Next Article in Journal
Optimal Power Control in Wireless Powered Sensor Networks: A Dynamic Game-Based Approach
Previous Article in Journal
Enhanced Passive RF-DC Converter Circuit Efficiency for Low RF Energy Harvesting
Open AccessArticle

Fault Diagnosis from Raw Sensor Data Using Deep Neural Networks Considering Temporal Coherence

by Ran Zhang 1,2,3, Zhen Peng 4, Lifeng Wu 1,2,3,*, Beibei Yao 1,2,3 and Yong Guan 1,2,3
1
College of Information Engineering, Capital Normal University, Beijing 100048, China
2
Beijing Engineering Research Center of High Reliable Embedded System, Capital Normal University, Beijing 100048, China
3
Beijing Advanced Innovation Center for Imaging Technology, Capital Normal University, Beijing 100048, China
4
Information Management Department, Beijing Institute of Petrochemical Technology, Beijing 102617, China
*
Author to whom correspondence should be addressed.
Academic Editor: Vittorio M. N. Passaro
Sensors 2017, 17(3), 549; https://doi.org/10.3390/s17030549
Received: 14 January 2017 / Revised: 7 March 2017 / Accepted: 7 March 2017 / Published: 9 March 2017
(This article belongs to the Section Physical Sensors)
Intelligent condition monitoring and fault diagnosis by analyzing the sensor data can assure the safety of machinery. Conventional fault diagnosis and classification methods usually implement pretreatments to decrease noise and extract some time domain or frequency domain features from raw time series sensor data. Then, some classifiers are utilized to make diagnosis. However, these conventional fault diagnosis approaches suffer from the expertise of feature selection and they do not consider the temporal coherence of time series data. This paper proposes a fault diagnosis model based on Deep Neural Networks (DNN). The model can directly recognize raw time series sensor data without feature selection and signal processing. It also takes advantage of the temporal coherence of the data. Firstly, raw time series training data collected by sensors are used to train the DNN until the cost function of DNN gets the minimal value; Secondly, test data are used to test the classification accuracy of the DNN on local time series data. Finally, fault diagnosis considering temporal coherence with former time series data is implemented. Experimental results show that the classification accuracy of bearing faults can get 100%. The proposed fault diagnosis approach is effective in recognizing the type of bearing faults. View Full-Text
Keywords: faults diagnosis; deep neural networks; raw sensor data; temporal coherence faults diagnosis; deep neural networks; raw sensor data; temporal coherence
Show Figures

Figure 1

MDPI and ACS Style

Zhang, R.; Peng, Z.; Wu, L.; Yao, B.; Guan, Y. Fault Diagnosis from Raw Sensor Data Using Deep Neural Networks Considering Temporal Coherence. Sensors 2017, 17, 549.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop