Long term prediction for generation amount of Converter gas based on steelmaking production status estimation

Long term prediction for generation amount of Converter gas is very important for the optimal scheduling of energy system in iron and steel making enterprises. In this paper, a long term prediction approach based on steelmaking production status estimation is proposed to address this issue. Steelmaking production status estimation has two stages, namely feature extraction and feature fusion. At the first stage, the generation time series of Converter gas is divided into some data segments with the same length, and then a method based on template matching is used to extract the time and frequency domain characteristics of steelmaking production status. At the second stage, an improved version of fuzzy C-mean clustering method is developed for feature fusion, which integrates the characteristics from different data segments to obtain a universal feature of steelmaking production status. Finally, the universal feature is used to reconstruct the generation time series of Converter gas. To verify the effectiveness of the proposed method for long term generation amount prediction of Converter gas, a set of experiments is conducted based on the real world data from an iron and steel enterprise. The experimental results demonstrate that the proposed method exhibits high accuracy and can provide an effective guidance for balancing and scheduling the byproduct Converter gas.