Underflow concentration prediction method based on thickener mechanism model

The invention provides an underflow concentration prediction method based on a thickener mechanism model. The method comprises the steps of collecting thickener field data; converting fluid pressure into flow rate; using the parameter-identified layered thickener mechanism model with parameters to perform underflow concentration prediction. The thickener field data includes top volume flow, feeding flow, fluid pressure and underflow volume density. After the fluid pressure is converted into the flow rate, an abnormal value is processed by using a 3sigma principle. The thickener mechanism modelis established by the steps of collecting historical data of the thickener field data; establishing a thickener mechanism model; converting the fluid pressure into the flow rate and conducting data preprocessing; constructing the layered thickener mechanism model with parameters. The method reduces prediction errors brought by a pure mechanism model and improves the prediction accuracy of the mechanism model. 本发明提供种基于浓密机