The Layout Measurement Points Prediction and Flatness Calculation for the Antenna Plate After Welding Assembly Based on the RBF Neural Network Model

Abstract

Due to the effect of the antenna plate flatness on the antenna performances, the flatness is one of the key performance indicators for the planar antenna. Before calculating the antenna plate flatness, the support assembly tools are built, and then measuring experiment for height coordinate values is carrying out on the assembly platform. This paper presents a predictive method that is the Radial Basis Function (RBF) neural network method to obtain the height coordinate values based on fewer measurement points on the antenna plate after welding assembly, and the antenna plate flatness is calculated by fitting least square plane using measuring point coordinate value through the least square method (LSM). Simultaneously, before or after welding assembly, comparing with the calculated flatness value, it is shown that the calculated flatness value by the predicted height coordinate values basically agrees well with the initial calculated flatness value. These results reveal that the RBF neural network prediction is adopted to be very correct and valid, which will reduce the measurement cost and improve measurement efficiency in future.