Format

Send to

Choose Destination
Sensors (Basel). 2019 Apr 29;19(9). pii: E2018. doi: 10.3390/s19092018.

Signal Status Recognition Based on 1DCNN and Its Feature Extraction Mechanism Analysis.

Author information

1
Graduate School, Army Engineering University of PLA, Nanjing 210000, China. hsz_221618@163.com.
2
School of Field Engineering, Army Engineering University of PLA, Nanjing 210000, China. lgdx_tj@163.com.
3
School of Field Engineering, Army Engineering University of PLA, Nanjing 210000, China. dinajy2001@126.com.
4
Graduate School, Army Engineering University of PLA, Nanjing 210000, China. wyyoung2013@126.com.

Abstract

In this paper, we construct a one-dimensional convolutional neural network (1DCNN), which directly takes as the input the vibration signal in the mechanical operation process. It can realize intelligent mechanical fault diagnosis and ensure the authenticity of signal samples. Moreover, due to the excellent interpretability of the 1DCNN, we can explain the feature extraction mechanism of convolution and the synergistic work ability of the convolution kernel by analyzing convolution kernels and their output results in the time-domain, frequency-domain. What's more, we propose a novel network parameter-optimization method by matching the features of the convolution kernel with those of the original signal. A large number of experiments proved that, this optimization method improve the diagnostic accuracy and the operational efficiency greatly.

KEYWORDS:

convolution kernel; convolutional neural network; feature extraction mechanism; intelligent fault diagnosis

Supplemental Content

Full text links

Icon for Multidisciplinary Digital Publishing Institute (MDPI) Icon for PubMed Central
Loading ...
Support Center