Study on fault diagnosis of blast furnace based on ICA-QNN

Focusing on the fuzziness problem of fault classification borders, and on the diagnostic uncertainty of overlapping data, a fault diagnosis method for furnace state based on independent component analysis (ICA) and quantum neural network (QNN) was presented. Firstly, the fast ICA algorithm was applied successfully to separate the state signals of fault blast furnace and to extract their state features. Secondly, QNN was used together to accomplish the fault diagnosis of furnace state, because it possesses better functions (abilities) of pattern recognition for fault with overlapping classes and uncertainty. The experimental results demonstrate that the ICA-QNN algorithms can recognize the fault pattern of furnace state effectively and accurately. Meanwhile, it also provided a new method with fault diagnosis for blast furnace.