A Reinforcement Learning Approach to 4D Crane Lifting Simulation for Tower Crane Cycle Time Estimation

Sung Hwan Cho; SangUk Han

doi:10.55785/JCAR.1.2.13

All Issue

2022 Vol.1, Issue 2 Preview Page Next Page

A Reinforcement Learning Approach to 4D Crane Lifting Simulation for Tower Crane Cycle Time Estimation 강화학습 기반의 4D 시뮬레이션을 통한 타워크레인 양중작업 소요시간 추정

8 July 2022. pp. 13-18

PDF XML

Abstract

A tower crane is critical equipment used to deliver resources from one place to another at height. Existing approaches to crane lift planning however are often limited as path planning and lift time prediction tend to be performed separately, which may result in infeasible lift time estimation in practice. This study thus proposes the integration of reinforcement learning-based simulation with lift time prediction, taking into account the spatio-temporal characteristics of crane movements. The resulting machine learning model using as an input the cycle time estimated from simulation achieves a correlation of 0.9548 with the actual time measured in a field. The proposed approach produces more feasible results, which may more likely occur in practice, compared to the traditional ones using only historical data. This study may contribute to the improvement of planning practice by providing insight into the use of a 3D model (e.g., BIM) for the automated generation of simulation and prediction of lift time at sites.

Keywords

Tower Crane

Cycle Time

Automation

Reinforcement Learning

Machine Learning

타워 크레인 양중 계획은 고소작업장에 자원을 신속하고 효율적으로 제공하기 위해 필수적이다. 그러나 이전의 양중 계획 연구는 경로 계획과 양중 시간 예측이 각각의 주제로 따로 수행되는 경향이 있어 현장여건을 고려한 정확한 양중 시간을 예측하는데 어려움이 있다. 본 연구에서는 3차원 가상환경에서 타워크레인의 기계적 특성을 반영한 강화학습 기반의 시뮬레이션을 통해 가상의 양중작업 데이터를 생성한다. 생성된 가상 데이터와 양중 조건 데이터로부터 학습된 기계학습 모델을 사용하여 타워크레인의 양중작업 소요시간을 추정한다. 학습된 모델의 추정 소요시간은 현장 관찰된 실제 양중작업 소요시간과 0.9548의 상관 관계를 보여준다. 따라서, 제안된 접근 방식은 현장조건 및 크레인의 물리적 특성을 반영함으로써 기존 방법에 비해 더 현실적인 양중 시간을 추정할 수 있을 것이라 기대되며, 현장에서 양중 계획을 수립하거나 기존의 양중 계획을 검토하는 데 활용되리라 기대된다.

키워드

타워크레인

양중작업 소요시간

자동화

강화학습

기계학습

References

국토교통부 건설산업과 (2021). 건설기계 현황 통계, 행정정보자료, 국토교통부, 대한민국, p. 6. https://stat.molit.go.kr/portal/cate/statView.do?hRsId=476&hFormId=5409&hDivEng=&month_yn= (Accessed June 27, 2022).

조훈희 (2010). 초고층 건축공사의 양중계획 및 기술 발전 방향. 한국건설관리학회 학회지, 11(1), pp. 15-18.

Cho, C.Y., Cho, M.Y., and Shin, Y.S. (2012). Prediction model for hoisting times of tower crane using discrete-event simulation in high-rise building construction. Journal of the Architectural Institute of Korea Structure & Construction, 28(1), pp. 151-158.

Cho, S., and Han, S. (2022). Reinforcement Learning-based Tower Crane 3D Lift Planning Simulation and Automation. Automation in Construction. (under review)

Han, S., Al-Hussein, M., Hasan, S., Gökçe, K. U., and Bouferguene, A. (2012). Simulation of mobile crane operations in 3D space. Proceedings of the 2012 Winter Simulation Conference, Institute of Electrical and Electronics Engineers, Berlin, Germany, pp. 1-12. 10.1109/WSC.2012.6465165

Hu, S., Fang, Y., and Bai, Y. (2021). Automation and optimization in crane lift planning: A critical review. Advanced Engineering Informatics, 49, 101346. 10.1016/j.aei.2021.101346

Kim, J.H., Park, M., Lee, H.S., and Hyun, H. (2018). Alternative Evaluation Model for Tower Crane Operation Plan in Modular Construction - Focusing on Modular Unit Installation and Finishing works. Korean Journal of Construction Engineering and Management, 19(2), 50-60.

Koh, S.G., Kim, B.S., and Kim, B.N. (2002). Travel time model for the warehousing system with a tower crane S/R machine. Computers and Industrial Engineering, 43(3), pp. 495-507. 10.1016/S0360-8352(02)00122-5

Lee, G., Kim, H.-H., Lee, C.-J., Ham, S.-I., Yun, S.-H., Cho, H., Kim, B. K., Kim, G. T., and Kim, K. (2009). A laser-technology-based lifting-path tracking system for a robotic tower crane. Automation in Construction, 18(7), pp. 865-874.6. 10.1016/j.autcon.2009.03.011

Leung, A.W., and Tam, C.M. (1999). Prediction of hoisting time for tower cranes for public housing construction in Hong Kong. Construction Management and Economics, 17(3), pp. 305-314. 10.1080/014461999371510

Leung, A.W., Tam, C.M., and Liu, D.K. (2001). Comparative study of artificial neural networks and multiple regression analysis for predicting hoisting times of tower cranes. Building and Environment, 36(4), pp. 457-467. 10.1016/S0360-1323(00)00029-9

Tam, C.M., Leung, A.W., and Liu, D.K. (2002). Nonlinear models for predicting hoisting times of tower cranes. Journal of Computing in Civil Engineering, 16(1), pp. 76-81. 10.1061/(ASCE)0887-3801(2002)16:1(76)

Zhang, P., Harris, F.C., and Olomolaiye, P.O. (1996). A computer‐based model for optimizing the location of a single tower crane. Building research and information, 24(2), pp. 113-123. 10.1080/09613219608727511

Zhang, Z., and Pan, W. (2020). Lift planning and optimization in construction: A thirty-year review. Automation in Construction, 118, 103271. 10.1016/j.autcon.2020.103271

Information

Publisher :Korean Society of Automation and Robotics in Construction
Publisher(Ko) :(사)한국건설자동화·로보틱스학회
Journal Title :Journal of Construction Automation and Robotics
Journal Title(Ko) :건설자동화·로보틱스 논문집
Volume : 1
No :2
Pages :13-18
Received Date : 2022-06-28
Revised Date : 2022-07-07
Accepted Date : 2022-07-08
DOI :https://doi.org/10.55785/JCAR.1.2.13

Journal of Construction Automation and Robotics ISSN:2800-0552(Print) 2951-116X(Online) 건설자동화·로보틱스 논문집

All Issue