scholarly journals A Novel Parallel Auto-Encoder Framework for Multi-Scale Data in Civil Structural Health Monitoring

Algorithms ◽  
2018 ◽  
Vol 11 (8) ◽  
pp. 112 ◽  
Author(s):  
Ruhua Wang ◽  
Ling Li ◽  
Jun Li
Keyword(s):  
Deep Learning ◽  
Dimension Reduction ◽  
Structural Damage ◽  
Natural Frequencies ◽  
Steel Structure ◽  
Mode Shapes ◽  
Multi Scale ◽  
Training Samples ◽  
Sparsity Constraint ◽  
Deep Learning Network

In this paper, damage detection/identification for a seven-storey steel structure is investigated via using the vibration signals and deep learning techniques. Vibration characteristics, such as natural frequencies and mode shapes are captured and utilized as input for a deep learning network while the output vector represents the structural damage associated with locations. The deep auto-encoder with sparsity constraint is used for effective feature extraction for different types of signals and another deep auto-encoder is used to learn the relationship of different signals for final regression. The existing SAF model in a recent research study for the same problem processed all signals in one serial auto-encoder model. That kind of models have the following difficulties: (1) the natural frequencies and mode shapes are in different magnitude scales and it is not logical to normalize them in the same scale in building the models with training samples; (2) some frequencies and mode shapes may not be related to each other and it is not fair to use them for dimension reduction together. To tackle the above-mentioned problems for the multi-scale dataset in SHM, a novel parallel auto-encoder framework (Para-AF) is proposed in this paper. It processes the frequency signals and mode shapes separately for feature selection via dimension reduction and then combine these features together in relationship learning for regression. Furthermore, we introduce sparsity constraint in model reduction stage for performance improvement. Two experiments are conducted on performance evaluation and our results show the significant advantages of the proposed model in comparison with the existing approaches.

scholarly journals Temperature Effects on Vibration-Based Damage Detection of a Reinforced Concrete Slab

2020 ◽  
Vol 10 (8) ◽  
pp. 2869 ◽  
Author(s):  
Zhenpeng Wang ◽  
Minshui Huang ◽  
Jianfeng Gu
Keyword(s):  
Elastic Modulus ◽  
Reinforced Concrete ◽  
Ambient Temperature ◽  
Temperature Effects ◽  
Structural Damage ◽  
Natural Frequencies ◽  
Damage Identification ◽  
Mode Shapes ◽  
Arx Model ◽  
Rc Slab

To study the variations in modal properties of a reinforced concrete (RC) slab (such as natural frequencies, mode shapes and damping ratios) under the influence of ambient temperature, a laboratory RC slab is monitored for over a year, the simple linear regression (LR) and autoregressive with exogenous input (ARX) models between temperature and frequencies are established and validated, and a damage identification based on particle swarm optimization (PSO) is utilized to detect the assumed damage considering temperature effects. Firstly, the vibration testing is performed for one year and the variations of natural frequencies, mode shapes and damping ratios under different ambient temperatures are analyzed. The obtained results show that the change of ambient temperature causes a major change of natural frequencies, which, on the contrary, has little effect on damping ratios and modal shapes. Secondly, based on a theoretical derivation analysis of natural frequency, the models are determined from experimental data on the healthy structure, and the functional relationship between temperature and elastic modulus is obtained. Based on the monitoring data, the LR model and ARX model between structural elastic modulus and ambient temperature are acquired, which can be used as the baseline of future damage identification. Finally, the established ARX model is validated based on a PSO algorithm and new data from the assumed 5% uniform damage and 10% uniform damage are compared with the models. If the eigenfrequency exceeds the certain confidence interval of the ARX model, there is probably another cause that drives the eigenfrequency variations, such as structural damage. Based on the constructed ARX model, the assumed damage is identified accurately.

