• Geomechanics and Engineering
• /
• v.12 no.3
• /
• pp.441-464
• /
• 2017

The determination of the mixture parameters of stabilization has become a great concern in geotechnical applications. This paper presents an effort about the application of artificial intelligence (AI) techniques including radial basis neural network (RBNN), multi-layer perceptrons (MLP), generalized regression neural network (GRNN) and adaptive neuro-fuzzy inference system (ANFIS) in order to predict the unconfined compressive strength (UCS) of silty soil stabilized with bottom ash (BA), jute fiber (JF) and steel fiber (SF) under different freeze-thaw cycles (FTC). The dosages of the stabilizers and number of freeze-thaw cycles were employed as input (predictor) variables and the UCS values as output variable. For understanding the dominant parameter of the predictor variables on the UCS of stabilized soil, a sensitivity analysis has also been performed. The performance measures of root mean square error (RMSE), mean absolute error (MAE) and determination coefficient ($R^2$) were used for the evaluations of the prediction accuracy and applicability of the employed models. The results indicate that the predictions due to all AI techniques employed are significantly correlated with the measured UCS ($p{\leq}0.05$). They also perform better predictions than nonlinear regression (NLR) in terms of the performance measures. It is found from the model performances that RBNN approach within AI techniques yields the highest satisfactory results (RMSE = 55.4 kPa, MAE = 45.1 kPa, and $R^2=0.988$). The sensitivity analysis demonstrates that the JF inclusion within the input predictors is the most effective parameter on the UCS responses, followed by FTC.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.5
• /
• pp.645-652
• /
• 2011

The present study investigated the tracking system of a reflector to trace the movement of sun. The system was designed to minimize the error between the vertical vector of reflector and the position of sun. The proposed system was able to collect the sun lights at a point as a useful source of light energy and transmit the collected light to a remote area through optical fibers. Also the study successfully solved the controller design problem due to the complexity of modeling of the sun tracking system using a fuzzy logic controller which mimics human reasoning.

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.11
• /
• pp.936-942
• /
• 2005

Recently the exoskeletal power assistive equipment which is a kind of wearable robot has been widely developed to help the human body motion. For the elderly people and patients, however, some limits exist due to the weight and volume of the equipments. As a feasible solution, a tendon-driven exoskeletal power assistive device fur the lower body, and caster walker are proposed in this research. Since the caster walker carries the heavy items, the weight and volume of the wearable exoskeleton are minimized. The key control is used to generate the joint torque required to assist motions such as sitting, standing and walking. Experiments were performed for several motions and the EMG sensors were used to measure the magnitude of assistance. When the motion of sitting down and standing up was compared with and without wearing the proposed device, the $25\%$ assistance was acquired.

• Fibers and Polymers
• /
• v.6 no.4
• /
• pp.348-354
• /
• 2005

These days consumers' various demands are accelerating research on apparel manufacturing system including automatic measurement, pattern generation, and clothing simulation. Accordingly, methods of reconstructing human body from point-clouds measured using a three dimensional scanning device are required for apparel CAD system to support these functions. In particular, we present in this study a human body reconstruction method focused on two issues, which are the decision of the number of control point for each sectional curve with error bound and the local knot removal for reducing the unusual concentration of control points. The approximation of sectional curves with error bounds as an approximation criterion leads all sectional curves to their own particular shapes apart from the number of control points. In addition, the application of the local knot removal to construction of human body sectional curves reduces the unusual concentration of control points effectively. The results may be used to produce an apparel CAD system as an automatic pattern generation system and a clothing simulation system through the low level control of NUBS or NURBS.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.4 no.2
• /
• pp.172-175
• /
• 2004

Generally, the yield rate of semiconductors is the major factor that affects directly the price of semiconductors. For a high yield rate of semiconductors, the air inside clean room is needed to be purified and high efficient filters are used for this. The filter are made of super-fine fiber and certain pinholes can be easily produced on the filter's surface by inadvertent manufacturing. As these pinholes are not easily detected with the bare sight, these pinholes exert a negative impact to filtration performance of the filter. In this research, not only the automatic test equipment for detecting pinholes is proposed, but also inverse modeling scheme based on artificial neural network is applied for tuning of its important parameters.

• Ocean Systems Engineering
• /
• v.14 no.1
• /
• pp.73-84
• /
• 2024

In order to achieve the best performance, the automatic control with advanced technology is made of sheathed steel to withstand a wide range of wave loads. This model shows how to control the vibration of the fiber panel as a solution using the new results from the Lyapunov stability question, a modification of the bat that making it easy to calculate and easy to use. It is used to reduce the storage space required in this system. The results show that the planned worker can compensate effectively for the unplanned delay. The results show that the proposed controller can compensate for delays and errors. Fuzzy control (predictive control) demonstrated the external vibration can be reduced.

