Application of Diagonal Recurrent Neural Network for Measuring Fouling in Condenser

A novel approach for online measurement of fouling in condenser is proposed in this paper. In the approach, terminal temperature difference is chosen to reflect fouling state, diagonal recurrent neural network is employed to approximate off-design condition terminal temperature difference, which separates the influence imposed by fouling on terminal temperature difference from other factors. In order to make the measurement model more compact and accurate, an adaptive dynamic back propagation algorithm is proposed to obtain the optimum number of hidden layer neurons. Based on the approach, an experimental system is developed and experiment on an actual condenser is carried out. The results show the approach measures the fouling correctly, and is more effective than thermal resistance method or heat transfer coefficient method.