Optimization of sensor locations for measurement of flue gas flow in industrial ducts and stacks using neural networks

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.