• Structural Monitoring and Maintenance
• /
• 제5권3호
• /
• pp.379-390
• /
• 2018

In this paper, a novel and effective damage diagnosis algorithm is proposed to detect and estimate damage using two stages least squares support vector machine (LS-SVM) and limited number of attached sensors on structures. In the first stage, LS-SVM1 is used to predict the unmeasured mode shapes data based on limited measured modal data and in the second stage, LS-SVM2 is used to predicting the damage location and severity using the complete modal data from the first-stage LS-SVM1. The presented methods are applied to a three story irregular frame and cantilever plate. To investigate the noise effects and modeling errors, two uncertainty levels have been considered. Moreover, the performance of the proposed methods has been verified through using experimental modal data of a mass-stiffness system. The obtained damage identification results show the suitable performance of the proposed damage identification method for structures in spite of different uncertainty levels.

• Smart Structures and Systems
• /
• 제11권1호
• /
• pp.69-86
• /
• 2013

An efficient methodology using static test data and changes in natural frequencies is proposed to identify the damages in structural systems. The methodology consists of two main stages. In the first stage, the Damage Signal Match (DSM) technique is employed to quickly identify the most potentially damaged elements so as to reduce the number of the solution space (solution parameters). In the second stage, a particle swarm optimization (PSO) approach is presented to accurately determine the actual damage extents using the first stage results. One numerical case study by using a planar truss and one experimental case study by using a full-scale steel truss structure are used to verify the proposed hybrid method. The identification results show that the proposed methodology can identify the location and severity of damage with a reasonable level of accuracy, even when practical considerations limit the number of measurements to only a few for a complex structure.

• Steel and Composite Structures
• /
• 제29권1호
• /
• pp.139-149
• /
• 2018

In this paper a new multi-step damage detection approach is provided. In the first step, condensed modal residual vector based indicator (CMRVBI) has been proposed to locate the suspected damaged elements of structures that have rotational degrees of freedom (DOFs). The CMRVBI is a new indicator that uses only translational DOFs of the structures to localize damaged elements. In the next step, salp swarm algorithm is applied to quantify damage severity of the suspected damaged elements. In order to assess the performance of the proposed approach, a numerical example including a three-layer square laminated composite plate is studied. The numerical results demonstrated that the proposed CMRVBI is effective for locating damage, regardless of the effect of noise. The efficiency of proposed approach is also compared during both steps. The results demonstrate that in noisy condition, the damage identification approach is capable for the studied structure.

• Structural Engineering and Mechanics
• /
• 제26권2호
• /
• pp.179-190
• /
• 2007

Damage detection based on measured vibration data has received intensive studies recently. Frequently, the damage to a structure may be reflected by a change of some system parameters, such as a degradation of the stiffness. In this paper, we apply a method to nondestructively locate and estimate the severity of damage in corrosion pipeline for which a few natural frequencies or mode shapes are available. The method is based on the strain modal sensitivity ratio (SMSR) and the orthogonality conditions sensitivities (OCS) applied to vibration features identified during the monitoring of the pipeline. The advantage of these methods is that it only requires measuring few modal parameters. The SMSR-based and OCS-based damage detection methods are illustrated using computer-simulated and laboratory testing data. The results show that the current method provides a precise indication of both the location and the extent of corrosion pipeline.

• 한국소음진동공학회논문집
• /
• 제16권7호
• /
• pp.720-728
• /
• 2006

A robust damage assessment technique is presented such that the location and severity of damage in structures can be identified using measured modal data. In order to identify the damage efficiently, the concept of design of experiment using orthogonal array is used for screening the main effects of each parameter which corresponds to possible damage location in FE model. Then, Taguchi method, which has been widely used for robust design in industry, is applied to parameter updating in analytical FE model. The numerical simulations of a truss structure show that damages in structure can be located from updated parameters.

• 한국구조물진단유지관리공학회 논문집
• /
• 제24권6호
• /
• pp.206-216
• /
• 2020

국내의 노후 철도교량이 증가함에 따라 노후화로 인한 유지관리비가 점점 증가하고 있으며, 지속적인 관리가 더욱 더 중요해지고 있다. 하지만 관리해야하는 노후 시설물은 증가하지만, 노후 시설물을 점검 및 진단을 할 수 있는 전문 인력은 부족해지고 있다. 이러한 문제를 해결하기 위해 본 연구는 정적 변형률 응답 데이터를 적용하여 AI 기술의 머신러닝 기법으로 구조물의 국부적인 손상을 탐지하는 개선된 학습모델을 제시하고자 한다. 손상탐지 머신러닝 학습 모델을 구성하기 위해 우선 무도상 철도 판형교의 설계도면을 참고하여 교량의 해석모델을 설정하였으며, 설정된 해석모델로 손상시나리오에 따른 정적변형률 데이터를 추출하여 통계적 기법을 이용해 교량의 신뢰도 기반의 Local 손상 지수를 제시하였다. 손상 탐지는 손상 유무 탐지, 크기 탐지, 위치 탐지 3단계의 과정을 수행하여 손상 크기 탐지에서 선형 회귀 모델을 추가로 고려해 임의의 손상을 탐지하였으며, 최종적으로 손상 탐지 머신러닝 분류 학습 모델과 회귀 모델을 이용한 임의의 손상 위치를 추정 및 검증하였다.

