Condition Classification of Fibre Ropes during Cyclic Bend over Sheave testing Using Machine Learning



Published Apr 11, 2022
Shaun Falconer Peter Krause Thomas Bäck Ellen Nordgård-Hansen Geir Grasmo


Fibre ropes have been shown to be a viable alternative to steel wire rope for offshore lifting operations. Visual inspection remains a common method of fibre rope condition monitoring and has the potential to be further automated by machine learning. This would provide a valuable aid to current inspection frameworks to make more accurate decisions on recertification or retirement of fibre ropes in operational use. Three different machine learning algorithms: decision tree, random forest and support vector machine are compared to classical statistical approaches such as logistic regression, k-nearest neighbours and Naïve-Bayes for condition classification for fibre ropes under cyclic-bend-over-sheave (CBOS) testing. By measuring the rope global elongation throughout the CBOS tests, a binary classification system has been used to label recorded samples as healthy or close to rupture. Predictions are made on one rope through leave-one-out cross validation. The models are then assessed through calculating the accuracy, probability of detection, probability of false alarm and Matthew’s Correlation Coefficient, and ranked based on the results. The results show that both machine learning and classical statistical methods are effective options for condition classification of fibre ropes under CBOS regimes. Typical values for Matthews Correlation Coefficient (MCC) were shown to exceed 0.8 for the best performing methods.

Abstract 425 | PDF Downloads 355



fibre rope, condition monitoring, machine learning, decision trees, random forest, support vector machines

ABS. (2011). ABS-90: Guidance notes on the Application of Synthetic Ropes for Offshore Mooring.
Altman, N. S. (1992). An Introduction to Kernel and Nearest-Neighbor Non-parametric Regression.The American Statistician,46(3), 175–185.doi: https :// doi .org /10.2307/2685209
Bradski, G. (2000). The OpenCV Library.Dr. Dobb’s Journal of Software Tools.
Breiman, L. (1996). Bagging predictors.Machine Learning,24(2), 123–140. doi: 10.1007/bf00058655
Breiman, L. (2001). Random Forests.Machine Learning,45(1), 5–32. doi: 10.1023/A:1010933404324
Breiman, L., Friedman, L. H., Olshen, R. A., & Stone, C. J.(1984). Classification and Regression Trees. Belmont,CA: Wadsworth Interantional Group.
Chang, C.-W., Lee, H.-W., & Liu, C.-H. (2018). A Review of Artificial Intelligence Algorithms Used for Smart Machine Tools. Inventions,3(3), 41. Retrieved from 10.3390/inventions3030041
Cortes, C., & Vapnik, V. (1995). Support-Vector Networks.Machine Learning,20(3), 273–297. doi: 10 .1007/BF00994018
Cramer, J. (2002). The Origins of Logistic Regression. Tinbergen Institute Working Paper No. 2002-119/4. doi:10.2139/ssrn.360300
DNVGL. (2017). DNVGL-RP-E304: Damage Assessmentof Fibre Ropes for Offshore Mooring.
DNVGL. (2018). DNVGL-OS-E303: Offshore fibre ropes.
Falconer, S., Grasmo, G., & Nordgård-Hansen, E. (2019). Condition monitoring of HMPE fibre rope using computer vision during CBOS testing. In Oipeec proceedings 2019 (pp. 129–147). The Hague.
Falconer, S., Gromsrud, A., Oland, E., & Grasmo, G. (2017). Preliminary Results on Condition Monitoring of Fiber Ropes using Automatic Width and Discrete LengthMeasurements. In Annual conference of the prognostics and health managemet society 2017.
Falconer, S., Nordgåard-Hansen, E., & Grasmo, G. (2020).Computer vision and thermal monitoring of HMPE fibre rope condition during CBOS testing. Ap-plied Ocean Research,102, 102248. Retrieved from 10.1016/j.apor.2020.102248
FLIR. (2015). ResearchIR 4. Wilsonville, OR: FLIR Systems, Inc.
Foster, G. P. (2002). Advantages of Fiber Rope Over WireRope.Journal of Industrial Textiles,32(1), 67–75. doi:10.1106/152808302031656
Fronzaglia, W., & Bosman, R. (2016). Working at depth:Less work with synthetic ropes and cables. InOceans2016 mts/ieee monterey(pp. 1–6). Monterey, CA. doi:10.1109/OCEANS.2016.7761483
Mingers, J.(1989). An Empirical Comparison of Se-lection Measures for Decision-Tree Induction.Ma-chine Learning,3(4), 319–342.doi: 10 .1023 / A :1022645801436
Nguyen, V. D., Kefalas, M., Yang, K., Apostolidis, A., Olhofer, M., Limmer, S., & Back, T. (2019). A Review: Prognostics and Health Management in Automotive and Aerospace. International Journal of Prognostics and Health Management,10, 1–35.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V.,Thirion, B., Grisel, O., Duchesnay, E.(2011). Scikit-learn: Machine Learning in Python.Journal ofMachine Learning Research,12(1), 2825–2830. doi:10.1016/j.patcog.2011.04.006
Rebel, G., Verreet, R., & Ridge, I. (2006). Lightweight ropesfor lifting applications. In Oipeec conference proceed-ings 2006(pp. 33–54). Athens.
Rish, I. (2014). An Empirical Study of the Na ̈ıve Bayes Classifier. IJCAI 2001 workshop on empirical meth-ods in artificial intelligence,3(2001), 41–46.Re-trieved from ̃isbell/reading/papers/Rish.pdf
Rokach, L., & Maimon, O. (2005). Decision Trees. InO.
Maimon & L. Rokach (Eds.),Data mining andknowledge discovery handbook(pp. 165–192). Boston,MA: Springer. doi: https://doi .org/10 .1007/0 -387-25465-X9
Shmilovici, A. (2005). Support Vector Machines. In O. Mai-mon & L. Rokach (Eds.),Data mining and knowl-edge discovery handbook(pp. 257–276). Boston, MA:Springer. doi:
Sutharssan, T., Stoyanov, S., Bailey, C., & Yin, C. (2015). Prognostic and health management for engineeringsystems: a review of the data-driven approach and al-gorithms.The Journal of Engineering,2015(7), 215–222. doi: 10.1049/joe.2014.0303
Xue, S., Tan, J., Shi, L., & Deng, J. (2020). Rope tension faultdiagnosis in hoisting systems based on vibration sig-nals using EEMD, improved permutation entropy, and PSO-SVM.Entropy,22(2). doi: 10.3390/e22020209
Zhou, P., Zhou, G., Zhu, Z., Tang, C., He, Z., Li, W., & Jiang,F. (2018). Health Monitoring for Balancing Tail Ropes of a Hoisting System Using a Convolutional NeuralNetwork.Applied Sciences,8(8), 1346. Retrievedfrom 10.3390/app808134
Technical Papers