Knowledge-Based Neural Network for Thinned Array Modeling With Active Element Patterns

To speed up the process for designing finite thinned arrays, an efficient artificial neural network (ANN) model considering mutual coupling effects is proposed in this communication. Array elements are divided into three categories based on the active element pattern (AEP) technique, and subarrays are constructed to extract the AEP of each category of elements as training samples. The proposed model including parallel ANN branches takes into account the mutual coupling between elements and avoids the calculation of the radiation pattern of the entire array. To improve modeling performance, furthermore, a prior knowledge input technique is used to reduce the complexity of the input-output relationship that an ANN has to learn. The existing knowledge is obtained by back propagation (BP) ANN modeling. Once the knowledge-based model is well trained, it is repeatedly called by the genetic algorithm (GA) for the optimal solution as a substitute for the full-wave simulation. Numerical examples of a U-shaped slot thinned array and a dual-layer patch thinned array are utilized to verify the efficiency of the proposed scheme.

Automated summary

In this communication, an efficient artificial neural network (ANN) model considering mutual coupling effects is proposed to accelerate the process of designing finite thinned arrays. The model divides array elements into three categories based on the active element pattern (AEP) technique and constructs subarrays to extract the AEP of each category as training samples. By taking into account mutual coupling between elements and utilizing a prior knowledge input technique, the proposed model avoids the calculation of the radiation pattern of the entire array and improves modeling performance. Numerical examples verify the efficiency of the proposed scheme using different types of thinned arrays.