A Novel Image-Based Framework for Process Monitoring and Fault Diagnosis of Mooring Lines
Mooring lines play a vital role in offshore marine operations by limiting marine vessels' free movement on the water. Problems in mooring lines must therefore be detected and solved beforehand to guarantee successful and loss-free offshore operations. Sudden and undetected failure of mooring lines has caused significant disruptions of operations. Many studies focus on mooring lines failure and give ts comprehensive description. Available solutions to detect faults in mooring lines comprise the conventional line tension measurements. Circle- based GPS approaches are less accurate, unreliable, expensive, difficult to install, and maintain. They usually have a limited lifetime or the most recent Deep Learning-based techniques, which are computationally costly, data-hungry, and inefficient to localize thin mooring lines from images. In this research study, we present MoorFDM: Mooring Fault Diagnosis and Monitoring- a novel image-based framework for process monitoring and fault diagnosis of thin mooring lines. MoorFDM monitors and detects faults well in the thin mooring lines from images using our novel line pooling algorithm. Our proposed framework is validated using web-based light mooring line images and images from an oil and gas company with accurate results.
Keywords: mooring lines, process monitoring, and fault diagnosis (PFD), thin objects detection, computer vision, deep learning.
BROOK A. The design of catenary mooring systems for offshore vessels. In: DYKE P., MOSCARDINI AO, ROBSON EH (eds.) Offshore and coastal modeling. New York: Springer-Verlag, 1985, pp. 303-322.
BABICZ J. Wartsila encyclopedia of ship technology. Gdańsk: Baobab Naval Consultancy, 2008.
CHAN, J. (2018, Jan 29). Floating Production Storage and Offloading – FPSO. Available: https://www.investopedia.com/terms/f/fpso-floating-production-storage-and-offloading.asp
What is an FPSO? (2020, Jan 29). Available: https://www.bluewater.com/fleet-operations/what-is-an-fpso/
Mobile Offshore Drilling Unit (MODUs). Wärtsilä Encyclopedia of Marine Technology (14-06-2020). Available: https://www.wartsila.com/encyclopedia/ term/mobile-offshore-drilling-unit-(modus)
SUN Y. Mobile offshore drilling unit," ed: Google Patents, 2014.
GIDDINGS I. C. IMO Guidelines for vessels with dynamic positioning systems. In: Proceedings of the Dynamic Positioning Conference, Houston, October 15-16, 2013. Houston: MTS DP, pp. 15-16.
How do Mooring Systems Work? RigZone. (Jun 14, 2020). Available: https://www.rigzone.com/training/insight.asp?insight_id=358&c_id=#:~:text=A%20mooring%20line%20connects%20an,Units%20and%20Floating%20Production%20Systems.&text=The%20mooring%20line%20can%20be,a%20combination%20of%20the%20three.
How Do FPSOs Work? RigZone (Jan 29, 2020). Available: https://www.rigzone.com/training/insight.asp?insight_id=299&c_id=
Mooring Systems (Jan 18, 2019). Available: http://abc-moorings.weebly.com/mooring-systems.html
Spread Mooring systems (Mar 23, 2018). Available: https://www.bluewater.com/products-technology/mooring-systems/turret-mooring-systems/
BAI Y. Risk Assessment applied to offshore structures. In: BAI Yong and WEI-LIANG, Jin Marine structural design. 2nd ed., Banbuey: Butterworth-Heinemann Elsevier, 2016, pp. 529-554,. doi: 10.1016/B978-008043921-1/50030-7
JIA Xiaoxu, SUN Ningtao, DIAO Zhidong, CUI Jianwei. Single point mooring system device - Google Patents, 1973. Available: https://patents.google.com/patent/CN102963501A/en
Choosing Between SPM CALM and CBM Mooring. Available: https://epcmholdings.com/spm-vs-cbm/
DAUGHDRILL W. H. and CLARK T. OTC 14000 -A. Considerations in reducing risks in FPSO and shuttle vessel lightering operations. In: Proceedings of Offshore Technology Conference, May 6-9, 2002, Houston, Texas, USA. Red Hook, New York: Curran Associates, Inc., 2002: 95-101
MA K.-t., SHU H., SMEDLEY P., L'HOSTIs D., and DUGGAL A. OTC-24025-MS- A historical review on integrity issues of permanent mooring systems. In: Proceedings of Offshore Technology Conference, May 5-8, 2003, Houston, Texas, USA. Red Hook, New York: Curran Associates, Inc., 2003: 223-229.
LUGSDIN A. Real-time monitoring of FPSO mooring lines, risers. Sea Technology, 2012, 53(7): 21-24.
Gryphon FPSO dislodged by storms. Offshore. (Mar 19, 2011,). Available: https://www.offshore-mag.com/production/article/16777360/gryphon-fpso-dislodged-by-storms
Fatality results from failure of ship's mooring fittings and supporting structure. IMCA. (Feb 06, 2003). Available: https://www.imca-int.com/alert/190/fatality-results-from-failure-of-ships-mooring-fittings-and-supporting-structure
BAI Yong. and BAI Qiang (eds.) Subsea pipelines and risers. Beijing: Elsevier Science, 2005.
Machine learning can make mooring safer and more cost effective. (Feb 06, 2003) Available: https://www.dnvgl.com/oilgas/perspectives/machine-learning-can-make-mooring-safer-and-more-cost-effective.html
FURLOW W. Monitoring, maintenance of mooring systems help to extend design life of production facilities. Oil and Gas Facilities, 2015, 4(04): 020-025. doi: 10.2118/0815-0020-OGF
LECUN Y., BENGIO Y., and HINTON G. Deep learning. Nature, 2015, 521: 436-444.
