Citation: Lima, R.P.G.; Mauricio
Villanueva, J.M.; Gomes, H.P.; Flores,
T.K.S. Development of a Soft Sensor
for Flow Estimation in Water Supply
Systems Using Artificial Neural
Networks. Sensors 2022, 22, 3084.
https://doi.org/10.3390/s22083084
Academic Editors: M. Jamal Deen,
Subhas Mukhopadhyay,
Yangquan Chen, Simone Morais,
Nunzio Cennamo and Junseop Lee
Received: 2 March 2022
Accepted: 6 April 2022
Published: 18 April 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
Development of a Soft Sensor for Flow Estimation in Water
Supply Systems Using Artificial Neural Networks
Robson Pacífico Guimarães Lima
1,2,
* , Juan Moises Mauricio Villanueva
3
, Heber Pimentel Gomes
4
and Thommas Kevin Sales Flores
3
1
Technology Center (CT), Postgraduate Program in Mechanical Engineering (PPGEM), Campus I,
Federal University of Paraiba (UFPB), Joao Pessoa 58058-600, PB, Brazil
2
Automation Coordination (CAUT), Federal Institute of Pernambuco (IFPE), Ipojuca 55590-000, PE, Brazil
3
Renewable and Alternatives Energies Center (CEAR), Electrical Engineering Department (DEE), Campus I,
Federal University of Paraiba (UFPB), Joao Pessoa 58058-600, PB, Brazil; jmauricio@cear.ufpb.br (J.M.M.V.);
thommas.flores@cear.ufpb.br (T.K.S.F.)
4
Technology Center (CT), Department of Civil and Environmental Engineering (DECV), Campus I,
Federal University of Paraiba (UFPB), Joao Pessoa 58058-600, PB, Brazil; heberp@uol.com.br
* Correspondence: robsonpacifico@ipojuca.ifpe.edu.br
Abstract:
A water supply system is considered an essential service to the population as it is about
providing an essential good for life. This system typically consists of several sensors, transducers,
pumps, etc., and some of these elements have high costs and/or complex installation. The indirect
measurement of a quantity can be used to obtain a desired variable, dispensing with the use of a
specific sensor in the plant. Among the contributions of this technique is the design of the pressure
controller using the adaptive control, as well as the use of an artificial neural network for the
construction of nonlinear models using inherent system parameters such as pressure, engine rotation
frequency and control valve angle, with the purpose of estimating the flow. Among the various
contributions of the research, we can highlight the suppression in the acquisition of physical flow
meters, the elimination of physical installation and others. The validation was carried out through
tests in an experimental bench located in the Laboratory of Energy and Hydraulic Efficiency in
Sanitation of the Federal University of Paraiba. The results of the soft sensor were compared with
those of an electromagnetic flux sensor, obtaining a maximum error of 10%.
Keywords: indirect measurement; soft sensor; water supply systems; artificial neural networks
1. Introduction
Water is a natural resource of fundamental importance for the survival of humans
and other living beings, and a good as relevant as this must be preserved in relation to
its conscious use. The problem of water waste, not only in domestic waste (excessive use
of water to wash sidewalks, time-consuming cleanliness with open registers, etc.) but
mainly in waste from the point of view of supply systems (leakage in pipes, for example)
makes the obstacle much higher. The feasibility of means that mitigate waste through an
efficient distribution to a given location is extremely important. Thus, in the context of
water distribution to the population, there is a need for an efficient resource distribution
system capable of meeting urban and rural demands. In this way, a water supply system
is defined as the set of works, equipment and services intended to supply drinking water
to a community for the purposes of domestic consumption, public services, industrial
consumption and other utilities [
1
]. This water supplied by the system must be in sufficient
quantity and of the best quality from a physical, chemical and bacteriological point of view.
A water supply system (WSS) represents the entire process of supplying treated water,
ranging from obtaining it to its use by the population. For this, a WSS uses a set of
equipment, works and services, whose objective is to supply the water demand of a given
Sensors 2022, 22, 3084. https://doi.org/10.3390/s22083084 https://www.mdpi.com/journal/sensors
