Title :
Optimisation of sensor locations for measurement of flue gas flow in industrial ducts and stacks using neural networks
Author :
Kang, H. ; Yang, Q. ; Butler, C. ; Xie, T. ; Benati, I.F.
Author_Institution :
Dept. of Manuf. & Eng. Syst., Brunel Univ., Uxbridge, UK
Abstract :
This paper presents a novel application of neural network modelling in the optimisation of sensor locations for measurement of flue gas flow in industrial ducts and stacks. The neural network model has been validated with experiment based upon a case-study power plant. The results have shown that the optimised sensor location can be determined using this model. The measurement accuracy of the flue gas flow can be significantly improved in the optimised sensor location, resulting in a possible reduction in the manual operation
Keywords :
ISO standards; feedforward neural nets; flow measurement; flowmeters; learning (artificial intelligence); modelling; optimisation; power plants; ISO10780 standard; Levenberg-Marquardt training; Pitot tube; case-study power plant; flue gas flow measurement; industrial ducts; industrial stacks; inverse model; measurement accuracy; neural network modelling; optimisation criterion; optimised sampling; reduced manual operation; sensor location optimisation; three-layered feedforward network; velocity profiles; Ducts; Elbow; Flue gases; Fluid flow measurement; Gas detectors; Gas industry; Neural networks; Predictive models; Sampling methods; Testing;
Conference_Titel :
Instrumentation and Measurement Technology Conference, 1999. IMTC/99. Proceedings of the 16th IEEE
Conference_Location :
Venice
Print_ISBN :
0-7803-5276-9
DOI :
10.1109/IMTC.1999.776724
