• 제어로봇시스템학회논문지
• /
• 제3권3호
• /
• pp.252-258
• /
• 1997

This paper presents neural networks for hybrid position/force control which is a type of position and force control for robot manipulators. The performance of conventional hybrid position/force control is excellent in the case of the exactly-known dynamic model of the robot, but degrades seriously as the uncertainty of the model increases. Hence, the neural network control scheme is presented here to overcome such shortcoming. The introduced neural term is designed to learn the uncertainty of the robot, and to control the robot through uncertainty compensation. Further more, the learning rule of the neural network is derived and is shown to be effective in the sense that it requires neither desired output of the network nor error back propagation through the plant. The proposed scheme is verified through the simulation of hybrid position/force control of a 6-dof robot manipulator.

• Structural Engineering and Mechanics
• /
• 제26권4호
• /
• pp.377-392
• /
• 2007

A discrete sliding mode control (SMC) method based on hybrid model of neural network and nominal model is proposed to reduce the vibration of flexible structures, which is a robust active controller developed by using a sliding manifold approach. Since the thick boundary layer will reduce the virtue of SMC, the multilayer feed-forward neural network is adopted to model the uncertainty part. The neural network is trained by Levenberg-Marquardt backpropagation. The design objective of the sliding mode surface is based on the quadratic optimal cost function. In course of running, the input signal of SMC come from the hybrid model of the nominal model and the neural network. The simulation shows that the proposed control scheme is very effective for large uncertainty systems.

• International Journal of Aeronautical and Space Sciences
• /
• 제16권4호
• /
• pp.510-519
• /
• 2015

Concerning the issue of high-dimensions, hybrid uncertainties of randomness and intervals including implicit and highly nonlinear limit state function, reliability analysis based on the hybrid uncertainty reliability mode combining with back propagation neural network (HU-BP neural network) is proposed in this paper. Random variables and interval variables are as input layer of the neural network, after the training and approximation of the neural network, the response variables are obtained through the output layer. Reliability index is calculated by solving the optimization model of the most probable point (MPP) searching in the limit state band. Two numerical cases are used to demonstrate the method proposed in this paper, and finally the method is employed to solving an engineering problem of the aerospace friction plate. For this high nonlinear, small failure probability problem with interval variables, this method could achieve a good analysis result.

• 제어로봇시스템학회논문지
• /
• 제12권11호
• /
• pp.1081-1087
• /
• 2006

Generally, biped walking is difficult to control because a biped robot is a nonlinear system with various uncertainties. In this paper, we propose a hybrid sliding-mode control method using a WNN uncertainty observer for stable walking of the 5-link biped robot with model uncertainties and the external disturbance. In our control system, the sliding mode control is used as main controller for the stable walking and a wavelet neural network(WNN) is used as an uncertainty observe. to estimate uncertainties of a biped robot model, and the error compensator is designed to compensate the reconstruction error of the WNN. The weights of WNN are trained by adaptation laws that are induced from the Lyapunov stability theorem. Finally, the effectiveness of the proposed control system is verified through computer simulations.

• Nuclear Engineering and Technology
• /
• 제55권9호
• /
• pp.3423-3440
• /
• 2023

In this work, a multivariate time-series machine learning meta-model is developed to predict the transient response of a typical nuclear power plant (NPP) undergoing a steam generator tube rupture (SGTR). The model employs Recurrent Neural Networks (RNNs), including the Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and a hybrid CNN-LSTM model. To address the uncertainty inherent in such predictions, a Bayesian Neural Network (BNN) was implemented. The models were trained using a database generated by the Best Estimate Plus Uncertainty (BEPU) methodology; coupling the thermal hydraulics code, RELAP5/SCDAP/MOD3.4 to the statistical tool, DAKOTA, to predict the variation in system response under various operational and phenomenological uncertainties. The RNN models successfully captures the underlying characteristics of the data with reasonable accuracy, and the BNN-LSTM approach offers an additional layer of insight into the level of uncertainty associated with the predictions. The results demonstrate that LSTM outperforms GRU, while the hybrid CNN-LSTM model is computationally the most efficient. This study aims to gain a better understanding of the capabilities and limitations of machine learning models in the context of nuclear safety. By expanding the application of ML models to more severe accident scenarios, where operators are under extreme stress and prone to errors, ML models can provide valuable support and act as expert systems to assist in decision-making while minimizing the chances of human error.

• Journal of Electrical Engineering and Technology
• /
• 제11권6호
• /
• pp.1684-1692
• /
• 2016

In order to adapt the fast dynamic performances of Buck DC/DC converter, and reduce the influence on converter performance owing to uncertain factors such as the disturbances of parameters and load, a control strategy based on two-dimensional hybrid cloud model is proposed. Firstly, two cloud models corresponding to the specific control inputs are determined by maximum determination approach, respectively, and then a control rule decided by the two cloud models is selected by a rule selector, finally, according to the reasoning structure of the rule, the control increment is calculated out by a two-dimensional hybrid cloud decision module. Both the simulation and experiment results show that the strategy can dramatically improve the dynamic performances of the converter, and enhance the adaptive ability to resist the random disturbances, and its control effect is superior to that of the current-mode control.

