A High-Stability Diagnosis Model Based on a Multiscale Feature Fusion Convolutional Neural Network

Recently, the diagnosis of rotating machines based on deep learning models has achieved great success. Many of these intelligent diagnosis models are assume that training and test data are subject to independent identical distributions (IIDs). Unfortunately, such an assumption is generally invalid i...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on instrumentation and measurement Vol. 70; p. 1
Main Authors Wang, Pengxin, Song, Liuyang, Guo, Xudong, Wang, Huaqing, Cui, Lingli
Format Journal Article
LanguageEnglish
Published New York IEEE 01.01.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Artificial neural networks
Convolution
Convolutional neural network
Convolutional neural networks
Deep learning
Diagnosis
Disturbances
Feature extraction
Feature fusion
Feature learning
Intelligent diagnosis
Kernel
Load modeling
Neural networks
Neurons
Noise
Rotating machinery
Rotating machines
Stability
Workload
Workloads
Online AccessGet full text

Cover

More Information
Summary:Recently, the diagnosis of rotating machines based on deep learning models has achieved great success. Many of these intelligent diagnosis models are assume that training and test data are subject to independent identical distributions (IIDs). Unfortunately, such an assumption is generally invalid in practical applications due to noise disturbances and changes in workload. To address the above problem, this paper presents a high-stability diagnosis model named the multiscale feature fusion convolutional neural network (MFF-CNN). MFF-CNN does not rely on tedious data preprocessing and target domain information. It is composed of multiscale dilated convolution, self-adaptive weighting, and the new form of Maxout (NFM) activation. It extracts, modulates, and fuses the input samples' multiscale features so that the model focuses more on the health state difference rather than the noise disturbance and workload difference. Two diagnostic cases, including a noisy cases and a variable load cases, are used to verify the effectiveness of the present model. The results show that the present model has a strong health state identification capability and anti-interference capability for variable loads and noise disturbances.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9456
1557-9662
DOI:10.1109/TIM.2021.3102745