• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.2 no.2
• /
• pp.231-239
• /
• 1998

In this paper, we designed a current controlling servo system for speed control of a PMSM. In existing auto-tuning methods for PI controller parameters, the output response is delayed and the overshoot is generated. By solving these existing problems in this paper, a new PI auto-tuning method is applied to the speed controller for fast-response and reduced overshoot. PMSM servo systems offer a great advantage in unmanned factories where a great number of servo motors are employed, because of its easy maintenance characteristics and controllability. The implemented servo system is composed of absolute position detecting circuits of a rotor, a new auto-tuning PI control algorithm, a speed controller by using DSP, and power driving section. The proposed servo system is verified for it's practical availability by considering experimental results.

• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.192-201
• /
• 2002

Automated text classification is considered as an important method to manage and process a huge amount of documents in digital forms that are widespread and continuously increasing. Recently, text classification has been addressed with machine learning technologies such as k-nearest neighbor, decision tree, support vector machine and neural networks. However, only few investigations in text classification are studied on real problems but on well-organized text corpus, and do not show their usefulness. This paper proposes and analyzes text classification methods for a real application, email document classification task. First, we propose a combining method of multiple neural networks that improves the performance through the combinations with maximum and neural networks. Second, we present another strategy of combining multiple machine learning classifiers. Voting, Borda count and neural networks improve the overall classification performance. Experimental results show the usefulness of the proposed methods for a real application domain, yielding more than 90% precision rates.

• Journal of the Korean Society for Library and Information Science
• /
• v.39 no.4
• /
• pp.105-118
• /
• 2005

As the number of users who ask and give answers in the query-answer documents retrieval system is growing exponentially, the query-answer document become a crucial information resource, as a new type of information retrieval service. A query-answer document Consists of three structural parts : a query, explanation on query, and answers Chosen by users who asked the query. To identify the role of each structural part in representing the topics of documents, the three structural parts were clustered automatically and the results of several clustering tests were compared in this study.

• Journal of KIISE:Computing Practices and Letters
• /
• v.10 no.6
• /
• pp.529-536
• /
• 2004

The main idea of this paper is to combine position information in sentence and query type classification to make the documents ranking to query more accessible. First, the use of conceptual graphs for the representation of document contents In information retrieval is discussed. The method is based on well-known strategies of text comparison, such as Dice Coefficient, with position-based weighted term. Second, we introduce a method for learning query type classification that improves the ability to retrieve answers to questions from Question Answering system. Proposed methods employ naive bayes classification in machine learning fields. And, we used a collection of approximately 30,000 question-answer pairs for training, obtained from Frequently Asked Question(FAQ) files on various subjects. The evaluation on a set of queries from international TREC-9 question answering track shows that the method with machine learning outperforms the underline other systems in TREC-9 (0.29 for mean reciprocal rank and 55.1% for precision).

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.17 no.6
• /
• pp.119-126
• /
• 2003

This paper presents an algorithm of automatically finding magnitude of each maintenance index regarding step response characteristic for speed control system of driving roller in rolling process. For speed response data with noise, we distinguished possible cases that the number of maximum values is 2 or more into three separate types. Also, we suggested a way of selecting a candidate for reasonable maximum overshoot in each type and developed a decision algorithm of checking whether a candidate chosen is correct maximum overshoot. In terms of two types of test, we showed that magnitude and position in time axis of maximum overshoot can be found well via such algorithm presented in this paper.

• Journal of Satellite, Information and Communications
• /
• v.11 no.4
• /
• pp.39-43
• /
• 2016

In this paper, we propose PID gain auto tuning method in steering type mobile robot. PID controller gain select method are various methods. Ziegler-Nichols step tuning method is one method tuning in PID controller. Use step tuning method find a the first gain and did experiment in steering mobile robot. and Make a new the second gains from the first gains. After appling the second gain in PID controller, Where perform observe for convergence time and stabilization error. Experiments result the second gain are useful in real steering mobile robot system.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.1
• /
• pp.74-79
• /
• 2002

Many control techniques have been proposed in order to improve the control performance in discrete-time domain control system. In control system using these techniques, the response-characteristic of system is dependent on the gains of the controller. Specially, There is a need to readjust the gain of controller when the response of system is changed by disturbance or load fluctuation. In this paper, I-PD controller and pre-compensator are designed by multilayer neural network. The gains of I-PD controller and pre-compensator are adjusted automatically by back propagation algorithm when the response characteristic of system is changed under a condition. Applying this control technique to the position control system using a DC servo motor as a driver, the control performance of controller is verified by the results of experiment.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.15 no.6
• /
• pp.177-182
• /
• 2007

In this paper, automotive hydraulic pipeline systems are modeled in which a straight blocked pipe, two pipes with sudden expansion or contraction are connected in series and terminated with a chamber. The frequency response characteristics of these composite pipeline systems are investigated experimentally. The theoretical analysis for various pipe configurations is base on transfer matrix method with frequency dependent viscous friction distributed parameter pipeline model. The gain and phase of transfer functions are included for comparison with experimental results. There is close agreement between the results of experimental and theoretical determination of pressure response in automotive hydraulic pipeline systems.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04a
• /
• pp.517-519
• /
• 2002

현재 통신망상에서 운영되고 있는 네트워크 장애처리시스템의 가장 큰 문제점은 통신망상에서 발생한 장애를 보고하는 기능은 지니고 있지만, 이에 대한 효율적 처리의 방안이 부족하다는 것이다. 또한 발생한 장애에 대한 데이터베이스 유지와 이를 활용하여 지식 정보화를 구축하는 측면과 통신망 사용자의 문의 및 불만 상담을 처리하고, 사용자에게 장애 처리에 대한 정보를 제공하는 기능은 거의 제공되고 있지 못하다. 이러한 통신망 상에서 발생하는 장애를 효과적으로 해결하기 위해서는 장애를 처리하는 네트워크 장애처리시스템(Network Trouble Management System)이 필수적으로 요구되며, 이에 대한 운영 방식을 효율적으로 개선함으로써 통신망 장애로 인한 시간적, 경제적 손실을 최소화하고, 사용자와 관리자 모두에게 효과적인 시스템에 대한 구축의 필요성이 증대하고 있다. 본 논문에서는 전문가 기반의 장애처리시스템에 자동 응답 시스템을 접목시켜 각 분야의 전문가들을 영입하고 관리할 수 있으며, 기존의 장애 처리 데이터베이스를 활용하여 사용자에게 장애처리에 대한 방안을 제시한 수 있는 전문가 기반의 확장 장애처리시스템을 구현함으로써 사용자에게 신뢰성 있는 고부가가치의 서비스를 제공할 수 있게 하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05b
• /
• pp.947-950
• /
• 2003

최근 WBI가 발달하면서 학습자는 교수자와 의사소통을 위하여 웹이 제공하는 다양한 형태를 이용하여 상호작용을 한다. WBI에서 상호작용 수단으로 가장 보편적으로 사용되고 있는 예로 Q&A 게시판을 들 수가 있는데, 기존의 일반적인 게시판의 경우 중복 질문 등에 대한 효율적 관리 및 이용이 되지 못하고 있다. 본 논문에서는 이러한 문제점을 보완하기 위하여 반복되는 중복 질문에 자동응답처리가 가능한 게시판을 구현하였고, 또한 빈도수가 높은 중복 질문을 FAQ에 적응적으로 갱신함으로서 학습자와 교수자간에 상호작용의 효율성을 높일 수 있도록 하였다.