The role of surrogate models in the development of digital twins of dynamic systems

Digital twin technology has significant promise, relevance and potential of widespread applicability in various industrial sectors such as aerospace, infrastructure and automotive. However, the adoption of this technology has been slower due to the lack of clarity for specific applications. A discrete damped dynamic system is used in this paper to explore the concept of a digital twin. As digital twins are also expected to exploit data and computational methods, there is a compelling case for the use of surrogate models in this context. Motivated by this synergy, we have explored the possibility of using surrogate models within the digital twin technology. In particular, the use of Gaussian process (GP) emulator within the digital twin technology is explored. GP has the inherent capability of addressing noise and sparse data and hence, makes a compelling case to be used within the digital twin framework. Cases involving stiffness variation and mass variation are considered, individually and jointly along with different levels of noise and sparsity in data. Our numerical simulation results clearly demonstrate that surrogate models such as GP emulators have the potential to be an effective tool for the development of digital twins. Aspects related to data quality and sampling rate are analysed. Key concepts introduced in this paper are summarised and ideas for urgent future research needs are proposed.

[1]  Sharif Rahman,et al.  Reliability-based Design Optimization by a Univariate Decomposition Method , 2010 .

[2]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[3]  S. Michael Spottswood,et al.  Reengineering Aircraft Structural Life Prediction Using a Digital Twin , 2011 .

[4]  Maurice Lemaire,et al.  Assessing small failure probabilities by combined subset simulation and Support Vector Machines , 2011 .

[5]  Jianfeng Yan,et al.  Digital twin and its application to power grid online analysis , 2019, CSEE Journal of Power and Energy Systems.

[6]  Satish Chandra,et al.  Kriging based saturation flow models for traffic conditions in Indian cities , 2018, Transportation Research Part A: Policy and Practice.

[7]  Alessandro Sabato,et al.  Wireless MEMS-Based Accelerometer Sensor Boards for Structural Vibration Monitoring: A Review , 2017, IEEE Sensors Journal.

[8]  Sondipon Adhikari,et al.  Gaussian process emulators for the stochastic finite element method , 2011 .

[9]  Ranjan Ganguli,et al.  Jet Engine Gas-Path Measurement Filtering Using Center Weighted Idempotent Median Filters , 2003 .

[10]  Timon Rabczuk,et al.  Threshold shift method for reliability-based design optimization , 2019, Structural and Multidisciplinary Optimization.

[11]  Neil D. Lawrence,et al.  Computationally Efficient Convolved Multiple Output Gaussian Processes , 2011, J. Mach. Learn. Res..

[12]  Reiner Anderl,et al.  Digital twin – Proof of concept , 2018 .

[13]  Harry R. Millwater,et al.  Probabilistic methods for risk assessment of airframe digital twin structures , 2019, Engineering Fracture Mechanics.

[14]  D. Goldberg,et al.  BOA: the Bayesian optimization algorithm , 1999 .

[15]  Souvik Chakraborty Simulation free reliability analysis: A physics-informed deep learning based approach , 2020 .

[16]  Roby Lynn,et al.  Part data integration in the Shop Floor Digital Twin: Mobile and cloud technologies to enable a manufacturing execution system , 2018, Journal of Manufacturing Systems.

[17]  Dongbin Xiu,et al.  The Wiener-Askey Polynomial Chaos for Stochastic Differential Equations , 2002, SIAM J. Sci. Comput..

[18]  Wei Zhang,et al.  A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals , 2017, Sensors.

[19]  Souvik Chakraborty Transfer learning based multi-fidelity physics informed deep neural network , 2020, ArXiv.

[20]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[21]  Zoubin Ghahramani,et al.  Sparse Gaussian Processes using Pseudo-inputs , 2005, NIPS.

[22]  Marc Sartor,et al.  Creation of helicopter dynamic systems digital twin using multibody simulations , 2019, CIRP Annals.

[23]  Michael Giering,et al.  Deep Learning for Structural Health Monitoring : A Damage Characterization Application , 2016 .

[24]  Vicente Ferreira de Lucena,et al.  A Digital Twin Architecture Based on the Industrial Internet of Things Technologies , 2019, 2019 IEEE International Conference on Consumer Electronics (ICCE).

[25]  Ranjan Ganguli,et al.  Genetic programming metamodel for rotating beams , 2007 .

[26]  Hao Ye,et al.  Measurement of Bridge Dynamic Responses Using Network-Based Real-Time Kinematic GNSS Technique , 2016 .

[27]  Andrew Y. C. Nee,et al.  Digital twin-driven product design framework , 2019, Int. J. Prod. Res..

[28]  Hao Zhang,et al.  A Multiwavelet Neural Network‐Based Response Surface Method for Structural Reliability Analysis , 2015, Comput. Aided Civ. Infrastructure Eng..

[29]  Ranjan Ganguli,et al.  Fuzzy Logic Intelligent System for Gas Turbine Module and System Fault Isolation , 2002 .

[30]  Jorge E. Hurtado,et al.  Neural-network-based reliability analysis: a comparative study , 2001 .