• Smart Structures and Systems
• /
• 제25권6호
• /
• pp.719-732
• /
• 2020

Real-time hybrid simulation (RTHS) which combines physical experiment with numerical simulation is an advanced method to investigate dynamic responses of structures subjected to earthquake excitation. The desired displacement computed from the numerical substructure is applied to the experimental substructure by a servo-hydraulic actuator in real time. However, the magnitude decay and phase delay resulted from the dynamics of the servo-hydraulic system affect the accuracy and stability of a RTHS. In this study, a robust stability analysis procedure for a general single-degree-of-freedom structure is proposed which considers the uncertainty of servo-hydraulic system dynamics. For discussion purposes, the experimental substructure is a portion of the entire structure in terms of a ratio of stiffness, mass, and damping, respectively. The dynamics of the servo-hydraulic system is represented by a multiplicative uncertainty model which is based on a nominal system and a weight function. The nominal system can be obtained by conducting system identification prior to the RTHS. A first-order weight function formulation is proposed which needs to cover the worst possible uncertainty envelope over the frequency range of interest. Then, the Nyquist plot of the perturbed system is adopted to determine the robust stability margin of the RTHS. In addition, three common delay compensation methods are applied to the RTHS loop to investigate the effect of delay compensation on the robust stability. Numerical simulation and experimental validation results indicate that the proposed procedure is able to obtain a robust stability margin in terms of mass, damping, and stiffness ratio which provides a simple and conservative approach to assess the stability of a RTHS before it is conducted.

• Communications for Statistical Applications and Methods
• /
• 제19권1호
• /
• pp.65-75
• /
• 2012

실험영역을 벗어난 점에서의 분산을 최소화 하는 외삽-최적의 문제는 모형의 불확실성을 내재하고 있다. 즉, 실험영역을 벗어나게 되면 모형의 불확실성이 높아지므로 모형의 타당성 여부를 진단하여야 한다. 본 연구에서는 외삽(extrapolation) 문제하에서 기본적인 3가지 실험, 즉 제약 실험과 최대최소 실험, 그리고 복합실험 등을 융합한 새로운 제약조건형의 실험 2가지를 제안하였다. 그리고 실험영역의 바깥에 위치한 점의 위치가 실험영역을 얼마나 벗어나느냐에 따른 실험결과에 대한 영향력도 고려하여 보았다. 문제의 특성상 유전 알고리즘을 이용하여 해를 구하였다.

• 응용통계연구
• /
• 제27권5호
• /
• pp.693-703
• /
• 2014

실험영역을 벗어나는 다중 외삽점들에 관한 실험설계를 기획하는 경우 실험자는 종종 어느 외삽점에 더 많은 노력을 집중하여야 하는지 주어진 모형이 있다하더라도, 고민하는 경우가 있다. 본 연구에서는 이러한 상황에 관한 실험설계 문제를 다루었다. 첫 번째는 주어진 모형이 실험영역을 벗어나더라도 모형이 타당한 경우 다중 외삽점에 관한 실험설계고 다른 하나는 그렇지 않은 경우이다. 첫 번째인 경우는 비교적 기존 문헌에서 알려진 방법들이 적용될 수 있으나 그렇지 않은 경우 즉, 모형의 타당성이 의심되는 경우는 다른 실험설계기준을 제시하여야 한다, 본 연구는 이와 관련 다양한 하이브리드 방법을 제시하여 다중 외삽점에서의 문제가 어떻게 모형 불확실성하에서 전개되어야 하는지 다루어 보았다, 이를 위해 서치알고리즘의 하나인 유전알고리즘을 적용하였다. 왜냐하면 전통적인 교환알고리즘의 복잡성보다는 유전알고리즘의 효율성이 더 뛰어났다고 보기 때문이다.

• Smart Structures and Systems
• /
• 제31권2호
• /
• pp.113-130
• /
• 2023

Hybrid simulation (HS) has attracted community attention in recent years as an efficient and effective experimental technique for structural performance evaluation in size-limited laboratories. Traditional hybrid simulations usually take deterministic properties for their numerical substructures therefore could not account for inherent uncertainties within the engineering structures to provide probabilistic performance assessment. Reliable structural performance evaluation, therefore, calls for stochastic hybrid simulation (SHS) to explicitly account for substructure uncertainties. The experimental design of SHS is explored in this study to account for uncertainties within analytical substructures. Both computational simulation and laboratory experiments are conducted to evaluate the pseudo-random Sobol sequence for the experimental design of SHS. Meta-modeling through polynomial chaos expansion (PCE) is established from a computational simulation of a nonlinear single-degree-of-freedom (SDOF) structure to evaluate the influence of nonlinear behavior and ground motions uncertainties. A series of hybrid simulations are further conducted in the laboratory to validate the findings from computational analysis. It is shown that the Sobol sequence provides a good starting point for the experimental design of stochastic hybrid simulation. However, nonlinear structural behavior involving stiffness and strength degradation could significantly increase the number of hybrid simulations to acquire accurate statistical estimation for the structural response of interests. Compared with the statistical moments calculated directly from hybrid simulations in the laboratory, the meta-model through PCE gives more accurate estimation, therefore, providing a more effective way for uncertainty quantification.