• Journal of the Korean Society of Systems Engineering
• /
• v.18 no.2
• /
• pp.75-93
• /
• 2022

Machine learning (ML) data-driven meta-model is proposed as a surrogate model to reduce the excessive computational cost of the physics-based model and facilitate the real-time prediction of a nuclear power plant's transient response. To forecast the transient response three machine learning (ML) meta-models based on recurrent neural networks (RNNs); specifically, Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and a sequence combination of Convolutional Neural Network (CNN) and LSTM are developed. The chosen accident scenario is a control element assembly withdrawal at power concurrent with the Loss Of Offsite Power (LOOP). The transient response was obtained using the best estimate thermal hydraulics code, MARS-KS, and cross-validated against the Design and control document (DCD). DAKOTA software is loosely coupled with MARS-KS code via a python interface to perform the Best Estimate Plus Uncertainty Quantification (BEPU) analysis and generate a time series database of the system response to train, test and validate the ML meta-models. Key uncertain parameters identified as required by the CASU methodology were propagated using the non-parametric Monte-Carlo (MC) random propagation and Latin Hypercube Sampling technique until a statistically significant database (181 samples) as required by Wilk's fifth order is achieved with 95% probability and 95% confidence level. The three ML RNN models were built and optimized with the help of the Talos tool and demonstrated excellent performance in forecasting the most probable NPP transient response. This research was guided by the Systems Engineering (SE) approach for the systematic and efficient planning and execution of the research.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.6
• /
• pp.435-441
• /
• 2003

This paper addresses that an approximation and tracking control of realtime recurrent neural networks(RTRN) using two-dimensional iterative teaming algorithm for an electro-hydraulic servo system. Two dimensional learning rule is driven in the discrete system which consists of nonlinear output fuction and linear input. In order to control the trajectory of position, two RTRN with the same network architecture were used. Simulation results show that two RTRN using 2-D learning algorithm are able to approximate the plant output and desired trajectory to a very high degree of a accuracy respectively and the control algorithm using two identical RTRN was very effective to trajectory tracking of the electro-hydraulic servo system.

• Structural Engineering and Mechanics
• /
• v.16 no.6
• /
• pp.643-654
• /
• 2003

Two real-time modeling prediction (RMP) schemes are presented in this paper for analyzing the behavior of deep excavations during construction. The first RMP scheme is developed from the traditional AR(p) model. The second is based on the simplified Elman-style recurrent neural networks. An on-line learning algorithm is introduced to describe the dynamic behavior of deep excavations. As a case study, in-situ measurements of an excavation were recorded and the measured data were used to verify the reliability of the two schemes. They proved to be both effective and convenient for predicting the behavior of deep excavations during construction. It is shown through the case study that the RMP scheme based on the neural network is more accurate than that based on the traditional AR(p) model.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.1
• /
• pp.9-14
• /
• 2004

Rational sense is affected by emotion. If we add the factor of estimated emotion by environment information into robots, we may get more intelligent and human-friendly robots. However, various sensory information and pattern classification are prescribed for robots to learn emotion so that the networks are suitable for the necessity of robots. Neural network has superior ability to extract character of system but neural network has defect of temporal cross talk and local minimum convergence. To solve the defects, many kinds of modular neural networks have been proposed because they divide a complex problem into simple several subproblems. The modular neural network, introduced by Jacobs and Jordan, shows an excellent ability of recomposition and recombination of complex work. On the other hand, the recurrent network acquires state representations and representations of state make the recurrent neural network suitable for diverse applications such as nonlinear prediction and modeling. In this paper, we applied recurrent network for the expert network in the modular neural network structure to learn data pattern based on emotional assessment. To show the performance of the proposed network, simulation of learning the environment and behavior pattern is proceeded with the real time implementation. The given problem is very complex and has too many cases to learn. The result will show the performance and good ability of the proposed network and will be compared with the result of other method, general modular neural network.

• Nuclear Engineering and Technology
• /
• v.55 no.3
• /
• pp.814-826
• /
• 2023

Sensor faults in nuclear power plant instrumentation have the potential to spread negative effects from wrong signals that can cause an accident misdiagnosis by plant operators. To detect sensor faults and make accurate accident diagnoses, prior studies have developed a supervised learning-based sensor fault detection model and an accident diagnosis model with faulty sensor isolation. Even though the developed neural network models demonstrated satisfactory performance, their diagnosis performance should be reevaluated considering real-time connection. When operating in real-time, the diagnosis model is expected to indiscriminately accept fault data before receiving delayed fault information transferred from the previous fault detection model. The uncertainty of neural networks can also have a significant impact following the sensor fault features. In the present work, a pilot study was conducted to connect two models and observe actual outcomes from a real-time application with an integrated system. While the initial results showed an overall successful diagnosis, some issues were observed. To recover the diagnosis performance degradations, additive logics were applied to minimize the diagnosis failures that were not observed in the previous validations of the separate models. The results of a case study were then analyzed in terms of the real-time diagnosis outputs that plant operators would actually face in an emergency situation.

