Adaptive Robust Predictive Control Method for Blast Furnace Hot Metal Quality Based on Lazy Learning

Abstract

The invention provides an adaptive robust prediction control method for blast furnace molten iron quality based on lazy learning, and relates to the technical field of automatic control of blast furnace smelting. Including determining the controlled quantity and the controlled quantity; collecting the historical input and output measurement data of the blast furnace to construct the initial database; constructing the query regression vector to determine the abnormal data; querying the similar learning subset from the database, selecting the optimal learning subset, and analyzing the abnormal data Processing; use the optimal learning subset as the training set to establish a predictive model; calculate the reference trajectory of the molten iron quality index, construct the predictive control performance index, and obtain the optimal control vector; send the optimal control vector to the underlying PLC system and adjust the actuator , collect a new set of blast furnace measurement data, preprocess the data and update the database. The method provided by the invention can effectively suppress the influence of input and output disturbances and overcome the influence of abnormal data, and stabilize the quality of molten iron in the blast furnace near the expected value, which is beneficial to the smooth running of the blast furnace and high-quality and high-yield.

Description

technical field [0001] The invention relates to the technical field of automatic control of blast furnace smelting, in particular to an adaptive robust predictive control method for blast furnace molten iron quality based on lazy learning. Background technique [0002] Blast furnace ironmaking, as the most important ironmaking method, is developing in the direction of large-scale, high efficiency, low energy consumption, and automation. The closed-loop automatic control of blast furnace ironmaking has always been a difficult problem in the field of metallurgical engineering and automation. Since the blast furnace ironmaking system is a complex physical and chemical reaction, multi-phase, multi-field coupling nonlinear, large lag, and dynamic time-varying system, it is difficult to establish an accurate mathematical model for it, and it is difficult to achieve stable control. At present, the indicators that are widely used to indirectly reflect the internal state of the blast...

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention is to provide a method for adaptive robust predictive control of blast furnace molten iron quality based on lazy learning, which effectively solves the problem of online update of the predictive model in nonlinear predictive control, and This method can reuse useful data samples, which greatly improves the utilization rate of offline and online input and output measurement data, can effectively suppress the influence of abnormal data on the controller, enhance the robustness of the controller, and thus improve the stability of the blast furnace ironmaking system sex

Images