A Study on the Performance Degradation Pattern of Caisson-type Quay Wall Port Facilities

doi:10.15683/kosdi.2022.3.31.146

All Issue

2022 Vol.18, Issue 1 Preview Page Next Page

Original Article

A Study on the Performance Degradation Pattern of Caisson-type Quay Wall Port Facilities 케이슨식 안벽 항만시설의 성능저하패턴 연구: 나용현¹, 박미연²*, 장신우³
Yong Hyoun Na¹, Mi Yeon Park²*, Shinwoo Jang³; ¹Chief Researcher, SH Tech & Policy Institute Co., Seongnam, Republic of Korea
²PH.D, SH Tech & Policy Institute Co., Seongnam, Republic of Korea
³Application Engineer, RaonX Solutions Inc., Seongnam, Republic of Korea

31 March 2022. pp. 146-153

PDF

Abstract

Purpose: In the case of domestic port facilities, port structures that have been in use for a long time have many problems in terms of safety performance and functionality due to the enlargement of ships, increased frequency of use, and the effects of natural disasters due to climate change. A big data analysis method was studied to develop an approximate model that can predict the aging pattern of a port facility based on the maintenance history data of the port facility. Method: In this study, member-level maintenance history data for caisson-type quay walls were collected, defined as big data, and based on the data, a predictive approximation model was derived to estimate the aging pattern and deterioration of the facility at the project level. A state-based aging pattern prediction model generated through Gaussian process (GP) and linear interpolation (SLPT) techniques was proposed, and models suitable for big data utilization were compared and proposed through validation. Result: As a result of examining the suitability of the proposed method, the SLPT method has RMSE of 0.9215 and 0.0648, and the predictive model applied with the SLPT method is considered suitable. Conclusion: Through this study, it is expected that the study of predicting performance degradation of big data-based facilities will become an important system in decision-making regarding maintenance.

Keywords

Big Data

Gaussian Process

Linear Interpolation

Condition Evaluation

Revised Project Level

Influence Factor

Machine Learning

연구목적: 국내 항만시설의 경우 사용년수가 오래된 항만구조물은 선박의 대형화 및 사용빈도 증가, 기후변화에 따른 자연재해의 영향 등으로 안전과 기능적 측면에서 상당히 많은 문제가 있다. 항만시설의 유지관리 이력 데이터를 기반으로 시설 노후화 패턴을 예측 할 수 있는 근사모델 개발을 위하여 빅데이터 분석 방법을 연구하였다. 연구방법: 본 연구에서는 케이슨식 안벽에 유지관리 데이터 수집하여 빅데이터를 바탕으로 시설물의 노후화 패턴 및 성능저하를 확인하기 위한 예측모델을 도출하였다. 가우시안 프로세스(GP)과 선형보간(SLPT) 기법을 통하여 생성된 상태기반 노후도 패턴 예측모델을 제안하고 유효성 검토를 통해 빅데이터 적용에 적합한 모델을 비교하고 제안하였다. 연구결과: 제안된 기법을 검토한 결과 SLPT기법은 RMSE 및 는 0.9215와 0.0648로 SLPT기법의 예측모델이 보다 더 적합한 것으로 검토 되었다. 결론: 이러한 연구를 통해 빅데이터 기반 시설물 성능저하 예측 연구는 유지관리를 위환 의사결정에서 중요한 체계가 될 것으로 기대된다.

키워드

빅데이터

가우시안 프로세스

선형보간

상태평가

영향인자

머신러닝

References

Port Association (2010). Unit Model Development for LCC Analysis Program at Port Facility Design Stage, p. 40.
Kim, S.W., Cha, K.H., Kim, J.H., Park, M.Y., Kong, J.S. (2012). "Development of condition state model for open type wharf considering deterioration factors." Korean Society of Civil Engineers, Vol. 28, No, 3, pp. 2138-2141.
Kim, H.J., Ju, G.N., Yun, C.H. (2012). "Science big data processing technology trend." The Korea Institute of Information and Communication Engineering, Vol. 29, No. 11, pp. 11-23.
Song, M.G., Kim, S.B. (2013). "A study of improving reliability on prediction model by analyzing method big data." The Journal of Digital Policy & Management, Vol. 11, pp. 103-112.
Kim, D.H., Jo, B.W. (2021). "A study on the development of a fire site risk prediction model based on initial information using big data analysis." Journal of the Korea Society of Disaster Information, Vol. 17, No. 2, pp. 245-253.
Rasmussen, C.E. (2004). Gaussian Processes in Machine Learning. Advanced Lectures on Machine Learning, pp. 63-71. 10.1007/978-3-540-28650-9_4
Belyaev, M., Burnaev, E., Kapushev, Y. (2015). "Gaussian process regression for structured data sets." Lecture Notes in Artificial Intelligence, Proceedings of SLDS, Vol. 9047, pp. 106-115. 10.1007/978-3-319-17091-6_6
Tan, M.H.Y, Li, G. (2019). "Gaussian process modeling using the principle of superposition." Technometrics, Vol. 61, No. 2, pp. 202-218. 10.1080/00401706.2018.1473799

Information

Publisher :The Korean Society of Disaster Information
Publisher(Ko) :한국재난정보학회
Journal Title :Journal of the Society of Disaster Information
Journal Title(Ko) :한국재난정보학회논문집
Volume : 18
No :1
Pages :146-153
DOI :https://doi.org/10.15683/kosdi.2022.3.31.146

[1] Port Association (2010). Unit Model Development for LCC Analysis Program at Port Facility Design Stage, p. 40.

[2] Kim, S.W., Cha, K.H., Kim, J.H., Park, M.Y., Kong, J.S. (2012). "Development of condition state model for open type wharf considering deterioration factors." Korean Society of Civil Engineers, Vol. 28, No, 3, pp. 2138-2141.

[3] Kim, H.J., Ju, G.N., Yun, C.H. (2012). "Science big data processing technology trend." The Korea Institute of Information and Communication Engineering, Vol. 29, No. 11, pp. 11-23.

[4] Song, M.G., Kim, S.B. (2013). "A study of improving reliability on prediction model by analyzing method big data." The Journal of Digital Policy & Management, Vol. 11, pp. 103-112.

[5] Kim, D.H., Jo, B.W. (2021). "A study on the development of a fire site risk prediction model based on initial information using big data analysis." Journal of the Korea Society of Disaster Information, Vol. 17, No. 2, pp. 245-253.

[6] Rasmussen, C.E. (2004). Gaussian Processes in Machine Learning. Advanced Lectures on Machine Learning, pp. 63-71. 10.1007/978-3-540-28650-9_4

[7] Belyaev, M., Burnaev, E., Kapushev, Y. (2015). "Gaussian process regression for structured data sets." Lecture Notes in Artificial Intelligence, Proceedings of SLDS, Vol. 9047, pp. 106-115. 10.1007/978-3-319-17091-6_6

[8] Tan, M.H.Y, Li, G. (2019). "Gaussian process modeling using the principle of superposition." Technometrics, Vol. 61, No. 2, pp. 202-218. 10.1080/00401706.2018.1473799

Journal of the Society of Disaster Information ISSN:1976-2208(Print) 2671-5287(Online) 한국재난정보학회논문집

All Issue