Surrogate neural network model for sensitivity analysis and uncertainty quantification of the mechanical behavior in the optical lens-barrel assembly. (1st October 2022)

• Record Type: Journal Article
• Authors: Shahane, Shantanu; Guleryuz, Erman; Abueidda, Diab W.; Lee, Allen; Liu, Joe; Yu, Xin; Chiu, Raymond; Koric, Seid; Aluru, Narayana R.; Ferreira, Placid M.
• Is Part Of: Computers & structures. Volume 270(2022)
• Publication Date: 2022-10-01
• Subjects: Machine learning -- Finite element analysis -- Lens assembly -- Sensitivity analyses -- Uncertainty quantification -- High performance computing; Structural engineering -- Data processing -- Periodicals; Electronic data processing -- Structures, Theory of -- Periodicals; 624.171
• DOI: 10.1016/j.compstruc.2022.106843
• Languages: English
• ISSNs: 0045-7949

Abstract

Highlights: Modeling of deformations in lenses due to various interferences during assembly in barrel. Analysis of sensitivity and uncertainty propagation from interference to lens deformations. Neural network as surrogate model for Monte-Carlo methods. Nonlinear finite element analysis performed on high-performance computing (HPC) cluster to train neural network. Abstract: Surrogate neural network-based models have been lately trained and used in a variety of science and engineering applications where the number of evaluations of a target function is limited by execution time. In cell phone camera systems, various errors, such as interferences at the lens-barrel and lens-lens interfaces and axial, radial, and tilt misalignments, accumulate and alter profile of the lenses in a stochastic manner which ultimately changes optical focusing properties. Nonlinear finite element analysis of the stochastic mechanical behavior of lenses due to the interference fits is used on high-performance computing (HPC) to generate sufficient training and testing data for subsequent deep learning. Once properly trained and validated, the surrogate neural network model enabled accurate and almost instant evaluations of millions of function evaluations providing the final lens profiles. This computational model, enhanced by artificial intelligence, enabled us to efficiently perform Monte-Carlo analysis for sensitivity and uncertainty quantification of the final lens profile to various interferences. It can be further coupled with an optical analysis to perform ray tracing and analyze the focal properties of the lens module. Moreover, it can provide a valuable tool for optimizing tolerance design and intelligent components matching for many similar press-fit assembly processes.