• Structural Engineering and Mechanics
• /
• 제17권3_4호
• /
• pp.483-492
• /
• 2004

This paper presents an efficient algorithm for the estimation of damage location and severity in bridge structures using Probabilistic Neural Network (PNN). Generally, the Back Propagation Neural Network (BPNN)-based damage detection methods need a lot of training patterns for neural network learning process and the optimum architecture of a BPNN is selected by trial and error. In this paper, the PNN instead of the conventional BPNN is used as a pattern classifier. The modal properties of damaged structure are somewhat different from those of undamaged one. The basic idea of proposed algorithm is that the PNN classifies a test pattern which consists of the modal characteristics from damaged structure, how close it is to each training pattern which is composed of the modal characteristics from various structural damage cases. In this algorithm, two PNNs are sequentially used. The first PNN estimates the damage location using mode shape and the results of the first PNN are put into the second PNN for the damage severity estimation using natural frequency. The proposed damage assessment algorithm using the PNN is applied to a cable-stayed bridge to verify its applicability.

• 한국농공학회논문집
• /
• 제54권4호
• /
• pp.65-71
• /
• 2012

The objective of this study was to estimate surface runoff from rice paddy plots using an artificial neural network (ANN). A field experiment with three treatment levels was conducted in the NICS saemangum experimental field located in Iksan, Korea. The ANN model with the optimal network architectures, named Paddy1901 with 19 input nodes, 1 hidden layer with 16 neurons nodes, and 1 output node, was adopted to predict surface runoff from the plots. The model consisted of 7 parameters of precipitation, irrigation rate, ponding depth, average temperature, relative humidity, wind speed, and solar radiation on the daily basis. Daily runoff, as the target simulation value, was computed using a water balance equation. The field data collected in 2011 were used for training and validation of the model. The model was trained based on the error back propagation algorithm with sigmoid activation function. Simulation results for the independent training and testing data series showed that the model can perform well in simulating surface runoff from the study plots. The developed model has a main advantage that there is no requirement for any prior assumptions regarding the processes involved. ANN model thus can be a good tool to predict surface runoff from rice paddy fields.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1997년도 춘계학술대회
• /
• pp.358-361
• /
• 1997

This paper describes a multichannel epileptic seizure detection algorithm based on wavelet transform(WT), artificial neural network(ANN) and expert system. First, through the WT, a small number of wavelet coefficients is used to represent the single channel epileptic spike. Next, 3-layer feed-forward network employing the error back propagation algorithm is trained and tested using parameters obtained above. Finally, 16 channel expert system which is based on clinical experience is introduced as a artifact rejection and reliable detection. The suggested algorithm was implemented on personal computer(PC). Two main events i.e., epileptiform and normal activities, were selected from 32 person's EEGs(normal: 20, seizure disorder: 12) in consensus among experts. The result was that WT reduced data input size and ANN detected 97 of the 100 EEGs containing definite spike - sensitivity of 97%. Expert rule system was capable of rejecting a wide variety of artifacts commonly found in EEG recordings. It also reduced false positive detections of ANN.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 B
• /
• pp.534-536
• /
• 1999

Fuzzy Systems which are based on membership functions and rules, can control nonlinear, uncertain, complex systems well. However, Fuzzy logic controller(FLC) has problems; It is difficult to design the stable FLC and FLC depends mainly on individual experience. Although FLC can be designed using the error back-propagation algorithm, it takes long time to converge into global, optimal parameters. Well-developed linear system theory should not be replaced by FLC, but instead, it should be suitably used with FLC. A new methodology is introduced for designing THEN-PART membership functions of FLC based on its well-tuned state feedback controller. A example of inverted pendulum is given for demonstration of the robustness of proposed methodology.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1992년도 하계학술대회 논문집 A
• /
• pp.225-230
• /
• 1992

In this paper, a new learning fuzzy logic controller(LFLC) is presented. The proposed controller is composed of the main control part and the learning part. The main control part is a fuzzy logic controller(FLC) based on linguistic rules and fuzzy inference. For the learning part, artificial neural network(ANN) is added to FLC so that the controller may adapt to unknown plant and environment. According to the output values of the ANN part, which is learned using error back-propagation algorithm, scale factors of the FLC part are determined. These scale factors transfer the range of values of input variables into corresponding universe of discourse in the FLC part in order to achieve good performance. The effectiveness of the proposed control strategy has been demonstrated through simulations involving the control of an unknown robot manipulator with load disturbance.

