• Smart Structures and Systems
• /
• 제30권6호
• /
• pp.557-569
• /
• 2022

Vibration-based structural health monitoring (SHM) is crucial for the dynamic maintenance of civil building structures to protect property security and the lives of the public. Analyzing these vibrations with modern artificial intelligence and deep learning (DL) methods is a new trend. This paper proposed an unsupervised deep learning method based on a convolutional autoencoder (CAE), which can overcome the limitations of conventional supervised deep learning. With the convolutional core applied to the DL network, the method can extract features self-adaptively and efficiently. The effectiveness of the method in detecting damage is then tested using a benchmark model. Thereafter, this method is used to detect damage and instant disaster events in a rubber bearing-isolated gymnasium structure. The results indicate that the method enables the CAE network to learn the intact vibrations, so as to distinguish between different damage states of the benchmark model, and the outcome meets the high-dimensional data distribution characteristics visualized by the t-SNE method. Besides, the CAE-based network trained with daily vibrations of the isolating layer in the gymnasium can precisely recover newly collected vibration and detect the occurrence of the ground motion. The proposed method is effective at identifying nonlinear variations in the dynamic responses and has the potential to be used for structural condition assessment and safety warning.

• Smart Structures and Systems
• /
• 제29권4호
• /
• pp.523-533
• /
• 2022

A novel metaheuristic search method, namely black widow optimization (BWO) is employed to increase the accuracy of slope stability analysis. The BWO is a recently-developed optimizer that supervises the training of an artificial neural network (ANN) for predicting the factor of safety (FOS) of a single-layer cohesive soil slope. The designed slope bears a loaded foundation in different distances from the crest. A sensitivity analysis is conducted based on the number of active individuals in the BWO algorithm, and it was shown that the best performance is acquired for the population size of 40. Evaluation of the results revealed that the capability of the ANN was significantly enhanced by applying the BWO. In this sense, the learning root mean square error fell down by 23.34%. Also, the correlation between the testing data rose from 0.9573 to 0.9737. Therefore, the postposed BWO-ANN can be promisingly used for the early prediction of FOS in real-world projects.

• Smart Structures and Systems
• /
• 제30권2호
• /
• pp.195-207
• /
• 2022

Computational drawbacks associated with regular predictive models have motivated engineers to use hybrid techniques in dealing with complex engineering tasks like simulating the compressive strength of concrete (CSC). This study evaluates the efficiency of tree potential metaheuristic schemes, namely shuffled complex evolution (SCE), multi-verse optimizer (MVO), and beetle antennae search (BAS) for optimizing the performance of a multi-layer perceptron (MLP) system. The models are fed by the information of 1030 concrete specimens (where the amount of cement, blast furnace slag (BFS), fly ash (FA1), water, superplasticizer (SP), coarse aggregate (CA), and fine aggregate (FA2) are taken as independent factors). The results of the ensembles are compared to unreinforced MLP to examine improvements resulted from the incorporation of the SCE, MVO, and BAS. It was shown that these algorithms can considerably enhance the training and prediction accuracy of the MLP. Overall, the proposed models are capable of presenting an early, inexpensive, and reliable prediction of the CSC. Due to the higher accuracy of the BAS-based model, a predictive formula is extracted from this algorithm.

• International journal of advanced smart convergence
• /
• 제12권1호
• /
• pp.41-52
• /
• 2023

The purpose of this study is to review the proposed solutions to the Blockchain trilemma put forward by various research scholars and to draw conclusions by comparing the findings of each study. We found that the models so far developed either compromise scalability, decentralization, or security. The first model compromises decentralization. By partially centralizing the network, transaction processing speed can be improved, but security strength is weakened. Examples of this include Algorand and EOS. Because Algorand randomly selects the node that decides the consensus, the security of Algorand is better than EOS, wherein a designated selector decides. The second model recognizes that scalability causes a delay in speed when transactions are included in a block, reducing the system's efficiency. Compromising scalability makes it possible to increase decentralization. Representative examples include Bitcoin and Ethereum. Bitcoin is more vital than Ethereum in terms of security, but in terms of scalability, Ethereum is superior to Bitcoin. In the third model, information is stored and managed through various procedures at the expense of security. The application case is to weaken security by applying a layer 1 or 2 solution that stores and reroutes information. The expected effect of this study is to provide a new perspective on the trilemma debate and to stimulate interest in continued research into the problem.

