Investigating an SVM-driven, one-class approach to estimating ship systems condition

References

• Bergstra JS, Bardenet R, Bengio Y, Kégl B. 2011. Algorithms for hyper-parameter optimization. In: Shawe-Taylor J, Zemel RS, Bartlett P, Pereira F, Weinberger KQ, editors. 25th Annual Conference on Neural Information Processing Systems (NIPS 2011); Dec 24; Granada, Spain. Neural Information Processing Systems Foundation, Advances in Neural Information Processing Systems.
   Google Scholar
• Chandroth G. 2004. Condition monitoring: the case for integrating data from independent sources. J Marine Eng Technol. 3(1):9–16. doi: 10.1080/20464177.2004.11020175
   Google Scholar
• Chang CC, Lin CJ. 2001. Training ν-support vector classifiers: theory and algorithms. Neural Comput. 13(9):2119–2147. doi: 10.1162/089976601750399335
   PubMed Web of Science ®Google Scholar
• Chawla NV, Japkowicz N, Kotcz A. 2004. Editorial: special issue on learning from imbalanced data sets. SIGKDD Explor Newsl. 6(1):1–6. doi: 10.1145/1007730.1007733
   Google Scholar
• Cipollini F, Oneto L, Coraddu A, Murphy AJ, Anguita D. 2018a. Condition-based maintenance of naval propulsion systems: data analysis with minimal feedback. Reliab Eng Syst Safe. 177:12–23.
   Web of Science ®Google Scholar
• Cipollini F, Oneto L, Coraddu A, Murphy AJ, Anguita D. 2018b. Condition-based maintenance of naval propulsion systems with supervised data analysis. Ocean Eng. 149:268–278. doi: 10.1016/j.oceaneng.2017.12.002
   Web of Science ®Google Scholar
• Coraddu A, Oneto L, Ghio A, Savio S, Anguita D, Figari M. 2016. Machine learning approaches for improving condition-based maintenance of naval propulsion plants. Proc Inst Mech Eng Part M. 230(1):136–153. doi: 10.1177/0954405415596141
   Web of Science ®Google Scholar
• Cortes C, Vapnik V. 1995. Support-vector networks. Mach Learn. 20(3):273–297.
   Web of Science ®Google Scholar
• Croarkin C, Tobias P, Filliben JJ, Hembree B, Guthrie W, Trutna L, Prins J, editors. 2018. NIST/SEMATECH e-handbook of statistical methods. NIST/SEMATECH. [accessed 2018 May 1]. http://www.itl.nist.gov/div898/handbook/.
   Google Scholar
• Dikis K. 2017. Establishment of a novel predictive reliability assessment strategy for ship machinery [dissertation]. University of Strathclyde, Department of Naval Architecture, Ocean and Marine Engineering.
   Google Scholar
• Dikis K, Lazakis I. 2016. Dynamic risk and reliability assessment of ship machinery and equipment. The 26th International Ocean and Polar Engineering Conference. Rodos (Rhodes), Greece: International Society of Offshore and Polar Engineers. p. 969–976.
   Google Scholar
• Dikis K, Lazakis I, Michala A, Raptodimos Y, Theotokatos G. 2017. Dynamic risk and reliability assessment for ship machinery decision making. Risk, Reliability and Safety: Innovating Theory and Practice – Proceedings of the 26th European Safety and Reliability Conference, ESREL 2016; Glasgow, Scotland. p. 685–692.
   Google Scholar
• Dinwoodie I. 2014. Modelling the operation and maintenance of offshore wind farms [dissertation]. University of Strathclyde, Department of Electronic and Electrical Engineering.
   Google Scholar
• Geman S, Bienenstock E, Doursat R. 1992. Neural networks and the bias/variance dilemma. Neural Comput. 4(1):1–58. doi: 10.1162/neco.1992.4.1.1
   Web of Science ®Google Scholar
• Gkerekos C, Lazakis I, Theotokatos G. 2016. Ship machinery condition monitoring using vibration data through supervised learning. In: Lazakis I, Theotokatos G, editors. Proceedings of MSO2016, International Conference on Maritime Safety and Operations; October; Glasgow, Scotland: University of Strathclyde Print Services. p. 103–110.
