• Journal of Computing Science and Engineering
• /
• 제5권4호
• /
• pp.305-313
• /
• 2011

Due to the expansion of high-speed Internet access, the need for secure and reliable networks has become more critical. The sophistication of network attacks, as well as their severity, has also increased recently. As such, more and more organizations are becoming vulnerable to attack. The aim of this research is to classify network attacks using neural networks (NN), which leads to a higher detection rate and a lower false alarm rate in a shorter time. This paper focuses on two classification types: a single class (normal, or attack), and a multi class (normal, DoS, PRB, R2L, U2R), where the category of attack is also detected by the NN. Extensive analysis is conducted in order to assess the translation of symbolic data, partitioning of the training data and the complexity of the architecture. This paper investigates two engines; the first engine is the back-propagation neural network intrusion detection system (BPNNIDS) and the second engine is the radial basis function neural network intrusion detection system (BPNNIDS). The two engines proposed in this paper are tested against traditional and other machine learning algorithms using a common dataset: the DARPA 98 KDD99 benchmark dataset from International Knowledge Discovery and Data Mining Tools. BPNNIDS shows a superior response compared to the other techniques reported in literature especially in terms of response time, detection rate and false positive rate.

• Journal of Advanced Marine Engineering and Technology
• /
• 제21권4호
• /
• pp.414-420
• /
• 1997

An intelligent speed control system for marine diesel engines is presented. The approach adopt¬ed is to use a conventional PID controller for normal operation and a feedforward controller for adaptive control. The feedforward controller is a neural network. The neural network is the inverse dynamics model of the plant, which is being trained on line. The parametric model of the diesel engine is represented in a linear second-order system, with a first-order combustion part and a revolution part each at a normal operating point. The time delay in the control of the com¬bustion part is approximated to the first-order system. The tuned PID parameters are set based on the model for normal operating point. To obtain the inverse dynamics of the diesel engine system, two neural networks are used, one for inverse, the other for forward dynamics. The former is posi¬tioned across the plant to learn its inverse dynamics during operation, and the latter is placed in series with the controlled plant. Simulation results are presented to illustrate the applicability of the proposed scheme to intelligent adaptive control of diesel engines.

• 한국항공우주학회지
• /
• 제37권6호
• /
• pp.556-561
• /
• 2009

다양한 비행환경에서 장시간 체공하며 원격 조종되는 무인항공기에서 추진시스템을 신뢰성 있게 운영하는 것은 매우 중요하다. 스마트 무인기의 수직 이착륙 및 전진 비행에 사용 되는 터보축엔진의 정확한 손상진단은 신뢰성과 이용률을 향상시킬 수 있을 것이다. 본 연구에서는 엔진 측정 파라미터들의 변화로부터 퍼지이론을 적용하여 손상된 구성품을 식별한 후 훈련된 신경망 알고리즘을 식별된 손상 패턴에 적용 손상된 양을 정확히 진단할 수 있는 방법을 새로이 제안하였다. 제안된 진단방법은 단일손상은 물론 다중손상도 진단할 수 있다.

• 한국추진공학회:학술대회논문집
• /
• 한국추진공학회 2008년 영문 학술대회
• /
• pp.72-79
• /
• 2008

The weak point of the artificial neural network(ANN) is that it is easy to fall in local minima when it learns too much nonlinear data. Accordingly, the classification ratio must be low. To overcome this weakness, the hybrid method has been proposed. That is, the ANN learns data selectively after detecting the defect position by the support vector machine(SVM). First, the SVM has been used for determination of the defect position and then the magnitude of the defect has been measured by the ANN. In off-design condition, the operation region of the engine is wide and the nonlinearity of learning data increases. The module system, dividing the whole operating region into reasonably small-size sections, has been suggested to solve this problem. In this study, the proposed algorithm has diagnosed the defects of triple components as well as single and dual components of the gas turbine engine in off-design condition.

• International Journal of Automotive Technology
• /
• 제7권6호
• /
• pp.687-695
• /
• 2006

This paper presents a network-based traction control system(TCS), where several electric control units(ECUs) are connected by a controller area network(CAN) communication system. The control system consists of four ECUs: the electric throttle controller, the transmission controller, the engine controller and the traction controller. In order to validate the traction control algorithm of the network-based TCS and evaluate its performance, a Hardware-In-the-Loop Simulation(HILS) environment was developed. Herein we propose a new concept of the HILS environment called the network-based HILS(Net-HILS) for the development and validation of network-based control systems which include smart sensors or actuators. In this study, we report that we have designed a network-based TCS, validated its algorithm and evaluated its performance using Net-HILS.

