• Structural Engineering and Mechanics
• /
• 제83권2호
• /
• pp.273-282
• /
• 2022

In this paper, we propose a new concept for error estimation in finite element solutions, which we call mode-based error estimation. The proposed error estimation predicts a posteriori error calculated by the difference between the direct finite element (FE) approximation and the recovered FE approximation. The mode-based FE formulation for the recently developed self-updated finite element is employed to calculate the recovered solution. The formulation is constructed by searching for optimal bending directions for each element, and deep learning is adopted to help find the optimal bending directions. Through various numerical examples using four-node quadrilateral finite elements, we demonstrate the improved predictive capability of the proposed error estimator compared with other competitive methods.

• 한국학교수학회논문집
• /
• 제11권3호
• /
• pp.513-541
• /
• 2008

본 연구의 목적은 8학년 학생들의 사각형 학습 및 기하학적 추론 능력의 발달을 위해서 GSP의 사용이 자와 각도기 같은 전통적인 도구의 사용보다 더 효과적인지를 탐구하고, 어떻게 그 소프트웨어의 사용이 학생들의 사각형 학습과 추론 능력의 발달에 영향을 끼치는지를 조사하는 것이다. 사후 학업 성취도 검사 결과에 의하면 GSP를 사용한 집단과 자와 각도기를 사용한 집단의 평균 성적에서 통계적으로 유의미한 차이가 발견되었다. GSP를 사용한 집단이 자와 각도기를 사용한 집단보다 유의미하게 높은 평균 성적을 보여주었다. 학생 면접 결과에 의하면, GSP의 사용이 학생들의 기하학적 추론 능력을 발달시키는데 더 효과적이었다. GSP를 사용한 집단의 학생들이 자와 각도기를 사용한 집단의 학생들보다 van Hiele 2와 3수준에서 더 높은 정도의 달성도를 보여주었다. GSP가 제공하는 수학적 개념에 대한 역동적인 시각적 효과와 조작 경험이 학생들이 사각형 학습을 개념적으로 접근하도록 하는데 중요한 역할을 하였고, 그런 경험들이 학생들이 기존에 갖고 있던 수학적 개념에 처한 오류를 확인하고 개념을 재정립하는데 도움을 주었다.

• Advances in nano research
• /
• 제14권1호
• /
• pp.17-25
• /
• 2023

Gold nanoparticles have recognized a promising drug carriers in many diseases. These nanoparticles could carry anti-inflammatory drugs in the case of muscle injury and for fatigue relief. On the other hand, specific surface of this kind of nanoparticles could be critical in amount of drug they could carry. Therefore, in this study, we explore different methodology and influencing parameters on the specific surface of gold nanoparticles. After specifying the main parameters, different machine learning and artificial neural network are adopted to model the effects of different parameters. Furthermore, response surface methodology is utilized to obtain a quadrilateral relationship between different parameters and specific surface. The results indicate that concentration of the gold salt solution is the most important parameter in increasing the size of gold nanoparticle and, as a consequence, increasing specific surface. Moreover, the ability of gold nanoparticles in prolonging retention of the drugs is discussed in detail.

• Steel and Composite Structures
• /
• 제46권3호
• /
• pp.319-334
• /
• 2023

Localizing damages is an essential task to monitor the health of the structures since they may not be able to operate anymore. Among the damage detection techniques, non-destructive methods are considerably more preferred than destructive methods since damage can be located without affecting the structural integrity. However, these methods have several drawbacks in terms of detecting abilities, time consumption, cost, and hardware or software requirements. Employing artificial intelligence techniques could overcome such issues and could provide a powerful damage detection model if the technique is utilized correctly. In this study, the crack localization in flat and folded plate structures has been conducted by employing a Backpropagated Artificial Neural Network (BPANN). For this purpose, cracks with 18 different dimensions in thin, flat, and folded structures having 15⁰, 30⁰, 45⁰, and 60⁰ folding angle have been modeled and subjected to free vibration analysis by employing the Classical Plate Theory with Finite Element Method. A Four-nodded quadrilateral element having six degrees of freedom has been considered to represent those structures mathematically. The first ten natural frequencies have been obtained regarding healthy and cracked structures. To localize the crack, the ratios of the frequencies of the cracked flat and folded structures to those of healthy ones have been taken into account. Those ratios have been given to BPANN as the input variables, while the crack locations have been considered as the output variables. A total of 500 crack locations have been regarded within the dataset obtained from the results of the free vibration analysis. To build the best intelligent model, a feature search has been conducted for BAPNN regarding activation function, the number of hidden layers, and the number of hidden neurons. Regarding the analysis results, it is concluded that the BPANN is able to localize the cracks with an average accuracy of 95.12%.