• 한국초전도ㆍ저온공학회논문지
• /
• 제25권4호
• /
• pp.65-69
• /
• 2023

Hydrogen is an eco-friendly energy source and is being actively researched in various fields around the world, including mobility and aerospace. In order to effectively utilize hydrogen energy, it should be used in a liquid state with high energy storage density, but when hydrogen is stored in a liquid state, BOG (boil-off gas) is generated due to the temperature difference with the atmosphere. This should be re-condensed when considering storage efficiency and economy. In particular, large-capacity liquid hydrogen storage tank is required a gaseous helium circulation cooling system that cools by circulating cryogenic refrigerant due to the increase in heat intrusion from external air as the heat transfer area increases and the wide distribution of the gas layer inside the tank. In order to effectively apply the system, thermo-hydraulic analysis through process analysis is required. In this study, the condenser design and system characteristics of a gaseous helium circulation cooling system for BOG recondensation of a liquefied hydrogen storage tank were compared.

• Smart Structures and Systems
• /
• 제33권1호
• /
• pp.65-91
• /
• 2024

The use of five optimization techniques for the prediction of a strength-based concrete mixture's best-fit model is examined in this work. Five optimization techniques are utilized for this purpose: Slime Mold Algorithm (SMA), Black Hole Algorithm (BHA), Multi-Verse Optimizer (MVO), Vortex Search (VS), and Whale Optimization Algorithm (WOA). MATLAB employs a hybrid learning strategy to train an artificial neural network that combines least square estimation with backpropagation. Thus, 72 samples are utilized as training datasets and 31 as testing datasets, totaling 103. The multi-layer perceptron (MLP) is used to analyze all data, and results are verified by comparison. For training datasets in the best-fit models of SMA-MLP, BHA-MLP, MVO-MLP, VS-MLP, and WOA-MLP, the statistical indices of coefficient of determination (R²) in training phase are 0.9603, 0.9679, 0.9827, 0.9841 and 0.9770, and in testing phase are 0.9567, 0.9552, 0.9594, 0.9888 and 0.9695 respectively. In addition, the best-fit structures for training for SMA, BHA, MVO, VS, and WOA (all combined with multilayer perceptron, MLP) are achieved when the term population size was modified to 450, 500, 250, 150, and 500, respectively. Among all the suggested options, VS could offer a stronger prediction network for training MLP.

• Smart Structures and Systems
• /
• 제33권3호
• /
• pp.201-215
• /
• 2024

Spline chirplet transform and local maximum synchrosqueezing are introduced to present a novel structural instantaneous frequency (IF) identification method named local maximum synchrosqueezing spline chirplet transform (LMSSSCT). Namely spline chirplet transform (SCT), a transform is firstly introduced based on classic chirplet transform and spline interpolated kernel function. Applying SCT in association with local maximum synchrosqueezing, the LMSSSCT is then proposed. The index of accuracy and Rényi entropy show that LMSSSCT outperforms the other time-frequency analysis (TFA) methods in processing analytical signals, especially in the presence of noise. Numerical examples of a Duffing nonlinear system with single degree of freedom and a two-layer shear frame structure with time-varying stiffness are used to verify the effectiveness of structural IF identification. Moreover, a nonlinear supported beam structure test is conducted and the LMSSSCT is utilized for structural IF identification. Numerical simulation and experimental results demonstrate that the presented LMSSSCT can effectively identify the IFs of nonlinear structures and time-varying structures with good accuracy and stability.

