This paper presents a novel application of neural network modeling in the optimization of sensor locations for the measurement of flue gas flow in industrial ducts and stacks. The proposed neural network model has been validated with an experiment based upon a case-study power plant. The results have shown that the optimized sensor location can be easily determined with this model. The industry can directly benefit from the improvement of measurement accuracy of the flue gas flow in the optimized sensor location and the reduction of manual measurement operation with Pitot tube
Abstract-This paper discusses the modeling of the flue gas flow in industrial ducts and stacks using artificial neural networks (ANN's). Based upon the individual velocity and other operating conditions, an ANN model has been developed for the measurement of the volume flow rate. The model has been validated by the experiment using a case-study power plant. The results have shown that the model can largely compensate for the nonrepresentativeness of a sampling location and, as a result, the measurement accuracy of the flue gas flow can be significantly improved.Index Terms-Error analysis, gas flow measurement, measurement system data handling, modeling, neural network application.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.