Robust Parameter Design for Functional Responses in Additive Manufacturing Using Gaussian Process Functional Regression

ABSTRACT In the realm of intelligent manufacturing, with additive manufacturing serving as a prime example, engineers frequently gather intensive quality data either in the temporal or spatial domain. At the same time, these quality data are often in the form of functional data (i.e. functional responses). However, traditional quality design methods such as Taguchi method and response surface methodology (RSM) are difficult to solve the robust parameter design (RPD) problems with high‐dimensional and complex functional response. To overcome this challenge, we propose a novel RPD method based on a Gaussian process functional regression (GPFR) model, which aims to find optimal parameter combinations to achieve accurate optimization results. Initially, the Latin hypercube design is used to obtain the experimental data. Subsequently, the GPFR model is used to describe the functional relationship between input factors and output responses in the 3D printing process. Finally, an optimization objective function is constructed using the grey relation analysis (GRA), and a genetic algorithm is employed to determine the optimal process parameters. A practical case from the additive manufacturing laboratory of the High‐end Equipment Research Center in Jiangsu Province, along with the corresponding confirmatory experiments, demonstrates the effectiveness and reliability of the proposed method.