Hybrid Model-Based and Data-Driven Solution for Uncertainty Quantification at the Microscale

Jose   Pablo   Quesada-Molina; Stefano      Mariani

Abstract

Background: Due to their size, microelectromechanical systems (MEMS) display performance indices affected by uncertainties linked to the mechanical properties and to the geometry of the films constituting their movable parts.

Objective: In this perspective, a recently proposed multiscale and hybrid solution for uncertainty quantification is discussed.

Methods: The proposed method is based on the (deep) learning of the morphology-affected elasticity of the polycrystalline films and of the microfabrication-induced defective geometry of the devices. The results at the material and at the device levels are linked through a reduced-order representation of the response of the entire device to the external stimuli, foreseen to finally feed a Monte Carlo uncertainty quantification engine.

Results: Preliminary results relevant to a single-axis resonant Lorentz force micro-magnetometer have shown a noteworthy capability of the proposed multiscale deep learning method to account for the mentioned uncertainty sources at the microscale.

Conclusion: A promising two-scale deep learning approach has been proposed for polysilicon MEMS sensors to account for both materials- and geometry-governed uncertainties and to properly describe the scale-dependent response of MEMS devices.

Keywords: Machine learning, artificial neural networks (ANNs), polysilicon mems, uncertainty quantification, Monte Carlo simulations, multiscale analysis.

