Recently, the amount of data to be processed and the complexity thereof have been increasing due to the development of information and communication technology, and industry's interest in such big data is increasing day by day. In the shipbuilding and offshore industry also, there is growing interes...
Recently, the amount of data to be processed and the complexity thereof have been increasing due to the development of information and communication technology, and industry's interest in such big data is increasing day by day. In the shipbuilding and offshore industry also, there is growing interest in the effective utilization of data, since various and vast amounts of data are being generated in the process of design, production, and operation. In order to effectively utilize big data in the shipbuilding and offshore industry, it is necessary to store and process large amounts of data. In this study, it was considered efficient to apply Hadoop and R, which are mostly used in big data related research. Hadoop is a framework for storing and processing big data. It provides the Hadoop Distributed File System (HDFS) for storing big data, and the MapReduce function for processing. Meanwhile, R provides various data analysis techniques through the language and environment for statistical calculation and graphics. While Hadoop makes it is easy to handle big data, it is difficult to finely process data; and although R has advanced analysis capability, it is difficult to use to process large data. This study proposes a big data platform based on Hadoop for applications in the shipbuilding and offshore industry. The proposed platform includes the existing data of the shipyard, and makes it possible to manage and process the data. To check the applicability of the platform, it is applied to estimate the weights of offshore structure topsides. In this study, we store data of existing FPSOs in Hadoop-based Hortonworks Data Platform (HDP), and perform regression analysis using RHadoop. We evaluate the effectiveness of large data processing by RHadoop by comparing the results of regression analysis and the processing time, with the results of using the conventional weight estimation program.
Recently, the amount of data to be processed and the complexity thereof have been increasing due to the development of information and communication technology, and industry's interest in such big data is increasing day by day. In the shipbuilding and offshore industry also, there is growing interest in the effective utilization of data, since various and vast amounts of data are being generated in the process of design, production, and operation. In order to effectively utilize big data in the shipbuilding and offshore industry, it is necessary to store and process large amounts of data. In this study, it was considered efficient to apply Hadoop and R, which are mostly used in big data related research. Hadoop is a framework for storing and processing big data. It provides the Hadoop Distributed File System (HDFS) for storing big data, and the MapReduce function for processing. Meanwhile, R provides various data analysis techniques through the language and environment for statistical calculation and graphics. While Hadoop makes it is easy to handle big data, it is difficult to finely process data; and although R has advanced analysis capability, it is difficult to use to process large data. This study proposes a big data platform based on Hadoop for applications in the shipbuilding and offshore industry. The proposed platform includes the existing data of the shipyard, and makes it possible to manage and process the data. To check the applicability of the platform, it is applied to estimate the weights of offshore structure topsides. In this study, we store data of existing FPSOs in Hadoop-based Hortonworks Data Platform (HDP), and perform regression analysis using RHadoop. We evaluate the effectiveness of large data processing by RHadoop by comparing the results of regression analysis and the processing time, with the results of using the conventional weight estimation program.
* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.
문제 정의
This chapter describes Hadoop and Hortonworks Data Platform (HDP), which is a big data platform based on Hadoop for applying big data in the shipbuilding and offshore industry.
This chapter examines the applicability of the Hadoop-based big data platform to the shipbuilding and offshore industry. Items that can utilize big data in the shipbuilding and offshore industry include new ship design and development, process optimization, model test substitution, and weight estimation.
제안 방법
In this study, statistical correlation analysis and regression analysis were performed using 37 existing FPSO data, and as a result, weight estimation formulas of FPSO topside were derived. We apply linear and nonlinear methods to regression analysis, and use R language for this process.
The big data platform proposed in this study is to improve the existing large-capacity data for Hadoopbased distributed storage (HDFS), to process data for the application purpose (MapReduce), and to store the processed data. We use RHadoop on HDP to implement the proposed platform practically, and verify that HDFS and MapReduce can be used effectively.
Therefore, this study suggests the big data platform for practical use of big data in the shipbuilding and offshore industry, and verifies its applicability by applying it to FPSO topside weight estimation. The effectiveness of large data processing by RHadoop is evaluated by comparing the results of regression analysis and the processing time with the results of the conventional weight estimation program.
2 GB, the 37 FPSO data were copied and pasted. Then, using these data, FPSO topside weight estimation was carried out with the R built-in function, biglm package, and RHadoop package to compare the processing speed.
If this big data can be effectively utilized in the shipbuilding and offshore industry, it will be possible to increase productivity and efficiency in various tasks, such as new ship design and development, process optimization, substitution of model test, and weight estimation. Therefore, this study proposes a platform using Hadoop, which is a representative big data framework, and applies it to the weight estimation of offshore structure topsides, to examine the applicability of big data in the shipbuilding and offshore industry.
