• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.9
• /
• pp.29-35
• /
• 2019

The structure of the machinery industry due to the 4th industrial revolution is changing from precision and durability to intelligent and smart machinery through sensing and interconnection(IoT). There is a growing need for research on prognostics and health management(PHM) that can prevent abnormalities in processing machines and accurately predict and diagnose conditions. PHM is a technology that monitors the condition of a mechanical system, diagnoses signs of failure, and predicts the remaining life of the object. In this study, the vibration generated during machining is measured and a classification algorithm for normal and fault signals is developed. Arbitrary fault signal is collected by changing the conditions of un stable supply cutting oil and fixing jig. The signal processing is performed to apply the measured signal to the learning model. The sampling rate is changed for high speed operation and performed machine learning using raw signal without FFT. The fault classification algorithm for 1D convolution neural network composed of 2 convolution layers is developed.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.158-158
• /
• 2015

대부분의 대규모 배수지는 고지대에 위치함으로써 자연유하를 통해 배, 급수지역으로 용수를 공급한다. 이를 위해 배수지 전단에는 가압장이 위치하여 정수장에서 처리된 용수를 고지대에 위치한 배수지로 송수한다. 이때 가압장에서 발생하는 전력소비량이 매우 높은 것으로 알려져 있으며, 효율적인 펌프운영을 통해 상당한 전력비용 절감이 가능할 것으로 판단된다. 일반적인 가압장의 운영은 시스템 운영자의 경험을 토대로 해당 가압장에 연결된 배수지의 수위에 따라 펌프의 작동여부를 결정하는 방법이 주로 사용되고 있다. 이러한 운영방법은 용수공급의 안전성을 우선시함으로써 배수지의 수위를 일정하게 유지하고자 빈번하게 펌프를 작동하게 되고 따라서 가압장에서 소모되는 전력량이 커서 운영효율 측면에서는 바람직하지 않다고 할 수 있다. 또한 빈번한 펌프의 작동으로 인해 펌프의 수명이 단축될 뿐만 아니라, 배수지내 용수의 수질저하 문제도 발생할 수 있다. 본 연구에서는 효율적인 펌프장 운영을 위해 급수지역의 24시간 용수사용량을 예측하고, 그에 따른 펌프장의 가압 유량 및 양정을 파악하여 적정용량의 펌프를 선정하고 운영함으로써 펌프의 운영비용의 최소화 및 안정적인 용수공급을 동시에 달성하고자 한다. 이를 위해, 실시간 최적화 모형을 개발하였다. 개발된 최적화 모형은 상수관망해석 프로그램(EPAENT)을 연계하여 수요절점의 수압조건 및 운영상황을 모의하였다. 최적화 기법으로는 유전자알고리즘을 사용하였으며, 실제 시스템의 운영상황를 반영하기 위한 다양한 제약조건(operational constraints)을 적용하였다. 개발된 모형은 정속펌프(혹은 On/Off 펌프) 뿐만 아니라, 최근 실무에서 널리 사용되고 있는 변속펌프(variable speed pump)를 추가적으로 고려하였다. 개발된 모형은 국내에서 실제 운영되고 있는 송, 배수 시스템에 적용하여 모형의 실무 적용가능성을 검증하였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.630-630
• /
• 2015

