A Dynamic Tuning Decision-Making Model Using Multi-Feature Fusion

Dielectric Filters (DFs) are tuned to meet the requirements of 5G communication systems. The tuning methods based on Tuning Decision-Making Models (TDMMs) are efficient. However, how to build TDMMs accurately and fast is rather difficult due to the complex performance representation and the poor consistency of DFs. In this brief, a dynamic tuning decision-making model using multi-feature fusion is proposed. The contributions of this brief are as follows: 1) For the problem of incomplete feature representation of DFs performance, the multiple features are fused to improve the accuracy of TDMMs; 2) to deal with the problem that high-quality samples are challenging to obtain, a guided sampling method is designed to determine the sampling range, driven by the characteristics of DFs; 3) to solve the problem of inefficient modeling for inconsistent DFs, TDMMs are built dynamically using transfer learning. Finally, the excellent performance of the proposed method is demonstrated through comparative simulations.