• Computers and Concrete
• /
• 제20권6호
• /
• pp.627-634
• /
• 2017

Predicting the compressive strength of concrete is important to assess the load-carrying capacity of a structure. However, the use of blended cements to accrue the technical, economic and environmental benefits has increased the complexity of prediction models. Artificial Neural Networks (ANNs) have been used for predicting the compressive strength of ordinary Portland cement concrete, i.e., concrete produced without the addition of supplementary cementing materials. In this study, models to predict the compressive strength of blended cement concrete prepared with a natural pozzolan were developed using regression models and single- and 2-phase learning ANNs. Back-propagation (BP), Levenberg-Marquardt (LM) and Conjugate Gradient Descent (CGD) methods were used for training the ANNs. A 2-phase learning algorithm is proposed for the first time in this study for predictive modeling of the compressive strength of blended cement concrete. The output of these predictive models indicates that the use of a 2-phase learning algorithm will provide better results than the linear regression model or the traditional single-phase ANN models.

• 한국정보시스템학회지:정보시스템연구
• /
• 제30권4호
• /
• pp.203-226
• /
• 2021

Purpose The purpose of this study is to enhance the accuracy score of personal credit scoring using the convolutional neural networks and secure the transparency of the deep learning model using eXplainalbe Artifical Inteligence(XAI) technique. Design/methodology/approach This study built a classification model by using the convolutional neural networks(CNN) and applied a methodology that is transformation of numerical data to imaged data to apply CNN on personal credit data. Then layer-wise relevance propagation(LRP) was applied to model we constructed to find what variables are more influenced to the output value. Findings According to the empirical analysis result, this study confirmed that accuracy score by model using CNN is highest among other models using logistic regression, neural networks, and support vector machines. In addition, With the LRP that is one of the technique of XAI, variables that have a great influence on calculating the output value for each observation could be found.

• Nuclear Engineering and Technology
• /
• 제53권2호
• /
• pp.522-531
• /
• 2021

We describe a new deep learning model - Convolutional eXtreme Gradient Boosting (ConvXGB) for classification problems based on convolutional neural nets and Chen et al.'s XGBoost. As well as image data, ConvXGB also supports the general classification problems, with a data preprocessing module. ConvXGB consists of several stacked convolutional layers to learn the features of the input and is able to learn features automatically, followed by XGBoost in the last layer for predicting the class labels. The ConvXGB model is simplified by reducing the number of parameters under appropriate conditions, since it is not necessary re-adjust the weight values in a back propagation cycle. Experiments on several data sets from UCL Repository, including images and general data sets, showed that our model handled the classification problems, for all the tested data sets, slightly better than CNN and XGBoost alone and was sometimes significantly better.

• Computers and Concrete
• /
• 제28권6호
• /
• pp.635-642
• /
• 2021

In this paper, soft learning techniques are used to predict the ultimate torsional capacity of Reinforced Concrete beams strengthened with Fiber Reinforced Polymer. Soft computing techniques, namely Artificial Neural Network, trained by various back propagation algorithms, and Particle Swarm Optimization (PSO) algorithm, have been used to model and predict the torsional strength of Reinforced Concrete beams strengthened with Fiber Reinforced Polymer. The performance of each model has been evaluated by using statistical parameters such as coefficient of determination (R²), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE). The hybrid PSO NN model resulted in an R² of 0.9292 with an RMSE of 5.35 for training and an R² of 0.9328 with an RMSE of 4.57 for testing. Another model, ANN BP, produced an R² of 0.9125 with an RMSE of 6.17 for training and an R² of 0.8951 with an RMSE of 5.79 for testing. The results of the PSO NN model were in close agreement with the experimental values. Thus, the PSO NN model can be used to predict the ultimate torsional capacity of RC beams strengthened with FRP with greater acceptable accuracy.

