• 시스템엔지니어링학술지
• /
• 제19권2호
• /
• pp.18-31
• /
• 2023

Exploring artificial intelligence and machine learning for nuclear safety has witnessed increased interest in recent years. To contribute to this area of research, a machine learning model capable of accurately predicting nuclear power plant response with minimal computational cost is proposed. To develop a robust machine learning model, the Best Estimate Plus Uncertainty (BEPU) approach was used to generate a database to train three models and select the best of the three. The BEPU analysis was performed by coupling Dakota platform with the best estimate thermal hydraulics code RELAP/SCDAPSIM/MOD 3.4. The Code Scaling Applicability and Uncertainty approach was adopted, along with Wilks' theorem to obtain a statistically representative sample that satisfies the USNRC 95/95 rule with 95% probability and 95% confidence level. The generated database was used to train three models based on Recurrent Neural Networks; specifically, Long Short-Term Memory, Gated Recurrent Unit, and a hybrid model with Long Short-Term Memory coupled to Convolutional Neural Network. In this paper, the System Engineering approach was utilized to identify requirements, stakeholders, and functional and physical architecture to develop this project and ensure success in verification and validation activities necessary to ensure the efficient development of ML meta-models capable of predicting of the nuclear power plant response.

• 전자공학회논문지SC
• /
• 제43권6호
• /
• pp.68-75
• /
• 2006

고 에너지 방사선을 이용하여 종양을 치료하는 과정 중 발생되는 오차를 확인하여 보다 정교한 치료를 수행함으로써 방사선치료 효율을 향상시킬 수 있다. 본 논문에서는 지금까지 주로 사용되어진 필름을 이용한 아날로그 방식대신 실 시간적으로 영상을 얻을 수 있는 디지털 방식의 비디오 기반 전자 포탈 영상 장치를 개발하였다. 시스템은 $Gd_2O_2S$ 인광판, $45^{\circ}$반사경 및 후레임 그래버를 이용 비디오 기반 전자 포탈 영상 장치를 제작하였으며 이를 방사선치료기의 QA장치로 활용하고자 하였다. 이 장치를 이용 치료기 자체의 정확도를 검증하기 위해 방사선 조사면 검증을 수행하였다. 방사선 조사면이 콜리메이터 회전오차에 의해 약 $0.6^{\circ}$틀어짐을 전자 포탈 영상 장치를 통해 획득된 영상의 윤곽선을 검출한 후 알 수 있어서 치료 위치 설정 중 발생할 수 있는 오차 확인을 위한 방사선 치료장치의 Q.A도구로 사용할 수 있었다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 추계학술대회 논문집
• /
• pp.375-378
• /
• 1995

Although laser interferometer measurement system has the advantage of range and accuracy, the traditional error measurement methods for geometric errors(two straightness and three angular errors) of a machine tool measures error components one at a time. It may also create an optical path difference and affect the measurement accuracy. In order to identify and compensate for geometric error of a moving body, an on-line measurement system for simultaneous detection of the five error components of a moving axis is required. An on-line measurement system with 5 degrees of freedom was developed for geometric error detection. Performance verification of the system was performed on an error generating mechanism. Experimental results show the feasibility of this system for identifying geometric errors of a side of machine tool.

• 한국의학물리학회지:의학물리
• /
• 제28권3호
• /
• pp.111-121
• /
• 2017

Verification of dose distribution is an essential part of ensuring the treatment planning system's (TPS) calculated dose will achieve the desired outcome in radiation therapy. Each measurement have uncertainty associated with it. It is desirable to reduce the measurement uncertainty. A best approach is to reduce the uncertainty associated with each step of the process to keep the total uncertainty under acceptable limits. Point dose patient specific quality assurance (QA) is recommended by American Association of Medical Physicists (AAPM) and European Society for Radiotherapy and Oncology (ESTRO) for all the complex radiation therapy treatment techniques. Relative and absolute point dose measurement methods are used to verify the TPS computed dose. Relative and absolute point dose measurement techniques have a number of steps to measure the point dose which includes chamber cross calibration, electrometer reading, chamber calibration coefficient, beam quality correction factor, reference conditions, influences quantities, machine stability, nominal calibration factor (for relative method) and absolute dose calibration of machine. Keeping these parameters in mind, the estimated relative percentage uncertainty associated with the absolute point dose measurement is 2.1% (k=1). On the other hand, the relative percentage uncertainty associated with the relative point dose verification method is estimated to 1.0% (k=1). To compare both point dose measurement methods, 13 head and neck (H&N) IMRT patients were selected. A point dose for each patient was measured with both methods. The average percentage difference between TPS computed dose and measured absolute relative point dose was 1.4% and 1% respectively. The results of this comparative study show that while choosing the relative or absolute point dose measurement technique, both techniques can produce similar results for H&N IMRT treatment plans. There is no statistically significant difference between both point dose verification methods based upon the t-test for comparing two means.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 춘계학술대회 논문집
• /
• pp.1591-1596
• /
• 2005

