Cloud computing based unsupervised fault diagnosis system in the context of Industry 4.0

Ali, Amr Mohamed; Mohamed, El-Adl; Yacout, Soumaya; Shaban, Yasser

doi:10.1590/0104-530X5378-20

Acessibilidade / Reportar erro

Brasil

Español English

sumário « anterior atual seguinte »

Sumário

Thematic Section: Digital transformation, intelligent manufacturing and supply chain management 4.0 • Gest. Prod. 27 (3) • 2020 • https://doi.org/10.1590/0104-530X5378-20 copy

Cloud computing based unsupervised fault diagnosis system in the context of Industry 4.0

Sistema de diagnóstico de falhas não supervisionadas baseado em computação em nuvem no contexto da Indústria 4.0

Authorship SCIMAGO INSTITUTIONS RANKINGS

Abstract:

New online fault monitoring and alarm systems, with the aid of Cyber-Physical Systems (CPS) and Cloud Technology (CT), are examined in this article within the context of Industry 4.0. The data collected from machines is used to implement maintenance strategies based on the diagnosis and prognosis of the machines' performance. As such, the purpose of this paper is to propose a Cloud Computing Platform containing three layers of technologies forming a Cyber-Physical System which receives unlabelled data to generate an interpreted online decision for the local team, as well as collecting historical data to improve the analyzer. The proposed troubleshooter is tested using unlabelled experimental data sets of rolling element bearing. Finally, the current and future Fault Diagnosis Systems and Cloud Technologies applications in the maintenance field are discussed.

Keywords:
Remote Fault Diagnosis System (RFDS); Logical Analysis of Data (LAD); Cyber-Physical System (CPS); Pattern recognition; Industry 4.0; Cloud computing

Feature Name	Formula
Range (R)	$R a n g e = M a x (y_{i}) - M i n (y_{i})$
Mean Value (M)	$M e a n = \frac{\sum_{i = 1}^{N} y_{i}}{N}$
Standard Divination (D)	$S T D E = \sqrt{\frac{\sum {(y_{i} - \bar{y})}^{2}}{(N - 1)}}$
Skewness(S)	$S k = \frac{n}{(n - 1) (n - 2)} {\sum (\frac{y_{i} - \bar{y}}{S T D E D})}^{3}$
Kurtosis (K)	$K u = \frac{n (n + 1)}{(n - 1) (n - 2) (n - 3)} {\sum (\frac{y_{i} - \bar{y}}{S T D E D})}^{4} - \frac{3 {(n - 1)}^{2}}{(n - 2) (n - 3)}$
Root Mean Square (RM)	$R M S = {\sqrt{\frac{1}{N} \sum_{i = 1}^{N} {(y_{i} - {\bar{y}}_{})}^{2}}}^{}$
Crest Factor (C)	$C F = \frac{M a x (y_{i})}{R M S}$

Date	Time	Range	Mean	STDE	SK	KU	RMS	CF
12/2/2004	10.32	0.840	-0.010	0.073	0.084	0.629	0.074	6.120
12/2/2004	11.02	1.184	-0.002	0.079	0.041	1.159	0.079	7.723
12/2/2004	12.02	0.722	-0.002	0.076	0.046	0.326	0.076	4.992
12/2/2004	13.02	0.725	-0.002	0.079	-0.013	0.553	0.079	4.500
12/2/2004	14.02	0.742	-0.002	0.079	0.038	0.385	0.079	4.801
19/2/2004	02.02	1.489	-0.003	0.207	-0.161	0.169	0.207	3.286
19/2/2004	03.02	1.995	-0.002	0.235	0.090	0.447	0.235	4.144
19/2/2004	04.02	3.940	-0.001	0.326	-0.122	1.597	0.326	5.096
19/2/2004	05.02	9.998	0.003	0.672	-0.766	14.114	0.672	7.436
19/2/2004	06.02	7.197	-0.002	0.484	-0.377	4.893	0.484	7.236

No.	Class Name	Quantity
1	Healthy class	751
2	Unhealthy class	206

Universidade Federal de São Carlos Departamento de Engenharia de Produção , Caixa Postal 676 , 13.565-905 São Carlos SP Brazil, Tel.: +55 16 3351 8471 - São Carlos - SP - Brazil
E-mail: gp@dep.ufscar.br

Acompanhe os números deste periódico no seu leitor de RSS

[1] “N” is the length of data, while “y” is the amplitude of vibration signal.

N.	Positive Patterns	Negative Patterns
1	R>1.169, K>0.1072, RM>4.917	D>-0.053, S>2.39, K<0.1669
2	R>1.109, D<-0.009, K>0.1054, RM>4.654	D>-0.115, K<0.0997, RM>4.034
3	R>1.029, M>-0.0019, D<-0.056, K>0.098, RM>5.21	R<1.024, M>-0.0018, D>-0.065, S<1.134, K<0.16
4	R>0.9175, D<-0.009, K>0.0988, RM>4.654	R<1.07, D>-0.0426, S<2.39, K<0.1669, RM>4.71
5	M>-0.0019, D<-0.0285, K>0.098895	R<1.029, D>-0.0536, S<2.39, K0.1669
6	R>0.991, M<-0.0019, D<-0.059, K>0.0988	R<1.078, M<-0.0019, D>-0.068, SK<2.39, K<0.166