• 비파괴검사학회지
• /
• 제29권2호
• /
• pp.130-136
• /
• 2009

터빈은 원자력발전소의 주요기기로서 고온 고압하에서 고속회전으로 인해 신뢰성 있는 검사가 요구된다. 터빈의 가동중검사의 경우 블레이드가 조립된 상태에서 검사가 수행되며 구조적 복잡성으로 인하여 탐촉자의 접근이 제한되며, 신호 해석이 매우 어렵다. 본 연구에서는 신뢰성 높은 신호해석을 위하여 실제 터빈과 크기 및 형상이 동일한 mock-up을 제작하였다. 터빈의 key와 내표면부의 결함탐상을 위해 pulse-echo 및 TOFD 기법을 개발하였고, dovetail 검사를 위하여 위상배열 초음파탐상기법을 개발하였다. 개발된 기법들을 가동중 터빈 검사에 효율적으로 적용하기 위해 자동화 검사 scanner를 제작하였으며, 현장적용을 통하여 신뢰성을 검증하였다.

• 대한음성학회지:말소리
• /
• 제37호
• /
• pp.23-48
• /
• 1999

To improve the performance of automatic labelling system, the context-dependent demiphone unit was proposed. A phone is divided into two parts: a left demiphone that accounts for the left side coarticulation and a right demiphone that copes with the right side context. Demiphone unit provides a better training of the transition between phones. In this paper, If the length of the phone is less than 120 msec, it is split into two demiphones. If the length of the phone is greater than 120 msec, it is divided into three parts. In order to evaluate the performance of the system, we use 452 phonetically balanced words(PBW) database for training and testing phoneme models. According to the experiment, the system using proposed demiphone unit compared with that using old demiphone unit gains 3.83% improved result(71.63%) within 10ms of the duo boundary, and 2.20% improved result(86.41%) within 20ms of the true boundary.

• 대한기계학회논문집A
• /
• 제20권2호
• /
• pp.473-480
• /
• 1996

Automatic fatigue crack length measuring system using DC electrical potential method and the system control program for automatic fatigue testing under random load condition were made in this study. And using these system and control program, fatigue tests were executed under constant and random load condition. As the result, the propagation of crack in random loading can be represented Paris equaiton and log normal probability function. But constant and random load test show different crack propagation properties.

• Computers and Concrete
• /
• 제9권5호
• /
• pp.375-387
• /
• 2012

The objective of this investigation was to develop rules for automatic categorization of concrete quality using selected artificial intelligence methods based on machine learning. The range of tested materials included concrete containing a new waste material - solid residue from coal combustion in fluidized bed boilers (CFBC fly ash) used as additive. The rapid chloride permeability test - Nordtest Method BUILD 492 method was used for determining chloride ions penetration in concrete. Performed experimental tests on obtained chloride migration provided data for learning and testing of rules discovered by machine learning techniques. It has been found that machine learning is a tool which can be applied to determine concrete durability. The rules generated by computer programs AQ21 and WEKA using J48 algorithm provided means for adequate categorization of plain concrete and concrete modified with CFBC fly ash as materials of good and acceptable resistance to chloride penetration.

• IEIE Transactions on Smart Processing and Computing
• /
• 제5권2호
• /
• pp.77-84
• /
• 2016

In the field of natural language processing, Universal Networking Language (UNL) has been used by various researchers as an inter-lingual approach to automatic machine translation. The UNL system consists of two main components, namely, EnConverter for converting text from a source language to UNL, and DeConverter for converting from UNL to a target language. Currently, many projects are researching how to apply UNL to different languages. In this paper, we introduce the tools that are UNL's applications and discuss how to reuse them to encode a Vietnamese sentence into UNL expressions and decode UNL expressions into a Vietnamese sentence. The testing was done with about 1,000 Vietnamese sentences (a dictionary that includes 4573 entries and 3161 rules). In addition, we compare the proportion of sentences translated based on a direct method (Google Translator) and another one based on UNL.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1997년도 춘계학술대회 논문집
• /
• pp.602-607
• /
• 1997

