Can neural networks compete with process calculations
Neural networks have been called a real alternative to rigorous theoretical models. A theoretical model for the calculation of refinery coker naphtha end point and coker furnace oil 90% point already was in place on the combination tower of a coking unit. Considerable data had been collected on the theoretical model during the commissioning phase and benefit analysis of the project. A neural net developed for the coker fractionator has equalled the accuracy of theoretical models, and shown the capability to handle normal operating conditions. One disadvantage of a neural network is the amount of data needed to create a good model. Anywhere from 100 to thousands of cases are needed to create a neural network model. Overall, the correlation between theoretical and neural net models for both the coker naphtha end point and the coker furnace oil 90% point was about .80; the average deviation was about 4 degrees. This indicates that the neural net model was at least as capable as the theoretical model in calculating inferred properties. 3 figs.
- OSTI ID:
- 6370708
- Journal Information:
- InTech; (United States), Vol. 39:12; ISSN 0192-303X
- Country of Publication:
- United States
- Language:
- English
Similar Records
Fundamentals of Delayed Coking Joint Industry Project
Fundamentals of Delayed Coking Joint Industry Project
Related Subjects
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
NEURAL NETWORKS
USES
PETROLEUM PRODUCTS
COKING
FRACTIONATION
MATHEMATICAL MODELS
NAPHTHA
PETROLEUM REFINERIES
CARBONIZATION
CHEMICAL REACTIONS
DECOMPOSITION
DISTILLATES
INDUSTRIAL PLANTS
SEPARATION PROCESSES
020400* - Petroleum- Processing
990200 - Mathematics & Computers