• 드라이브 ㆍ 컨트롤
• /
• 제19권1호
• /
• pp.16-25
• /
• 2022

The purpose of this study was to calculate and analyze the engine load factor of major agricultural operations using a 78 kW class agricultural tractor for estimating the emission of air pollutants and greenhouse. Engine load data were collected using controller area network (CAN) communication. Main agricultural operations were selected as plow tillage (PT), rotary tillage (RT), baler operation (BO), loader operation (LO), driving on soil (DS), and driving on concrete (DC). The engine power was calculated using the measured engine load data. A weight factor was applied to load factor for considering usage ratio according to agricultural operations. Weight factors for different agricultural operations were calculated to be 27.4%, 32.9%, 17.5%, 7.7%, 4.5%, and 10.0% for PT, RT, BO, LO, DS, and DC, respectively. As a result of the field test, load factors were 0.74, 0.93, 0.41, 0.23, 0.27, and 0.21 for PT, RT, BO, LO, DS, and DC, respectively. The engine load factor was the highest for RT. Finally, as a result of applying the weight factor for usage ratio of agricultural operations, the integrated engine load factor was estimated to be 0.63, which was about 1.31 times higher than the conventional applied load factor of 0.48. In future studies, we plan to analyze the engine load factor by considering various horsepower and working conditions of the tractor.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.1006-1011
• /
• 1991

In this paper, a neural network estimator which estimates the output of the wide range oxygen sensor is proposed, The neural network estimator is constructed to give the output of the wide range oxygen sensor from rpm, fuel injection time, throttle position, and output voltage of the exhaust gas oxygen sensor. And, using this estimator, PI controller for air-fuel ratio control is designed. Experiment results show that the proposed method gives good results for SONATA engine under light load and constant rpms.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2022년도 춘계학술대회
• /
• pp.108-109
• /
• 2022

본 연구는 선박 내부의 기관실에서 금속체 표면파를 이용하여 통신할 때 기관 구동으로 발생하는 잡음 간섭에 대하여 실험을 통한 데이터를 수집, 분석하였다. 실험은 순톤수 265톤 예인 선박의 기관실의 임의의 7구역을 선정하여 기관 구동 전과 구동 중에 생기는 잡음 성분을 신호 분석기를 통해 측정하고 표면파 통신에 미치는 영향을 측정하였다. 잡음 성분의 분석을 토대로 실제의 통신망을 구성하여 금속 격벽으로 이루어진 구역에서의 표면파 통신의 특성을 확인하기 위하여 실제의 통신망은 3개의 금속 격벽 사이로 통신장비를 설치하여 무선통신과 비교 실험을 진행하여 그 차이점을 확인하였다. 그 결과 표면파 통신의 경우에는 격벽 3개의 환경에서 기관의 구동 전후에 송수신 rate는 기관 구동 전과 구동 중인 상태에서 유의미한 차이가 없었으나 무선을 사용하는 Wi-Fi의 경우 구동 중인 상태에서 현저한 성능 저하를 나타냄을 확인하였다. 실험 데이터를 분석한 결과 기관 구동으로 인한 잡음은 무선통신에는 영향을 주지만 표면파 통신에 영향을 주지 않음을 확인하였다. 따라서 선박 내의 전자파 잡음이 많은 구역에서도 선박의 금속 구조물을 이용하여 표면파 통신 시스템을 구성하였을 때 무선통신을 대체할 수 있고 나아가 선박 내 밀폐 공간 및 기관실에서의 표면파 통신의 적용이 가능할 것으로 생각한다.

• 한국자동차공학회논문집
• /
• 제4권4호
• /
• pp.18-26
• /
• 1996

Based on experimental analysis, the characteristics of pulsating pressure wave propagation is clarified by testing of 4-stroke gasoline engine. The pulsating pressure wave in exhaust system is generated by pulsating gas flow due to working of exhaust valve. The pulsating pressure wave is closely concerned to the loss of engine power according to back pressure and exhaust noise. It is difficult to exactly calculate pulsating pressure wave propagation in exhaust system because of nonlinear effect. Therefore, in the first step for solving these problems, this paper contains experimental model and analysis method which are applied two-port network analysis. Also, it shows coherence function, frequency response function, back pressure, and gradient of temperature in exhaust system.

• International Journal of Computer Science & Network Security
• /
• 제21권6호
• /
• pp.35-46
• /
• 2021

Small and Medium Enterprises (SMEs) are increasingly using ERP systems to connect and manage all their functions, whether internally between the different departments, or externally with customers in electronic commerce. However, the selection of the right ERP system is usually an issue, due to the complexities of identifying the criteria, weighting them, and selecting the best system and provider. Because cost is usually important for SMEs, ERP systems based on Cloud Software as a Service (SaaS) has been adopted by many SMEs. However, SMEs face an issue of selecting the right system. Therefore, this paper proposes a fuzziness ranking engine system in order to match the SMEs requirements with the most suitable service provider. The extensive experimental result shows that our approach has better result compared with traditional approaches.