In this article, a novel linear mmWave antenna array with series‐feed network is proposed to enhance the bandwidth and reduce sidelobe level without increasing the patch size. The proposed linear array is consisted of four identical wideband array elements, which are all under operation TM10 and TM02 modes by loading shorting pin and rectangular slots. Additionally, through loading symmetry circle‐shaped slots for the four elements, impedance matching of linear array is achieved. Furthermore, multi‐parameters unified‐optimization (MPUO) based on imperial competition algorithm (ICA) is proposed to uniformly optimize all linear array parameters. To verify this design, the proposed linear array is fabricated with a small patch area of 7.5 × 3.914 × 0.254 mm3. The measured results show that the bandwidth is enhanced to 2.05GHz, which is 0.57GHz wider than that of simulation. The simulated peak gain reaches 13dBi while the sidelobe level is reduced to about −19 dB at 28.6GHz. Moreover, the computation cost using MPUO is reduced by 98.12% compared with that of independent parameters optimization.

In this paper, we propose an efficient synthesis method based on two-stage optimization to synthesize the concentric ring array (CRA) through exploiting the potential benefits of machine learning approach, called K-Nearest Neighbor-Bagging (K-BAG). In the first stage, the training dataset of K-BAG is obtained through an optimization algorithm to train the K-BAG. After that, in the second stage, the randomly selected geometrical parameters of CRA are input to the trained K-BAG, then the structural parameters and correspondingly simulated results are obtained simultaneously in output, which can acquire better solutions compared with that of only considering optimization algorithm. The proposed method improves simulation efficiency and K-BAG robustness while guaranteeing the peak sidelobe level compared with other optimization algorithms of previous researches.