Due to the complex motor structure and its operating environment， there is a strong nonlinear relationship between different faults and their fault features， the motor diagnosis driven by the single signal cannot satisfy the requirements. Considering this dilemma， a motor fault diagnosis method driven by multi-sensor information based on attention mechanism and SVM-AdaBoost （SAB） is proposed in this study. First， the corresponding frequency features of current and magnet signals are extracted by Hilbert transform and Fourier transform. Then， the SAB classifier is utilized to train multi-source signals and obtain sub-classifier results respectively. Finally， based on attention machanism， an attention weight matrix is adjusted to fuse the information and calculate the final diagnosis results. The proposed method is verified by realizing the diagnosis of broken rotor bar fault， stator short circuit fault and bearing fault. The proposed method reveals that the sensitivity of different signals to various faults is different. Compared with the traditional methods， the proposed method examine its superiority in terms of the robustness， generalization ability and fault diagnosis accuracy.