   Google Scholar
• Gkerekos C, Lazakis I, Theotokatos G. 2017a. Implementation of a self-learning algorithm for main engine condition monitoring. In: Soares C, Teixeira A, editors. Maritime transportation and harvesting of sea resources; vol. 2; 7. Croydon: CRC Press. p. 981–989.
   Google Scholar
• Gkerekos C, Lazakis I, Theotokatos G. 2017b. Ship machinery condition monitoring using performance data through supervised learning. Proceedings of Smart Ships Technology 2017 Conference; 1. London: Royal Institution of Naval Architects (RINA). p. 105–111.
   Google Scholar
• Gkerekos C, Lazakis I, Theotokatos G. 2018. Exploiting machine learning for ship systems anomaly detection and healthiness forecasting. Proceedings of Smart Ships Technology 2018 Conference; 1. London: Royal Institution of Naval Architects (RINA). p. 1–6.
   Google Scholar
• Hastie T, Tibshirani R, Friedman J. 2001. The elements of statistical learning. Springer Series in Statistics. New York (NY): Springer.
   Google Scholar
• Hountalas DT. 2000. Prediction of marine diesel engine performance under fault conditions. Appl Therm Eng. 20(18):1753–1783. doi: 10.1016/S1359-4311(00)00006-5
   Web of Science ®Google Scholar
• Hsu C-W, Chang C-C, Lin C-J. 2016. A Practical Guide to Support Vector Classification. [accessed 2018 May 1]. https://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf.
   Google Scholar
• Khan SS, Madden MG. 2010. A survey of recent trends in one class classification. In: Coyle L, Freyne J, editors. Artificial intelligence and cognitive science. Berlin: Springer; p. 188–197.
   Google Scholar
• Kohavi R. 1995. A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Mellish CS, editor. Proceedings of the 14th International Joint Conference on Artificial Intelligence; vol 2, p. 1137–1143.
   Google Scholar
• Kowalski J, Krawczyk B, Woźniak M. 2017. Fault diagnosis of marine 4-stroke diesel engines using a one-vs-one extreme learning ensemble. Eng Appl Artif Intell. 57:134–141. doi: 10.1016/j.engappai.2016.10.015
   Web of Science ®Google Scholar
• Lamaris V, Hountalas D. 2010. A general purpose diagnostic technique for marine diesel engines – application on the main propulsion and auxiliary diesel units of a marine vessel. Energy Convers Manag. 51(4):740–753. doi: 10.1016/j.enconman.2009.10.031
   Web of Science ®Google Scholar
• Law AM. 2006. How to build valid and credible simulation models. Proceedings of the 38th Conference on Winter Simulation. Monterey (CA): Winter Simulation Conference. p. 58–66. WSC '06.
   Google Scholar
• Lazakis I, Ölçer A. 2015. Selection of the best maintenance approach in the maritime industry under fuzzy multiple attributive group decision-making environment. Proc Inst Mech Eng Part M. 230(2):297–309.
   Web of Science ®Google Scholar
• Lazakis I, Turan O, Aksu S. 2010. Increasing ship operational reliability through the implementation of a holistic maintenance management strategy. Ships Offshore Struc. 5(4):337–357. doi: 10.1080/17445302.2010.480899
   Web of Science ®Google Scholar
• Li P, Liu L, Gong H. 2010. The research of the intelligent fault diagnosis optimized by aca for marine diesel engine. In: Luo Q, editor. Advancing computing, communication, control and management. Springer; p. 174–181. https://www.springer.com/gb/book/9783642051722.
   Google Scholar
• MAN B&W Diesel A/S. 2004. Instruction book ‘Operation’ for 50-108MC/MC-C engines. 2nd ed. Copenhagen: MAN B&W Diesel A/S.
   Google Scholar
• Manzini R, Regattieri A, Pham H, Ferrari E. 2009. Maintenance for industrial systems. Springer Science & Business Media. https://www.springer.com/gb/book/9781848825741.
