Article
Online and Offline Diagnosis of Motor Power Cables Based on
1D CNN and Periodic Burst Signal Injection
Heonkook Kim
1,2
, Hyeyun Jeong
1
, Hojin Lee
1
and Sang Woo Kim
1,
*
Citation: Kim, H.; Jeong, H.; Lee, H.;
Kim, S.W. Online and Offline
Diagnosis of Motor Power Cables
Based on 1D CNN and Periodic Burst
Signal Injection. Sensors 2021, 21, 5936.
https://doi.org/10.3390/s21175936
Academic Editor: Jose Antonino-Daviu
Received: 2 August 2021
Accepted: 30 August 2021
Published: 3 September 2021
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2021 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/).
1
Department of Electrical Engineering, Pohang University of Science and Technology, 77 Cheongam-Ro,
Nam-Gu, Pohang 37673, Korea; kimhk85@postech.ac.kr (H.K.); jhy90@postech.edu (H.J.);
suvvus@postech.edu (H.L.)
2
Hyundai Robotics Co., Ltd., 50, Techno Sunhwan-ro 3-gil, Yuga, Dalseong-gun, Daegu 43022, Korea
* Correspondence: swkim@postech.edu; Tel.: +82-54-279-2237; Fax: +82-54-279-2903
Abstract:
We introduce a new approach for online and offline soft fault diagnosis in motor power
cables, utilizing periodic burst injection and nonintrusive capacitive coupling. We focus on diagnosing
soft faults because local cable modifications or soft faults that occur without any indication while
the cable is still operational can eventually develop into hard faults; furthermore, advance diagnosis
of soft faults is more beneficial than the later diagnosis of hard faults, with respect to preventing
catastrophic production stoppages. Both online and offline diagnoses with on-site diagnostic ability
are needed because the equipment in the automated lines operates for 24 h per day, except during
scheduled maintenance. A 1D CNN model was utilized to learn high-level features. The advantages
of the proposed method are that (1) it is suitable for wiring harness cables in automated factories,
where the installed cables are extremely short; (2) it can be simply and identically applied for both
online and offline diagnoses and to a variety of cable types; and (3) the diagnosis model can be directly
established from the raw signal, without manual feature extraction and prior domain knowledge.
Experiments conducted with various fault scenarios demonstrate that this method can be applied to
practical cable faults.
Keywords: cable fault; 1D CNN; soft faults; industrial robots; online detection
1. Introduction
With the growth of fully automated production lines in modern manufacturing, the
early detection of faults in the motor power cable of automation machinery has become a
demanding requirement to reduce unscheduled maintenance. A single hard fault in the
motor cable could result in unplanned production line downtime because the machines
need to be taken offline to ensure safety during inspection. Depending on the industry, this
catastrophic production line stoppage could result in a huge loss of productivity. For this
reason, the integrity of the motor cables in manufacturing automation, such as automotive
factory floors, must be ensured for safe operation. Therefore, online diagnostics of cables
are crucial, because unscheduled maintenance occurs when the machine is working; thus,
the suspicious cable cannot be isolated from production lines but exhibits intermittent fault
symptoms. Offline diagnostics are still required for regular maintenance when the machine
can be offline for preventive maintenance.
In factory floors, power cables with connectors are installed close to vibrating motors
and welding machines; these have high current consumption and produce heat. The
harsh industrial environment around cables can cause aging degradation of the cable [
1
],
resulting in cable faults, i.e., soft and hard faults. Local modifications to the cable or soft
faults due to the stressful environment can, while the cable is still working and without any
indication, be transformed into hard faults by subsequent partial component damage, e.g.,
to the cable conductors, coatings, and shield [
2
]; this makes it difficult to observe ongoing
aging damage to the cable.
Sensors 2021, 21, 5936. https://doi.org/10.3390/s21175936 https://www.mdpi.com/journal/sensors
