Abstract: A method based on the combination of image morphological texture feature extraction and cuckoo search-spiking neural network (CS-SNN) algorithm is introduced to solve the problem of fine quantitative diagnosis and recognition of demagnetization faults in dual primary permanent magnet synchronous linear motor (DPPMSLM). First, according to the constraints of DPPMSLM topology, the three-line magnetic density signal in the air gap space of the motor is extracted by finite element simulation as an effective fault signal. Secondly, the image texture analysis method is introduced to map the one-dimensional data signal to the two-dimensional gray image, and then the gamma correction and edge detection technology are used to enhance the image information, so as to extract the texture features of the image to form the fault feature vector. Then, a two-stage CS-SNN classifier is established to accurately diagnose and classify the location and severity of demagnetization faults. Finally, through the production of demagnetization prototype and experimental platform verification, the new method proposed in this paper can accurately identify the location and severity of demagnetization fault of DPPMSLM, and has good robustness, which is an effective and feasible method.