• 한국공간구조학회논문집
• /
• 제20권2호
• /
• pp.51-58
• /
• 2020

Recently, deep learning that is the most popular and effective class of machine learning algorithms is widely applied to various industrial areas. A number of research on various topics about structural engineering was performed by using artificial neural networks, such as structural design optimization, vibration control and system identification etc. When nonlinear semi-active structural control devices are applied to building structure, a lot of computational effort is required to predict dynamic structural responses of finite element method (FEM) model for development of control algorithm. To solve this problem, an artificial neural network model was developed in this study. Among various deep learning algorithms, a recurrent neural network (RNN) was used to make the time history response prediction model. An RNN can retain state from one iteration to the next by using its own output as input for the next step. An eleven-story building structure with semi-active tuned mass damper (TMD) was used as an example structure. The semi-active TMD was composed of magnetorheological damper. Five historical earthquakes and five artificial ground motions were used as ground excitations for training of an RNN model. Another artificial ground motion that was not used for training was used for verification of the developed RNN model. Parametric studies on various hyper-parameters including number of hidden layers, sequence length, number of LSTM cells, etc. After appropriate training iteration of the RNN model with proper hyper-parameters, the RNN model for prediction of seismic responses of the building structure with semi-active TMD was developed. The developed RNN model can effectively provide very accurate seismic responses compared to the FEM model.

• Asia pacific journal of information systems
• /
• 제8권3호
• /
• pp.51-73
• /
• 1998

This paper is to evaluate the application potentials of data mining in the areas of Supply Chain Management (SCM) and to suggest the architectures of Decision Support Systems (DSS) that support data mining activities. We first briefly introduce data mining and review the recent literatures on SCM and then evaluate data mining applications to SCM in three aspects: marketing, operations management and information systems. By analyzing the cases about pricing models in distribution channels, demand forecasting and quality control, it is shown that artificial intelligence techniques such as artificial neural networks, case-based reasoning and expert systems, combined with traditional analysis models, effectively mine the useful knowledge from the large volume of SCM data. Agent-based information system is addressed as an important architecture that enables the pursuit of global optimization of SCM through communication and information sharing among supply chain constituents without loss of their characteristics and independence. We expect that the suggested architectures of intelligent DSS provide the basis in developing information systems for SCM to improve the quality of organizational decisions.

• 대한임베디드공학회논문지
• /
• 제18권3호
• /
• pp.101-108
• /
• 2023

Optimizing the performance of deep neural networks on embedded systems is a challenging task that requires efficient compilers and runtime systems. We propose a TVM-based approach that consists of three steps: quantization, auto-scheduling, and ahead-of-time compilation. Our approach reduces the computational complexity of models without significant loss of accuracy, and generates optimized code for various hardware platforms. We evaluate our approach on three representative CNNs using ImageNet Dataset on the NVIDIA Jetson AGX Xavier board and show that it outperforms baseline methods in terms of processing speed.

• Smart Structures and Systems
• /
• 제5권4호
• /
• pp.369-379
• /
• 2009

The sudden collapse of Interstate 35 Bridge in Minneapolis gave a wake-up call to US municipalities to re-evaluate aging bridges. In this situation, structural health monitoring (SHM) technology can provide the essential help needed for monitoring and maintaining the nation's infrastructure. Monitoring long span bridges such as cable-stayed bridges effectively requires the use of a large number of sensors. In this article, we introduce a probabilistic approach to identify optimal locations of sensors to enhance damage detection. Probability distribution functions are established using an artificial neural network trained using a priori knowledge of damage locations. The optimal number of sensors is identified using multi-objective optimization that simultaneously considers information entropy and sensor cost-objective functions. Luling Bridge, a cable-stayed bridge over the Mississippi River, is selected as a case study to demonstrate the efficiency of the proposed approach.

