A Production Plan and Error Feedback DBN-DNN based prediction method for LDG Generation in steel industry

Linz Donawiz converter Gas (LDG) is a kind of important secondary energy source in iron and steel enterprises. Accurate prediction of LDG generation may provide guidance for scheduling decision. In this paper, a two-stage method for predicting LDG generation is proposed. According to the characteristics of LDG generation data, an improved k-means clustering integrating dynamic time warping is proposed to divide the time series data into typical characteristic curves. Then, an error feedback deep belief network (EF-DBN-DNN) model is established to predict the starting time of LDG generation by considering the relationship between production plan and the actual performance, Actual data of LDG system in an iron and steel enterprise are employed to verify the effectiveness of the proposed method, and the results show that the prediction accuracy of the proposed one is suitable for practical application.