Knowledge-based neural network modeling techniques using space-mapping concept have been demonstrated in the existing literature as efficient methods to overcome the accuracy limitations of empirical/equivalent circuit models when matching new electromagnetic data. For different modeling problems, the mapping structures can be different. In this paper, we propose a unified automated model generation algorithm that uses l1 optimization to automatically determine the type and the topology of the mapping structure in a knowledge-based neural network model. By encompassing various types of mappings of the knowledge-based neural network model in the existing literature, we present a new unified model structure and derive new sensitivity formulas for the training of the unified model. The proposed l1 formulation of modeling can force some weights of the mapping neural networks to zeros while leaving other weights as nonzeros. We utilize this feature to allow l1 optimization to automatically determine which mapping is necessary and which mapping is unnecessary. Using the proposed l1 optimization method, the mapping structure can be determined to address different needs of different modeling problems. The structure of the final knowledge-based model can be flexible combinations of some or all of linear mapping, nonlinear mapping, input mapping, frequency mapping, and output mapping. In this way, the proposed algorithm is more systematic and can further speed up the knowledge-based modeling process than existing knowledge-based modeling algorithms. The proposed method is illustrated by three microwave filter modeling examples.

Additional Metadata
Keywords Design automation, electromagnetic (EM) modeling, knowledge-based neural network, microwave filter, parametric model
Persistent URL dx.doi.org/10.1109/TMTT.2016.2630059
Journal IEEE Transactions on Microwave Theory and Techniques
Citation
Na, W. (Weicong), Feng, F. (Feng), Zhang, C. (Chao), & Zhang, Q.J. (2017). A Unified Automated Parametric Modeling Algorithm Using Knowledge-Based Neural Network and l1 Optimization. IEEE Transactions on Microwave Theory and Techniques, 65(3), 729–745. doi:10.1109/TMTT.2016.2630059