Using the calculation of the variable conditions for steam turbines as the theoretical basis, a multivariate regression model for regulating pressure was established based on the Frugell formula and the Weierstrass approximation theorem. According to the historical operation data of a 660MW generating set, the model was subjected to regression analysis and verification. The results show that the model has a high degree of fit, and the independent variable has a significant influence on the dependent variable; When the steady state conditions are met, the predicted results are consistent with the measured values and the relative error is about 1.2%, which enable soft pressure measurement of the regulation stage. The model was applied to the distributed control system (DCS) of the power plant, and an on-line warning system was established to adjust the pressure anomaly and the partial flow malfunction in the turbine under variable conditions.
