It is difficult to combine human sensory cognition with quality detection to form a pattern recognition system based on human perception. In the future, miniature stepper motor modules will be widely used in advanced intelligent equipment. However, the reducer module based on powder metallurgy parts and the stepper motor may have various defects during operation, with varying definitions of those that affect the user comfort. It is tremendously important to develop an intelligent system to effectively simulate human senses. In this work, an elaborated personification of the perceptual system is proposed to simulate the ventral and flow of the human perception system: two branch systems consisting of a spatiotemporal convolutional neural network (S-CNN) and a concatenated HoppingNet temporal convolutional neural network (T-CNN). To ensure high robustness of the system, we combined principal component analysis (PCA) with the opinions of an experienced quality control (QC) team members to screen the data, and used a bionic ear to simulate human perception characteristics. After repeated comparisons of the tester, the results show that our anthropoid pattern sensing system has high accuracy and robustness for a stepper motor module.
Neural Network Configurations Analysis for Multilevel Speech Pattern Recognition System with Mixture of Experts
