FRC-TOuNN: Topology Optimization of Continuous Fiber Reinforced Composites using Neural Network

In this paper, we present a topology optimization (TO) framework to simultaneously optimize the matrix and fiber distribution of functionally graded continuous fiber-reinforced composites (FRC). Current approaches in density-based TO for FRC use underlying finite element mesh both analysis design representation. This poses several limitations while enforcing sub-element spacing generating high-resolution fibers. contrast, propose mesh-independent representation based on neural network (NN) capture distribution. The implicit NN-based enables geometric material queries at higher resolution than discretization. leads accurate extraction functionally-graded Further, by integrating simulations into NN computational framework, can leverage automatic differentiation end-to-end automated sensitivity analysis, i.e., no longer need manually derive cumbersome expressions. We demonstrate effectiveness efficiency proposed method through numerical examples involving various objective functions. also show that optimized reinforced be directly fabricated high using additive manufacturing.