Lifetime Prediction Using a Tribology-Aware, Deep Learning-Based Digital Twin of Ball Bearing-Like Tribosystems in Oil and Gas

The recent decline in crude oil prices due to global competition and COVID-19-related demand issues has highlighted the need for the efficient operation of an oil and gas plant. One such avenue is accurate predictions about the remaining useful life (RUL) of components used in oil and gas plants. A tribosystem is comprised of the surfaces in relative motion and the lubricant between them. Lubricant oils play a significant role in keeping any tribosystem such as bearings and gears working smoothly over the lifetime of the oil and gas plant. The lubricant oil needs replenishment from time to time to avoid component breakdown due to the increased presence of wear debris and friction between the sliding surfaces of bearings and gears. Traditionally, this oil change is carried out at pre-determined times. This paper explored the possibilities of employing machine learning to predict early failure behavior in sensor-instrumented tribosystems. Specifically, deep learning and tribological data obtained from sensors deployed on the components can provide more accurate predictions about the RUL of the tribosystem. This automated maintenance can improve the overall efficiency of the component. The present study aimed to develop a deep learning-based digital twin for accurately predicting the RUL of a tribosystem comprised of a ball bearing-like test apparatus, a four-ball tester, and lubricant oil. A commercial lubricant used in the offshore oil and gas components was tested for its extreme pressure performance, and its welding load was measured using a four-ball tester. Three accelerated deterioration tests was carried out on the four-ball tester at a load below the welding load. Based on the wear scar measurements obtained from the experimental tests, the RUL data were used to train a multivariate convolutional neural network (CNN). The training accuracy of the model was above 99%, and the testing accuracy was above 95%. This work involved the model-free learning prediction of the remaining useful lifetime of ball bearing-type contacts as a function of key sensor input data (i.e., load, friction, temperature). This model can be deployed for in-field tribological machine elements to trigger automated maintenance without explicitly measuring the wear phenomenon.

[1]  Francesco Topputo,et al.  Deep Learning for Autonomous Lunar Landing , 2018 .

[2]  Robert X. Gao,et al.  Deep heterogeneous GRU model for predictive analytics in smart manufacturing: Application to tool wear prediction , 2019, Comput. Ind..

[3]  Qiang Feng,et al.  Group maintenance optimization of subsea Xmas trees with stochastic dependency , 2021, Reliab. Eng. Syst. Saf..

[4]  George Chryssolouris,et al.  The use of Digital Twin for predictive maintenance in manufacturing , 2019, Int. J. Comput. Integr. Manuf..

[5]  Aurélien Géron,et al.  Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems , 2017 .

[6]  Zhaojian Yang,et al.  A Predictive Maintenance Method for Shearer Key Parts Based on Qualitative and Quantitative Analysis of Monitoring Data , 2019, IEEE Access.

[7]  Frederick R. Forst,et al.  On robust estimation of the location parameter , 1980 .

[8]  Sha'ri Mohd Yusof,et al.  A Literature Review of Subsea Asset Integrity Framework for Project Execution Phase , 2015 .

[9]  Tore Markeset,et al.  Maintenance cost evaluation of a system to be used in Arctic conditions: a case study , 2011 .

[10]  Eric Bechhoefer,et al.  Lubrication Oil Condition Monitoring and Remaining Useful Life Prediction with Particle Filtering , 2020 .

[11]  Itxaro Errandonea,et al.  Digital Twin for maintenance: A literature review , 2020, Comput. Ind..

[12]  Jiang Zhe,et al.  Lubricating oil conditioning sensors for online machine health monitoring – A review , 2017 .

[13]  Fan Zhang,et al.  A review on time series forecasting techniques for building energy consumption , 2017 .

[14]  Bruno Castanier,et al.  Maintenance optimization for subsea oil pipelines , 2006 .

[15]  Duc Truong Pham,et al.  Machine-learning techniques and their applications in manufacturing , 2005 .

[16]  Eric Bechhoefer,et al.  A survey of lubrication oil condition monitoring, diagnostics and prognostics techniques and systems , 2012 .

[17]  Alberto Arredondo,et al.  Influence of temperature on the corrosion and tribocorrosion behaviour of High-Strength Low-Alloy steels used in offshore applications , 2018 .

[18]  Tore Markeset,et al.  Identifying Challenges in the Maintenance of Subsea Petroleum Production Systems , 2011, APMS.

[19]  Christian Mudrak.  Subsea Production Systems - A Review of Components, Maintenance and Reliability , 2016 .

[20]  Robert J.K. Wood,et al.  Early wear detection and its significance for condition monitoring , 2021, Tribology International.

[21]  Congbin Yang,et al.  Data Super-Network Fault Prediction Model and Maintenance Strategy for Mechanical Product Based on Digital Twin , 2019, IEEE Access.

[22]  Amir F. Atiya,et al.  An Empirical Comparison of Machine Learning Models for Time Series Forecasting , 2010 .

[23]  Victor Talpaert,et al.  Deep Reinforcement Learning for Autonomous Driving: A Survey , 2020, IEEE Transactions on Intelligent Transportation Systems.

[24]  Bohdan M. Pavlyshenko,et al.  Machine-Learning Models for Sales Time Series Forecasting , 2018, Data.

[25]  Bernardo Tormos,et al.  Analytical approach to wear rate determination for internal combustion engine condition monitoring based on oil analysis , 2003 .

[26]  Zhien Zhang,et al.  Prediction of CO2 absorption by physical solvents using a chemoinformatics-based machine learning model , 2019, Environmental Chemistry Letters.

[27]  N. Manikandan,et al.  Digital Twin of an Automotive Brake Pad for Predictive Maintenance , 2019, Procedia Computer Science.

[28]  Raymond G. Gosine,et al.  Digital Twin for the Oil and Gas Industry: Overview, Research Trends, Opportunities, and Challenges , 2020, IEEE Access.

[29]  Xiang Li,et al.  Remaining useful life estimation in prognostics using deep convolution neural networks , 2018, Reliab. Eng. Syst. Saf..

[30]  Thyago P. Carvalho,et al.  A systematic literature review of machine learning methods applied to predictive maintenance , 2019, Comput. Ind. Eng..

[31]  Huiyue Dong,et al.  Review of digital twin about concepts, technologies, and industrial applications , 2020 .

[32]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[33]  M. Shafiee,et al.  Decision support methods and applications in the upstream oil and gas sector , 2019, Journal of Petroleum Science and Engineering.

[34]  C. Higgs,et al.  Spreading Process Maps for Powder-Bed Additive Manufacturing Derived from Physics Model-Based Machine Learning , 2019, Metals.

[35]  Myunghee Cho Paik,et al.  Uncertainty quantification using Bayesian neural networks in classification: Application to biomedical image segmentation , 2020, Comput. Stat. Data Anal..

[36]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[37]  Matthew Marshall,et al.  Failure analysis of pipeline indents using steel precision balls under subsea conditions , 2018 .

[38]  Saurabh Kumar,et al.  Online condition monitoring of engine oil , 2005 .

[39]  Min Zhang,et al.  Failure prediction using machine learning and time series in optical network. , 2017, Optics express.

[40]  L. Lake,et al.  Comparison of permeability predictions on cemented sandstones with physics-based and machine learning approaches , 2020 .