• International Journal of Korean Welding Society
• /
• 제1권1호
• /
• pp.17-22
• /
• 2001

Because the quantitative relationships between welding parameters and welding result are not yet blown, optimal values of welding parameters for $CO_2$ robotic arc welding is a difficult task. Using the various artificial data processing methods may solve this difficulty. This research aims to develop an expert system for $CO_2$ robotic arc welding to recommend the optimal values of welding parameters. This system has three main functions. First is the recommendation of reasonable values of welding parameters. For such work, the relationships in between the welding parameters are investigated by the use of regression analysis and fuzzy system. The second is the estimation of bead shape by a neural network system. In this study the welding current voltage, speed, weaving width, and root gap are considered as the main parameters influencing a bead shape. The neural network system uses the 3-layer back-propagation model and a generalized delta rule as teaming algorithm. The last is the optimization of the parameters for the correction of undesirable weld bead. The causalities of undesirable weld bead are represented in the form of rules. The inference engine derives conclusions from these rules. The conclusions give the corrected values of the welding parameters. This expert system was developed as a PC-based system of which can be used for the automatic or semi-automatic $CO_2$ fillet welding with 1.2, 1.4, and 1.6mm diameter the solid wires or flux-cored wires.

• 한국해양공학회지
• /
• 제38권3호
• /
• pp.103-114
• /
• 2024

Remote sensing wave observation data are crucial when analyzing ocean waves, the main external force of coastal disasters. Nevertheless, it has limitations in accuracy when used in low-wind environments. Therefore, this study collected the raw data from MIROS Wave and Current Radar (MWR) and wave radar at the Ieodo Ocean Research Station (IORS) and applied the optimal filter by combining filters provided by MIROS software. The data were validated by a comparison with South Jeju ocean buoy data. The results showed it maintained accuracy for significant wave height, but errors were observed in significant wave periods and extreme waves. Hence, this study used an artificial neural network (ANN) to improve these errors. The ANN was generalized by separating the data into training and test datasets through stratified sampling, and the optimal model structure was derived by adjusting the hyperparameters. The application of ANN effectively improved the accuracy in significant wave periods and high wave conditions. Consequently, this study reproduced past wave data by enhancing the reliability of the MWR, contributing to understanding wave generation and propagation in storm conditions, and improving the accuracy of wave prediction. On the other hand, errors persisted under high wave conditions because of wave shadow effects, necessitating more data collection and future research.

• Wind and Structures
• /
• 제38권1호
• /
• pp.75-91
• /
• 2024

Reliable wind signal reconstruction can be beneficial to the operational safety of long-span bridges. Non-Gaussian characteristics of wind signals make the reconstruction process challenging. In this paper, non-Gaussian wind signals are converted into a combined prediction of two kinds of features, actual wind speeds and wind angles of attack. First, two decomposition techniques, empirical mode decomposition (EMD) and variational mode decomposition (VMD), are introduced to decompose wind signals into intrinsic mode functions (IMFs) to reduce the randomness of wind signals. Their principles and applicability are also discussed. Then, four artificial intelligence (AI) algorithms are utilized for wind signal reconstruction by combining the particle swarm optimization (PSO) algorithm with back propagation neural network (BPNN), support vector regression (SVR), long short-term memory (LSTM) and bidirectional long short-term memory (Bi-LSTM), respectively. Measured wind signals from a bridge site in a deep-cutting gorge are taken as experimental subjects. The results showed that the reconstruction error of high-frequency components of EMD is too large. On the contrary, VMD fully extracts the multiscale rules of the signal, reduces the component complexity. The combination of VMD-PSO-Bi-LSTM is demonstrated to be the most effective among all hybrid models.

• Computers and Concrete
• /
• 제34권4호
• /
• pp.427-446
• /
• 2024

The I-shaped steel reinforced recycled aggregate concrete (SRRC) composite structure has the advantages of high bearing capacity and environmental protection, and the interfacial bond strength is an important theory. To this end, the I-shaped SRRC bond strength and its calculation based on artificial neural network (ANN) will be studied. Firstly, 39 push out tests of I-shaped SRRC were conducted, the load-slip curve has obvious regularity, which is divided into 4 segments by 3 regular points. Three bond strengths were defined based on these three rule points, and the approximate ranges of their values and the laws of influence of each factor on them were found. Secondly, the Elman ANN model used for the prediction of bond strength was established, and the parameters of Elman ANN predicting I-shaped SRRC bond strength were studied, and the effects of detailed parameters on the prediction results were revealed. Finally, the bond strength of SRRC was predicted using Elman and BP (back propagation) neural network models, both of which showed good prediction results. This study is a theoretical basis for the design and fine simulation of I-shaped SRRC composite structures.

