International Journal of Naval Architecture and Ocean Engineering

The Society of Naval Architects of Korea (대한조선학회)
권호 표지
DOI QR코드

DOI QR Code

Machine Learning Methodology for Management of Shipbuilding Master Data

  • Received : 2019.06.19
  • Accepted : 2020.03.03
  • Published : 2020.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

The continuous development of information and communication technologies has resulted in an exponential increase in data. Consequently, technologies related to data analysis are growing in importance. The shipbuilding industry has high production uncertainty and variability, which has created an urgent need for data analysis techniques, such as machine learning. In particular, the industry cannot effectively respond to changes in the production-related standard time information systems, such as the basic cycle time and lead time. Improvement measures are necessary to enable the industry to respond swiftly to changes in the production environment. In this study, the lead times for fabrication, assembly of ship block, spool fabrication and painting were predicted using machine learning technology to propose a new management method for the process lead time using a master data system for the time element in the production data. Data preprocessing was performed in various ways using R and Python, which are open source programming languages, and process variables were selected considering their relationships with the lead time through correlation analysis and analysis of variables. Various machine learning, deep learning, and ensemble learning algorithms were applied to create the lead time prediction models. In addition, the applicability of the proposed machine learning methodology to standard work hour prediction was verified by evaluating the prediction models using the evaluation criteria, such as the Mean Absolute Percentage Error (MAPE) and Root Mean Squared Logarithmic Error (RMSLE).

Keywords

Acknowledgement

This work was partly supported by National IT Industry Promotion Agency grant funded by Ministry of Science and ICT of Korea (S0604-17-1001, Prediction based smart SCM framework for offshore industry and S1106-16-1020, Production strategy and execution simulation technology development for the optimization of offshore plant production cost). Also, this work was partly supported by Korea Evaluation Institute of Industrial Technology grant funded by the Ministry Of Trade, Industry and Energy of Korea (10050495, Development of the simulation based production management system for the middle-sized shipbuilding companies).

References

  1. Ham, D.K., 2016. A Study of Data-Mining Methodology in Offshore Plant's Out-fittings Procurement Management. Dissertation, Korea Maritime & Ocean University.
  2. Ham, D.K., Back, M.G., Park, J.G., Woo, J.H., 2016. A study of piping leadtime forecast in offshore plant's outfittings procurement management. J. Soc. Nav. Archit. Korea 53 (1), 29-36. https://doi.org/10.3744/SNAK.2016.53.1.29
  3. Hur, M.H., Lee, S.K., Kim, B.S., Cho, S.Z., Lee, D.H., Lee, D.H., 2015. A study on the man-hour prediction system for shipbuilding. J. Intell. Manuf. 26 (6), 1267-1279. https://doi.org/10.1007/s10845-013-0858-3
  4. Jo, S.J., Kang, S.H., 2016. Industrial applications of machine learning (artificial intelligence). Ind. Eng. Mag. 23 (2), 34-38.
  5. Jung, S.H., Sim, C.B., 2014. A study on a working pattern analysis prototype using correlation analysis and linear regression analysis in welding BigData environment. . Korea Inst. Electronic Commun. Sci. 9 (10), 1071-1078. https://doi.org/10.13067/JKIECS.2014.9.10.1071
  6. Kim, S.H., Roh, M.I., Kim, K.S., 2016. A study on big data platform based on Hadoop for the applications in ship and offshore industry. Korean J. Comput. Des. Eng. 21 (3), 334-340. https://doi.org/10.7315/CDE.2016.334
  7. Lee, Y.H., 2017. A Reference Model for Big Data Analysis in Shipbuilding Industry. Dissertation. Ulsan National Institute of Science and Technology.
  8. Lee, B.W., Yang, J.H., 2008. Ensemble learning of region experts. J. Korea Inf. Sci. Soc. 35 (1A), 120-121.
  9. Lee, J.G., Lee, T.H., Yun, S.R., 2014a. Machine learning for big data analysis. J. Korean Inst. Commun. Sci. 31 (11), 14-26.
  10. Lee, S.K., Kim, B.S., Huh, M.H., Part, J.S., Kang, S.K., Cho, S.Z., Lee, D.G., Lee, D.H., 2014b. Knowledge discovery in inspection reports of marine structures. Expert Syst. Appl. 41 (4), 1153-1167. https://doi.org/10.1016/j.eswa.2013.07.109
  11. Oh, M.J., Roh, M.I., Park, S.W., Kim, S.H., 2018. Estimation of material requirement of piping materials in an offshore structure using big data analysis. J. Soc. Nav. Archit. Korea 55 (3), 243-251. https://doi.org/10.3744/SNAK.2018.55.3.243

Cited by

  1. Hybrid NHPSO-JTVAC-SVM Model to Predict Production Lead Time vol.11, pp.14, 2020, https://doi.org/10.3390/app11146369
  2. One-Dimensional Convolutional Neural Networks for Hyperspectral Analysis of Nitrogen in Plant Leaves vol.11, pp.24, 2021, https://doi.org/10.3390/app112411853