Ball balance belong to a kind of automatic balancers opten referred to as direct balancer or passive mass systems. In such systems the balancing is achieved with free masses. One of the most prevalent problems encountered in washing is the vibration during spin cycle. The primary cause of this vibration is mass unbalance associated with non unform distribution of clothes. Front loading type machine of European style, especially, has inherent unbalance mass due to its shape and this then makes the vibration worse than top loading type machine, which is more popular in Korea. Since the mass distribution of cloths is random and can not be predicted in advance, direct automatic balances appear to be the only feasible alternative. The results form computer simulation and experimental testing will be presented together with stability implications.

• Journal of Biosystems Engineering
• /
• 제16권3호
• /
• pp.239-247
• /
• 1991

This study was conducted to investigate the feasbility of continuously variable V-belt transmission(CVVT) as automatic power transmission system of combine harvesters. An experimental set-up for testing the performance of CVVT and the automatic transmission system was designed and used to analyze the power transmission characteristics of CVVT. The transmission efficiency of CVVT was increased logarithmically with increase of the load of driven shaft, but was not affected by the speed ratios of transmission. More than 80% of transmission efficiency was obtained in the 25N-m load and more of driven-shaft, and the maximum efficiency was 88~91%. When rapid speed change of the CVVT was attempted, the speed of driven shaft was stabilized within about 0.4 seconds after shift operation in both cases of increasing and decreasing of the speed.

• International Journal of Railway
• /
• 제5권2호
• /
• pp.65-70
• /
• 2012

This paper introduced a novel railway system, Automatic Train Protection and Block (ATPB) briefly, which is proposed to improve the efficiency of existing regional train lines with low cost in Japan. The biggest superiority of ATPB system is a great use of universal and mature technologies, such as GPS and regular mobile telephone networks, so that there is nearly no increment of trackside equipments in the reconstruction. Then in order to guarantee the system safety, a formal model of ATPB is established and analyzed by formal method VDM++. Firstly, the specification is specified by VDM++ formally without ambiguity. Secondly, its internal consistency is proved by discharging the proof obligations. And finally, its satisfiability is checked by systematic testing, which executes specification and checks the outputs against corresponding inputs.

• ETRI Journal
• /
• 제19권4호
• /
• pp.363-388
• /
• 1997

This paper describes a research result on automatic generation of abstract test cases from formal specifications by applying many related algorithms and techniques such as the testing framework, rural Chinese postman tour and unique input output sequence concepts. In addition, an efficient algorithm for verifying the strong connectivity of the reference finite state machine and the concept of unique event sequence are explained. We made use of several techniques to from an integrated framework for abstract test case generation from LOTOS and SDL specifications. A prototype of the proposed framework has been built with special attention to real protocol in order to generate the executable test cases in an automatic way. The abstract test cases in tree and tabular combined notation (TTCN) language will be applied to the TTCN compiler in order to obtain the executable test cases which re relevant to the industrial application.

• ETRI Journal
• /
• 제37권3호
• /
• pp.502-511
• /
• 2015

Intrusion detection plays a key role in detecting attacks over networks, and due to the increasing usage of Internet services, several security threats arise. Though an intrusion detection system (IDS) detects attacks efficiently, it also generates a large number of false alerts, which makes it difficult for a system administrator to identify attacks. This paper proposes automatic fuzzy rule generation combined with a Wiener filter to identify attacks. Further, to optimize the results, simplified swarm optimization is used. After training a large dataset, various fuzzy rules are generated automatically for testing, and a Wiener filter is used to filter out attacks that act as noisy data, which improves the accuracy of the detection. By combining automatic fuzzy rule generation with a Wiener filter, an IDS can handle intrusion detection more efficiently. Experimental results, which are based on collected live network data, are discussed and show that the proposed method provides a competitively high detection rate and a reduced false alarm rate in comparison with other existing machine learning techniques.