• Journal of the Korea Concrete Institute
• /
• v.22 no.1
• /
• pp.19-27
• /
• 2010

Aging and severe environments are major causes of damage in reinforced concrete (RC) structures such as buildings and bridges. Deterioration such as concrete cracks, corrosion of steel, and deformation of structural members can significantly degrade the structural performance and safety. Therefore, effective and easy-to-use methods are desired for repairing and strengthening such concrete structures. Various methods for strengthening and rehabilitation of RC structures have been developed in the past several decades. Recently, FRP composite materials have emerged as a cost-effective alternative to the conventional materials for repairing, strengthening, and retrofitting deteriorating/deficient concrete structures, by externally bonding FRP laminates to concrete structural members. The main purpose of this study is to investigate the effectiveness of adaptive neuro-fuzzy inference system (ANFIS) in predicting behavior of circular type concrete column retrofitted with FRP. To construct training and testing dataset, experiment results for the specimens which have different retrofit profile are used. Retrofit ratio, strength of existing concrete, thickness, number of layer, stiffness, ultimate strength of fiber and size of specimens are selected as input parameters to predict strength, strain, and stiffness of post-yielding modulus. These proposed ANFIS models show reliable increased accuracy in predicting constitutive properties of concrete retrofitted by FRP, compared to the constitutive models suggested by other researchers.

• Computers and Concrete
• /
• v.16 no.3
• /
• pp.399-414
• /
• 2015

Nowadays, fiber reinforced polymer (FRP) composites are widely used for rehabilitation, repair and strengthening of reinforced concrete (RC) structures. Also, recent advances in concrete technology have led to the production of high strength concrete, HSC. Such concrete due to its very high compression strength is less ductile; so in seismic areas, ductility is an important factor in design of HSC members (especially FRP strengthened members) under flexure. In this study, the Adaptive Neuro-Fuzzy Inference System (ANFIS) and multiple regression analysis are used to predict the curvature ductility factor of FRP strengthened reinforced HSC (RHSC) beams. Also, the effects of concrete strength, steel reinforcement ratio and externally reinforcement (FRP) stiffness on the complete moment-curvature behavior and the curvature ductility factor of the FRP strengthened RHSC beams are evaluated using the analytical approach. Results indicate that the predictions of ANFIS and multiple regression models for the curvature ductility factor are accurate to within -0.22% and 1.87% error for practical applications respectively. Finally, the effects of height to wide ratio (h/b) of the cross section on the proposed models are investigated.

• Proceedings of the KIEE Conference
• /
• 2007.11a
• /
• pp.242-243
• /
• 2007

본 논문은 1310nm 단일모드 광섬유를 이용하여 온도센서로 활용하기 위한 연구이다. 기존광섬유센서의 연구는 복잡한 여러 가지 기기를 이용하여 구성된 시스템이었다. 그리고 산란 변화를 주기 위하여 Bragg 격자나 Pulse generator를 이용하여 광주파수의 변화를 측정하거나, YAG 레이저를 이용 벌크형 시스템을 택하여 구성하였는데 실험 환경을 구성하는 어려움과 측정된 데이터의 정확도에 대한 문제점이 있었다. 본 연구에서 제안한 유도 브릴루앙 산란(sBs: stimulated Brillouin scattering)광을 이용한 온도센서 시스템은 기존의 측정방식 보다 간소화된 직렬방식의 시스템이다. 광주파수에서 발생하는 노이즈와 애매한 결과에 대해서 신뢰성과 정확도를 확보하기 위하여 지능형인 뉴로-퍼지 알고리즘을 이용하여 분석함으로써 기존 시스템 보다 정확한 데이터를 얻고자 하였다. 본 연구에서 sBs는 빛의 산란 특성 중 광주파수가 온도에 변화에 대해 각각의 온도 변화당 천이가 이루어졌음을 측정하였다. 시스템에서 출력된 데이터를 뉴로-퍼지로 분석한 변화율은 1.1MHz/의 결과를 얻었다.

• Smart Structures and Systems
• /
• v.18 no.3
• /
• pp.525-540
• /
• 2016

The CFRP-confined circular concrete-filled steel tubular column is composed of concrete, steel, and CFRP. Its failure mechanics are complex. The most important difficulties are lack of an available method to establish a relationship between a specific damage mechanism and its acoustic emission (AE) characteristic parameter. In this study, AE technique was used to monitor the evolution of damage in CFRP-confined circular concrete-filled steel tubular columns. A fuzzy c-means method was developed to determine the relationship between the AE signal and failure mechanisms. Cluster analysis results indicate that the main AE sources include five types: matrix cracking, debonding, fiber fracture, steel buckling, and concrete crushing. This technology can not only totally separate five types of damage sources, but also make it easier to judge the damage evolution process. Furthermore, typical damage waveforms were analyzed through wavelet analysis based on the cluster results, and the damage modes were determined according to the frequency distribution of AE signals.