Chaos identification and prediction of pressure time series in water supply network

This paper focus on the chaos identification and prediction of the pressure time series in water supply network. Firstly, due to the water pressure data collected from the SCADA contains a lot of noise and some mutation, the wavelet transform method is introduced, and it effectively distinguished the pressure mutation parts from noise. Secondly, based on chaotic identification theory, the Rosenstein method was applied to calculate the maximum Lyapunov exponent and the chaos was verified in the pressure time series. Thirdly, for the complexity of the pressure sequence, the embedded space technology combined with neural network modeling method is proposed to predict the pressure time series. Finally, a practical example shows that the prediction method has a good stability and accuracy.