A novel method for the performance control of a gas transmission compressor.

Pearson, W N; Armitage, Alistair; Henderson, Douglas

Abstract

This paper presents the application of feed forward neural networks to the performance control of a gas transmission compressor. It is estimated that a global saving in compressor fuel gas of 1% could prevent the production of 6 million tonnes of CO2, per year, [1]. Results of compressor model testing suggest that compressor speed can be estimated to within ± 2.5%. The neural network property of function approximation is used to predict compressor speed for given process constraints and instrument input sets. The effects of training set size, instrument noise, reduced input sets and extrapolation from the training domain, are quantified. Various neural network architectures and training schema were examined. The embedding of a neural network into an expert system is also discussed.

• Conference Name: ASME TURBO EXPO 2002: Controls, Diagnostics and Instrumentation, Cycle Innovations, Marine, Oil and Gas Applications
• Start Date: May 26, 2002
• End Date: May 31, 2002
• Publication Date: Jun 3, 2002
• Deposit Date: Jun 6, 2008
• Publicly Available Date: May 16, 2017
• Peer Reviewed: Peer Reviewed
• Pages: 1173-1183
• ISBN: 0791836010 CD of Proceedings
• Keywords: Compressors; Control systems; Carbon dioxide; Emission control; Approximation theory; Neural networks; Computer architecture;Uncontrolled terms: Performance control - Gas transmission compressor
• Public URL: http://researchrepository.napier.ac.uk/id/eprint/1808
• Contract Date: May 16, 2017