Failure Diagnosis of Microstrip Antenna Array Based on Convolutional Neural Network

Antenna failure diagnosis is one of the essential problems in the area of radar and wireless communications. In this paper, a new method based on convolutional neural network (CNN) is proposed for antenna array failure diagnosis and compared with support vector machine (SVM). Numerical test results demonstrate that the method of antenna failure diagnosis by CNN is accurate and feasible. The accuracy of CNN under different amounts of training data are also discussed in this paper.