기존의 내배수시설에 대한 모의 및 시스템 운영과 관련하여 기존의 연구들은 강우의 설계빈도 및 제한적 호우 시나리오에 국한된 침수의 모의 및 대응에 기반을 하고 있다. 이러한 연구들의 경우 해석에 따른 모의결과에 기반하고 있기 때문에 도시지역에 실시간으로 발생하는 수문현상을 적절하게 반영하지 못하고 있으며, 이에 따른 내배수시설의 효율적 운영 및 침수발생 지점의 예측에 대한 불확실성이 크다고 볼 수 있다. 본 연구에서는 도시하천에서의 외수위 변화 예측에 따른 단기간 내 펌프 조기가동의 효과를 검토에 따른 향후 내수침수 위험성을 감소시키고자 한다. 인공신경망을 이용하여 보다 정확한 단기간 내 외수위 변동성에 대한 분석을 실시하였으며, 상하류 관측수위 기반 펌프 조기가동에 대한 운영 알고리즘을 개선하고자 한다. 이를 위해 최근 몇 년간의 하천의 홍수사상들 중 교차상관계수($R^2$) 값이 비교적 높은 다수의 수문 관측 사상들을 수집 및 적용이 필요하다고 판단되었으며 도림천 유역 내에 위치한 펌프장들에 대한 외수위 관측자료들을 수집하여 연구에 적용하였다. 인공신경망 구성을 위해 입력값으로는 상류지점의 관측 수위지점 자료를 지정하여 입력을 실시하였으며, 출력값으로는 하류단 수위지점 자료를 지정하여 수위 예측을 실시하였다. 다만 수위예측의 경우에 있어 수위를 가장 잘 대변할 수 있는 수위관측소를 선정하는 것이 매우 중요하다고 판단되었으며, 해당 연구에서는 주요 빗물펌프장들의 외수위 자료를 대표 적용하였다. 선정된 지점과 하류의 수위예측지점을 연계하여 운영할 경우 효율적인 수위 예측이 가능하기 때문이다. 결과적으로 수위관측소 지점이 빗물펌프장임을 감안하여 상류단 빗물펌프장의 유역특성이 반영된 유출특성 및 토출특성으로 인하여 하류의 수위 변동에 영향을 미치며 이는 펌프장의 방류수문 개폐시기 및 조기가동의 시점을 선정하는데 있어 밀접한 연관이 있다고 판단된다.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.735-742
• /
• 2019

In this paper, we propose a method of extracting speech features for phoneme recognition based on spikegram. The Fourier-transform-based features are widely used in phoneme recognition, but they are not extracted in a biologically plausible way and cannot have high temporal resolution due to the frame-based operation. For better phoneme recognition, therefore, it is desirable to have a new method of extracting speech features, which analyzes speech signal in high temporal resolution following the model of human auditory system. In this paper, we analyze speech signal based on a spikegram that models feature extraction and transmission in auditory system, and then propose a method of feature extraction from the spikegram for phoneme recognition. We evaluate the performance of proposed features by using a DNN-based phoneme recognizer and confirm that the proposed features provide better performance than the Fourier-transform-based features for short-length phonemes. From this result, we can verify the feasibility of new speech features extracted based on auditory model for phoneme recognition.

• Journal of Korean Library and Information Science Society
• /
• v.50 no.3
• /
• pp.191-216
• /
• 2019

This study is to suggest the revitalization plan of the medical school libraries in the future, on the basis of analysis for the overall operation situation of the medical school libraries among the medical libraries. So based on the website, it is divided into 1) whether independent homepage exists, 2) service target, 3) books, 4) classification system, 5) manpower, 6) facilities (area, number of seats available), 7) equipment (pc, printer, copy machine, etc.), 8) services, and then analyzed. Consequently, as the ways to revitalize the medical libraries, firstly, it is necessary to establish legal standards and develop guidelines for the medical school library's books, sizes, librarians, etc. Secondly, establishing a cooperative community network between medical school libraries is necessary. Thirdly, policies such as support at the national level, specialization education of librarians, development of operational guidelines, and activation of inter-library networks are needed to revitalize the medical school libraries. It is also expected that research on the actual situation of the medical libraries should be conducted at the national level or at the level of the association of medical libraries.

