Prediction of Array Antenna Assembly Accuracy Based on Auto-Encoder and Boosting-OSKELM

Abstract

As a complex mechanical and electrical product, array antenna involves many parts and requires high precision, so its assembly process is complex, changeable and difficult to control. As a result, the assembly accuracy often fails to meet the design requirements and needs to be reassembled repeatedly, resulting in the delay of delivery date. In order to realize the accurate and efficient prediction of array antenna assembly accuracy, a prediction method based on auto-encoder and online sequential kernel extreme learning machine with boosting (Boosting-OSKELM) is proposed in this paper. The method is mainly divided into two steps: Firstly, the auto-encoder with fine-tuning trick is used for training and representation reduction of the data. Then, the data is taken as the input of Boosting-OSKELM to complete the initial training of the model. When new sample data is generated, Boosting-OSKELM can realize the online correction of the model through rapid iteration. The test shows that this method has strong robustness in prediction accuracy and online learning ability.