JAISWAL V. and RUSKIN A. Mooring line failure detection using machine learning. In: Proceedings of Offshore Technology Conference, May 6-9, 2019, Houston, Texas, USA. Red Hook, New York: Curran Associates, Inc., 2019: 124-132. doi: 10.4043/29511-MS
HUSSAIN S., HASHMANI M., MOINUDDIN M., YOSHIDA M., and KANJO H. Image retrieval based on color and texture feature using artificial neural network. In: Proceedings of 2nd International Multi-Topic Conference (IMTIC 2012) Jashmoro, Pakistan, March 28-30, 2012. Chennai: Springer Nature: 2012: 501-511:.
ALHUSSAIN H. and BUDIMAN A. A Fully adaptive image classification approach for industrial revolution 4.0. In: Proceedings of the 3rd International Conference of Reliable Information and Communication Technology (IRICT 2018) Kuala Lumpur, Malaysia, July 23–24, 2018. Chennai: Springer 2018, 843:311.
JAMEEL S. M., HASHMANI M. A., ALHUSSAIN H., REHMAN M., and BUDIMAN A. An optimized deep convolutional neural network architecture for concept drifted image classification. Proceedings of SAI Intelligent Systems Conference, London, September 5-6, 2019. London: SAI, 2019: 932-942.
MORRIS T. Computer vision and image processing. London: Palgrave Macmillan, 2004.
REDMON J., DIVVALA S., GIRSHICK R., and FARHADI A. You only look once: Unified, real-time object detection. In: Proceedings of the 2016 IEEE conference on computer vision and pattern recognition, Las Vegas, June 27-30, 2016. Piscataway, New Jersey: IEEE, 2016: 779-788.
REDMON J. and FARHADI A. YOLO9000: better, faster, stronger. In: Proceedings of the 2017 IEEE conference on computer vision and pattern recognition, Honolulu, July 21-26, 2017. Piscataway, New Jersey: IEEE, 2017: 7263-7271.
LIU W., ANGUELOV D., ERHAN D., SCZEGEDY C., REED S. SSD: Single shot multibox detector. In: Proceedings of the European conference on computer vision, Amsterdam, October 11-14, 2016. Amsterdam: Springer, 2016: 21-37.
FU C.-Y., LIU W., RANGA A., TYAGI A., and BERG A. C. DSSD: Deconvolutional single shot detector, arXiv preprint arXiv:1701.06659, 2017.
GIRSHICK R., DONAHUE J., DARRELL T., and MALIK J. Rich feature hierarchies for accurate object detection and semantic segmentation," in Proceedings of the 14th IEEE conference on computer vision and pattern recognition, Columbus, USA, June 23-28, 2014. Piscataway, New Jersey: IEEE, 2014:580-587.
GIRSHICK R. Fast R-CNN. Proceedings of the IEEE international conference on computer vision, Santiago, December 11-18, 2015. Los Alamitos, California: IEEE, 2015:1440-1448.
REN S., HE K., GIRSHICK R., and SUN J. Faster r-cnn: Towards real-time object detection with region proposal networks. In: JORDAN M., LECUNN Y., SOLLA S. (eds.) Advances in neural information processing systems, Cambridge, MA: MIT, 2015:91-99.
DAI J., LI Y., HE K., and SUN J. R-FCN: Object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, Barcelona, December 5-10, 2016. Cambridge, MA: MIT, 2016:379-387.
HE K., GKIOXARI G., DOLLÁR P., and GIRSHICK R. Mask R-CNN. In: Proceedings of the 2017 IEEE conference on computer vision and pattern recognition, Honolulu, July 21-26, 2017. Piscataway, New Jersey: IEEE, 2017: 2961-2969.
HUSSAIN MAS (Sept 21, 2018). Line Detection using Convolutional Neural Networks. Available: https://github.com/muneebaadil/line-detection-using-cnns/blob/master/docs/report.pdf
LI X., LI J., HU X., and YANG J. Line-CNN: End-to-End Traffic line detection with line proposal unit. IEEE Transactions on Intelligent Transportation Systems, 21(1),2019:248-256.
LIU B., LIU H., and YUAN J. Lane Line Detection based on Mask R-CNN. In: 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019), Dalian, March 29-30, 2019. Beijing: Atlantis Press.
GHAFOORIAN M., NUGTEREN C., BAKA N., BOOIJ O., and HOFMANN M. EL-GAN: embedding loss driven generative adversarial networks for lane detection. In: Proceedings of the European Conference on Computer Vision (ECCV), Munich, September 8-14, 2018. Berlin: Springer Science+Business Media, 2018: 234-243.
WANG S.and LU P. On the monitoring of mooring system performance. In: Proceedings of the 21st SNAME Offshore Symposium, Houston, USA, Feb 16, 2016. Houston: SNAME Texas Section, 2016:345-351.
KIRYATI N., ELDAR Y., and. BRUCKSTEIN A. M. A probabilistic Hough transform. Pattern Recognition, 24(4), 1991: 303-316.
ROSASCO L., VITO E. D., CAPONNETTO A., PIANA M., and VERRI A. J. N. C. Are loss functions all the same? Neural Computation, 16(5), 2004:1063-1076.
- There are currently no refbacks.