Fault Diagnosis of a Rotor-Bearing System Under Variable Rotating Speeds Using Two-Stage Parameter Transfer and Infrared Thermal Images

Abstract

Current fault diagnosis methods for rotor-bearing system are mostly based on analyzing the vibration signals collected at steady rotating speeds. In those methods, the data collected under one operating condition cannot be accurately used for diagnosis under a different condition. Moreover, in vibration monitoring, installing the necessary sensors will affect the equipment structure and hence the vibration response itself. The present paper proposes a new method based on two-stage parameter transfer and infrared thermal images for fault diagnosis of rotor-bearing system under variable rotating speeds. The method of parameter transfer enables the use of data (or parameters) acquired under one operating condition (called the source domain) to be extended for use in a different operating condition (called the target domain). First, scaled exponential linear unit (SELU) and modified stochastic gradient descent (MSGD) are used to construct an enhanced convolutional neural network (ECNN). Second, a stacked convolutional auto-encoder (CAE) trained based on unlabeled source-domain thermal images is employed to initialize a source-domain ECNN. Third, model parameters from the pre-trained source-domain ECNN are transferred to the target-domain ECNN to adapt to the characteristics of the target domain. The collected thermal images for a rotor-bearing system under variable speeds are used to test the transfer diagnosis performance of the proposed method. The experimental results demonstrate the performance improvement and the advantages of the proposed method.

Optimal Deep Transfer Learning-Based Human-Centric Biomedical Diagnosis for Acute Lymphoblastic Leukemia Detection

“…The recent developments of deep learning (DL) have concentrated on the view of classification models by the use of a convolution neural network (CNN) [ 8 ]. The utilization of automated classification models can improve the performance of the decision-making process in the biomedical sector [ 9 ]. It can be employed for the detection of normal WBCs and the differentiation of particular kinds of cells like erythroid and myeloid precursors.…”

A Zero-Shot Intelligent Fault Diagnosis System Based on EEMD

“…Many studies focus on exploiting a more accurate distribution matching by either marginal distribution adaptation or joint distribution adaptation [23]. Furthermore, deep neural networks such as convolutional neural network have been introduce into transfer framework to improve the distribution matching in feature space [24]. However, the majority methods have the premise that training and testing have unified label set.…”

Intelligent Process Monitoring of Laser-Induced Graphene Production With Deep Transfer Learning

“…However, In engineering practice, collecting and labeling large quantities of image samples with degraded performance of LIG production are usually laborious and even impractical. Unsupervised initialization combined with parameter transfer learning can provide powerful tools to handle this challenge [22]. With the unlabeled monitoring data that is typically easy to collect, a pre-trained unsupervised learning model can be used to initialize the deep learning model by transferring the parameters.…”