• Transactions of the Korean Society of Pressure Vessels and Piping
• /
• v.19 no.2
• /
• pp.93-101
• /
• 2023

In this study, a deep learning algorithm was used to diagnose electric potential signals obtained through CIPS and DCVG, used indirect inspection methods to confirm the soundness of buried pipes. The deep learning algorithm consisted of CNN(Convolutional Neural Network) model for diagnosing the electric potential signal and Grad CAM(Gradient-weighted Class Activation Mapping) for showing the flaw prediction point. The CNN model for diagnosing electric potential signals classifies input data as normal/abnormal according to the presence or absence of flaw in the buried pipe, and for abnormal data, Grad CAM generates a heat map that visualizes the flaw prediction part of the buried pipe. The CIPS/DCVG signal and piping layout obtained from the 3D finite element model were used as input data for learning the CNN. The trained CNN classified the normal/abnormal data with 93% accuracy, and the Grad-CAM predicted flaws point with an average error of 2m. As a result, it confirmed that the electric potential signal of buried pipe can be diagnosed using a CNN-based deep learning algorithm.

• Annual Conference of KIPS
• /
• 2020.11a
• /
• pp.793-795
• /
• 2020

본 논문에서는 스파이킹 뉴론(Spiking Neuron)들이 쿨롱에너지 포텐셜 (Coulomb Energy Potential)을 가지는 스파이킹 신경회로망에서의 학습알고리즘을 일반화하여 구간연산(Interval Arithmetic)의 학습이 가능한 학습알고리즘을 제안한다. 제안하는 학습알고리즘은 입력 데이터로서 구간(Interval) 데이터와 포인트(Point) 데이터를 모두 학습 할 수 있는 일반화된 학습알고리즘으로서 간단한 컴퓨터 시뮬레이션을 통하여 범위(Lower bound & Upper bound)를 가지는 구간데이터와 포인트데이터의 통합적인 학습이 가능하고 전문가시스템(expert system)에서의 "don't care attributes"의 학습 등에도 활용이 가능함을 보인다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.6
• /
• pp.766-772
• /
• 2009

Generally, wind industry has been oriented to large power systems which require large windy areas and often need to overcome environment restrictions. However, small-scale wind turbines are closer to the consumers and have a large market potential, and much more efforts are required to become economically attractive. In this paper, a prototype of a small-scale urban wind generation system for battery charging application is described and a neural network based MPPT(Maximum Power Point Tracking) algorithm which can be effectively applied to urban wind turbine system is proposed. Through Matlab based simulation studies and actual implementation of the proposed algorithm, the feasibility of the proposed scheme is verified.

• Proceedings of the KOSOMBE Conference
• /
• v.1998 no.11
• /
• pp.207-208
• /
• 1998

Classification of extracellularly recorded action potential into each unit is an important procedure for further analysis of spike trains as point process. We utilize feedforward neural network structures, multilayer perceptron and radial basis function network to implement spike classifier. For the efficient training of classifiers, nonlinear energy operator that can trace the instantaneous frequency as well as the amplitude of the input signal is used. Trained classifiers shows successful operation, up to 90% correct classification was possible under 1.2 of signal-to-noise ratio.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.415-418
• /
• 1996

Etching Process, one of the most important process in semiconductor fabrication, has input control part of which components are pressure, gas flow, RF power and etc., and plasma gas which is complex and not exactly understood is used to etch wafer in etching chamber. So this process has not real-time feedback controller based on input-output relation, then it uses EPD(End Point Detection) signal to determine when to start or when to stop etching. Various type EPD controller control etching process using EPD signal obtained from optical intensity of etching chamber. In development EPD controller we concentrate on compensation of this signal intensity and setting the relative signal magnitude at first of etching. We compensate signal intensity using neural network learning method and set the relative signal magnitude using fuzzy inference method. Potential of this method which improves EPD system capability is proved by experiences.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.429-438
• /
• 2006

Neural Networks(NNs) are applied for solving a wide variety of nonlinear problems in several areas, such as image processing, pattern recognition etc. Although NN can be simulated by using software, many potential NN applications required real-time processing. Thus they need to be implemented as hardware. The hardware implementation of multi-layer perceptrons(MLPs) in several kind of NNs usually uses a fixed-point arithmetic due to a simple logic operation and a shorter processing time compared to the floating-point arithmetic. However, the fixed-point arithmetic-based MLP has a drawback which is not able to apply the MLP software that use floating-point arithmetic. We propose a design method for MLPs which has the floating-point arithmetic-based fully-pipelining architecture. It has a processing speed that is proportional to the number of the hidden nodes. The number of input and output nodes of MLPs are generally constrained by given problems, but the number of hidden nodes can be optimized by user experiences. Thus our design method is using optimized number of hidden nodes in order to improve the processing speed, especially in field of a repeated processing such as image processing, pattern recognition, etc.