In this paper, we designed the aspheric lens by mathematical methods which are solved by refractive index. Based on these mathematical method, we manufactured the aspheric lens. Because of the usefulness of manufacturing, we used the acryl as the material. And we used a high speed machine to manufacture the aspheric lens. Also it sits in judgment the aberration of spherical distribution by using the grid fringe. Asource of laser produced by laser sheet generator passed the optical system of the aspheric lens. Though a character is to verify that the accuracy of the aspheric lens by experiment of the straight character.

• 한국가시화정보학회지
• /
• 제21권1호
• /
• pp.119-126
• /
• 2023

Acquiring experimental data for PIV verification or machine learning training data is resource-demanding, leading to an increasing interest in synthetic particle images as simulation data. Conventional synthetic particle image generation algorithms do not follow physical laws, and the use of CFD is time-consuming and requires computing resources. In this study, we propose a new method for synthetic particle image generation, based on a Physics-Informed Neural Networks(PINN). The PINN is utilized to infer the flow fields, enabling the generation of synthetic particle images that follow physical laws with reduced computation time and have no constraints on spatial resolution compared to CFD. The proposed method is expected to contribute to the verification of PIV algorithms.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2009년도 춘계 종합학술대회 논문집
• /
• pp.833-838
• /
• 2009

최근 PDA나 스마트폰 같은 휴대용 장치의 사용이 비약적으로 증가함에 따라, 이 기종의 하드웨어 플랫폼 상에서 플랫폼 독립성을 제공하는 자바 기술이 임베디드 소프트웨어 분야에 핵심 플랫폼이 되어가고 있다. 특히, 휴대용 장치에서는 자바의 여러 스펙중 KVM(Kilobyte Virtual Machine)을 사용하고 있다. 본 논문에서는 상기 구현한 KVM에 대한 검증을 위해 Java Game 응용 프로그램을 설계 및 구현 하였으며, 실시간 운영체제인 iRTOS상에서 검증하였다.

• 한국정밀공학회지
• /
• 제30권5호
• /
• pp.507-512
• /
• 2013

This paper proposes a new model to compensate for errors of a five-axis machine tool. A matrix with error components, that is, an error matrix, is separated from the error synthesis model of a five-axis machine tool. Based on the kinematics and inversion of the error matrix which can be obtained not by using a numerical method, an error compensation model is established and used to calculate compensation values of joint variables. The proposed compensation model does not need numerical methods to find the compensation values from the error compensation model, which includes nonlinear equations. An experiment using a double ball-bar is implemented to verify the proposed model.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2009년도 제40회 하계학술대회
• /
• pp.857_858
• /
• 2009

On account of small size and light weight, a high-speed machine is regarded as a key technology for many future applications of drive systems. In high-speed applications, permanent magnet (PM) synchronous motors have a number of merits such as high efficiency and high power density. Accordingly, they are suitable for driving the air-blower of a fuel cell electric vehicle (FCEV) where space and energy savings are critical. Particularly, a surface-mounted PM motor of them is mainly used as a high-speed machine. However, the motor has a fatal flaw owing to a retaining can to maintain the mechanical integrity of a rotor assembly. The can results in the increase of magnetic air-gap length in the surface-mounted PM motor. Thus, in this paper, an interior PM motor is designed in order to drive the air-blower of FCEV instead of the surface-mounted PM motor, and the experimental results of two models are compared to verify the capability of the interior PM motor for a high-speed machine.

• Journal of Platform Technology
• /
• 제10권1호
• /
• pp.20-28
• /
• 2022

인공지능기반의 건강 데이터 검증은 임상 연구에 도움을 줄 뿐만 아니라, 새로운 치료법을 개발하는데 필수 요소가 되었다. 미국 식품의약 관리국이 의학진단 분야 중 인공지능을 이용하여 성인 당뇨병 환자의 경증 이상 당뇨병성 망막증을 감지하는 의료기기 마케팅을 승인한 이래, 인공지능을 이용한 테스트가 증가하고 있다. 본 연구에서는 구글에서 지원하는 Teachable Machine 을 이용하여 이미지 분류 기반의 인공지능모델을 생성하고, 학습을 통한 예측 모델을 완성하였다. 이는 현재 만성질환의 환자들 중 발생하는 안구 질환 중 백내장의 조기 발견하는데 용이하게 할 뿐만 아니라, 눈 건강을 위해 헬스케어 프로그램으로 안 질환 예방을 위한 디지털 개인건강 헬스케어 앱을 개발하기 위한 기초 연구로 진행되었다.