A neural network based generative optimization algorithm was investigated for designing athermalized lens design. In particular, deep learning framework was developed by employing PyTorch and incorporated lens variable conversion techniques along with a differentiable ray tracing module. The framework, combining supervised optimization with unsupervised optimization, could generate diversified lens designs starting from reference lens system including aspheric surfaces. Our generative optimization algorithm could also be applied to the design of athermal lens systems that minimize thermal focus shift with temperature changes. In addition, using the developed algorithm and considering the first order thermal expansion coefficient of each lens, we were able to design an all-plastic athermal lens system composed of polycarbonate and polymethyl methacrylate materials. The RMS spot size averaged over all fields and Seidel aberration were minimized for thermally expanded lens systems at various temperatures. The developed framework is expected to help lens designers create optimal designs.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.