Condition prediction of flue gas turbine based on Echo State Network

Echo State Network is one pioneering recurrent neural network with the core structure of a randomly generated and unchangeable reservoir. This paper provides a Condition prediction model of flue gas turbine by applying Echo State Network and makes prediction of the overall vibration value. Compared to Elman neural network prediction model, examples show that Echo State Network has wonderful dynamic characteristics with smaller error and less prediction time. The model has a good performance in non-linear time series prediction, indicating that the model is feasible in the condition prediction of flue gas turbine.