Application of artificial neural network to failure diagnosis on process industry equipments

Most of the key equipments in the process industry are almost 24 h running under the complex working environment, and they will inevitably start to malfunction and lead to casualties and production loss. By analyzing the characteristics of key equipments in process industry and problems in diagnosis, the fault diagnosis based on artificial neural network (ANN) in the field of equipments vibration analysis are researched. Firstly, BP neural network is introduced. Secondly, making use of the normalizing method of different batch samples, ANN model of the equipment vibration diagnosis is constructed. Finally, the ANN model is applied to failure diagnosis of a 1550 rolling mill, and the rationality and effectiveness of this methodology is proved.