Hybrid optimization for build orientation in fused filament fabrication using low- and high-fidelity build time estimation models.

Build time is one of the crucial aspects of the fused filament fabrication (FFF) process. A reliable estimate of build time is vital, as it is the basis for estimating production cost, process planning, and build orientation optimization (BOO). In the last two decades, many researchers have developed methods to estimate the build time of FFF processes. However, the efficient applicability of these methods as low-fidelity models in lieu of high-fidelity model like G-code generation software in the context of BOO considering their correlation and computational cost has not been well researched. This paper thus initially evaluates the correlation coefficient and computational cost of different build time estimate models proposed in literature and benchmarks them with a high-fidelity model which itself is validated with experiments. Then, the work proposes a hybrid optimization framework that uses multifidelity models to obtain optimum build orientation with improved computational performance. First, we do a multi-modal build orientation optimization by a Covariance Matrix Self-Adaptation Evolution Strategy with Repelling Subpopulations (RS-CMSA) algorithm using a low-fidelity model and use these as the initial points in a gradient-based optimization method using a high-fidelity model. The proposed hybrid method has been illustrated with example case studies as well as compared and evaluated to a standard optimization algorithm using a single fidelity model to demonstrate the overall methodology and its effectiveness. [ABSTRACT FROM AUTHOR]