Tool wear condition (TCM) has a significant impact on machining quality, efficiency and cost, so it is vitally important in manufacturing systems. The current work of TCM mainly process the time series signals from multisensory by intelligent algorithm. However, the limited of these method is; 1) the image information are not integrated into the time series signals, 2) the traditional methods are facing the problems of poor generalization and fast convergence. Thus, a novel integrated model based on the multisensory feature fusion and neural network is presented. After the PAA pre-processed, the developed model recodes the sensor data into images using GAF and inputs to CNN model with the tool infrared images, then realizes the output of flank wear value. Compared with other algorithms, the results show that the algorithm has better classification ability.