• Nuclear Engineering and Technology
• /
• v.56 no.9
• /
• pp.3571-3584
• /
• 2024

Reactor core transient calculation is very important for the reactor safety analysis, in which the kernel is neutron kinetics calculation by simulating the variation of neutron density or thermal power over time. Compared with the point kinetics method, the time-space neutron kinetics calculation can provide accurate variation of neutron density in both space and time domain. But it consumes a lot of resources. It is necessary to develop a surrogate model that can quickly obtain the temporal and spatial variation information of neutron density or power with acceptable calculation accuracy. This paper uses the time-varying characteristics of power to construct a time function, parameterizes the time-varying characteristics which contains the information about the spatial change of power. Thereby, the amount of targets to predict in the space domain is compressed. A surrogate method using the machine learning is proposed in this paper. In the construction of a neural network, the input is processed by a convolutional layer, followed by a fully connected layer or a deconvolution layer. For the problem of time sequence disturbance, a structure combining convolutional neural network and recurrent neural network is used. It is verified in the tests of a series of 1D, 2D and 3D reactor models. The predicted values obtained using the constructed neural network models in these tests are in good agreement with the reference values, showing the powerful potential of the surrogate models.

• Journal of Power Electronics
• /
• v.18 no.1
• /
• pp.70-80
• /
• 2018

A novel strategy based on a zero common mode voltage pulse-width modulation (ZCMV-PWM) technique and zero-sequence circulating current (ZSCC) feedback control is proposed in this study to eliminate ZSCCs between three-level neutral point clamped (NPC) voltage source inverters, with common AC and DC buses, that are operating in parallel. First, an equivalent model of ZSCC in a three-phase three-level NPC inverter paralleled system is developed. Second, on the basis of the analysis of the excitation source of ZSCCs, i.e., the difference in common mode voltages (CMVs) between paralleled inverters, the ZCMV-PWM method is presented to reduce CMVs, and a simple electric circuit is adopted to control ZSCCs and neutral point potential. Finally, simulation and experiment are conducted to illustrate effectiveness of the proposed strategy. Results show that ZSCCs between paralleled inverters can be eliminated effectively under steady and dynamic states. Moreover, the proposed strategy exhibits the advantage of not requiring carrier synchronization. It can be utilized in inverters with different types of filter.

• Journal of Intelligence and Information Systems
• /
• v.9 no.1
• /
• pp.139-155
• /
• 2003

This paper presents the new methodology of analyzing and classifying patterns of customers in mobile telecommunication market to enhance the performance of predicting the credit information based on the decision tree and neural network. With the application of variance selection process from decision tree, the systemic process of defining input vector's value and the rule generation were developed. In point of customer management, this research analyzes current customers and produces the patterns of them so that the company can maintain good customer relationship and makes special management on the customer who has huh potential of getting out of contract in advance. The real implementation of proposed method shows that the predicted accuracy is higher than existing methods such as decision tree(CART, C4.5), regression, neural network and combined model(CART and NN).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.11
• /
• pp.2137-2142
• /
• 2016

The electrical current generated by heart creates not only electric potential but also a magnetic field. In this study, the signals obtained magnetocardiogram(MCG) using 61 channel superconducting quantum interference device(SQUID) system, and the clinical significance of various feature parameters has been developed MCG. Neural network algorithm was used to perform the classification of ischemic heart disease. The MCG signal was obtained to facilitate the extraction of parameters through a process of pre-processing. The data used to research the normal group 10 and ischemic heart disease group 10 with visible signs of stable angina patients. The available clinical indicators were extracted by characteristic point, characteristic interval parameter, and amplitude ratio parameter. The extracted parameters are determined to analysis the significance and clinical parameters were defined. It is possible to classify ischemic heart disease using the MCG feature parameters as a neural network input.