• 한국강구조학회 논문집
• /
• 제15권4호통권65호
• /
• pp.413-422
• /
• 2003

구조 설계를 위해 초기 부재를 가정할 때나 건축 실무에서 개산 견적을 계산할 때 기술자의 직관이나 비슷한 조건의 기존 설계 평균값을 사용하고 있으나 설계 조건은 모두 다르기 때문에 큰 오차가 발생할 수밖에 없다. 이러한 문제점을 해결하기 위해서 확률론적인 절차가 내재되어 있어 불확실성을 다룰 수 있는 인공 신경 회로망의 이용하여 와렌 트러스를 설계하므로써 적용성을 평가하였다. 제안된 신경망 설계변수값와 구조설계 단계에 따라 다양한 와렌 트러스를 설계하여 MIDAS 프로그램 설계결과의 10% 오차 이내로 근사 설계를 하므로써 모델의 타당성을 검증하였다. 제안된 모델은 약간의 오차를 포함하지만 적은 시간과 노력으로 신뢰할 수 있는 설계 결과를 얻을 수 있으며, 부재 테이블을 사용하는 비선형 관계의 구조설계에도 적용 가능한 특성을 가지고 있다.

• Computers and Concrete
• /
• 제8권2호
• /
• pp.125-142
• /
• 2011

In the present paper, a numerical simulation method based on mesoscopic composite structure of concrete, the truss network model, is developed to evaluate the diffusivity of concrete in order to account for the microstructure of concrete, the binding effect of chloride ions and the chloride concentration dependence. In the model, concrete is described as a three-phase composite, consisting of mortar, coarse aggregates and the interfacial transition zones (ITZs) between them. The advantage of the current model is that it can easily represent the movement of mass (e.g. water or chloride ions) through ITZs or the potential cracks within concrete. An analytical method to estimate the chloride diffusivity of mortar and ITZ, which are both treated as homogenious materials in the model, is introduced in terms of water-to-cement ratio (w/c) and sand volume fraction. Using the newly developed approaches, the effect of cracking of concrete on chloride diffusion is reflected by means of the similar process as that in the test. The results of calculation give close match with experimental observations. Furthermore, with consideration of the binding capacity of chloride ions to cement paste and the concentration dependence for diffusivity, the one-dimensional nonlinear diffusion equation is established, as well as its finite difference form in terms of the truss network model. A series of numerical analysises performed on the model find that the chloride diffusion is substantially influenced by the binding capacity and concentration dependence, which is same as that revealed in some experimental investigations. This indicates the necessity to take into account the binding capacity and chloride concentration dependence in the durability analysis and service life prediction of concrete structures.

• International Journal of Aeronautical and Space Sciences
• /
• 제18권4호
• /
• pp.651-661
• /
• 2017

A truss-braced wing (TBW) aircraft has recently received increasing attention due to higher aerodynamic efficiency compared to conventional cantilever wing aircraft. For conceptual TBW aircraft design, we developed a propulsion-and-airframe integrated design environment by replacing a semi-empirical turbofan engine model with a thermodynamic cycle-based one built upon the numerical propulsion system simulation (NPSS). The constructed NPSS model benefitted TBW aircraft design study, as it could handle engine installation effects influencing engine fuel efficiency. The NPSS model also contributed to broadening TBW aircraft design space, for it provided turbofan engine design variables involving a technology factor reflecting progress in propulsion technology. To effectively consolidate the NPSS propulsion model with the TBW airframe model, we devised a rapid, approximate substitute of the NPSS model by reduced-order modeling (ROM) to resolve difficulties in model integration. In addition, we formed an artificial neural network (ANN) that associates engine component attributes evaluated by object-oriented weight analysis of turbine engine (WATE++) with engine design variables to determine engine weight and size, both of which bring together the propulsion and airframe system models. Through propulsion-andairframe design space exploration, we optimized TBW aircraft design for fuel saving and revealed that a simple engine model neglecting engine installation effects may overestimate TBW aircraft performance.

• Structural Engineering and Mechanics
• /
• 제44권3호
• /
• pp.379-403
• /
• 2012

In recent years, the need for optimal design of structures under time-history loading aroused great attention in researchers. The main problem in this field is the extremely high computational demand of time-history analyses, which may convert the solution algorithm to an illogical one. In this paper, a new framework is developed to solve the size optimization problem of steel truss structures subjected to ground motions. In order to solve this problem, the covariance matrix adaptation evolution strategy algorithm is employed for the optimization procedure, while a generalized regression neural network is utilized as a meta-model for fitness approximation. Moreover, the computational cost of time-history analysis is decreased through a wavelet analysis. Capability and efficiency of the proposed framework is investigated via two design examples, comprising of a tower truss and a footbridge truss.

