Citation: Shan, N.; Xu, X.; Bao, X.;
Qiu, S. Fast Fault Diagnosis in
Industrial Embedded Systems Based
on Compressed Sensing and Deep
Kernel Extreme Learning Machines.
Sensors 2022, 22, 3997. https://
doi.org/10.3390/s22113997
Academic Editor: Jongmyon Kim
Received: 26 April 2022
Accepted: 23 May 2022
Published: 25 May 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Fast Fault Diagnosis in Industrial Embedded Systems Based on
Compressed Sensing and Deep Kernel Extreme
Learning Machines
Nanliang Shan , Xinghua Xu, Xianqiang Bao and Shaohua Qiu *
National Key Laboratory of Science and Technology on Vessel Integrated Power System, Naval University of
Engineering, Wuhan 430033, China; nanliang@stu.xmu.edu.cn (N.S.); xinghuaxv@163.com (X.X.);
baoxianqiang@nudt.edu.cn (X.B.)
* Correspondence: qiush@whu.edu.cn
Abstract:
With the complexity and refinement of industrial systems, fast fault diagnosis is crucial
to ensuring the stable operation of industrial equipment. The main limitation of the current fault
diagnosis methods is the lack of real-time performance in resource-constrained industrial embedded
systems. Rapid online detection can help deal with equipment failures in time to prevent equipment
damage. Inspired by the ideas of compressed sensing (CS) and deep extreme learning machines
(DELM), a data-driven general method is proposed for fast fault diagnosis. The method contains
two modules: data sampling and fast fault diagnosis. The data sampling module non-linearly
projects the intensive raw monitoring data into low-dimensional sampling space, which effectively
reduces the pressure of transmission, storage and calculation. The fast fault diagnosis module
introduces the kernel function into DELM to accommodate sparse signals and then digs into the
inner connection between the compressed sampled signal and the fault types to achieve fast fault
diagnosis. This work takes full advantage of the sparsity of the signal to enable fast fault diagnosis
online. It is a general method in industrial embedded systems under data-driven conditions. The
results on the CWRU dataset and real platforms show that our method not only has a significant
speed advantage but also maintains a high accuracy, which verifies the practical application value in
industrial embedded systems.
Keywords:
fast fault diagnosis; industrial embedded systems; compressed sensing; deep kernel
extreme learning machine
1. Introduction
With the development of modern industrial systems and the pursuit of extreme
efficiency, complex industrial systems are gradually automated, sophisticated and inte-
grated [
1
]. Mechanical failure of key components can easily lead to the collapse of the
entire system. To accurately capture the internal status information of key components,
high-precision industrial sensors are used to obtain time-series monitoring signals for
health status assessment. Due to a large number of checkpoints, high sampling rate and
long detection time, the health monitoring system has acquired massive status data. On the
one hand, it has prompted the fault diagnosis of complex industrial systems to move into
the “data-driven” era [
2
], on the other hand, it has also brought great difficulty to fast fault
diagnosis in resource-constrained industrial embedded systems [3].
The existing research on fast fault diagnosis of the rotating components has achieved
valuable results. Such as a data-driven bearing prognostic scheme that was designed
based on novel health indicators and gated recurrent unit network [
4
]. The work [
5
]
studies the statistical characteristics of the spalling propagation for rotating components,
which is conducive to predicting the occurrence of failures. The work [
6
] enables dynamic
modeling of defect extension and appearance of rotating components, which helps us to
predict service life based on defect models. However, there is still a lot of work to be
Sensors 2022, 22, 3997. https://doi.org/10.3390/s22113997 https://www.mdpi.com/journal/sensors
