• 전기학회논문지
• /
• 제57권12호
• /
• pp.2313-2321
• /
• 2008

In order to develop reliable on-site partial discharge(PD) pattern recognition algorithm, the fuzzy neural network based on fuzzy set(FNN) and the polynomial network pattern classifier based on fuzzy Inference(PNC) were investigated and designed. Using PD data measured from laboratory defect models, these algorithms were learned and tested. Considering on-site situation where it is not easy to obtain voltage phases in PRPDA(Phase Resolved Partial Discharge Analysis), the measured PD data were artificially changed with shifted voltage phases for the test of the proposed algorithms. As input vectors of the algorithms, PRPD data themselves were adopted instead of using statistical parameters such as skewness and kurtotis, to improve uncertainty of statistical parameters, even though the number of input vectors were considerably increased. Also, results of the proposed neuro-fuzzy algorithms were compared with that of conventional BP-NN(Back Propagation Neural Networks) algorithm using the same data. The FNN and PNC algorithms proposed in this study were appeared to have better performance than BP-NN algorithm.

• Geomechanics and Engineering
• /
• 제36권4호
• /
• pp.381-390
• /
• 2024

The introduction of bio-based materials has been recommended in the geotechnical engineering field to reduce environmental pollutants such as heavy metals and greenhouse gases. However, bio-treated soil methods face limitations in field application due to short research periods and insufficient verification of engineering performance, especially when compared to conventional materials like cement. Therefore, this study aimed to develop a machine learning model for predicting the unconfined compressive strength, a representative soil property, of biopolymer-based soil treatment (BPST). Four machine learning algorithms were compared to determine a suitable model, including linear regression (LR), support vector regression (SVR), random forest (RF), and neural network (NN). Except for LR, the SVR, RF, and NN algorithms exhibited high predictive performance with an R² value of 0.98 or higher. The permutation feature importance technique was used to identify the main factors affecting the strength enhancement of BPST. The results indicated that the unconfined compressive strength of BPST is affected by mean particle size, followed by biopolymer content and water content. With a reliable prediction model, the proposed model can present guidelines prior to laboratory testing and field application, thereby saving a significant amount of time and money.

• Journal of the Korean Data and Information Science Society
• /
• 제19권4호
• /
• pp.1305-1325
• /
• 2008

As index option markets grow recently, many analysts and investors become interested in forecasting the volatility of KOSPI 200 Index to achieve portfolio's goal from the point of financial risk management and asset evaluation. To serve this purpose, we introduce NN and SVM integrated with other financial series models such as GARCH, EGARCH, and EWMA. Moreover, according to the empirical test, Integrating NN with GARCH or EWMA models improves prediction power in terms of the precision and the direction of the volatility of KOSPI 200 index. However, integrating SVM with financial series models doesn't improve greatly the prediction power. In summary, SVM-EGARCH was the best in terms of predicting the direction of the volatility and NN-GARCH was the best in terms of the prediction precision. We conclude with advantages of the integration process and the need for integrating models to enhance the prediction power.

• 한국지리정보학회지
• /
• 제5권2호
• /
• pp.16-24
• /
• 2002

원격탐사 응용분야 중 토지피복 분류를 통한 지구환경의 원격탐지기법은 환경 관리, 도시계획 및 지리정보시스템의 응용분야에 광범위하게 사용되고 있는 접근방식이다. 본 연구는 다목적 실용위성(Korea Multi-Purpose Satellite : KOMPSAT)의 전자광학카메라(electro-optical camera : EOC)를 통해 취득한 영상의 토지피복 정보를 추출하는 방안을 제시하였다. 사용영상은 다중 분광정보를 보유하고 있는 공간해상도 30m의 Landsat TM과 6.6m의 공간해상도와 단일밴드로 구성되어 있는 KOMPSAT EOC영상이며, 연구 대상지역은 청주시 미호천 수계이다. 영상합성은 IHS(intensity hue saturation), HPF(high pass filtering), CN(color normalization), 그리고 Wavelet 변환방식을 적용하여 결과를 비교하였다. 합성된 영상은 RBF-NN(radial basis function neural network)과 ANN(artificial neural network)법을 이용하여 피복분류를 실시하였으며, 이상의 과정을 통해 최적 결과를 도출하는 영상합성 및 분류기법을 제시하였다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2016년도 추계학술대회
• /
• pp.148-150
• /
• 2016

영상 신호에 대해 인공지능적인 프로세스를 수행하는 방법들 중에 우수한 성능을 나타내면서 주목을 끌고 있는 방법으로 Convolution Neural Network(CNN)이 있다. 이를 구성할 때 전반부는 convolution network로 구현되고, 후반부는 Neural Network(NN)로 구현된다. 이때, 전반부에서 convolution 과정을 수행하기 위해 다양한 필터가 사용되는데, 이 필터들의 초기값에 따라 CNN의 성능이 달라지게 된다. 본 논문에서는 CNN의 성능을 향상시키기 위해 convolution network의 초기값을 설정하는 방법에 대해 제안하며, 이를 컴퓨터 실험을 통해 증명하기 위해 필기체 인식이라는 응용 알고리즘을 구현하였다.

