Sensors· 2017Q1
A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals
- 1,668citations
- Q1SCImago
- 2017year
Short summary
A novel deep learning model, WDCNN, achieves 100% accuracy in diagnosing faults using raw vibration signals and outperforms state-of-the-art models under varying loads and noisy conditions.
AI-generated from the title and abstract; the full text is not read.
Key points
- Introduces WDCNN, a deep learning model for fault diagnosis using raw vibration signals.
- Wide first-layer kernels suppress high-frequency noise and extract features.
- AdaBN is used to improve the model's domain adaptation capabilities.
- Achieves 100% classification accuracy on normal signals.
- Outperforms state-of-the-art models under varying loads and noisy conditions.
AI-generated from the title and abstract; the full text is not read.
Abstract
Intelligent fault diagnosis techniques have replaced time-consuming and unreliable human analysis, increasing the efficiency of fault diagnosis. Deep learning models can improve the accuracy of intelligent fault diagnosis with the help of their multilayer nonlinear mapping ability. This paper proposes a novel method named Deep Convolutional Neural Networks with Wide First-layer Kernels (WDCNN). The proposed method uses raw vibration signals as input (data augmentation is used to generate more inputs), and uses the wide kernels in the first convolutional layer for extracting features and suppressing high frequency noise. Small convolutional kernels in the preceding layers are used for multilayer nonlinear mapping. AdaBN is implemented to improve the domain adaptation ability of the model. The proposed model addresses the problem that currently, the accuracy of CNN applied to fault diagnosis is not very high. WDCNN can not only achieve 100% classification accuracy on normal signals, but also outperform the state-of-the-art DNN model which is based on frequency features under different working load and noisy environment conditions.
The authors' abstract, as published at the source. Sensors, 2017 · 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