• 한국수자원학회논문집
• /
• 제31권1호
• /
• pp.13-25
• /
• 1998

신경회로망은 어떤 사상에 대한 인과관계를 연상기억능력을 통하여 인식할 수 있는 기능을 가지고 있을 뿐 아니라 비선형현상에 대한 적응능력이 뛰어나 수문계의 강우-유출 현상에 대한 적용가능성은 많으나 이를 수문학적으로 검증하는데는 아직 검토단계라 할 수 있으며 적용에 따른 방법론에 대한 연구가 필요하다 할 수있다. 본 연구에서는 하천유역에서 호우의 발생에 따른 하천의 홍수유출수문곡선을 모의하기 위한 블랙박스모형으로서 신경회로망이론의 적용에 따른 문제를 수문학적으로 규명하고자 하였다. 이를 위한 방법으로서 홍수발생의 직접적인 원인인 강우패턴을 신경회로망의 입력패턴으로하고 이에 따른 출력패턴을 유출수문곡선이라는 가정하에 신경회로망모형을 구성하고 평창강유역에서 발생된 과거 홍수기록자료를 이용하여 그 결과를 제시하였다. 본 연구결과에 의하면 신경회로망의 학습이 수행되는 동안 어떠한 형태로든 수문학적 개념을 토대로 구성된 모형의 구조에 잘 적응되고 있음을 알수 있었다. 이 결과를 토대로 지금까지 복잡한 과정을 거쳐야하는 강우-유출 모형화 과정에서 발생되는 문제점들을 효율적으로 해결할 수 있는 접근방법으로서 활용될수 있을 것으로 기대된다.

• 터널과지하공간
• /
• 제28권6호
• /
• pp.692-705
• /
• 2018

발파를 이용한 터널의 굴착 시 수반되는 가장 큰 문제 중 하나는 발파 시 발생하는 지반진동으로 이를 저감시키기 위한 노력의 일환으로 와이어쏘 장비를 이용하여 터널 심발공 주변에 인공 자유면을 형성하고 이를 통해 파쇄도를 향상시키며 동시에 발파 진동을 저감시키는 기술이 개발되어 오고 있다. 본 연구에서는, 실규모 발파 실험 및 3D-DFPA 해석 기법을 통해 인공 자유면의 구조조건에 따른 진동저감 및 발파 효과에 대한 고찰을 수행하였으며, 이에 더불어 인공 자유면 발파에서의 효율적 설계를 위한 경험적 기준을 제안하였다. 분석 결과, 인공 슬롯 자유면은 홉킨슨 효과에 의한 스폴파괴 유발 및 충격진동의 전파경로 차단 등 발파 진동 저감을 야기하는 것으로 판단되었으며, 인공 자유면이 존재하는 경우, 존재하지 않는 경우에 비해 파쇄체적 및 파쇄효율이 모두 증가하는 경향을 보였다. 이는 인공 자유면이 실제 자유면과 동일한 역할을 수행함에 따라 최소저항선의 감소효과를 야기하는 것으로 판단되었으며, 실험 결과를 토대로 발파 공경 및 최소저항선에 대한 발파 파쇄체적의 상관관계를 도출 및 경험적 설계 기준을 제안하였다. 결론적으로, 인공 자유면 발파를 수행 시 발파 공경 대 최소저항선의 비가 약 5에서 8사이의 값을 갖도록 설계하는 것이 가장 이상적인 표준발파 조건에서의 파쇄효과를 기대할 수 있을 것으로 판단되었다.