Overview of Integrated Equipment Fault Diagnosis Methods Based on Deep Learning

With the continuous development of modern industrialization, more complex and large scale integrated equipment, the traditional fault diagnosis methods can meet the accuracy under the background of big data integration equipment fault diagnosis, deep learning with a strong ability to learn and learn to data analysis ability, very suitable for integrated equipment coupling fault diagnosis and industrialization under the background of dynamic diagnosis. This paper first introduces the deep learning in various fields of application in the integration equipment, and then introduces the application in fault diagnosis of deep learning four methods (deep belief networks, stacked auto-encoders, convolutional neural networks, circulating neural network), analysis the advantages and disadvantages of four kinds of methods, application fields and summarize the problems to be resolved; Then the challenges and solutions of deep learning in integrated equipment fault diagnosis are summarized. Finally, the future development direction of deep learning in integrated equipment field is prospected.