You can only gain access to certain items and special pricing if you have logged in. Login Now.

CC-98-138 Model-based Validation And Reconciliation in the Process Plant

Michael Keaton, Michael Keenan, PrimusTech; Edwin D. Soderstrom, Condea Vista

Format:
Electronic (digital download/no shipping)

Associate Member, International Member, Petrochemical Member, Refining Member - $0.00
Government, NonMember - $35.00

Description:

Models are the key element for validating and reconciling process data, whether from process instrumentation or the lab. Combining models with statistics and heuristics can provide a viable mechanism for validating instrumentation, analyzers, laboratory data and other information required for control, advanced control, optimization and corporate information Advances in empirical techniques such as neural networks, PLS, PCR, and other regression methods, have made model-based validation and reconciliation systems economically attractive. Model-based systems provide the added value of being able to replace suspect data with reasonable estimates based on redundant information existing in the plant. This paper describes how empirical models are applied for validation and reconciliation. An example of an operating model-based validation system in a process plant is presented.

Product Details:

Product ID: CC-98-138
Publication Year: 1998