• Smart Structures and Systems
• /
• 제26권1호
• /
• pp.35-47
• /
• 2020

This paper proposes the use of transmissibility functions combined with a machine learning algorithm, Artificial Neural Networks (ANNs), to assess damage in a truss bridge. A new approach method, which makes use of the input parameters calculated from the transmissibility function, is proposed. The network not only can predict the existence of damage, but also can classify the damage types and identity the location of the damage. Sensors are installed in the truss joints in order to measure the bridge vibration responses under train and ambient excitations. A finite element (FE) model is constructed for the bridge and updated using FE software and experimental data. Both single damage and multiple damage cases are simulated in the bridge model with different scenarios. In each scenario, the vibration responses at the considered nodes are recorded and then used to calculate the transmissibility functions. The transmissibility damage indicators are calculated and stored as ANNs inputs. The outputs of the ANNs are the damage type, location and severity. Two machine learning algorithms are used; one for classifying the type and location of damage, whereas the other for finding the severity of damage. The measurements of the Nam O bridge, a truss railway bridge in Vietnam, is used to illustrate the method. The proposed method not only can distinguish the damage type, but also it can accurately identify damage level.

• Smart Structures and Systems
• /
• 제10권6호
• /
• pp.557-572
• /
• 2012

This paper focuses on the vibration control of long-span reticulated steel structures under multi-dimensional earthquake excitation. The control system and strategy are constructed based on Magneto-Rheological (MR) dampers. The LQR and Hrovat controlling algorithm is adopted to determine optimal MR damping force, while the modified Bingham model (MBM) and inverse neural network (INN) is proposed to solve the real-time controlling current. Three typical long-span reticulated structural systems are detailedly analyzed, including the double-layer cylindrical reticulated shell, single-layer spherical reticulated shell, and cable suspended arch-truss structure. Results show that the proposed control strategy can reduce the displacement and acceleration effectively for three typical structural systems. The displacement control effect under the earthquake excitation with different PGA is similar, while for the cable suspended arch-truss, the acceleration control effect increase distinctly with the earthquake excitation intensity. Moreover, for the cable suspended arch-truss, the strand stress variation can also be effectively reduced by the MR dampers, which is very important for this kind of structure to ensure that the cable would not be destroyed or relaxed.

• 한국농공학회논문집
• /
• 제49권6호
• /
• pp.37-46
• /
• 2007

In designing the structure, the stress path is the basic data. But the stress path is not standardized to analysis the structure. So the one-dimensional frame element structure model with the triangle irregular network is used to solve the problem. And the refined evolutionary structural optimization(RESO) used in structural topology optimization is applied to this study. Through this process, the search method of the stress path is advanced and the burden of the calculation. is reduced.

• 한국농공학회논문집
• /
• 제46권4호
• /
• pp.65-71
• /
• 2004

Stress Path Search Model of Evolutionary Structural Successive Optimization (SPSMESO) using Triangular Irregular Network(TIN) was developed for improving over burden at initial design of ESO and strict stress direction of strut-and-tie model and truss model. TIN was applied for discretizing structures in flexible stress path and segments of TIN was analyzed as one-dimensional line element for calculating stress. Finally, stress path was searched using ESO algorithm. SPSMESO was efficient to express the direction of stress for 2D structure and time saving.

• Smart Structures and Systems
• /
• 제30권6호
• /
• pp.673-686
• /
• 2022

Deep learning algorithms for Structural Health Monitoring (SHM) have been extracting the interest of researchers and engineers. These algorithms commonly used loss functions and evaluation indices like the mean square error (MSE) which were not originally designed for SHM problems. An updated loss function which was specifically constructed for deep-learning-based structural damage detection problems has been proposed in this study. By tuning the coefficients of the loss function, the weights for damage localization and quantification can be adapted to the real situation and the deep learning network can avoid unnecessary iterations on damage localization and focus on the damage severity identification. To prove efficiency of the proposed method, structural damage detection using convolutional neural networks (CNNs) was conducted on a truss bridge model. Results showed that the validation curve with the updated loss function converged faster than the traditional MSE. Data augmentation was conducted to improve the anti-noise ability of the proposed method. For reducing the training time, the normalized modal strain energy change (NMSEC) was extracted, and the principal component analysis (PCA) was adopted for dimension reduction. The results showed that the training time was reduced by 90% and the damage identification accuracy could also have a slight increase. Furthermore, the effect of different modes and elements on the training dataset was also analyzed. The proposed method could greatly improve the performance for structural damage detection on both the training time and detection accuracy.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2007년도 정기 학술대회 논문집
• /
• pp.141-144
• /
• 2007

Given a number of training data, a traditional BPN is normally trained by minimizing the absolute difference between target outputs and approximate outputs. When BPN is used as a meta-model for inequality constraint function, approximate optimal solutions are sometimes actually infeasible in a case where they are active at the constraint boundary. The paper describes the development of the efficient BPN based meta-model that enhances the constraint feasibility of approximate optimal solution. The modified BPN based meta-model is obtained by including the decision condition between lower/upper bounds of a constraint and an approximate value. The proposed approach is verified through a simple mathematical function and a ten-bar planar truss problem.