• 한국터널지하공간학회 논문집
• /
• 제10권2호
• /
• pp.153-166
• /
• 2008

본 논문에서는 IT 기술을 이용한 터널 자동화 설계 시스템 개발에 관한 내용을 다루었다. 먼저 개발 시스템에 대한 개념 및 개발 과정과 시스템을 구성하는 각 요소기술 및 개별 모듈 개발에 관한 내용을 기술하였다. 본 시스템의 요소기술인 ANN-기반의 터널 저동 예측 기술에 대해 그 개념과 ANN 학습과정 및 검증과정을 기술하였다 ANN-기반의 터널거동 예측은 FEM 및 FDM 등 연속체 기반의 해석을 토대로 구축한 DB를 ANN을 통해 일반화 한 후 개발된 엔진을 세부모듈에 접목시켜 별도의 해석 없이 유사 단면 혹은 현장에 적용이 가능하도록 하였다. 본 논문에서는 구체적인 개발과정과 향후 적용방향에 대해 구체적인 내용을 기술하였다.

• Smart Structures and Systems
• /
• 제2권3호
• /
• pp.253-274
• /
• 2006

The structural monitoring of multi-wire strands is of importance to prestressed concrete structures and cable-stayed or suspension bridges. This paper addresses the monitoring of strands by ultrasonic guided waves with emphasis on the signal processing and automatic defect classification. The detection of notch-like defects in the strands is based on the reflections of guided waves that are excited and detected by magnetostrictive ultrasonic transducers. The Discrete Wavelet Transform was used to extract damage-sensitive features from the detected signals and to construct a multi-dimensional Damage Index vector. The Damage Index vector was then fed to an Artificial Neural Network to provide the automatic classification of (a) the size of the notch and (b) the location of the notch from the receiving sensor. Following an optimization study of the network, it was determined that five damage-sensitive features provided the best defect classification performance with an overall success rate of 90.8%. It was thus demonstrated that the wavelet-based multidimensional analysis can provide excellent classification performance for notch-type defects in strands.

• 한국공간구조학회논문집
• /
• 제23권4호
• /
• pp.81-88
• /
• 2023

Numerous factors contribute to the deterioration of reinforced concrete structures. Elevated temperatures significantly alter the composition of the concrete ingredients, consequently diminishing the concrete's strength properties. With the escalation of global CO2 levels, the carbonation of concrete structures has emerged as a critical challenge, substantially affecting concrete durability research. Assessing and predicting concrete degradation due to thermal effects and carbonation are crucial yet intricate tasks. To address this, multiple prediction models for concrete carbonation and compressive strength under thermal impact have been developed. This study employs seven machine learning algorithms-specifically, multiple linear regression, decision trees, random forest, support vector machines, k-nearest neighbors, artificial neural networks, and extreme gradient boosting algorithms-to formulate predictive models for concrete carbonation and thermal impact. Two distinct datasets, derived from reported experimental studies, were utilized for training these predictive models. Performance evaluation relied on metrics like root mean square error, mean square error, mean absolute error, and coefficient of determination. The optimization of hyperparameters was achieved through k-fold cross-validation and grid search techniques. The analytical outcomes demonstrate that neural networks and extreme gradient boosting algorithms outshine the remaining five machine learning approaches, showcasing outstanding predictive performance for concrete carbonation and thermal effect modeling.