• Journal of Ship and Ocean Technology
• /
• v.12 no.3
• /
• pp.26-35
• /
• 2008

Recognition of real time locations of crews for a naval ship is important, not only for the operation efficiency but also for the safety of onboard crews in the ship. More than 100 crews are dwelling in a modem naval ship and they are involved in various duties. Moreover many visitors come in and out frequently while the ship is moored in a harbor. It sometimes requires considerable time and efforts to find a person for urgent mission. It would enhance the operational efficiency if locations of onboard crews are recognized and monitored in real time. An active type RFID tag, which has a specific ID number, is distributed to each crew member, which should be carried during his stay in the ship. A number of fixed type RFID readers are to be located at the major passages of the ship, which are connected to the main computer via Local Area Network. The location of a crew would be identified by the ID number of his RFID tag and the location of the RFID reader which detected the RFID tag. A middleware is needed to process the collected data in the main computer. The data is fed to application softwares, which actually display locations of the concerned crews. The software is coded using GUI (Graphic User Interface) for better user friendliness, which has the function of storing the location history of a crew, and sending warning messages to appropriate persons, if unallowable behavior is detected. An auxiliary naval ship is selected for an experimental application study of the proposed system. It turns out that the required budget and time for the realization of the system is within the allowable limits. But complementary measures to protect the privacy of onboard crews should be considered and adopted, before the application of the system is realized.

• Journal of the Korean Society for Railway
• /
• v.19 no.4
• /
• pp.555-563
• /
• 2016

Line capacity of railways is a core criterion to decide maximum trips in accordance with traffic demand and a priority in railway investment to improve transportation capability. Particularly, because two operators will start revenue services in the HSR from mid-2016, the line capacity should be carefully calculated and controlled to avoid conflicts between the maximum number of KTXs, and the number needed to guarantee the effective competition of the operators. Meanwhile, there have been many arguments about calculating the line capacity, because this number is affected by the number of trips by train types, stopping pattern and dwell time in each station, journey time, crossing or passing, safety headway between trains, etc. To deal successfully with these kinds of problems, this study proposes a simulation method to calculate the line capacity that considers train operation according to the operator's service policies.

• Journal of the Korean Society for Railway
• /
• v.18 no.6
• /
• pp.578-585
• /
• 2015

Track elastic components can be technically and economically efficient when integrated well into track superstructure of a railway network. In such cases, the elastic rail pad is larger than a 800m radius curve provides smooth rail branching and allows for high-speed operation ($V{\geq}160km/h$). High track resistance causes the tamping intervals to stand out because the constantly increasing share of the sleeper pad further extends the increase of the tamping interval and the long grinding period; the engineering and construction of the small curve radius track provides some measures for reducing the solid sounds. Installation of elastic mats under the ballast can have a good effect, particularly in the context of protection against dust during construction or extensive renovation measures when laying new lines. However, such a process requires special attention and proper installation.

• Journal of Korean Society of Water and Wastewater
• /
• v.35 no.5
• /
• pp.335-349
• /
• 2021

As the frequency of seismic disasters in Korea has increased rapidly since 2016, interest in systematic maintenance and crisis response technologies for structures has been increasing. A data-based leading management system of Lifeline facilities is important for rapid disaster response. In particular, the water supply network, one of the major Lifeline facilities, must be operated by a systematic maintenance and emergency response system for stable water supply. As one of the methods for this, the importance of the structural health monitoring(SHM) technology has emerged as the recent continuous development of sensor and signal processing technology. Among the various types of SHM, because all machines generate vibration, research and application on the efficiency of a vibration-based SHM are expanding. This paper reviews a vibration-based pipeline SHM system for seismic disaster response of water supply pipelines including types of vibration sensors, the current status of vibration signal processing technology and domestic major research on structural pipeline health monitoring, additionally with application plan for existing pipeline operation system.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.5
• /
• pp.1045-1054
• /
• 2021

As APT attacks become more frequent and sophisticated, not only the advancement of the security systems but also the competence of the cybersecurity officers of each institution that operates them is becoming increasingly important. In a large-scale cyber defence exercise with many blue teams participating and many systems to simulate and defend against, it should be possible to simulate attacks to generate various attack patterns, network payloads, and system events. However, if one RT framework is used, there is a limitation that it can be easily detected by the blue team. In the case of operating multiple RT frameworks, a lot of time and effort by experts for exercise setup and operation for each framework is required. In this paper, we propose iRF(integrated RT framework) that can automatically operate large-scale cyber defence exercise by integrating a number of open RT frameworks and RT frameworks created by ourselves.