Hao Wu, Jinsong Zhao
Index: 10.1016/j.compchemeng.2018.04.009
Full Text: HTML
Numerous accidents in chemical processes have caused emergency shutdowns, property losses, casualties and/or environmental disruptions in the chemical process industry. Fault detection and diagnosis (FDD) can help operators timely detect and diagnose abnormal situations, and take right actions to avoid adverse consequences. However, FDD is still far from widely practical applications. Over the past few years, deep convolutional neural network (DCNN) has shown excellent performance on machine-learning tasks. In this paper, a fault diagnosis method based on a DCNN model consisting of convolutional layers, pooling layers, dropout, fully connected layers is proposed for chemical process fault diagnosis. The benchmark Tennessee Eastman (TE) process is utilized to verify the outstanding performance of the fault diagnosis method.
Reactive Scheduling of Crude Oil using Structure Adapted Gen...
2018-04-03 [10.1016/j.compchemeng.2018.04.005] |
A CFD simulation study of boiling mechanism and BOG generati...
2018-04-03 [10.1016/j.compchemeng.2018.04.003] |
Optimal Synthesis of Periodic Sorption Enhanced Reaction Pro...
2018-04-03 [10.1016/j.compchemeng.2018.04.004] |
Optimization-based approach for maximizing profitability of ...
2018-04-03 [10.1016/j.compchemeng.2018.04.001] |
Computer aided chemical product design - ProCAPD & tailor-ma...
2018-04-01 [10.1016/j.compchemeng.2018.03.029] |
Home | MSDS/SDS Database Search | Journals | Product Classification | Biologically Active Compounds | Selling Leads | About Us | Disclaimer
Copyright © 2024 ChemSrc All Rights Reserved