tests are conducted to verify the accuracy of simulation results. Findings Both simulation and experimental results show that the impact damage with low visible detectability can significantly reduce composites’ compressive strength. For all four groups’ composite laminates, the residual strength ratio is around 35% or even lower. The kernel impact damage near the plates’ geometric center promotes the degradation process of local materials and finally leads to the early occurrence of mechanical fracture. In addition, the impact damage projection area is not sensitive to the parameters of stacking sequences, while the residual compression strength is proportional to the number of 0-degree layers within whole laminates. Originality/value This study helps to understand the effect of an impact event on CFRP laminates’ compressive bearing capacity and provides a numerical method in simulating the damage responses under both impact and compression load.

scholarly journals DeepLocate: Smartphone Based Indoor Localization with a Deep Neural Network Ensemble Classifier

Sensors ◽  
2019 ◽  
Vol 20 (1) ◽  
pp. 133 ◽  
Author(s):  
Imran Ashraf ◽  
Soojung Hur ◽  
Sangjoon Park ◽  
Yongwan Park
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Indoor Localization ◽  
Ensemble Classifier ◽  
Location Based Services ◽  
Magnetic Data ◽  
Neural Network Ensemble ◽  
Localization Accuracy ◽  
Mean Error ◽  
The Impact

A quickly growing location-based services area has led to increased demand for indoor positioning and localization. Undoubtedly, Wi-Fi fingerprint-based localization is one of the promising indoor localization techniques, yet the variation of received signal strength is a major problem for accurate localization. Magnetic field-based localization has emerged as a new player and proved a potential indoor localization technology. However, one of its major limitations is degradation in localization accuracy when various smartphones are used. The localization performance is different from various smartphones even with the same localization technique. This research leverages the use of a deep neural network-based ensemble classifier to perform indoor localization with heterogeneous devices. The chief aim is to devise an approach that can achieve a similar localization accuracy using various smartphones. Features extracted from magnetic data of Galaxy S8 are fed into neural networks (NNs) for training. The experiments are performed with Galaxy S8, LG G6, LG G7, and Galaxy A8 smartphones to investigate the impact of device dependence on localization accuracy. Results demonstrate that NNs can play a significant role in mitigating the impact of device heterogeneity and increasing indoor localization accuracy. The proposed approach is able to achieve a localization accuracy of 2.64 m at 50% on four different devices. The mean error is 2.23 m, 2.52 m, 2.59 m, and 2.78 m for Galaxy S8, LG G6, LG G7, and Galaxy A8, respectively. Experiments on a publicly available magnetic dataset of Sony Xperia M2 using the proposed approach show a mean error of 2.84 m with a standard deviation of 2.24 m, while the error at 50% is 2.33 m. Furthermore, the impact of devices on various attitudes on the localization accuracy is investigated.

scholarly journals Impact Damage Resistance and Post-Impact Tolerance of Optimum Banana-Pseudo-Stem-Fiber-Reinforced Epoxy Sandwich Structures

2020 ◽  
Vol 10 (2) ◽  
pp. 684 ◽  
Author(s):  
Mohamad Zaki Hassan ◽  
S. M. Sapuan ◽  
Zainudin A. Rasid ◽  
Ariff Farhan Mohd Nor ◽  
Rozzeta Dolah ◽  
...  
Keyword(s):  
Composite Structures ◽  
Sandwich Structures ◽  
Impact Damage ◽  
Fiber Composite ◽  
Peak Load ◽  
Weight Ratio ◽  
Synthetic Fiber ◽  
Damage Area ◽  
Banana Fibers ◽  
The Impact

Banana fiber has a high potential for use in fiber composite structures due to its promise as a polymer reinforcement. However, it has poor bonding characteristics with the matrixes due to hydrophobic–hydrophilic incompatibility, inconsistency in blending weight ratio, and fiber length instability. In this study, the optimal conditions for a banana/epoxy composite as determined previously were used to fabricate a sandwich structure where carbon/Kevlar twill plies acted as the skins. The structure was evaluated based on two experimental tests: low-velocity impact and compression after impact (CAI) tests. Here, the synthetic fiber including Kevlar, carbon, and glass sandwich structures were also tested for comparison purposes. In general, the results showed a low peak load and larger damage area in the optimal banana/epoxy structures. The impact damage area, as characterized by the dye penetration, increased with increasing impact energy. The optimal banana composite and synthetic fiber systems were proven to offer a similar residual strength and normalized strength when higher impact energies were applied. Delamination and fracture behavior were dominant in the optimal banana structures subjected to CAI testing. Finally, optimization of the compounding parameters of the optimal banana fibers improved the impact and CAI properties of the structure, making them comparable to those of synthetic sandwich composites.

