A Fault Diagnosis Method Based on Incremental Compensation and Dynamic Adaptive Enhancement

Abstract

The invention discloses a fault diagnosis method based on incremental compensation and dynamic self-adaptive enhancement, which comprises the following steps: 1. collecting vibration signals in various states from a vibration sensor at the motor drive end; 2. predicting fault data of bearing equipment Processing; 3. Add random noise to the training samples as the input of the denoising autoencoder for unsupervised greedy layer-by-layer pre-training; 4. When there is new equipment status data, use the existing trained DAE model to add Extract the failure mode, and use the mode similarity algorithm to compare similar modes, then use the incremental active fusion algorithm to incrementally merge the newly added failure mode, and use the weight dynamic compensation algorithm to calculate the dynamic weight; And the unlabeled fault data weighted by dynamic deep learning training is used as the input vector to train the SVM classifier; 6. Use the BP algorithm to globally fine-tune the relevant parameters in the entire model; 7. Classify and diagnose fault types.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis of bearing equipment, in particular to a fault diagnosis method based on incremental compensation and dynamic self-adaptive enhancement. Background technique [0002] The core of "Industry 4.0" is intelligent manufacturing, which is the deep integration of information technology and intelligent technology, and is an important symbol to measure the degree of national industrial modernization. At present, Western countries still restrict exports to my country in terms of high-end equipment technology. Breakthroughs in key technologies such as intelligent maintenance of equipment are an important way to improve the level of international division of labor and the right to speak. Research hotspots. [0003] With the development of industrial Internet of Things and information technology, it is becoming easier and easier to obtain operating status data in the production process, making the data...

AI Technical Summary

Problems solved by technology

However, due to the massive and multi-source characteristics of the incremental data stream of advanced equipment in recent years, especially due to the high reliability of intelligent equipment, although the amount of newly generated state data is huge, the number of fault samples in the new data is insufficient. and feature dispersion

The above-mentioned traditional methods have certain limitations in processing this type of data. Therefore, how to deal with massive and multi-source incremental state information under unbalanced conditions and form dynamic and accurate feature knowledge is a difficult problem in equipment maintenance.

Images