Dynamic Hybrid Models With Active Sampling and Adaptive Selection of Double-Domain Features for the Tuning of Microwave Cavity Filters
- 5 January 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 54 (8) , 4828-4840
Abstract
Microwave cavity filters are essential electromechanical coupling devices in communication systems. Structural-parameter tuning by experienced operators improves the filter performance but is demanding and time-consuming. The automatic tuning method has received extensive research attentions using data-driven modeling approaches. However, two main issues affect the accuracy and efficiency of the model construction: 1) features of tuning processes, as model inputs, have limited adaptability and extraction accuracy to different resonant states and 2) models require plentiful training data and the training process is time-consuming. Thus, dynamic hybrid models are developed in this study with self-selected inputs, self-organized samples, and a self-learning structure. First, spatial features are extracted to flexibly depict the tuning characteristic, and double-domain (spatial or circuital) features are selected adaptively to accommodate distinct resonance states. Second, a trustworthiness-curiosity-driven active sampling method is exploited to attain fewer and better-training data. Third, an improved broad learning systemBLS is developed using new modules of incremental node calculation and weight pruning, characterized by more lightweight and flexible structures. The proposed method is effective and flexible demonstrated by simulations and experiments, and the tuning task of microwave cavity filters is fulfilled in a more accurate and efficient manner.Keywords
Funding Information
- National Natural Science Foundation of China (61773354)
- Natural Science Foundation of Hubei province, China (2020CFA031)
- 111 Project (B17040)
- China Scholarship Council (202106410100)
- Fundamental Research Funds for National Universities (CUGDCJJ202210)
This publication has 41 references indexed in Scilit:
- Recent Advances in Multiphysics Optimization for Microwave Filters Using Space Mapping Techniques2021
- Tensor product‐based model transformation approach to tower crane systems modelingAsian Journal of Control, 2021
- Advanced RF and Microwave Design Optimization: A Journey and a Vision of Future TrendsIEEE Journal of Microwaves, 2021
- What Are We Curious about?Trends in Cognitive Sciences, 2020
- A Hybrid Modeling Method Based on Neural Networks and Its Application to Microwave Filter TuningIFAC-PapersOnLine, 2020
- A cuckoo search optimization-based forward consecutive mean excision model for threshold adaptation in cognitive radioSoft Computing, 2019
- Importance Estimation for Neural Network Pruning2019
- Extracting Coupling Matrix From Lossy Filters With Uneven-Qs Using Differential Evolution Optimization TechniqueInternational Journal of RF and Microwave Computer-Aided Engineering, 2018
- Parametric modeling of microwave filter using combined MLS-SVR and pole-residue-based transfer functionsInternational Journal of RF and Microwave Computer-Aided Engineering, 2018
- Tuning-aided implicit space mappingInternational Journal of RF and Microwave Computer-Aided Engineering, 2008