• 한국지능시스템학회논문지
• /
• 제16권4호
• /
• pp.472-478
• /
• 2006

본 논문에서는 기동표적의 추적에 대한 새로운 퍼지 뉴럴 네트워크 기반의 다중모델 기법을 소개한다. 표적의 가속도를 효과적으로 다루기 위하여, 이 논문에서는 표적의 가속도를 시변 변수인 표적의 추가적인 잡음으로 두고 각각의 가속도 간격의 정도에 따라 얻어지는 모든 잡음에 대한 변수에 의해 각각의 하부 모델들을 특성화시켰다. 모르는 가속도에 따른 시변 변수를 적응적으로 어립잡기는 어렵기 때문에 정밀한 계산을 위하여 퍼지 뉴럴 네트워크가 이용되었다. 퍼지 뉴럴 네트워크의 동정을 위해서는 오차 역전파 학습법을 사용하였다. 그리고 제안된 알고리즘의 수행 가능성을 보여주기 위하여 몇 가지 예를 제시하였다.

• 대한기계학회논문집A
• /
• 제23권11호
• /
• pp.1929-1939
• /
• 1999

This paper presents a neural network approach, which was named PRONET, to 3D object recognition and pose calculation. 3D objects are represented using a set of centroidal profile patterns that describe the boundary of the 2D views taken from evenly distributed view points. PRONET consists of the training stage and the execution stage. In the training stage, a three-layer feed-forward neural network is trained with the centroidal profile patterns using an error back-propagation method. In the execution stage, by matching a centroidal profile pattern of the given image with the best fitting centroidal profile pattern using the neural network, the identity and approximate orientation of the real object, such as a workpiece in arbitrary pose, are obtained. In the matching procedure, line-to-line correspondence between image features and 3D CAD features are also obtained. An iterative model posing method then calculates the more exact pose of the object based on initial orientation and correspondence.

• 한국공작기계학회논문집
• /
• 제10권2호
• /
• pp.38-47
• /
• 2001

In this paper, a new scheme of adaptive-neuro control system is presented to implement real-time control of robot manipulator using Digital Signal Processors. Digital signal processors, DSPs, are micro-processors that are particularly developed for fast numerical computations involving sums and products of measured variables, thus it can be programmed and executed through DSPs. In addition, DSPs are as fast in computation as most 32-bit micro-processors and yet at a fraction of therir prices. These features make DSPs a viable computational tool in digital implementation of sophisticated controllers. Unlike the well-established theory for the adaptive control of linear systems, there exists relatively little general theory for the adaptive control of nonlinear systems. Adaptive control technique is essential for providing a stable and robust perfor-mance for application of robot control. The proposed neuro control algorithm is one of learning a model based error back-propagation scheme using Lyapunov stability analysis method.The proposed adaptive-neuro control scheme is illustrated to be a efficient control scheme for the implementation of real-time control of robot system by the simulation and experi-ment.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2003년도 봄 학술발표회 논문집
• /
• pp.327-334
• /
• 2003

Thermal Prestressing Method for continuous composite girder bridges is a new design and construction method developed to induce initial composite stresses in the concrete slab at negative bending regions. Due to the induced initial stresses, prevention of tensile cracks at concrete slab, reduction of steel girder section, and reduction of reinforcing bars are possible. Thus, economical and construction efficiency can be improved. Method for determining optimum heating region of Thermal Prestressing Method, has not been established although such method is essential for increasing efficiency of the designing process. Trial-and-error method used in previous studies is far from efficient and more rational method for computing optimal heating region is required. In this study, efficient method for determining optimum heating region in the use of Thermal Prestressing Method is developed based on artificial neural network algorithm, which is widely adopted to pattern recognition, optimization, diagnosis, and estimation problems in various fields. Back-propagation algorithm, which is commonly used as a learning algorithm in neural network problems, is used for training of the neural network. Through case studies of 2-span continuous and 3-span continuous composite girder bridges using the developed process, the optimal heating regions are obtained.

• Structural Engineering and Mechanics
• /
• 제46권5호
• /
• pp.673-693
• /
• 2013

This paper presents a systematic design and training procedure for the feed-forward back-propagation neural network (NN) modeling of both forward and inverse behavior of a rotary magnetorheological (MR) damper based on experimental data. For the forward damper model, with damper force as output, an optimization procedure demonstrates accurate training of the NN architecture with only current and velocity as input states. For the inverse damper model, with current as output, the absolute value of velocity and force are used as input states to avoid negative current spikes when tracking a desired damper force. The forward and inverse damper models are trained and validated experimentally, combining a limited number of harmonic displacement records, and constant and half-sinusoidal current records. In general the validation shows accurate results for both forward and inverse damper models, where the observed modeling errors for the inverse model can be related to knocking effects in the measured force due to the bearing plays between hydraulic piston and MR damper rod. Finally, the validated models are used to emulate pure viscous damping. Comparison of numerical and experimental results demonstrates good agreement in the post-yield region of the MR damper, while the main error of the inverse NN occurs in the pre-yield region where the inverse NN overestimates the current to track the desired viscous force.