Graphical Abstract

[1] 
Ko, W. Trends and frontiers of MEMS. Sens. Actuators A Phys.,  2007, 136(1), 62-67.
[http://dx.doi.org/10.1016/j.sna.2007.02.001] 
[2] 
System‐Level Modeling of MEMS In: Bechtold, T.; Schrag, G.; Feng, L., Eds.; Advanced Micro and Nanosystems; Wiley 2013.
[http://dx.doi.org/10.1002/9783527647132] 
[3] 
Arney, S. Designing for MEMS reliability. MRS Bull.,  2001, 26(4), 296-299.
[http://dx.doi.org/10.1557/mrs2001.63] 
[4] 
Hartzell, A.; Silva, M.; Shea, H. MEMS reliability; Springer: New York, USA, 2011. 
[http://dx.doi.org/10.1007/978-1-4419-6018-4] 
[5] 
De Laat, M.; Pérez Garza, H.; Herder, J.; Ghatkesar, M. A review on in situ stiffness adjustment methods in MEMS. J. Micromech. Microeng.,  2016, 26(6), 063001.
[http://dx.doi.org/10.1088/0960-1317/26/6/063001] 
[6] 
Mirzazadeh, R.; Eftekhar Azam, S.; Mariani, S. Micromechanical characterization of polysilicon films through on-chip tests. Sensors (Basel),,  2016, 16(8), 1191.
[http://dx.doi.org/10.3390/s16081191] [PMID: 27483268] 
[7] 
Mirzazadeh, R.; Eftekhar Azam, S.; Mariani, S. Mechanical characterization of polysilicon MEMS: A hybrid TMCMC/POD-kriging ap-proach. Sensors (Basel),  2018, 18(4), 1243.
[http://dx.doi.org/10.3390/s18041243] [PMID: 29673228] 
[8] 
Mariani, S.; Ghisi, A.; Mirzazadeh, R.; Eftekhar Azam, S. On-Chip testing: A miniaturized lab to assess sub-micron uncertainties in pol-ysilicon MEMS. Micro Nanosyst.,  2018, 10, 84-93.
[http://dx.doi.org/10.2174/1876402911666181204122855] 
[9] 
Agarwal, N.; Aluru, N. Stochastic analysis of electrostatic MEMS subjected to parameter variations. J. Microelectromech. Syst.,  2009, 18(6), 1454-1468.
[http://dx.doi.org/10.1109/JMEMS.2009.2034612] 
[10] 
Gennat, M.; Meinig, M.; Shaporin, A.; Kurth, S.; Rembe, C.; Tibken, B. Determination of parameters with uncertainties for quality control in MEMS fabrication. J. Microelectromech. Syst.,  2013, 22(3), 613-624.
[http://dx.doi.org/10.1109/JMEMS.2012.2236076] 
[11] 
Uhl, T.; Martowicz, A.; Codreanu, I.; Klepka, A. Analysis of uncertainties in MEMS and their influence on dynamic properties. Arch. Mech.,  2009, 61, 349-370.
[12] 
Weinberg, M.S.; Kourepenis, A. Error sources in in-plane silicon tuning-fork MEMS gyroscopes. J. Microelectromech. Syst.,  2006, 15(3), 479-491.
[http://dx.doi.org/10.1109/JMEMS.2006.876779] 
[13] 
Marconi, J.; Tiso, P.; Quadrelli, D.E.; Braghin, F. A higher-order parametric nonlinear reduced-order model for imperfect structures using Neumann expansion. Nonlinear Dyn.,  2021, 104(4), 3039-3063.
[http://dx.doi.org/10.1007/s11071-021-06496-y] 
[14] 
Quesada Molina, J.P.; Rosafalco, L.; Mariani, S. Mechanical characterization of polysilicon MEMS devices: A stochastic, Deep Learning-based approach. In: EuroSime 2020, Thermal, Mechanical and Multiphysics Simulation and Experiments in Micro-Electronics and Micro-Systems; Cracow: Poland, 2020, pp. 6-27.
[15] 
Goodfellow, I.; Bengio, Y.; Courville, A. Deep Learning; MIT Press: Boston, 2016. 
[16] 
Schmidhuber, J. Deep learning in neural networks: An overview. Neural Netw.,  2015, 61, 85-117.
[http://dx.doi.org/10.1016/j.neunet.2014.09.003] [PMID: 25462637] 
[17] 
Mariani, S.; Quesada Molina, J.P. A two-scale multi-physics deep learning model for smart MEMS sensors. J. Mater. Sci. Chem. Eng.,  2021, 9(8), 41-52.
[http://dx.doi.org/10.4236/msce.2021.98004] 
[18] 
Bagherinia, M.; Bruggi, M.; Corigliano, A.; Mariani, S.; Lasalandra, E. Geometry optimization of a Lorentz force, resonating MEMS mag-netometer. Microelectron. Reliab.,  2014, 54(6-7), 1192-1199.
[http://dx.doi.org/10.1016/j.microrel.2014.02.020] 
[19] 
Bagherinia, M.; Mariani, S. Stochastic effects on the dynamics of the resonant structure of a Lorentz force MEMS magnetometer. Actuators,  2019, 8(2), 36.
[http://dx.doi.org/10.3390/act8020036] 
[20] 
Han, J.S.; Ko, J.S.; Korvink, J.G. Structural optimization of a large-displacement electromagnetic Lorentz force microactuator for optical switching applications. J. Micromech. Microeng.,  2004, 14(11), 1585-1596.
[http://dx.doi.org/10.1088/0960-1317/14/11/021] 
[21] 
Comi, C.; Corigliano, A.; Langfelder, G.; Longoni, A.; Tocchio, A.; Simoni, B. A resonant microaccelerometer with high sensitivity operat-ing in an oscillating circuit. J. Microelectromech. Syst.,  2010, 19(5), 1140-1152.
[http://dx.doi.org/10.1109/JMEMS.2010.2067437] 
[22] 
Kumar, V.; Mazrouei Sebdani, S.; Pourkamali, S. Sensitivity enhancement of a Lorentz force MEMS magnetometer with frequency modu-lated output. J. Microelectromech. Syst.,  2017, 26(4), 870-878.
[http://dx.doi.org/10.1109/JMEMS.2017.2693818] 
[23] 
Herrera-May, A.L.; Soler-Balcazar, J.C.; Vázquez-Leal, H.; Martínez-Castillo, J.; Vigueras-Zuñiga, M.O.; Aguilera-Cortés, L.A. Recent advances of MEMS resonators for lorentz force based magnetic field sensors: Design, applications and challenges. Sensors (Basel),  2016, 16(9), 1359.
[http://dx.doi.org/10.3390/s16091359] [PMID: 27563912] 
[24] 
Cang, R.; Ren, M.Y. Deep network-based feature extraction and
reconstruction of complex material microstructures. In: ASME 2016
International Design Engineering Technical Conferences and
Computers and Information in Engineering Conference; Charlotte:
North Carolina, USA, 2016.
[http://dx.doi.org/10.1115/DETC2016-59404] 
[25] 
Lubbers, N.; Lookman, T.; Barros, K. Inferring low-dimensional
microstructure representations using convolutional neural networks. Phys. Rev. E,  2017, 96(5-1), 052111.
[26] 
Schmidt, J.; Marques, M.R.G.; Botti, S.; Marques, M.A.L. Recent advances and applications of machine learning in solid-state materials science. NPJ Comput Mater.,  2019, 5, 83.
[27] 
Himanen, L.; Geurts, A.; Foster, A.S.; Rinke, P. Data-driven materials science: Status, challenges, and perspectives. Adv. Sci. (Weinh.),  2019, 6(21), 1900808.
[http://dx.doi.org/10.1002/advs.201900808] [PMID: 31728276] 
[28] 
Bock, F.E.; Aydin, R.C.; Cyron, C.J.; Huber, N.; Kalidindi, S.R.; Klusemann, B. A review of the application of machine learning and data mining approaches in continuum materials mechanics. Front. Mater.,  2019, 6, 110.
[http://dx.doi.org/10.3389/fmats.2019.00110] 
[29] 
He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image
recognition. arXiv,  2016, 2016, 1512.03385.
[30] 
Hopcroft, M.A.; Nix, W.D.; Kenny, T.W. What is the young’s modulus of silicon? J. Microelectromech. Syst.,  2010, 19(2), 229-238.
[http://dx.doi.org/10.1109/JMEMS.2009.2039697] 
[31] 
den Toonder, J.M.J.; van Dommele, J.A.W.; Baaijens, F.P.T. The relation between single crystal elasticity and the effective elastic behav-iour of polycrystalline materials: Theory, measurement and computation. Model. Simul. Mater. Sci. Eng.,  1999, 7(6), 909-928.
[http://dx.doi.org/10.1088/0965-0393/7/6/301] 
[32] 
Ostoja-Starzewski, M. Material spatial randomness: From statistical to representative volume element. Probab. Eng. Mech.,  2006, 21(2), 112-132.
[http://dx.doi.org/10.1016/j.probengmech.2005.07.007] 
[33] 
Wang, Z.; Yan, W.; Oates, T. Time series classification from scratch with deep neural networks: A strong baseline. arXiv,  2017, 2016, 1611.06455.
[http://dx.doi.org/10.1109/IJCNN.2017.7966039] 
[34] 
Karim, F.; Majumdar, S.; Darabi, H.; Harford, S. Multivariate LSTM-FCNs for time series classification. Neural Netw.,  2019, 116, 237-245.
[http://dx.doi.org/10.1016/j.neunet.2019.04.014] [PMID: 31121421] 
[35] 
Glorot, X.; Bengio, Y. Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics; Chia Laguna Resort: Sardinia, Italy, 2010, pp.13-15.

Cite As