• 한국추진공학회:학술대회논문집
• /
• 한국추진공학회 2003년도 제21회 추계학술대회 논문집
• /
• pp.267-270
• /
• 2003

본 연구에서는 신경회로망을 이용한 가스터빈 엔진의 지능형 성능 진단 컴퓨터 프로그램을 개발하였다. 최근에는 엔진 손상을 분석하는데 있어서 주요 구성품의 가스 경로를 실시간 모니터링(monitoring)하는 가스경로해석(GPA, Gas Path Analysis)방법이 사용되고 있다. 그러나 엔진손상의 형태나 정도가 다양하고 복잡하기 때문에 가스경로해석 접근법만 가지고서는 엔진의 손상상태를 모두 모니터링하기란 쉽지 않다. 따라서 이 문제를 해결하기 위해 학습과 진단을 할 수 있는 신경회로망을 적용하였다. 본 연구에서는 PT6A-62 터보프롭 엔진의 진단에 1개의 은닉층을 갖는 역전파 신경회로망(BPN, Back Propagation Neural Network)이 제안되었다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2006년도 춘계학술대회 학술발표 논문집 제16권 제1호
• /
• pp.125-129
• /
• 2006

By advent of NNC(Neural Network Chip), it is possible that process in parallel and discern the importance of signal with learning oneself by experience in external signal. So, the design of general purpose operation unit using VHDL(VHSIC Hardware Description Language) on the existing FPGA(Field Programmable Gate Array) can replaced EN(Expert Network) and learning algorithm. Also, neural network operation unit is possible various operation using learning of NN(Neural Network). This paper present general purpose operation unit using hierarchical structure of EN. EN of presented structure learn from logical gate which constitute a operation unit, it relocated several layer. The overall structure is hierarchical using a module, it has generality more than FPGA operation unit.

• International Journal of Aeronautical and Space Sciences
• /
• 제9권1호
• /
• pp.100-110
• /
• 2008

It is not easy to monitor and identify all engine faults and conditions using conventional fault detection approaches like the GPA (Gas Path Analysis) method due to the nature and complexity of the faults. This study therefore focuses on a model based diagnostic method using Neural Network algorithms proposed for fault detection on a turbo shaft engine (PW 206C) selected as the power plant for a tilt rotor type unmanned aerial vehicle (Smart UAV). The model based diagnosis should be performed by a precise performance model. However component maps for the performance model were not provided by the engine manufacturer. Therefore they were generated by a new component map generation method, namely hybrid method using system identification and genetic algorithms that identifies inversely component characteristics from limited performance deck data provided by the engine manufacturer. Performance simulations at different operating conditions were performed on the PW206C turbo shaft engine using SIMULINK. In order to train the proposed BPNN (Back Propagation Neural Network), performance data sets obtained from performance analysis results using various implanted component degradations were used. The trained NN system could reasonably detect the faulted components including the fault pattern and quantity of the study engine at various operating conditions.

• Smart Structures and Systems
• /
• 제20권6호
• /
• pp.669-682
• /
• 2017

The normalised version of bispectrum, the so-called bicoherence, has often proved a reliable method of damage detection on engineering applications. Indeed, higher-order spectral analysis (HOSA) has the advantage of being able to detect non-linearity in the structural dynamic response while being insensitive to ambient vibrations. Skewness in the response may be easily spotted and related to damage conditions, as the majority of common faults and cracks shows bilinear effects. The present study tries to extend the application of HOSA to damage localisation, resorting to a neural network based classification algorithm. In order to validate the approach, a non-linear finite element model of a 4-meters-long cantilever beam has been built. This model could be seen as a first generic concept of more complex structural systems, such as aircraft wings, wind turbine blades, etc. The main aim of the study is to train a Neural Network (NN) able to classify different damage locations, when fed with bispectra. These are computed using the dynamic response of the FE nonlinear model to random noise excitation.

• Journal of Platform Technology
• /
• 제6권4호
• /
• pp.34-40
• /
• 2018

현재 인공신경망은 단일 작업에 대해선 뛰어난 성능을 보이나, 다른 종류의 작업을 학습하면 이전 학습 내용을 잊어버리는 단점이 있다. 이를 catastrophic forgetting이라고 한다. 인공신경망의 활용도를 높이긴 위해선 이 현상을 극복해야 한다. catastrophic forgetting을 극복하기 위한 여러 노력이 있다. 하지만 많은 노력이 있었음에도 완벽하게 catastrophic forgetting을 극복하지는 못하였다. 본 논문에서는 여러 노력 중 elastic weight consolidation(EWC)에 사용되는 핵심 개념을 이용하여, 순차적 반복학습을 제시한다. 인공신경망 학습에 많이 쓰이는 MNIST를 확장한 EMNIST 데이터 셋을 이용하여 catastrophic forgetting 현상을 재현하고 이를 순차적 반복학습을 통해 극복하는 실험을 진행하였으며, 그 결과 모든 작업에 대해서 학습이 가능하였다.