   Google Scholar
• Matthews B. 1975. Comparison of the predicted and observed secondary structure of t4 phage lysozyme. Biochim Biophys Acta. 405(2):442–451. doi: 10.1016/0005-2795(75)90109-9
   PubMed Web of Science ®Google Scholar
• Mohanty AR. 2014. Machinery condition monitoring. Boca Raton (FL): CRC Press.
   Google Scholar
• Moore Stephens. 2017. Future operating costs report. Report No: DPS38615.
   Google Scholar
• Neale M. and Associates. 1979. A guide to the condition monitoring of machinery. London, Great Britain: Committee for Terotechnology. Report No.
   Google Scholar
• Randall RB. 2011. Vibration-based condition monitoring. Hoboken (NJ): Wiley.
   Google Scholar
• Raptodimos Y, Lazakis I. 2018. Using artificial neural network-self-organising map for data clustering of marine engine condition monitoring applications. Ships Offshore Struc. 13(6):649–656. doi: 10.1080/17445302.2018.1443694
   Web of Science ®Google Scholar
• Saltelli A, Tarantola S, Campolongo F, Ratto M. 2004. Sensitivity analysis in practice: a guide to assessing scientific models. West Sussex: Wiley.
   Google Scholar
• Schölkopf B, Platt JC, Shawe-Taylor JC, Smola AJ, Williamson RC. 2001. Estimating the support of a high-dimensional distribution. Neural Comput. 13(7):1443–1471. doi: 10.1162/089976601750264965
   PubMed Web of Science ®Google Scholar
• Schölkopf B, Smola AJ, Williamson RC, Bartlett PL. 2000. New support vector algorithms. Neural Comput. 12(5):1207–1245. doi: 10.1162/089976600300015565
   PubMed Web of Science ®Google Scholar
• Schölkopf B, Williamson R, Smola A, Shawe-Taylor J, Platt J. 1999. Support vector method for novelty detection. Proceedings of the 12th International Conference on Neural Information Processing Systems; Cambridge: MIT Press. p. 582–588. NIPS'99.
   Google Scholar
• Stopford M. 2009. Maritime economics. 3rd ed. Abington: Routledge.
   Google Scholar
• UNCTAD. 2015. Review of maritime transport. New York: United Nations Conference on Trade and Development. Report No: UNCTAD/RMT/2015.
   Google Scholar
• Van Hulse J, Khoshgoftaar TM, Napolitano A. 2007. Experimental perspectives on learning from imbalanced data. Proceedings of the 24th International Conference on Machine Learning; New York (NY); ACM. p. 935–942. ICML '07.
   Google Scholar
• Verbert K, Schutter BD, Babuška R. 2017. Timely condition-based maintenance planning for multi-component systems. Reliab Eng Syst Safe. 159:310–321. doi: 10.1016/j.ress.2016.10.032
   Web of Science ®Google Scholar
• Watzenig D, Sommer MS, Steiner G. 2009. Engine state monitoring and fault diagnosis of large marine diesel engines. Elektrotech Informationstech. 126(5):173–179. doi: 10.1007/s00502-009-0639-z
   Google Scholar
• Widodo A, Yang BS. 2007. Support vector machine in machine condition monitoring and fault diagnosis. Mech Syst Signal Process. 21(6):2560–2574. doi: 10.1016/j.ymssp.2006.12.007
   Web of Science ®Google Scholar
• Wu X, Srihari RK. 2003. New ν-support vector machines and their sequential minimal optimization. Proceedings of the 20th International Conference on Machine Learning (ICML-03); Washington (DC). p. 824–831.
   Google Scholar
• Yang W, Court R, Jiang J. 2013. Wind turbine condition monitoring by the approach of SCADA data analysis. Renew Energ. 53:365–376. doi: 10.1016/j.renene.2012.11.030
   Web of Science ®Google Scholar
• Yin Z, Hou J. 2016. Recent advances on SVM based fault diagnosis and process monitoring in complicated industrial processes. Neurocomputing. 174, Part B:643–650. doi: 10.1016/j.neucom.2015.09.081
   Web of Science ®Google Scholar