Skip to content

Latest commit

 

History

History
109 lines (83 loc) · 2.55 KB

papernotes1.md

File metadata and controls

109 lines (83 loc) · 2.55 KB

TOC


笔记题目

1.标题

Multiscale Convolutional Neural Networks for Fault Diagnosis of Wind Turbine Gearbox

发表日期

2019

作者

Jiang, Guoqian He, Haibo Yan, Jun Xie, Ping

关键词

fault diagnosis feature extraction gears learning (artificial intelligence) mechanical engineering computing neural nets pattern classification vibrational signal processing wind turbines signal processing CNN architecture intelligent fault diagnosis method health conditions raw vibration signals wind turbine gearbox multiscale convolutional neural networks WT gearbox test rig MSCNN approach hierarchical learning structure multiscale learning classification multiscale feature extraction multiscale convolutional neural network architecture end-to-end learning-based fault diagnosis system Feature extraction Fault diagnosis Vibrations Convolutional neural networks Wind turbines Machine learning Signal processing Convolutional neural network (CNN) classification deep learning intelligent fault diagnosis multiscale feature extraction wind turbine (WT) gearbox

发表期刊

IEEE Trans. Ind. Electron.


2.方法概括

目标

In this paper, our goal is to develop an end-to-end fault diagnosis system based on CNNs, which is motivated by its excellent feature learning ability. The desirable system can automatically learn and discover discriminative features from raw temporal vibration signals and then classify different health conditions of the WT gearbox.

背景理论与方法

convolutional neural networks

==方法要点==

==核心创新点==

The key idea of the proposed MSCNN is to incorporate multiscale feature learning ability into the traditional CNN architecture.

总结


3.关键文献列表

  • Li, C. and P. Shang, Multiscale Tsallis permutation entropy analysis for complex physiological time series. Physica A: Statistical Mechanics and its Applications, 2019. 523: p. 10-20.link
  • Cui, Z., W. Chen and Y. Chen, Multi-Scale Convolutional Neural Networks for Time Series Classification. 2016.link

4.好词好句

单词

句子


5.笔记