• International Journal of Ocean System Engineering
• /
• v.3 no.3
• /
• pp.116-130
• /
• 2013

The prediction of ocean currents in real time over the warning times of a few hours or days is required in planning many operation-related activities in the ocean. Traditionally this is done through numerical models which are targeted toward producing spatially distributed information. This paper discusses a complementary method to do so when site-specific predictions are desired. It is based on the use of a recurrent type of neural network as well as the statistical tool of model tree. The measurements made at a site in Indian Ocean over a period of 4 years were used. The predictions were made over 72 time steps in advance. The models developed were found to be fairly accurate in terms of the selected error statistics. Among the two modeling techniques the model tree performed better showing the necessity of using distributed models for different sub-domains of data rather than a unique one over the entire input domain. Typically such predictions were associated with average errors of less than 2.0 cm/s. Although the prediction accuracy declined over longer intervals, it was still very satisfactory in terms of theselected error criteria. Similarly prediction of extreme values matched with that of the rest of predictions. Unlike past studies both east-west and north-south current components were predicted fairly well.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.2
• /
• pp.121-130
• /
• 2012

This paper proposes an intuitive real-time robot control system using human body movement. Recently, it has been developed that motion generation for humanoid robots with reflecting human body movement, which is measured by a motion capture. However, in the existing studies about robot control system by human body movement, the detailed structure information of a robot, for example, degrees of freedom, the range of motion and forms, must be examined in order to calculate inverse kinematics. In this study, we have proposed Associative Motion Generation as humanoid robot motion generation method which does not need the detailed structure information. The associative motion generation system is composed of two neural networks: nonlinear principal component analysis and Jordan recurrent neural network, and the associative motion is generated with the following three steps. First, the system learns the correspondence relationship between an indication and a motion using training data. Second, associative values are extracted for associating a new motion from an unfamiliar indication using nonlinear principal component analysis. Last, the robot generates a new motion through calculation by Jordan recurrent neural network using the associative values. In this paper, we propose a real-time humanoid robot control system based on Associative Motion Generation, that enables user to control motion intuitively by human body movement. Through the task processing and subjective evaluation experiments, we confirmed the effective usability and affective evaluations of the proposed system.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.8
• /
• pp.898-906
• /
• 1999

A control structure is introduced for the purpose of rejecting periodic (or repetitive) disturbances on a tracking system. The objective of the proposed structure is to drive the output of the system to the reference input that will result in perfect following without any changing the inner configuration of the system. The structure includes an adaptation block which learns the dynamics of the periodic disturbance and forces the interferences, caused by disturbances, on the output of the system to be reduced. Since the control structure acquires the dynamics of the disturbance by on-line adaptation, it is possible to generate control signals that reject any slowly varying time-periodic disturbance provided that its amplitude is bounded. The artificial neural network is adopted as the adaptation block. The adaptation is done at an on-line process. For this , the real-time recurrent learning (RTRL) algoritnm is applied to the training of the artificial neural network.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.168-171
• /
• 2002

A neural network model for predicting the quality or soundness of the injected plastic aspherical lens based on process parameters has been developed. The approach uses a Real Time Recurrent Neural Network 4-5-2 (RTRN) trained based on input/output data that were taken from FE analysis worts carried out through a CAE software. The system has been developed to search an optimum set of process parameters and reduce the time required for planning the conditions of plastic injection molding at the design stage.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.9
• /
• pp.23-30
• /
• 1997

In this paper, a decision feedback recurrent neural equalization (DFRNE) scheme is proposed for adaptive equalization problems. The proposed equalizer models a nonlinear infinite impulse response (IIR) filter. The modified Real-Time recurrent Learning Algorithm (RTRL) is used to train the DFRNE. The DFRNE is applied to both linear channels with only intersymbol interference and nonlinear channels for digital video cassette recording (DVCR) system. And the performance of the DFRNE is compared to those of the conventional equalizaion schemes, such as a linear equalizer, a decision feedback equalizer, and neural equalizers based on multi-layer perceptron (MLP), in view of both bit error rate performance and mean squared error (MSE) convergence. It is shown that the DFRNE with a reasonable size not only gives improvement of compensating for the channel introduced distortions, but also makes the MSE converge fast and stable.