Antenna array fault diagnosis method based on sparse Bayesian learning

The invention discloses an antenna array fault diagnosis method based on sparse Bayesian learning, and relates to the field of antenna array signal processing. The method includes: measuring the voltage of a fault array by employing a probe at a plurality of measuring points of a near-field area; then performing sparse processing on a measured voltage data vector (performing difference operation on the measured voltage data vector and a near-field voltage data vector of a faultless array), and reconstructing an excitation vector of the fault array through a sparse Bayesian learning algorithm by employing the sparse data vector; and then calculating the quantity and the positions of array elements according to the excitation vector obtained by reconstruction to realize the goal of the method. Compared with the conventional array fault diagnosis algorithm, according to the method, the required near-field data samples are less, the success rate of diagnosis is higher, and the method can be applied to a conformal