[31]  Sondipon Adhikari,et al.  A Critical Assessment of Kriging Model Variants for High-Fidelity Uncertainty Quantification in Dynamics of composite Shells , 2016, Archives of Computational Methods in Engineering.

[32]  Sondipon Adhikari,et al.  Bayesian assimilation of multi-fidelity finite element models , 2012 .

[33]  Jessica Daecher,et al.  Introduction To Perturbation Techniques , 2016 .

[34]  Souvik Chakraborty,et al.  Hybrid Framework for the Estimation of Rare Failure Event Probability , 2017 .

[35]  V. Dubourg Adaptive surrogate models for reliability analysis and reliability-based design optimization , 2011 .

[36]  Souvik Chakraborty,et al.  Graph-Theoretic-Approach-Assisted Gaussian Process for Nonlinear Stochastic Dynamic Analysis under Generalized Loading , 2019 .

[37]  Ayan Sadhu,et al.  A literature review of next‐generation smart sensing technology in structural health monitoring , 2019, Structural Control and Health Monitoring.

[38]  Lijun Liu,et al.  Real-time simultaneous identification of structural systems and unknown inputs without collocated acceleration measurements based on MEKF-UI , 2017 .

[39]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[40]  Ranjan Ganguli,et al.  Helicopter rotor blade frequency evolution with damage growth and signal processing , 2005 .

[41]  Souvik Chakraborty,et al.  Polynomial Correlated Function Expansion , 2017 .

[42]  Souvik Chakraborty,et al.  Efficient data-driven reduced-order models for high-dimensional multiscale dynamical systems , 2018, Comput. Phys. Commun..

[43]  Enrico Zio,et al.  A Novel Hybrid Method of Parameters Tuning in Support Vector Regression for Reliability Prediction: Particle Swarm Optimization Combined With Analytical Selection , 2016, IEEE Transactions on Reliability.

[44]  Hao Xu,et al.  DL-PDE: Deep-learning based data-driven discovery of partial differential equations from discrete and noisy data , 2019, Communications in Computational Physics.

[45]  R. Ganguli,et al.  The digital twin of discrete dynamic systems: Initial approaches and future challenges , 2020, Applied Mathematical Modelling.

[46]  Sankaran Mahadevan,et al.  Dynamic Bayesian Network for Aircraft Wing Health Monitoring Digital Twin , 2017 .

[47]  Sondipon Adhikari,et al.  Structural dynamic analysis using Gaussian process emulators , 2010 .

[48]  Karen Willcox,et al.  Engineering Design with Digital Thread , 2017, AIAA Journal.

[49]  Wenliang Zhong,et al.  A modified stochastic perturbation method for stochastic hyperbolic heat conduction problems , 2016 .

[50]  Gilbert-Rainer Gillich,et al.  Signal Post-processing for Accurate Evaluation of the Natural Frequencies , 2017 .

[51]  Ranjan Ganguli,et al.  Noise and Outlier Removal from Jet Engine Health Signals Using Weighted FIR Median Hybrid Filters , 2002 .

[52]  Quan Liu,et al.  Dynamic strain measurement of hydraulic system pipeline using fibre Bragg grating sensors , 2016 .

[53]  Christian Cremona,et al.  Structural Health Monitoring as a Big-Data Problem , 2018, Structural Engineering International.

[54]  Neil D. Lawrence,et al.  Sparse Convolved Gaussian Processes for Multi-output Regression , 2008, NIPS.

[55]  Ilias Bilionis,et al.  Multi-output separable Gaussian process: Towards an efficient, fully Bayesian paradigm for uncertainty quantification , 2013, J. Comput. Phys..

[56]  Karen E. Willcox,et al.  Distributionally robust optimization for engineering design under uncertainty , 2019, International Journal for Numerical Methods in Engineering.

[57]  P Perdikaris,et al.  Multi-fidelity modelling via recursive co-kriging and Gaussian–Markov random fields , 2015, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[58]  Timon Rabczuk,et al.  Transfer learning enhanced physics informed neural network for phase-field modeling of fracture , 2019, Theoretical and Applied Fracture Mechanics.

[59]  He Zhang,et al.  Digital Twin in Industry: State-of-the-Art , 2019, IEEE Transactions on Industrial Informatics.

[60]  Bruno Sudret,et al.  Global sensitivity analysis using polynomial chaos expansions , 2008, Reliab. Eng. Syst. Saf..

[61]  Ilias Bilionis,et al.  Multi-output local Gaussian process regression: Applications to uncertainty quantification , 2012, J. Comput. Phys..

[62]  Fei Tao,et al.  Digital twin-driven product design, manufacturing and service with big data , 2017, The International Journal of Advanced Manufacturing Technology.

[63]  Carl E. Rasmussen,et al.  Gaussian Processes for Machine Learning (GPML) Toolbox , 2010, J. Mach. Learn. Res..

[64]  Satish Chandra,et al.  Kriging-Based Approach for Estimation of Vehicular Speed and Passenger Car Units on an Urban Arterial , 2017 .

[65]  S. Mahadevan,et al.  Fatigue damage modelling of composite materials , 2002 .