Bearing fault mode diagnosis method and system based on deep learning

Abstract

The invention discloses a bearing fault mode diagnosis method and system based on deep learning. The method comprises: a learning rate is adjusted automatically, noises are introduced, and a linear correction unit is introduced as an activation function, and thus a deep belief network is improved based on the activation function; a data set and long- and short-term memory networks are migrated toobtain a synthetic data set, a trained data set is extended based on the synthetic data set, and the improved deep belief network is trained based on training data set training to obtain a bearing fault diagnosis model; and a vibration signal of the bearing is collected and a bearing failure mode is diagnosed based on the bearing vibration signal and the bearing fault diagnosis model. On the basisof combination of a semi-supervised learning and a migration learning algorithm, the diagnostic accuracy is improved while no insufficient data are provided.

Description

technical field [0001] The invention relates to the technical field of structural fault diagnosis of lifting equipment, in particular to a method and system for diagnosing bearing fault modes based on deep learning. Background technique [0002] With the development of social production, complex production equipment, and the growth of data scale, state-based equipment fault diagnosis is an effective method to improve production efficiency and enhance safety in production. Using machine learning and other intelligent means to fully mine the inherent information of production data is an important research direction for data-based fault diagnosis. Machine learning has become the mainstream of intelligent fault diagnosis in recent years. Equipment fault diagnosis is essentially a classification problem of equipment operation mode, which is mainly divided into two steps: feature extraction and classification. A typical health monitoring and fault diagnosis system usually includ...

AI Technical Summary

Problems solved by technology

However, non-stationary vibration signals in actual scenes often do not meet the stationarity assumption of FFT, thus affecting the diagnosis results

Images