Details of Grant 

EPSRC Reference:	GR/K51853/01
Title:	APPROXIMATION AND CONTROL OF INDUSTRIAL NONLINEAR DYNAMIC PROCESSES
Principal Investigator:	Morris, Professor AJ
Other Investigators:	Martin, Professor EB Green, Professor G Montague, Professor G
Researcher Co-Investigators:
Project Partners:	BNFL Pre Nexus Migration
Department:	Chemical Engineering & Advanced Material
Organisation:	Newcastle University
Scheme:	Standard Research (Pre-FEC)
Starts:	01 February 1996	Ends:	31 October 1999	Value (£):	162,390
EPSRC Research Topic Classifications:
EPSRC Industrial Sector Classifications:	Chemicals Creative Industries
Related Grants:
Panel History:
Summary on Grant Application Form
This project will build upon and exploit recent developments in the understanding of the mathematics of non-linear time-varying dynamics and multivariate statistics for use in the design of artificial neural networks. The application of dynamic networks to real industrial processes has immediate and strategic implications for improving the design and control of complex processes. The research is generic, bur initially it will be linked to specific, well-defined, industrial projects The programme will deliver practical and theoretically underpinned, neural network methods for the approximation of time-varying input-output process behaviour. Situations will be addressed where the process is not necessarily at equilibrium or when it is exhibiting chaotic behaviour. The work will focus on the control of these processes using both approximate network inverses and model based approaches. Pilot work on short term chaotic time series will be extended to aid the design, scale-up and control of deterministic chaotic processes. Initially these techniques will be applied to the complex fluidised bed reactor using validated simulation models, pilot plant experiments and industrial data. The use of industrial data will necessitate the investigation of the effects of process and measurement noise, outlying and missing data, on the identification and control algorithms. Other demonstrator processes will be selected from those represented by the 24 members of the DTI Neural Network Process Monitoring and Control Club. The results will also be widely distributed to the process industries through EPICC, the UK's European Process Industry Competitiveness Centre.
Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk Summary Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL:
Further Information:
Organisation Website:	http://www.ncl.ac.uk