Design and Fabrication of a Magnetic Actuator for Torque and Force Control Estimated by the ANN/SA Algorithm
Magnetic manipulation has the potential to recast the medical field both from an operational and drug delivery point of view as it can provide wireless controlled navigation over surgical devices and drug containers inside a human body. The presented system in this research implements a unique eight...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-02-01
|
Series: | Micromachines |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-666X/13/2/327 |
_version_ | 1797477930140434432 |
---|---|
author | Pooriya Kazemzadeh Heris Mir Behrad Khamesee |
author_facet | Pooriya Kazemzadeh Heris Mir Behrad Khamesee |
author_sort | Pooriya Kazemzadeh Heris |
collection | DOAJ |
description | Magnetic manipulation has the potential to recast the medical field both from an operational and drug delivery point of view as it can provide wireless controlled navigation over surgical devices and drug containers inside a human body. The presented system in this research implements a unique eight-coil configuration, where each coil is designed based on the characterization of the working space, generated force on a milliscale robot, and Fabry factor. A cylindrical iron-core coil with inner and outer diameters and length of 20.5, 66, and 124 mm is the optimized coil. Traditionally, FEM results are adopted from simulation and implemented into the motion logic; however, simulated values are associated with errors; 17% in this study. Instead of regularizing FEM results, for the first time, artificial intelligence has been used to approximate the actual values for manipulation purposes. Regression models for Artificial Neural Network (ANN) and a hybrid method called Artificial Neural Network with Simulated Annealing (ANN/SA) have been created. ANN/SA has shown outstanding performance with an average <i>R</i><sup>2</sup>, and a root mean square error of 0.9871 and 0.0153, respectively. Implementation of the regression model into the manipulation logic has provided a motion with 13 μm of accuracy. |
first_indexed | 2024-03-09T21:24:45Z |
format | Article |
id | doaj.art-7fe4258c22574ba5ae78b040ea15a32f |
institution | Directory Open Access Journal |
issn | 2072-666X |
language | English |
last_indexed | 2024-03-09T21:24:45Z |
publishDate | 2022-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Micromachines |
spelling | doaj.art-7fe4258c22574ba5ae78b040ea15a32f2023-11-23T21:12:09ZengMDPI AGMicromachines2072-666X2022-02-0113232710.3390/mi13020327Design and Fabrication of a Magnetic Actuator for Torque and Force Control Estimated by the ANN/SA AlgorithmPooriya Kazemzadeh Heris0Mir Behrad Khamesee1Department of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo, ON N2L 3G1, CanadaDepartment of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo, ON N2L 3G1, CanadaMagnetic manipulation has the potential to recast the medical field both from an operational and drug delivery point of view as it can provide wireless controlled navigation over surgical devices and drug containers inside a human body. The presented system in this research implements a unique eight-coil configuration, where each coil is designed based on the characterization of the working space, generated force on a milliscale robot, and Fabry factor. A cylindrical iron-core coil with inner and outer diameters and length of 20.5, 66, and 124 mm is the optimized coil. Traditionally, FEM results are adopted from simulation and implemented into the motion logic; however, simulated values are associated with errors; 17% in this study. Instead of regularizing FEM results, for the first time, artificial intelligence has been used to approximate the actual values for manipulation purposes. Regression models for Artificial Neural Network (ANN) and a hybrid method called Artificial Neural Network with Simulated Annealing (ANN/SA) have been created. ANN/SA has shown outstanding performance with an average <i>R</i><sup>2</sup>, and a root mean square error of 0.9871 and 0.0153, respectively. Implementation of the regression model into the manipulation logic has provided a motion with 13 μm of accuracy.https://www.mdpi.com/2072-666X/13/2/327electromagnetismmagnetic manipulatormagnetic actuatordeep learningANNANN/SA |
spellingShingle | Pooriya Kazemzadeh Heris Mir Behrad Khamesee Design and Fabrication of a Magnetic Actuator for Torque and Force Control Estimated by the ANN/SA Algorithm Micromachines electromagnetism magnetic manipulator magnetic actuator deep learning ANN ANN/SA |
title | Design and Fabrication of a Magnetic Actuator for Torque and Force Control Estimated by the ANN/SA Algorithm |
title_full | Design and Fabrication of a Magnetic Actuator for Torque and Force Control Estimated by the ANN/SA Algorithm |
title_fullStr | Design and Fabrication of a Magnetic Actuator for Torque and Force Control Estimated by the ANN/SA Algorithm |
title_full_unstemmed | Design and Fabrication of a Magnetic Actuator for Torque and Force Control Estimated by the ANN/SA Algorithm |
title_short | Design and Fabrication of a Magnetic Actuator for Torque and Force Control Estimated by the ANN/SA Algorithm |
title_sort | design and fabrication of a magnetic actuator for torque and force control estimated by the ann sa algorithm |
topic | electromagnetism magnetic manipulator magnetic actuator deep learning ANN ANN/SA |
url | https://www.mdpi.com/2072-666X/13/2/327 |
work_keys_str_mv | AT pooriyakazemzadehheris designandfabricationofamagneticactuatorfortorqueandforcecontrolestimatedbytheannsaalgorithm AT mirbehradkhamesee designandfabricationofamagneticactuatorfortorqueandforcecontrolestimatedbytheannsaalgorithm |