An Efficient Geometric Parameter Optimization Method for Microstrip Bandpass Filter Based on One-Dimensional Convolutional Neural Network

Machine learning-assisted electromagnetic simulation has become an effective acceleration tool for designing microwave components by introducing high-precision models and optimization algorithms, featuring fast design and high efficiency. However, enormous amount of data generated from the blind preliminary and computationally expensive simulation is required to predict the accuracy response. An efficient geometric parameter optimization method for microstrip bandpass filter (BPF) based on a one-dimensional convolutional neural network is proposed. Nonlinear convergence factor, adaptive weight, and Gaussian difference mutation strategies are integrated using the whale optimization algorithm to avoid the local optimum and improve optimization accuracy. Computational efficiency is improved significantly with small-scale training data. The validity and efficiency of the proposed method are confirmed by fifth-order microstrip BPFs, and the performance of the predicted structure parameters is significantly improved, which shows great promise for application in optimization and performance improvement in microwave electromagnetic simulation.