• Structural Engineering and Mechanics
• /
• 제91권1호
• /
• pp.87-102
• /
• 2024

In recent years, the focus on vibration analysis of multilayer smart structures has attracted considerable attention in many engineering applications. In this work, vibration analysis of a three-layer microporous beam with a core amplified by a composite material reinforced with graphene platelets and two piezoelectric thin films is discussed. It is assumed that piezoelectric layers with a thickness of 0.01 core are very thin and the properties of the matrix and reinforcement vary in the thickness directions. The governing equations of motion are obtained using an energy approach and the method of numerical differential quadrature to solve them. The results of this work are compared to other research and there is good agreement between them. The influences of the volumetric weight fraction of graphene wafers, different graphene platelets distributions, porosity distribution, mass scale parameters and thin ratio of graphene platelets take into account the natural dimensionless frequencies of the micro-beam. The results of this study show that the symmetric distribution of graphene platelets based on the symmetric porosity distribution has a great influence on the natural frequencies without basic dimension of the micro-beam, while the shape ratios of graphene platelets do not have a significant influence on natural frequency changes.

• 농업과학연구
• /
• 제50권3호
• /
• pp.357-364
• /
• 2023

In this study, we propose a ripe tomato bunch localization method based on convolutional neural networks, to be applied in robotic harvesting systems. Tomato images were obtained from a smart greenhouse at the Rural Development Administration (RDA). The sample images for training were extracted based on tomato maturity and resized to 128 × 128 pixels for use in the classification model. The model was constructed based on four-layer convolutional neural networks, and the classes were determined based on stage of maturity, using a Softmax classifier. The localization of the ripe tomato bunch region was indicated on a class activation map. The class activation map could show the approximate location of the tomato bunch but tends to present a local part or a large part of the ripe tomato bunch region, which could lead to poor performance. Therefore, we suggest a recursive method to improve the performance of the model. The classification results indicated that the accuracy, precision, recall, and F1-score were 0.98, 0.87, 0.98, and 0.92, respectively. The localization performance was 0.52, estimated by the Intersection over Union (IoU), and through input recursion, the IoU was improved by 13%. Based on the results, the proposed localization of the ripe tomato bunch area can be incorporated in robotic harvesting systems to establish the optimal harvesting paths.

• 지능정보연구
• /
• 제26권2호
• /
• pp.131-145
• /
• 2020

산업혁신의 흐름에 발맞추어 다양한 분야에서 활용되고 있는 IoT 기술은 빅데이터의 접목을 통한 새로운 비즈니스 모델의 창출 및 사용자 친화적 서비스 제공의 핵심적인 요소로 부각되고 있다. 사물인터넷이 적용된 디바이스에서 누적된 데이터는 사용자 환경 및 패턴 분석을 통해 맞춤형 지능 시스템을 제공해줄 수 있어 편의 기반 스마트 시스템 구축에 다방면으로 활용되고 있다. 최근에는 이를 공공영역 혁신에 확대 적용하여 CCTV를 활용한 교통 범죄 문제 해결 등 스마트시티, 스마트 교통 등에 활용하고 있다. 그러나 이미지 데이터를 활용하는 기존 연구에서는 개인에 대한 사생활 침해 문제 및 비(非)일반적 상황에서 객체 감지 성능이 저하되는 한계가 있다. 본 연구에 활용된 IoT 디바이스 기반의 센서 데이터는 개인에 대한 식별이 불필요해 사생활 이슈로부터 자유로운 데이터로, 불특정 다수를 위한 지능형 공공서비스 구축에 효과적으로 활용될 수 있다. 대다수의 국민들이 일상적으로 활용하는 도시철도에서의 지능형 보행자 트래킹 시스템에 IoT 기반의 적외선 센서 디바이스를 활용하고자 하였으며 센서로부터 측정된 온도 데이터를 실시간 송출하고, CNN-LSTM(Convolutional Neural Network-Long Short Term Memory) 알고리즘을 활용하여 구간 내 보행 인원의 수를 예측하고자 하였다. 실험 결과 MLP(Multi-Layer Perceptron) 및 LSTM(Long Short-Term Memory), RNN-LSTM(Recurrent Neural Network-Long Short Term Memory)에 비해 제안한 CNN-LSTM 하이브리드 모형이 가장 우수한 예측성능을 보임을 확인하였다. 본 논문에서 제안한 디바이스 및 모델을 활용하여 그간 개인정보와 관련된 법적 문제로 인해 서비스 제공이 미흡했던 대중교통 내 실시간 모니터링 및 혼잡도 기반의 위기상황 대응 서비스 등 종합적 메트로 서비스를 제공할 수 있을 것으로 기대된다.