• Nuclear Engineering and Technology
• /
• v.53 no.4
• /
• pp.1181-1188
• /
• 2021

When abnormal events occur in a nuclear power plant, operators must conduct appropriate abnormal operating procedures. It is burdensome though for operators to choose the appropriate procedure considering the numerous main plant parameters and hundreds of alarms that should be judged in a short time. Recently, various research has applied deep-learning algorithms to support this problem by classifying each abnormal condition with high accuracy. Most of these models are trained with simulator data because of a lack of plant data for abnormal states, and as such, developed models may not have tolerance for plant data in actual situations. In this study, two approaches are investigated for a deep-learning model trained with simulator data to overcome the performance degradation caused by noise in actual plant data. First, a preprocessing method using several filters was employed to smooth the test data noise, and second, a data augmentation method was applied to increase the acceptability of the untrained data. Results of this study confirm that the combination of these two approaches can enable high model performance even in the presence of noisy data as in real plants.

• Journal of Power Electronics
• /
• v.19 no.4
• /
• pp.835-845
• /
• 2019

This paper presents a robust-optimal control strategy to improve the output-voltage error-tracking and control capability of a DC-DC boost converter. The proposed strategy employs an optimized Fractional-order Proportional-Integral (FoPI) controller that serves to eliminate oscillations, overshoots, undershoots and steady-state fluctuations. In order to significantly improve the error convergence-rate during a transient response, the FoPI controller is augmented with a pre-stage nonlinear error-modulator. The modulator combines the variations in the error and error-derivative via the signed-distance method. Then it feeds the aggregated-signal to a smooth sigmoidal control surface constituting an optimized hyperbolic secant function. The error-derivative is evaluated by measuring the output-capacitor current in order to compensate the hysteresis effect rendered by the parasitic impedances. The resulting modulated-signal is fed to the FoPI controller. The fixed controller parameters are meta-heuristically selected via a Particle-Swarm-Optimization (PSO) algorithm. The proposed control scheme exhibits rapid transits with improved damping in its response which aids in efficiently rejecting external disturbances such as load-transients and input-fluctuations. The superior robustness and time-optimality of the proposed control strategy is validated via experimental results.

• Wind and Structures
• /
• v.5 no.2_3_4
• /
• pp.267-276
• /
• 2002

Research being undertaken at the University of Auckland has enabled Vortec Energy to improve the performance of the Vortec 7 Diffuser Augmented Wind Turbine. Computational Fluid Dynamic (CFD) modelling of the Vortec 7 was used to ascertain the effectiveness of geometric modifications to the Vortec 7. The CFD work was then developed to look at new geometries, and refinement of these led to greater power augmentation for a given diffuser exit area ratio. Both full scale analysis of the Vortec 7 and a wind tunnel investigation of the development design have been used for comparison with the CFD model.

• Proceedings of the KIPE Conference
• /
• 2018.07a
• /
• pp.275-277
• /
• 2018

Recently, the importance of an early response has been emphasized due to the large fire. The most efficient method of extinguishing a large fire is early response to a small flame. To implement this solution, we propose a fire detection mechanism based on a deep learning artificial intelligence. In this study, a small amount of data sets is manipulated by an image augmentation technique using rotating, tilting, blurring, and distorting effects in order to increase the number of the data sets by 5 times, and we study the flame detection algorithm using faster R-CNN.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.4
• /
• pp.151-156
• /
• 2021

Low-end IoT devices do not have enough computation and memory resources for DNN learning and inference. Integer quantization of real-type neural network models can reduce model size, hardware computational burden, and power consumption. This paper describes the design and implementation of a web-based quantization platform for CNN deep learning accelerator chips. In the web service platform, we implemented visualization of the model through a convenient UI, analysis of each step of inference, and detailed editing of the model. Additionally, a data augmentation function and a management function of files that store models and inference intermediate results are provided. The implemented functions were verified using three YOLO models.

• Journal of Positioning, Navigation, and Timing
• /
• v.10 no.2
• /
• pp.139-144
• /
• 2021

In this paper, we described configuration and construction of infrastructure for the KASS Reference Station (KRS), subsystem of Korea Augmentation Satellite System (KASS). KASS system consists of three subsystems(KRS, Mission Control Center (MCC), KASS Uplink Station (KUS)). One of these subsystems, KRS receives GNSS data for generating range error and integrity verification and sends to MCC. It is needed to antenna facilities for mounting GNSS antenna and shelter for operating KRS and infra equipment(power and network system, lightning and grounding system, fire extinguish) for operating KRS. For this reason, we have established the requirements for KRS infrastructure and constructed infrastructure for KRS to meet the requirements of KRS infrastructure.

