Mechanical fault diagnosis method based on multi-sensor information fusion migration network

Abstract

The invention discloses a mechanical fault diagnosis method based on a multi-sensor information fusion migration network, which includes firstly collecting multi-sensor data, obtaining multiple source domain data sets and target domain data sets, and then constructing a network diagnosis suitable for multi-sensor information fusion migration Model, which has a feature sharing layer and M convolutional neural networks; then constructs the loss function of each convolutional neural network; then performs multi-sensor information fusion migration network diagnostic model training, based on M source domain data sets and target The target domain training data of the domain dataset, in each iteration, train the first to the Mth network sequentially according to the order of the source domain sensors until the number of iterations or classification accuracy is reached; finally, the target domain test data of the target domain dataset Input into the model, after the model and loss function processing and the weighted average of M outputs, the final classification and diagnosis results are obtained. The invention can effectively improve the precision of mechanical fault diagnosis.

Description

technical field [0001] The invention relates to the technical field of mechanical fault diagnosis, in particular to a mechanical fault diagnosis method based on multi-sensor information fusion migration network. Background technique [0002] The structure of the mechanical system is complex and there are many parts. In order to monitor the status of the mechanical system, multiple sensors are usually installed at different positions of the key components of the system to obtain information of different sensitivity and complementarity. However, existing methods usually only use the information of a single sensor for fault diagnosis, and the reliability of diagnosis is affected by various factors such as sensor installation location, signal transmission path, and variable working conditions. How to effectively use and fuse multi-sensor information to improve the classification accuracy and diagnostic reliability of mechanical fault diagnosis models is a difficult problem in th...

AI Technical Summary

Problems solved by technology

However, the existing fusion methods based on feature layer and decision layer are usually based on shallow network structure, which cannot automatically learn deep feature representation. Facing complex mechanical system diagnosis problems, the effect of fusion is often not ideal, and there are certain limitations.

Images