• Smart Structures and Systems
• /
• 제12권3_4호
• /
• pp.345-361
• /
• 2013

Locating and assessing the severity of damage in large or complex structures is one of the most challenging problems in the field of civil engineering. Considering that the wavelet packet transform (WPT) has the ability to clearly reflect the damage characteristics of structural response signals and the artificial neural network (ANN) is capable of learning in an unsupervised manner and of forming new classes when the structural exhibits change, this paper investigates a multi-stage structural damage diagnosis method by using the WPT and ANN based on "energy-damage" theory, in which, the wavelet packet component energies are first extracted to be damage sensitive feature and then adopted as input into an improved back propagation (BP) neural network model for damage diagnosis in a step by step mode. To validate the efficacy of the presented approach of the damage diagnosis, the benchmark structure of the American Society of Civil Engineers (ASCE) is employed in the case study. The results of damage diagnosis indicate that the method herein is computationally efficient and is able to detect the existence of different damage patterns in the simulated experiment where minor, moderate and severe damages corresponds to involving in the loss of stiffness on braces or the removal bracing in various combinations.

• 한국측량학회지
• /
• 제28권1호
• /
• pp.21-28
• /
• 2010

산불은 산림의 주요 교란요소중의 하나로써 산림 구조와 기능에 매우 큰 영향을 미치며, 산불피해강도에 따라 피해 후 식생회복 과정이 달라질 수 있다. 산불피해지의 피해강도와 식생회복 과정을 파악하기 위해서는 많은 인력과 예산이 필요하다. 위성영상자료를 이용한 산불피해지의 피해량 분석은 신속한 정보는 물론 대규모 피해지의 객관적인 결과를 원격으로 신속하게 취득할 수 있다. 이에 본 연구에서는 충청남도 청양 예산 지역의 산불발생 전 후 위성영상을 이용한 분류 기법을 통해 연구대상 지역의 산불피해 정보를 산출하고자 하였다. 이를 위해 산불발생 전 후의 다 시기 Landsat 위성영상을 이용한 영상 분류를 통해 산불피해 지역의 면적을 산출하였으며 수치임상도와의 중첩분석을 통해 피해지역 삼림의 수종, 영급, 경급 및 수관밀도별 피해량을 효과적으로 산정할 수 있었으며 분류결과와 NDVI를 이용하여 식생회복을 모니터링 할 수 있었다.

• 한국농공학회논문집
• /
• 제50권3호
• /
• pp.3-15
• /
• 2008

North Korea is one of the vulnerable countries facing the threat of a drought, so that it is unavoidable to experience fatal damage when drought is occurred, and it is necessary to improve the drought response capability of water resources systems. However, it is still difficult to find research efforts for drought characteristics and drought management in North Korea. This study is to quantify drought duration and magnitude and to analyze drought characteristics in North Korea. In order to quantitatively identify historical drought conditions and to evaluate their variability, drought indices are commonly used. In this study, drought indices including dry-day index, deciles of normal precipitation, Phillips drought index, standardized precipitation index and Palmer drought severity index are calculated and compared monthly using the weather data for the twenty one meteorological stations in North Korea. The indices compared with the drought damage records that have reported from 1990 to present to understand how the indices can explain the drought. A comparative study was also conducted to evaluate the relative severity of the significant droughts occurred during 2000 and 2001 which were reported as the worst drought in North Korea. Drought indices calculated from this study demonstrated that those can be the effective tools in quantitatively evaluating drought severity and measures of drought. Thus it is recommended the distributed trend of drought be considered when the plan or measures for drought in North Korea are established.

• 대한원격탐사학회지
• /
• 제35권4호
• /
• pp.517-534
• /
• 2019

In abrupt fire disturbances, high quality images suitable for wildfire damage assessment can be difficult to acquire. Quantifying wildfire burn area and severity are essential measures for quick short-term disaster response and efficient long-term disaster restoration. Planetscope (PS) imagery offers 3 m spatial and daily temporal resolution, which can overcome the spatio-temporal resolution tradeoff of conventional satellites, albeit at the cost of spectral resolution. This study investigated the potential of augmenting PS imagery by integrating the spectral information from Sentinel-2 (S2) differenced Normalized Burn Ratio (dNBR) to PS differenced Normalized Difference Vegetation Index (dNDVI) using histogram matching,specifically for wildfire burn area and severity assessment of the Okgye wildfire which occurred on April 4th, 2019. Due to the difficulty in acquiring reference data, the results of the study were compared to the wildfire burn area reported by Ministry of the Interior and Safety. The burn area estimates from this study demonstrated that the histogram-matched (HM) PS dNDVI image produced more accurate burn area estimates and more descriptive burn severity intervals in contrast to conventional methods using S2. The HM PS dNDVI image returned an error of only 0.691% whereas the S2 dNDVI and dNBR images overestimated the wildfire burn area by 5.32% and 106%, respectively. These improvements using PS were largely due to the higher spatial resolution, allowing for the detection of sparsely distributed patches of land and narrow roads, which were indistinguishable using S2 dNBR. In addition, the integration of spectral information from S2 in the PS image resolved saturation effects in areas of low and high burn severity.