STRUCTURAL DAMAGE DETECTION BY MULTI-SCALE CROSS-SAMPLE ENTROPY

2015 ◽  
Vol 2 (1) ◽  
Author(s):  
Jui-Chang Liang ◽  
Ming-Jing Wang ◽  
Tzu-Kang Lin
Keyword(s):  
Structural Damage ◽  
Damage Index ◽  
Steel Structure ◽  
Vibration Signal ◽  
Sample Entropy ◽  
Ambient Vibration ◽  
Multi Scale ◽  
Damage Location ◽  
Damage Condition ◽  
Accuracy Rates

This study proposes a structural health monitoring (SHM) system based on multi-scale entropy (MSE) and multi-scale cross-sample entropy (MSCE). By measuring the ambient vibration signal from a structure, the damage condition can be rapidly evaluated via a MSE analysis. The damage location can then be detected by analyzing the signals of different floors under the same damage condition via a MSCE analysis. Moreover, a damage index is proposed to efficiently quantify the SHM process. A numerical simulation of a four-story steel structure is used to verify that the damage location and condition can be detected by the proposed SHM algorithm, and the location can be efficiently quantified by the damage index. Based on the results, the damage condition can be correctly assessed, and accuracy rates of 60% and 86% for the damage location can be achieved using the MSCE and damage index methods, respectively.

Frequency-based damage detection in cantilever beam using vision-based monitoring system with motion magnification technique

2018 ◽  
Vol 29 (20) ◽  
pp. 3923-3936 ◽  
Author(s):  
Andrew Jaeyong Choi ◽  
Jae-Hung Han
Keyword(s):  
Genetic Algorithm ◽  
Damage Detection ◽  
Monitoring System ◽  
Cantilever Beam ◽  
Structural Damage ◽  
Natural Frequencies ◽  
Solution Space ◽  
Mode Shapes ◽  
High Resolution Data ◽  
Motion Magnification

This article proposes a method for damage detection using vision-based monitoring with motion magnification technique. The methods based on the vibration characteristics of structures such as natural frequency, mode shapes, and modal damping have been applied to structural damage detection. However, the conventional methods have limitations for practical applications. Vision-based monitoring system can be employed as a new structural monitoring system because of its simplicity, potentially low cost, and unique capability of collecting high-resolution data. A methodology called video motion magnification has been developed to amplify non-visible small motions in a video to reveal the dynamic response. The video motion magnification method can be applied to measure small displacements to calculate the natural frequencies and the operational deflection shapes of the structures. Unlike conventional optimization methods, a genetic algorithm explores the entire solution space and can obtain the global optimum. In this article, identification of the location and magnitude of damage in a cantilever beam is formulated as an optimization problem using a real-value genetic algorithm by minimizing the objective function, which directly compares the first three natural frequencies changes from the phase-based motion magnification measurement and from the analytical model of a damaged cantilever beam.

scholarly journals Deep Learning Network Intensification for Preventing Noisy-Labeled Samples for Remote Sensing Classification

2021 ◽  
Vol 13 (9) ◽  
pp. 1689
Author(s):  
Chuang Lin ◽  
Shanxin Guo ◽  
Jinsong Chen ◽  
Luyi Sun ◽  
Xiaorou Zheng ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Network Performance ◽  
Aerial Image ◽  
Label Noise ◽  
Remote Sensing Classification ◽  
Learning Network ◽  
Training Samples ◽  
Deep Learning Network ◽  
The Impact

The deep-learning-network performance depends on the accuracy of the training samples. The training samples are commonly labeled by human visual investigation or inherited from historical land-cover or land-use maps, which usually contain label noise, depending on subjective knowledge and the time of the historical map. Helping the network to distinguish noisy labels during the training process is a prerequisite for applying the model for training across time and locations. This study proposes an antinoise framework, the Weight Loss Network (WLN), to achieve this goal. The WLN contains three main parts: (1) the segmentation subnetwork, which any state-of-the-art segmentation network can replace; (2) the attention subnetwork (λ); and (3) the class-balance coefficient (α). Four types of label noise (an insufficient label, redundant label, missing label and incorrect label) were simulated by dilate and erode processing to test the network’s antinoise ability. The segmentation task was set to extract buildings from the Inria Aerial Image Labeling Dataset, which includes Austin, Chicago, Kitsap County, Western Tyrol and Vienna. The network’s performance was evaluated by comparing it with the original U-Net model by adding noisy training samples with different noise rates and noise levels. The result shows that the proposed antinoise framework (WLN) can maintain high accuracy, while the accuracy of the U-Net model dropped. Specifically, after adding 50% of dilated-label samples at noise level 3, the U-Net model’s accuracy dropped by 12.7% for OA, 20.7% for the Mean Intersection over Union (MIOU) and 13.8% for Kappa scores. By contrast, the accuracy of the WLN dropped by 0.2% for OA, 0.3% for the MIOU and 0.8% for Kappa scores. For eroded-label samples at the same level, the accuracy of the U-Net model dropped by 8.4% for OA, 24.2% for the MIOU and 43.3% for Kappa scores, while the accuracy of the WLN dropped by 4.5% for OA, 4.7% for the MIOU and 0.5% for Kappa scores. This result shows that the antinoise framework proposed in this paper can help current segmentation models to avoid the impact of noisy training labels and has the potential to be trained by a larger remote sensing image set regardless of the inner label error.