However, effective research for actual application is very rare. Therefore, this study suggests the big data platform for practical use of big data in the shipbuilding and offshore industry, and verifies its applicability by applying it to FPSO topside weight estimation. The effectiveness of large data processing by RHadoop is evaluated by comparing the results of regression analysis and the processing time with the results of the conventional weight estimation program.
This section verifies the accuracy of the FPSO weight estimation formulas obtained through correlation analysis and linear/nonlinear regression analysis by comparing the FPSO topside weight with the results of weight estimation.
이론/모형
In other words, the larger the correlation coefficient, the more closely the two variables are related. Correlation coefficients can be obtained by the Pearson method, which is a parametric correlation coefficient, and the Spearman method, which is a nonparametric correlation coefficient, depending on whether or not variables follow certain distributions (normal distribution, t-distribution, etc.). The Pearson method was used in this study, assuming a correlation coefficient of 0.
후속연구
In the future, we plan to apply the platform proposed in this study by deriving more diverse and vast data application targets in the shipbuilding and offshore industry.
Therefore, this study proposes a big data platform for application in the shipbuilding and offshore industry. Fig.
As mentioned above, some researches have been carried out to apply big data to the shipbuilding and offshore industry, but there are few cases that used big data technology, and applied it practically. Therefore, this study proposes a platform to effectively utilize big data, and evaluate its applicability and utility in the shipbuilding and offshore industry, through application to an example. Table 1 compares the related studies mentioned above to this study.
참고문헌 (14)
Bae, D.M., Park, H. S. and Oh, K. H., 2013, Big Data Trend and Policy Implication, Information and Communication Policy, 25(10) (2013) pp.37-74.
Ha, S., Seo, S.H., Roh, M.I. and Shin, H.K., Simplified Nonlinear Model for the Weight Estimation of FPSO Plant Topside Using the Statistical Method, Ships and Offshore Structures, 11(6) (2016) pp.603-619.
Ha, S., Um, T.S., Roh, M.I. and Shin, H.K., A Structural Weight Estimation Model of FPSO Topsides using an Improved Genetic Programming Method, Ships and Offshore Structure, 12(1) (2017) pp.43-55.
Lee, D.H., Analysis of Production Process in Shipbuilding Industry using Process Mining, Ph.D. thesis, Pusan National University (2014), Korea.
Lee, H.H., Application of Big Data for Strengthen of Manufacturing Business, Seoul, Korea: Korea Institute for Industrial Economics and Trade (KIET), (2013).
Kim, K.I., Jung, J.S. and Park, K.K., Assessment of External Force Acting on Ship using Big Data in Maritime Traffic, Journal of Korea Intelligent Information System Society, 23(5) (2013) pp.379-384.
Kim, S.R. and Kang, M.M., The Trends and Prospects in Cloud-Based Bigdata Technology, Journal of Korean Institute of Information Scientists and Engineers, 32(2) (2014) pp.22-31.
Kim, S.R. and Kang, M.M., Today and Tomorrow of Big Data Analysis Technology, Journal of Institute of Information Scientists and Engineers, 32(1) (2014) pp.8-17.
Kim, U.G., Ship & Offshore industry and Big Data collected during Operation of Ships as ICT Convergence Model, Journal of Mechanical Science and Technology, 54(12) (2014) pp.49-52.
Kim, Y.J., Park, J.K., Lee, J.H., Yang, H.Y. and Jung, M.A., A Study on the Bigdata Technology and Analysis Technique for Vessel Design Automation, Journal of Korea Institute of Communication Sciences, 2013(6) (2013) pp.213-215.
Kim, W.K., Park, M.K. and Han, M.K., Design of a Framework for Support System of Ship Design Engineering, Journal of Korea Institute of Information and Communication Engineering, 16(10) (2012) pp.2316-2322.
Perera, L.P., Handling Big Data in Ship Performance & Navigation Monitoring, Smart Ship Technology, London, UK, January 24-25, (2017)
Um, T.S., Roh, M.I., Shin, H.K. and Ha, S., Simplified Model for the Weight Estimation of Floating Offshore Structure Using the Genetic Programming Method, Transactions of the Society of CAD/CAM Engineers, 19(1) (2014) pp.1-11.
Wang, H., Osen, O.L., Li, G., Li, W., Dai, HN. and Zeng, W., Big Data and Industrial Internet of Things for the Maritime Industry in Northwestern Norway, IEEE Region 10 Conference, Macao, China, November 1-4, (2015), doi: 10.1109/TENCON.2015.7372918
※ AI-Helper는 부적절한 답변을 할 수 있습니다.