A new method to determine the number of experimental data using statistical modeling methods
- 문서 유형
- 연구출판물 · 학술지 논문
- 등재
- KCISCIEScopus
- 저널 순위
- JCR Q3Scopus Q2
- 저널
- JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY31(6) · pp.2901 · 2017
- 피인용
- Web of Science 6Scopus 6KCI 4
- FWCI (Scopus)
- 0.48
- JCR IF
- JCR 2016 1.128
- ISSN
- 1738-494X
저자
- 정정호제1저자School of Mechanical Engineering, Pusan National University, Busan, South Korea
- 강영진School of Mechanical Engineering, Pusan National University, Busan, South Korea
- 임오강School of Mechanical Engineering, Pusan National University, Busan, South Korea
- 노유정교신저자School of Mechanical Engineering, Pusan National University, Busan, South Korea
초록
For analyzing the statistical performance of physical systems, statistical characteristics of physical parameters such as material properties need to be estimated by collecting experimental data. For accurate statistical modeling, many such experiments may be required, but data are usually quite limited owing to the cost and time constraints of experiments. In this study, a new method for determining a reasonable number of experimental data is proposed using an area metric, after obtaining statistical models using the information on the underlying distribution, the Sequential statistical modeling (SSM) approach, and the Kernel density estimation (KDE) approach. The area metric is used as a convergence criterion to determine the necessary and sufficient number of experimental data to be acquired. The proposed method is validated in simulations, using different statistical modeling methods, different true models, and different convergence criteria. An example data set with 29 data describing the fatigue strength coefficient of SAE 950X is used for demonstrating the performance of the obtained statistical models that use a pre-determined number of experimental data in predicting the probability of failure for a target fatigue life.
키워드
Number of experimental dataStatistical modelingSequential statistical modelingKernel density estimationArea metric
식별자
- Scopus EID
- 2-s2.0-85021289107
- WoS UID
- 000404236400033
- KCI
- ART002228125



로그인
연구물 목록으로