Multi-layer Long Short-term Memory based Condenser Vacuum Degree Prediction Model on Power Plant

Abstract

A multi-layer LSTM (Long short-term memory) model is proposed for condenser vacuum degree prediction of power plants. Firstly, Min-max normalization is used to pre-process the input data. Then, the model proposes the two-layer LSTM architecture to identify the time series pattern effectively. ADAM（Adaptive moment）optimizer is selected to find the optimum parameters for the model during training. Under the proposed forecasting framework, experiments illustrates that the two-layer LSTM model can give a more accurate forecast to the condenser vacuum degree compared with other simple RNN (Recurrent Neural Network) and one-layer LSTM model.

Steam turbine power prediction based on encode-decoder framework guided by the condenser vacuum degree

“…), which is a key factor for predicting the output power of the steam turbine. However, as an intermediate factor between the condenser and the steam turbine, the condenser vacuum degree varies dynamically based on the time and the condition status of the equipment [ 2 – 4 ], which brings difficulty in accurate modelling the vacuum degree temporally. In addition, since the different types of input variables for the condenser and the steam turbine, it is challenging to jointly model these two pieces of equipment by introducing the vacuum degree information into the output power prediction.…”