scholarly journals Changes in the Dynamic Characteristics of a Small-Scale Gymnasium Model Due to Simulated Earthquake Damage

2021 ◽  
Vol 16 (7) ◽  
pp. 1074-1085
Author(s):  
Jun Fujiwara ◽  
Akiko Kishida ◽  
Takashi Aoki ◽  
Ryuta Enokida ◽  
Koichi Kajiwara ◽  
...  
Keyword(s):  
Structural Damage ◽  
Natural Frequencies ◽  
Mode Shapes ◽  
Modal Parameters ◽  
Small Scale ◽  
Building Structures ◽  
Shake Table Tests ◽  
Large Span ◽  
Similarity Rule ◽  
Measured Response

In this study, the authors used shake-table tests to assess the modal parameters of a small-scale gymnasium model with simulated damage, the feasibility of estimating the damage to large-span building structures was studied. In Japan, large-span structures, such as gymnasiums, are expected to be used as evacuation shelters when a natural disaster occurs. As the shelter itself may be damaged in case of an earthquake, it is critical to determine whether damage has occurred, where it occurred, and how serious it is, before the shelter is used. The small-scale gymnasium was designed based on the similarity rule. Observed earthquake ground motions scaled to aftershock levels were applied to the model. The natural frequencies and mode shapes were obtained from the measured response accelerations. To study the influence of structural damage on the modal parameters, a gymnasium model with simulated damage was also tested. The results indicate that the modal parameters, e.g., natural frequencies and mode shapes, can be obtained from the response accelerations, and the damage patterns can be estimated from the changes in these modal parameters.

Experimental Verification of the Structural Damage Identification Method Developed for Beam Structures

2006 ◽  
Vol 326-328 ◽  
pp. 1113-1116
Author(s):  
Deokki Youn ◽  
Usik Lee ◽  
Oh Yang Kwon
Keyword(s):  
Experimental Verification ◽  
Structural Damage ◽  
Natural Frequencies ◽  
Damage Identification ◽  
Mode Shapes ◽  
Damage State ◽  
Intact State ◽  
Identification Method ◽  
Structural Damage Identification ◽  
Cantilevered Beam

In this paper, an experimental verification has been conducted for a frequency response function (FRF)-based structural damage identification method (SDIM) proposed in the previous study [1]. The FRF-based SDIM requires the natural frequencies and mode shapes measured in the intact state and the FRF-data measured in the damaged state. Experiments are conducted for the cantilevered beam specimens with one and three slots. It is shown that the proposed FRF-based SDIM provides damage identification results that agree quite well with true damage state.

scholarly journals SA-Net: A scale-attention network for medical image segmentation

PLoS ONE ◽  
2021 ◽  
Vol 16 (4) ◽  
pp. e0247388
Author(s):  
Jingfei Hu ◽  
Hua Wang ◽  
Jie Wang ◽  
Yunqi Wang ◽  
Fang He ◽  
...  
Keyword(s):  
Deep Learning ◽  
Medical Image ◽  
Multiple Scales ◽  
Medical Images ◽  
Semantic Segmentation ◽  
Medical Image Segmentation ◽  
Retinal Images ◽  
Multi Scale ◽  
Multiple Datasets ◽  
Deep Learning Network

Semantic segmentation of medical images provides an important cornerstone for subsequent tasks of image analysis and understanding. With rapid advancements in deep learning methods, conventional U-Net segmentation networks have been applied in many fields. Based on exploratory experiments, features at multiple scales have been found to be of great importance for the segmentation of medical images. In this paper, we propose a scale-attention deep learning network (SA-Net), which extracts features of different scales in a residual module and uses an attention module to enforce the scale-attention capability. SA-Net can better learn the multi-scale features and achieve more accurate segmentation for different medical image. In addition, this work validates the proposed method across multiple datasets. The experiment results show SA-Net achieves excellent performances in the applications of vessel detection in retinal images, lung segmentation, artery/vein(A/V) classification in retinal images and blastocyst segmentation. To facilitate SA-Net utilization by the scientific community, the code implementation will be made publicly available.

Sign in / Sign up

Export Citation Format

Share Document