Stochastic Mechanical Characterization of Polysilicon MEMS: A Deep Learning Approach

Quesada-Molina, José Pablo; Rosafalco, Luca; Mariani, Stefano

doi:10.3390/ecsa-6-06574

Cited by 3 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, the proposed strategy is going to be re-formulated within the frame of a data-driven approach. Specifically, the mechanical properties of polysilicon are characterized by a neural network, trained with the same data used in this work for upscaling its elastic properties [21][22][23][24]. Next step of the procedure is therefore the multiscale [25,26], fully data-driven analysis of the designed device and, to a larger extent, of the scattering measured in ever downsizing MEMS devices.…”

Section: Discussionmentioning

confidence: 99%

A Stochastic Model to Describe the Scattering in the Response of Polysilicon MEMS

Dassi

Merola

Riva

et al. 2021

7th International Electronic Conference on Sensors and Applications

Self Cite

View full text Add to dashboard Cite

The current miniaturization trend in the market of inertial microsystems is leading to movable device parts with sizes comparable to the characteristic length-scale of the polycrystalline silicon film morphology. The relevant output of micro electro-mechanical systems (MEMS) is thus more and more affected by a scattering, induced by features resulting from the micro-fabrication process. We recently proposed an on-chip testing device, specifically designed to enhance the aforementioned scattering in compliance with fabrication constraints. We proved that the experimentally measured scattering cannot be described by allowing only for the morphology-affected mechanical properties of the silicon films, and etch defects must be properly accounted for too. In this work, we discuss a fully stochastic framework allowing for the local fluctuations of the stiffness and of the etch-affected geometry of the silicon film. The provided semi-analytical solution is shown to catch efficiently the measured scattering in the C-V plots collected through the test structure. This approach opens up the possibility to learn on-line specific features of the devices, and to reduce the time required for their calibration.

show abstract

Section: Discussionmentioning

confidence: 99%

A Stochastic Model to Describe the Scattering in the Response of Polysilicon MEMS

Dassi

Merola

Riva

et al. 2021

7th International Electronic Conference on Sensors and Applications

Self Cite

View full text Add to dashboard Cite

show abstract

“…They found that the micro-grooves between the grains are the critical reason leading to structural fracture. Mariani et al [114][115][116] The variation of the tensile strength of MEMS materials makes it difficult to predict the failure threshold or quantify reliability through numerical analysis. Therefore, some studies have proposed probabilistic models for MEMS structural materials, which regard the tensile strength of the material as a random variable.…”

Section: Strength Model Of Brittle Materialsmentioning

confidence: 99%

“…They found that the micro-grooves between the grains are the critical reason leading to structural fracture. Mariani et al [114][115][116] produced a series of studies. In 2011, Mariani et al performed multi-scale modeling of MEMS structures.…”

Section: Strength Model Of Brittle Materialsmentioning

confidence: 99%

“…In 2019 and 2020, José Pablo Quesada Molina et al used deep learning to characterize the mechanical properties of polysilicon materials based on the data set (which was generated numerically, as shown in Figure 12). The deep learning model could predict the relationship between the grain characteristics and the mechanical properties of polysilicon [115,116].…”

Section: Strength Model Of Brittle Materialsmentioning

confidence: 99%

“…Figure 12. (a) morphologies of statistical volume elements (b) schematic of the receptive field of a convolutional layer[115] …”

mentioning

confidence: 99%

See 2 more Smart Citations

Reliability of MEMS in Shock Environments: 2000–2020

Peng

You

2021

Micromachines

View full text Add to dashboard Cite

The reliability of MEMS in shock environments is a complex area which involves structural dynamics, fracture mechanics, and system reliability theory etc. With growth in the use of MEMS in automotive, IoT, aerospace and other harsh environments, there is a need for an in-depth understanding of the reliability of MEMS in shock environments. Despite the contributions of many articles that have overviewed the reliability of MEMS panoramically, a review paper that specifically focuses on the reliability research of MEMS in shock environments is, to date, absent. This paper reviews studies which examine the reliability of MEMS in shock environments from 2000 to 2020 in six sub-areas, which are: (i) response model of microstructure, (ii) shock experimental progresses, (iii) shock resistant microstructures, (iv) reliability quantification models of microstructure, (v) electronics-system-level reliability, and (vi) the coupling phenomenon of shock with other factors. This paper fills the gap around overviews of MEMS reliability in shock environments. Through the framework of these six sub-areas, we propose some directions potentially worthy of attention for future research.

show abstract

A Deep Learning Approach for Polycrystalline Microstructure-Statistical Property Prediction

Quesada-Molina

Mariani

2021

Computational Science – ICCS 2021

Self Cite

View full text Add to dashboard Cite

Upscaling of the mechanical properties of polycrystalline aggregates might require complex and time-consuming procedures, if adopted to help in the design and reliability analysis of micro-devices. In inertial micro electro-mechanical systems (MEMS), the movable parts are often made of polycrystalline silicon films and, due to the current trend towards further miniaturization, their mechanical properties must be characterized not only in terms of average values but also in terms of their scattering. In this work, we propose two convolutional network models based on the ResNet and DenseNet architectures, to learn the features of the microstructural morphology and allow automatic upscaling of the statistical properties of the said film properties. Results are shown for film samples featuring different values of a length scale ratio, so as to assess accuracy and computational efficiency of the proposed approach.

show abstract

Stochastic Mechanical Characterization of Polysilicon MEMS: A Deep Learning Approach

Cited by 3 publications

References 26 publications

A Stochastic Model to Describe the Scattering in the Response of Polysilicon MEMS

A Stochastic Model to Describe the Scattering in the Response of Polysilicon MEMS

Reliability of MEMS in Shock Environments: 2000–2020

A Deep Learning Approach for Polycrystalline Microstructure-Statistical Property Prediction

Contact Info

Product

Resources

About