Simulation and Experimental Investigation of Impact Damage in Composite Shell

2005 ◽  
Vol 297-300 ◽  
pp. 1339-1343 ◽  
Author(s):  
Gui Ping Zhao ◽  
Chong Du Cho ◽  
Oh Yang Kwon
Keyword(s):  
Energy Absorption ◽  
Impact Damage ◽  
Displacement Transducer ◽  
Cfrp Laminates ◽  
Three Point Bending ◽  
Reinforced Plastics ◽  
Side Door ◽  
Impact Tester ◽  
Fiber Reinforced Plastics ◽  
The Impact

In this paper, the energy absorption characteristics on extruded aluminum box-section strengthened with carbon-fiber-reinforced plastics (CFRP) laminates and/or foam material were investigated under impact loading. Impact tests using a pneumatic impact tester were conducted with the specimens in three-point bending flexure with consideration given to the side-door impact beams in vehicles. The absorbed energy to the specimen during the impact was determined from the loaddisplacement curve, which was obtained from the strain gauge attached to the impactor and the laser displacement transducer. From the results, it was found that the strengthening by externally bonding with CFRP laminates improved the impact-induced energy absorption. Also, the effect of the improvement was clearly seen in the case of the use of filling form material in the aluminum extrusion together with attaching CFRP laminates.

scholarly journals Neurophysiology Based on Deep Neural Network under Artificial Prosthesis Vision

2021 ◽  
Vol 2074 (1) ◽  
pp. 012083
Author(s):  
Xiangli Lin
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Image Recognition ◽  
Deep Neural Network ◽  
Recognition Rate ◽  
Visual Prosthesis ◽  
Processing Strategies ◽  
Recognition Ability ◽  
Reduction Methods ◽  
The Impact

Abstract With the vigorous development of electronic technology and computer technology, as well as the continuous advancement of research in the fields of neurophysiology, bionics and medicine, the artificial visual prosthesis has brought hope to the blind to restore their vision. Artificial optical prosthesis research has confirmed that prosthetic vision can restore part of the visual function of patients with non-congenital blindness, but the mechanism of early prosthetic image processing still needs to be clarified through neurophysiological research. The purpose of this article is to study neurophysiology based on deep neural networks under simulated prosthetic vision. This article uses neurophysiological experiments and mathematical statistical methods to study the vision of simulated prostheses, and test and improve the image processing strategies used to simulate the visual design of prostheses. In this paper, based on the low-pixel image recognition of the simulating irregular phantom view point array, the deep neural network is used in the image processing strategy of prosthetic vision, and the effect of the image processing method on object image recognition is evaluated by the recognition rate. The experimental results show that the recognition rate of the two low-pixel segmentation and low-pixel background reduction methods proposed by the deep neural network under simulated prosthetic vision is about 70%, which can significantly increase the impact of object recognition, thereby improving the overall recognition ability of visual guidance.

Damage Classification in CFRP Laminates Using Principal Component Analysis (PCA) Approach

2012 ◽  
Vol 225 ◽  
pp. 189-194
Author(s):  
Mohamed Thariq Hameed Sultan ◽  
Azmin Shakrine M. Rafie ◽  
Noorfaizal Yidris ◽  
Faizal Mustapha ◽  
Dayang Laila Majid
Keyword(s):  
Signal Processing ◽  
Damage Detection ◽  
Impact Damage ◽  
Research Work ◽  
Principal Component ◽  
Damage Classification ◽  
Cfrp Laminates ◽  
Work Related ◽  
Detection And Identification ◽  
The Impact

Signal processing is an important element used for identifying damage in any SHM-related application. The method here is used to extract features from the use of different types of sensors, of which there are many. The responses from the sensors are also interpreted to classify the location and severity of the damage. This paper describes the signal processing approaches used for detecting the impact locations and monitoring the responses of impact damage. Further explanations are also given on the most widely-used software tools for damage detection and identification implemented throughout this research work. A brief introduction to these signal processing tools, together with some previous work related to impact damage detection, are presented and discussed in this paper.

Experimental Research on the Impact Damage of Composite Laminates at Different Energies

2014 ◽  
Vol 887-888 ◽  
pp. 850-853
Author(s):  
A Ying Zhang ◽  
Han Xiong Lv ◽  
Ye Zhang ◽  
Dong Xing Zhang
Keyword(s):  
Crack Length ◽  
Experimental Research ◽  
Impact Energy ◽  
Composite Laminates ◽  
Impact Damage ◽  
Energy Levels ◽  
Cfrp Laminates ◽  
The Matrix ◽  
Impact Area ◽  
The Impact

The effects of the impact energy on the impact damage of CFRP laminates were studied in this paper. Impact tests for the CFRP laminates with the size of 600 mm×700 mm were subjected to different the impact energy levels from 5 J to 50 J. The matrix length was investigated according to different energy levels. The experimental results reveal that the crack length increases linearly with the increasing impact energy. The impact damage of CFRP laminates tends to be more severe as impact energy increases, and the impact area and crater depth increases with increasing impact energy. The surface of impact dent of specimen looks like W shape.

Sign in / Sign up

Export Citation Format

Share Document