ABSTRACT
The oil and gas industry is one of Indonesia's vital industries, and it contributes the most to the country's foreign exchange. Piping is an important piece of equipment in the oil and gas production facilities; therefore, the piping inspection plan should be well prepared. An integral part of inspection plan development is a piping circuit; it allows an inspector to manage the necessary inspections, calculations, and better recordkeeping. A problem faced in piping circuit development is the need for relatively many working hours and variability results. Although this problem is often encountered, piping circuit development generated by manual work is still common in practice. To overcome the issues in the piping circuit development, therefore a k-prototype algorithm was introduced. A k-prototype algorithm was used to accommodate the shortcomings in grouping objects with features comprised of mixed categorical and numerical data. This study concludes that the k-prototype algorithm is a promising clustering technique that can reduce the time spent developing the piping circuit and eliminating the resulting variability.
Supplemental Material
Available for Download
- Arum Sutrisni Putri, “Potensi Sumber Daya Alam Minyak Bumi,” kompas.com, May 2020.Google Scholar
- American Petroleum Institute, API 580 - Risk Based Inspection, 3rd ed., no. February. Washington D.C.: API, 2016.Google Scholar
- American Petroleum Institute, “API 574 - Inspection Practices for Piping System Components,” no. November, 2016.Google Scholar
- A. Rachman and R. M. C. Ratnayake, “Corrosion loop development of oil and gas piping system based on machine learning and group technology method,” J. Qual. Maint. Eng., vol. 26, no. 3, pp. 349–368, 2019, doi: 10.1108/JQME-07-2018-0058.Google ScholarCross Ref
- M. K. Chang, R. R. Chang, C. M. Shu, and K. N. Lin, “Application of risk based inspection in refinery and processing piping,” J. Loss Prev. Process Ind., vol. 18, no. 4–6, pp. 397–402, 2005, doi: 10.1016/j.jlp.2005.06.036.Google ScholarCross Ref
- N. N. Farahin and W. Pao, “Prototype of Piping Inspection and Maintenance Protocol,” 2012, doi: 10.13140/RG.2.2.27260.95366.Google Scholar
- P.-N. Tan, M. Steinbach, and V. Kumar, Introduction to Data Mining. Pearson Addison Wesley, 2006.Google ScholarDigital Library
- D. T. Larose and C. D., Data Mining and Predictive Analytics, Second Edi. John Wiley & Sons, Inc, 2015.Google ScholarDigital Library
- Z. Wang and S. Li, “Data-driven risk assessment on urban pipeline network based on a cluster model,” Reliab. Eng. Syst. Saf., vol. 196, no. January 2019, p. 106781, 2020, doi: 10.1016/j.ress.2019.106781.Google ScholarCross Ref
- P. E. Bhaskaran, M. Chennippan, and T. Subramaniam, “Future prediction & estimation of faults occurrences in oil pipelines by using data clustering with time series forecasting,” J. Loss Prev. Process Ind., vol. 66, no. June, p. 104203, 2020, doi: 10.1016/j.jlp.2020.104203.Google ScholarCross Ref
- F. S. Hashemi-Nasab and H. Parastar, “Pattern recognition analysis of gas chromatographic and infrared spectroscopic fingerprints of crude oil for source identification,” Microchem. J., vol. 153, no. September 2019, p. 104326, 2020, doi: 10.1016/j.microc.2019.104326.Google ScholarCross Ref
- J. S. Al-Thuwaini, G. Zangl, and R. Phelps, “Innovative approach to assist history matching using artificial intelligence,” 2006 SPE Intell. Energy Conf. Exhib., vol. 2, pp. 405–411, 2006, doi: 10.2118/99882-ms.Google ScholarCross Ref
- S. Harous, M. Al Harmoodi, and H. Biri, “A Comparative Study of Clustering Algorithms for Mixed Datasets,” in Proceedings - 2019 Amity International Conference on Artificial Intelligence, AICAI 2019, 2019, pp. 484–488, doi: 10.1109/AICAI.2019.8701347.Google ScholarCross Ref
- Z. Huang, “Clustering Large Data Sets with Mixed Numeric and Categorical Values,” in The First Pacific Asia Knowledge Discovery and Data Mining Conference, 1997, pp. 21–34, doi: 10.1117/12.538864.Google Scholar
- Z. Huang, “Extensions to the k-Means Algorithm for Clustering Large Data Sets with Categorical Values.,” Data Min. Knowl. Discov., vol. 2, no. 3, pp. 283–304, 1998.Google ScholarDigital Library
- A. Ahmad and L. Dey, “A k-mean clustering algorithm for mixed numeric and categorical data,” Data Knowl. Eng., vol. 63, no. 2, pp. 503–527, 2007, doi: 10.1016/j.datak.2007.03.016.Google ScholarDigital Library
- S. Esmaeilzadeh, A. Salehi, G. Hetz, F. Olalotiti-lawal, H. Darabi, and D. Castineira, “Multiscale modeling of compartmentalized reservoirs using a hybrid clustering-based non-local approach,” J. Pet. Sci. Eng., vol. 184, no. April 2019, p. 106485, 2020, doi: 10.1016/j.petrol.2019.106485.Google ScholarCross Ref
- M. Jannadi and K. Ben Driss, “Composed clustering of non-relational data with mixed types using K-modes and K-prototypes algorithms,” 2020, doi: 10.1145/3423603.3424050.Google ScholarDigital Library
- J. Ji, W. Pang, C. Zhou, X. Han, and Z. Wang, “A fuzzy k-prototype clustering algorithm for mixed numeric and categorical data,” Knowledge-Based Syst., vol. 30, pp. 129–135, 2012, doi: 10.1016/j.knosys.2012.01.006.Google ScholarDigital Library
- J. Li, X. Gao, and L. C. Jiao, “A GA-Based Clustering Algorithm for Large Data Sets With Mixed Numeric and Categorical Values,” in Proceedings - 5th International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 2003, 2003, pp. 102–107, doi: 10.1109/ICCIMA.2003.1238108.Google ScholarCross Ref
Index Terms
- Piping Circuit Development using K-Prototype Clustering
Recommendations
Self-Organizing-Map Based Clustering Using a Local Clustering Validity Index
Classical clustering methods, such as partitioning and hierarchical clustering algorithms, often fail to deliver satisfactory results, given clusters of arbitrary shapes. Motivated by a clustering validity index based on inter-cluster and intra-cluster ...
Improving a Centroid-Based Clustering by Using Suitable Centroids from Another Clustering
AbstractFast centroid-based clustering algorithms such as k-means usually converge to a local optimum. In this work, we propose a method for constructing a better clustering from two such suboptimal clustering solutions based on the fact that each ...
Real Coded Genetic Algorithm for Development of Optimal G-K Clustering Algorithm
Swarm, Evolutionary, and Memetic ComputingAbstractClustering has been used as a popular technique for identifying a natural grouping or meaningful partition of a given data set by using a distance or similarity function. This paper proposes a novel real coded Genetic algorithm (GA) for the ...
Comments