Sintered ore FeO prediction method and system based on data and knowledge fusion

The invention discloses a data and knowledge fused sintered ore FeO prediction method and system, and the method comprises the steps: obtaining sample parameters related to the FeO content of sintered ore and a data density center of the sample parameters; on the basis of the highest temperature of the sinter bed, inferring the sintering FeO content grade on line by using the mechanism knowledge base, constructing a sintering process FeO content on-line estimation model according to the data density center of the sample parameters and the sintering FeO content grade, and predicting the FeO content of the sinter, so the technical problem that the existing prediction precision of the FeO content of the sinter is low is solved; and the problem of non-uniform data caused by different sampling frequencies is solved by utilizing kernel function-based high-dimensional mapping data density center extraction, so the prediction precision of the FeO content of the sintered ore is improved. In addition, based on the LSTM