Article
Maintenance Prediction through Sensing Using Hidden
Markov Models—A Case Study
Alexandre Martins
1,2,
* , Inácio Fonseca
3
, José Torres Farinha
3,4
, João Reis
1,5
and António J. Marques Cardoso
2
Citation: Martins, A.; Fonseca, I.;
Farinha, J.T.; Reis, J.; Cardoso, A.J.M.
Maintenance Prediction through
Sensing Using Hidden Markov
Models—A Case Study. Appl. Sci.
2021, 11, 7685. https://doi.org/
10.3390/app11167685
Academic Editors: João Carlos de
Oliveira Matias and Paolo Renna
Received: 15 July 2021
Accepted: 17 August 2021
Published: 21 August 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
EIGeS—Research Centre in Industrial Engineering, Management and Sustainability, Lusófona University,
Campo Grande, 376, 1749-024 Lisboa, Portugal; p40500@ulusofona.pt
2
CISE—Electromechatronic Systems Research Centre, University of Beira Interior, Calçada Fonte do Lameiro,
P-62001-001 Covilhã, Portugal; ajmc@ubi.pt
3
ISEC/IPC—Polytechnic Institute of Coimbra, 3045-093 Coimbra, Portugal; inacio@isec.pt (I.F.);
tfarinha@isec.pt (J.T.F.)
4
CEMMPRE—Centre for Mechanical Engineering, Materials and Processes, University of Coimbra,
3030-788 Coimbra, Portugal
5
GOVCOPP—Department of Economics, Management, Industrial Engineering and Tourism, Campus
Universitário de Santiago, Aveiro University, 3810-193 Aveiro, Portugal
* Correspondence: alex_bmts@hotmail.com
Abstract:
The availability maximization is a goal for any organization because the equipment
downtime implies high non-production costs and, additionally, the abnormal stopping and restarting
usually imply loss of product’s quality. In this way, a method for predicting the equipment’s health
state is vital to maintain the production flow as well as to plan maintenance intervention strategies.
This paper presents a maintenance prediction approach based on sensing data managed by Hidden
Markov Models (HMM). To do so, a diagnosis of drying presses in a pulp industry is used as case
study, which is done based on data collected every minute for three years and ten months. This paper
presents an approach to manage a multivariate analysis, in this case merging the values of sensors,
and optimizing the observable states to insert into a HMM model, which permits to identify three
hidden states that characterize the equipment’s health state: “Proper Function”, “Alert state”, and
“Equipment Failure”. The research described in this paper demonstrates how an equipment health
diagnosis can be made using the HMM, through the collection of observations from various sensors,
without information of machine failures occurrences. The approach developed demonstrated to be
robust, even the complexity of the system, having the potential to be generalized to any other type
of equipment.
Keywords:
Hidden Markov Models; industrial sensors; condition-based maintenance; big data;
cluster analysis; principal component analysis
1. Introduction
Sensors are currently one of the largest sources of data, being responsible for making
a direct connection between a physical phenomenon and a data acquisition system, con-
verting signals from several types of variables (mechanical, chemical, etc.) into electrical
signals. Thus, sensors are responsible for translating the equipment condition, giving
outputs that can be seen as observable states. In other words, they provide data that,
after being studied, can provide very useful information for companies. One of the ways
in which companies maintain competitiveness and customer satisfaction is through the
application of sensing, as this will allow them to carry out Condition-Based Maintenance
(CBM). This is aimed at the increasing of profits, namely, due to the non-existence of
unexpected stoppages in production. For instance, according to Pais et al. [
1
], Data Mining
and Artificial Intelligence (AI) can contribute to safeguard the company’s profits and the
safety of people and property.
Appl. Sci. 2021, 11, 7685. https://doi.org/10.3390/app11167685 https://www.mdpi.com/journal/applsci
