Abstract: To solve the problem of multi-sensor simultaneous faults detection for autonomous underwater vehicle(AUV),a fault feature extraction method is proposed by combining wavelet analysis technology with neural network technology.After the wavelet reconstruction of detail coefficients for multi-resolution wavelet decomposition,the reconstructed detail coefficients are fused to obtain the overall high-frequency detail information,which is taken as a type of fault feature.At the same time,a full-order state observer model for AUV is built based on the improved Elman network.The difference between the model output value and actual measurement value of sensors is taken as another fault feature.In order to locate the simultaneous faults of multiple sensors for AUV,a method of fuzzy weighted attribute information fusion is proposed.The importance degree and confidence degree of the two fault feature values are transformed by the method of fuzzy synthetic conversion.Based on the results of conversion,the weighted fusion of every fault feature is made,and the simultaneous faults location of multiple sensors for AUV is realized.The results of pool experiment for AUV show that the method is feasible and effective.