• Nuclear Engineering and Technology
• /
• v.55 no.10
• /
• pp.3716-3724
• /
• 2023

Loose parts monitoring and detecting alarm type in real Nuclear Power Plant have challenges such as background noise, insufficient alarm data, and difficulty of distinction between alarm data that occur during start and stop. Although many signal processing methods and alarm determination algorithms have been developed, it is not easy to determine valid alarm and extract the meaning data from alarm signal including background noise. To address these issues, this paper proposes a denoising autoencoder-based majority vote classification. Training and test data are prepared by acquiring alarm data from real NPP and simulation facility for data augmentation, and noisy data is reproduced by adding Gaussian noise. Using DAEs with 3, 5, 7, and 9 layers, features are extracted for each model and classified into neural networks. Finally, the results obtained from each DAE are classified by majority voting. Also, through comparison with other methods, the accuracy and the false alarm rate are compared, and the excellence of the proposed method is confirmed.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2006.11a
• /
• pp.167-172
• /
• 2006

It follows recently in an order augmentation of overseas construction market plant field and the project of oil gas field is increasing. Consequently, the hazard which secures the competitive power of the overseas plant enterprise of the domestic building industry enterprises the technical competitiveness security which stands, productivity improvement and strategy management propulsion back positive disposal plan establishment are demanded. Even from in that oil gas field of overseas plant enterprise for an industrial competitive power improvement the application of EPC circulation information which relates with a project accomplishment is more demanded, the EPC phased star efficiently it manages the circulation information contents which occurs from the business which is various it is not presented it cannot there is a contents classification system for. If with him about lower the draft the problem point of information omission back of occurrence and business subject for of the fringe land and duplication business occurs, about lower the productivity decrease actual condition is appearing with such problem point. The research which it sees consequently in order to improve the use characteristic of the augmentation of practical application of the contents management system of oil gas field and building industry information civil official establishhes the contents management system the BPM for (Business Process Management) to present the contents classification system of base, it does to sleep. The part of Business Process materiality the knowledge which is demanded, contents information and system anger it analyzes system anger of industrial equipment circulation information it takes a triangular position and to sleep it does.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.7
• /
• pp.1344-1349
• /
• 2012

The Korean DGPS station transmits the 200 bps GPS enhancement signal using the MSK modulation in frequency range of 283.5 kHz to 325 kHz. The land-based stations of 6 sites provide the service area of 80 km with the output power of 500 W. The ocean-based stations of 11 sites provide the output power of 300 W, which provide the DGPS service to 185 kM. Some places are serviced from two or three DGPS stations. The interferences among the DGPS stations using the high power can be occurred. Also, the performances of the user terminasl in dual service area can be degraded. In this paper, the protection ratios for the DGPS service are defined. Using the MF wave propagation model, the interferences among the DGPS stations and the adjacent wireless ground stations are analyzed. Also, the performances of DGPS user terminals are analyzed in the viewpoint of interference.

• Nuclear Engineering and Technology
• /
• v.55 no.6
• /
• pp.2096-2106
• /
• 2023

Rotating machinery is widely applied in important equipment of nuclear power plants (NPPs), such as pumps and valves. The research on intelligent fault diagnosis of rotating machinery is crucial to ensure the safe operation of related equipment in NPPs. However, in practical applications, data-driven fault diagnosis faces the problem of small and imbalanced samples, resulting in low model training efficiency and poor generalization performance. Therefore, a deep convolutional conditional generative adversarial network (DCCGAN) is constructed to mitigate the impact of imbalanced samples on fault diagnosis. First, a conditional generative adversarial model is designed based on convolutional neural networks to effectively augment imbalanced samples. The original sample features can be effectively extracted by the model based on conditional generative adversarial strategy and appropriate number of filters. In addition, high-quality generated samples are ensured through the visualization of model training process and samples features. Then, a deep convolutional neural network (DCNN) is designed to extract features of mixed samples and implement intelligent fault diagnosis. Finally, based on multi-fault experimental data of motor and bearing, the performance of DCCGAN model for data augmentation and intelligent fault diagnosis is verified. The proposed method effectively alleviates the problem of imbalanced samples, and shows its application value in intelligent fault diagnosis of actual NPPs.