A Biochemical Fault Detection Method Based on Stack Noise Reduction Sparse Automatic Encoder

摘要

A method based on stack noise reduction sparse automatic coder is proposed for biochemical process fault detection. Based on SDSA, softmax classifier is introduced to build a deep neural network model, and particle swarm optimization algorithm is used to optimize the parameters of the model to improve the sensitivity of the model in fault detection. The effectiveness of the proposed method is verified by the simulation of Eastman process in Tennessee.