• Korean Chemical Engineering Research
• /
• 제61권1호
• /
• pp.123-141
• /
• 2023

인공신경망을 이용한 모델 개발에서 데이터의 품질은 모델 성능에 큰 영향을 주고, 양질의 충분한 데이터가 인공신경망 훈련을 위해 필요하다. 하지만, 공학 분야에서는 적은 양의 데이터로 모델을 개발해야 하는 경우가 자주 발생한다. 본 논문은 토양에 살포된 축산 분뇨로부터 암모니아 방출량에 대한 적은 수의 데이터(83 개)를 사용하여 인공신경망 모델의 예측 성능을 향상할 수 있는 방안을 제시하였다. Michaelis-Menten 식으로 표현되는 암모니아 방출량 문제는 11개 입력변수에 대하여 2개 출력변수로 구성되었다. 출력변수는 최대 질소 발생량(N_max, kg/ha)과 N_max의 절반에 도달하는 시간(K_m, h) 이다. 범주형 입력변수에 대해 다차원 등간격 기법인 one-hot encoding 을 이용하여 데이터 전처리를 수행하였고, 훈련데이터 66개에 대하여 generative adversarial network (GAN)을 이용하여 13개 데이터를 추가로 보강하였다. 또한, 인공신경망의 초매개변수인 은닉층 수, 각 은닉층 내 뉴런 수, 활성화 함수의 최적 조합을 찾기 위하여 Gaussian process (GP)를 사용하였다. 기존의 인공신경망 구조(Lim et al., 2007) 는 17개 평가데이터에 대하여 mean absolute error (MAE)는 K_m에서 0.0668, N_max에서 0.1860이었다. 본 연구에서 제시된 인공신경망 모델은 K_m에서 0.0414, N_max에서 0.0818로 MAE 가 기존 모델 대비 각각 38%, 56% 감소하였다. 본 연구에서 제시된 방법은 적은 양의 데이터를 갖는 문제에서 인공신경망 성능을 향상하기 위하여 활용할 수 있을 것이다.

• 한국수자원학회논문집
• /
• 제53권6호
• /
• pp.395-408
• /
• 2020

본 연구논문은 북부아프리카의 알제리에 위치한 하천유역에서 다중선행일 유출량의 예측을 위하여 진화적 최적화기법과 k-fold 교차검증을 결합한 세 개의 서로 다른 기계학습 접근법 (인공신경망, 적응 뉴로퍼지 시스템, 그리고 웨이블릿 기반 신경망)을 개발하고 적용하는 것이다. 인공신경망과 적응 뉴로퍼지 시스템은 root mean squared error (RMSE), Nash-Sutcliffe efficiency (NSE), correlation coefficient (R), 그리고 peak flow criteria (PFC) 의 네 개의 통계지표를 기반으로 하여 모형의 훈련 및 테스팅 결과 유사한 모형수행결과를 나타내었다. 웨이블릿 기반 신경망모형은 하루선행일 테스팅의 결과 RMSE = 8.590 ㎥/sec 과 PFC = 0.252로 분석되어서 인공신경망의 RMSE = 19.120 ㎥/sec, PFC = 0.446 과 적응 뉴로퍼지 시스템의 RMSE = 18.520 ㎥/sec, PFC = 0.444 보다 양호한 결과를 나타내었고, NSE와 R의 값도 웨이블릿 기반 신경망모형이 우수한 것으로 나타났다. 그러므로 웨이블릿 기반 신경망은 알제리 세이보스 하천에서 다중선행일의 예측을 위하여 효율적인 도구로 사용할 수 있다.

• 한국공간구조학회논문집
• /
• 제24권3호
• /
• pp.43-51
• /
• 2024

Dynamic responses of nuclear power plant structure subjected to earthquake loads should be carefully investigated for safety. Because nuclear power plant structure are usually constructed by material of reinforced concrete, the aging deterioration of R.C. have no small effect on structural behavior of nuclear power plant structure. Therefore, aging deterioration of R.C. nuclear power plant structure should be considered for exact prediction of seismic responses of the structure. In this study, a machine learning model for seismic response prediction of nuclear power plant structure was developed by considering aging deterioration. The OPR-1000 was selected as an example structure for numerical simulation. The OPR-1000 was originally designated as the Korean Standard Nuclear Power Plant (KSNP), and was re-designated as the OPR-1000 in 2005 for foreign sales. 500 artificial ground motions were generated based on site characteristics of Korea. Elastic modulus, damping ratio, poisson's ratio and density were selected to consider material property variation due to aging deterioration. Six machine learning algorithms such as, Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Artificial Neural Networks (ANN), eXtreme Gradient Boosting (XGBoost), were used t o construct seispic response prediction model. 13 intensity measures and 4 material properties were used input parameters of the training database. Performance evaluation was performed using metrics like root mean square error, mean square error, mean absolute error, and coefficient of determination. The optimization of hyperparameters was achieved through k-fold cross-validation and grid search techniques. The analysis results show that neural networks present good prediction performance considering aging deterioration.