Neural Network Gaussian Process Considering Input Uncertainty for Composite Structure Assembly

Abstract

Developing machine-learning-enabled smart manufacturing is promising for a composite structure assembly process. To improve production quality and efficiency of the assembly process, accurate predictive analysis on dimensional deviations and residual stress of the composite structures is required. The novel composite structure assembly involves two challenges: 1) the highly nonlinear and anisotropic properties of composite materials; and 2) inevitable uncertainty in the assembly process. To overcome those problems, in this article, we propose a neural network Gaussian process model considering input uncertainty for composite structure assembly. Deep architecture of our model allows us to approximate a complex process better, and consideration of input uncertainty enables robust modeling with complete incorporation of the process uncertainty. Based on simulation and case study, the neural network Gaussian process considering input uncertainty can outperform other benchmark methods when the response function is nonsmooth and nonlinear. Although we use composite structure assembly as an example, the proposed methodology can be applied to other engineering systems with intrinsic uncertainties.