Citation: Moheimani, R.; Gonzalez,
M.; Dalir, H. An Integrated
Nanocomposite Proximity Sensor:
Machine Learning-Based
Optimization, Simulation, and
Experiment. Nanomaterials 2022, 12,
1269. https://doi.org/10.3390/
nano12081269
Academic Editors: Deepak Kukkar
and Ki-Hyun Kim
Received: 10 March 2022
Accepted: 5 April 2022
Published: 8 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
An Integrated Nanocomposite Proximity Sensor: Machine
Learning-Based Optimization, Simulation, and Experiment
Reza Moheimani
1
, Marcial Gonzalez
1
and Hamid Dalir
2,
*
1
Ray W. Herrick Laboratories, School of Mechanical Engineering, Purdue University,
West Lafayette, IN 47907, USA; rezam@purdue.edu (R.M.); marcial-gonzalez@purdue.edu (M.G.)
2
Department of Mechanical and Energy Engineering, Indiana University-Purdue University,
Indianapolis, IN 46202, USA
* Correspondence: hdalir@purdue.edu
Abstract: This paper utilizes multi-objective optimization for efficient fabrication of a novel Carbon
Nanotube (CNT) based nanocomposite proximity sensor. A previously developed model is utilized
to generate a large data set required for optimization which included dimensions of the film sensor,
applied excitation frequency, medium permittivity, and resistivity of sensor dielectric, to maximize
sensor sensitivity and minimize the cost of the material used. To decrease the runtime of the original
model, an artificial neural network (ANN) is implemented by generating a one-thousand samples
data set to create and train a black-box model. This model is used as the fitness function of a genetic
algorithm (GA) model for dual-objective optimization. We also represented the 2D Pareto Frontier
of optimum solutions and scatters of distribution. A parametric study is also performed to discern
the effects of the various device parameters. The results provide a wide range of geometrical data
leading to the maximum sensitivity at the minimum cost of conductive nanoparticles. The innovative
contribution of this research is the combination of GA and ANN, which results in a fast and accurate
optimization scheme.
Keywords:
proximity sensor; artificial neural network; multi-objective optimization; genetic algorithm;
capacitance; carbon nano tubes
1. Introduction
Thanks to the fascinating and broad applications, wearable electronics grow swiftly
and require mainly a very efficient sensing system [
1
–
6
]. Fabrication and design of these
systems require a balance between system functionality and cost/energy reduction
[7–9]
.
The recent employment optimization methods in the energy consumption of sensory
designs are highlighted, which also has motivated researchers to identify more efficient
sensors. However, not many optimization strategies are available in the sensor literature
nowadays [
10
–
15
]. Among commercial sensors used in wearable smart devices, flexible
nano-based sensors whose sensing materials are nanoparticles such as carbon nanotubes
(CNTs), graphene, and metal nanowires become appealing and valuable because they are
skin-friendly and durable to withstand mechanical damage [16–21].
Proximity sensors are especially demanding candidates for nondestructive measure-
ment of collision prevention in biomedical industries [
22
–
29
]. Consequently, it is essential to
detect the presence of an object without making contact. Although some optical, ultrasonic,
and inductive-based models for proximity sensing have been developed, capacitive-based
sensors have a simpler design, easier readout, and a wider range of functionality for metallic
and non-metallic targets [
30
–
32
]. The design of a capacitive proximity sensor should be in-
formed by fundamental electrostatic theories and the tradeoff of sensitivity, resolution, and
energy consumption. Although theoretical analyses are somewhat simplified, with some
idealized assumptions and strict boundary conditions, and all sensor responses cannot be
completely stated, such models still contribute to optimizing sensor parameters to obtain
Nanomaterials 2022, 12, 1269. https://doi.org/10.3390/nano12081269 https://www.mdpi.com/journal/nanomaterials
