IEEE Transactions on Industrial Informatics· 2019Q1
Deep Residual Shrinkage Networks for Fault Diagnosis
- 1,385citations
- Q1SCImago
- 2019year
Short summary
Deep residual shrinkage networks (DRSNs) automatically learn to filter noise and diagnose faults from vibration signals, achieving high accuracy without requiring expert signal processing knowledge.
AI-generated from the title and abstract; the full text is not read.
Key points
- Deep residual shrinkage networks (DRSNs) are developed for fault diagnosis using vibration signals.
- Soft thresholding layers are integrated to eliminate unimportant features and reduce noise.
- Trainable neural networks automatically determine thresholds, removing the need for expert signal processing knowledge.
- The method achieves high fault diagnosing accuracy, validated through experiments with various noise types.
AI-generated from the title and abstract; the full text is not read.
Abstract
This article develops new deep learning methods, namely, deep residual shrinkage networks, to improve the feature learning ability from highly noised vibration signals and achieve a high fault diagnosing accuracy. Soft thresholding is inserted as nonlinear transformation layers into the deep architectures to eliminate unimportant features. Moreover, considering that it is generally challenging to set proper values for the thresholds, the developed deep residual shrinkage networks integrate a few specialized neural networks as trainable modules to automatically determine the thresholds, so that professional expertise on signal processing is not required. The efficacy of the developed methods is validated through experiments with various types of noise.
The authors' abstract, as published at the source. IEEE Transactions on Industrial Informatics, 2019 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Control and Systems Engineering
Control and Systems EngineeringEngineering