Data-Driven Model-Free Control of Torque-Applying System for a Mechanically Closed-Loop Test Rig Using Neural Networks

532 Views
1160 Downloads
Export citation: ABNT
PARVARESH, Aida ;MARDANI, Mohsen .
Data-Driven Model-Free Control of Torque-Applying System for a Mechanically Closed-Loop Test Rig Using Neural Networks. 
Strojniški vestnik - Journal of Mechanical Engineering, [S.l.], v. 66, n.5, p. 337-347, may 2020. 
ISSN 0039-2480.
Available at: <https://www.sv-jme.eu/article/data-driven-model-free-control-of-torque-applying-system-for-a-mechanically-closed-loop-test-rig-using-neural-networks/>. Date accessed: 26 jan. 2021. 
doi:http://dx.doi.org/10.5545/sv-jme.2019.6499.
Parvaresh, A., & Mardani, M.
(2020).
Data-Driven Model-Free Control of Torque-Applying System for a Mechanically Closed-Loop Test Rig Using Neural Networks.
Strojniški vestnik - Journal of Mechanical Engineering, 66(5), 337-347.
doi:http://dx.doi.org/10.5545/sv-jme.2019.6499
@article{sv-jmesv-jme.2019.6499,
	author = {Aida  Parvaresh and Mohsen  Mardani},
	title = {Data-Driven Model-Free Control of Torque-Applying System for a Mechanically Closed-Loop Test Rig Using Neural Networks},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {66},
	number = {5},
	year = {2020},
	keywords = {identification; data-driven system; closed-loop test rig; hydraulic actuator; neural networks},
	abstract = {This paper presents a data-driven approach that utilizes the gathered experimental data to model and control a test rig constructed for the high-powered gearboxes. For simulating a wide variety of operational conditions, the test rig should be capable of providing different speeds and torques; this is possible using a torque-applying system. For this purpose, Electro-Hydraulic Actuators (EHAs) are used. Since applying accurate torque is a crucial demand as it affects the performance evaluation of the gearboxes, precise modelling of the actuation system along with a high-performance controller are required. In order to eliminate the need to solve complex nonlinear equations of EHA that originate from friction, varying properties of flow, and similar, a data-driven system based on neural networks is used for modelling. In this manner, the model of the system, which captures the whole dynamic of the system, can be obtained without any simplifying assumptions. The model is validated with experimental data, and the learning factors are set to zero to reduce the high computational costs. After that, another network of neurons is used as a controller. The performance of the proposed controller under normal conditions and in the presence of disturbances are investigated. The results show a good tracking of this controller for various reference inputs in different conditions with acceptable characteristics. Additionally, the obtained results are compared with a conventional proportional-integral-derivative (PID) controller results, and the superior features of the proposed scheme are concluded.},
	issn = {0039-2480},	pages = {337-347},	doi = {10.5545/sv-jme.2019.6499},
	url = {https://www.sv-jme.eu/article/data-driven-model-free-control-of-torque-applying-system-for-a-mechanically-closed-loop-test-rig-using-neural-networks/}
}
Parvaresh, A.,Mardani, M.
2020 May 66. Data-Driven Model-Free Control of Torque-Applying System for a Mechanically Closed-Loop Test Rig Using Neural Networks. Strojniški vestnik - Journal of Mechanical Engineering. [Online] 66:5
%A Parvaresh, Aida 
%A Mardani, Mohsen 
%D 2020
%T Data-Driven Model-Free Control of Torque-Applying System for a Mechanically Closed-Loop Test Rig Using Neural Networks
%B 2020
%9 identification; data-driven system; closed-loop test rig; hydraulic actuator; neural networks
%! Data-Driven Model-Free Control of Torque-Applying System for a Mechanically Closed-Loop Test Rig Using Neural Networks
%K identification; data-driven system; closed-loop test rig; hydraulic actuator; neural networks
%X This paper presents a data-driven approach that utilizes the gathered experimental data to model and control a test rig constructed for the high-powered gearboxes. For simulating a wide variety of operational conditions, the test rig should be capable of providing different speeds and torques; this is possible using a torque-applying system. For this purpose, Electro-Hydraulic Actuators (EHAs) are used. Since applying accurate torque is a crucial demand as it affects the performance evaluation of the gearboxes, precise modelling of the actuation system along with a high-performance controller are required. In order to eliminate the need to solve complex nonlinear equations of EHA that originate from friction, varying properties of flow, and similar, a data-driven system based on neural networks is used for modelling. In this manner, the model of the system, which captures the whole dynamic of the system, can be obtained without any simplifying assumptions. The model is validated with experimental data, and the learning factors are set to zero to reduce the high computational costs. After that, another network of neurons is used as a controller. The performance of the proposed controller under normal conditions and in the presence of disturbances are investigated. The results show a good tracking of this controller for various reference inputs in different conditions with acceptable characteristics. Additionally, the obtained results are compared with a conventional proportional-integral-derivative (PID) controller results, and the superior features of the proposed scheme are concluded.
%U https://www.sv-jme.eu/article/data-driven-model-free-control-of-torque-applying-system-for-a-mechanically-closed-loop-test-rig-using-neural-networks/
%0 Journal Article
%R 10.5545/sv-jme.2019.6499
%& 337
%P 11
%J Strojniški vestnik - Journal of Mechanical Engineering
%V 66
%N 5
%@ 0039-2480
%8 2020-05-26
%7 2020-05-26
Parvaresh, Aida, & Mohsen  Mardani.
"Data-Driven Model-Free Control of Torque-Applying System for a Mechanically Closed-Loop Test Rig Using Neural Networks." Strojniški vestnik - Journal of Mechanical Engineering [Online], 66.5 (2020): 337-347. Web.  26 Jan. 2021
TY  - JOUR
AU  - Parvaresh, Aida 
AU  - Mardani, Mohsen 
PY  - 2020
TI  - Data-Driven Model-Free Control of Torque-Applying System for a Mechanically Closed-Loop Test Rig Using Neural Networks
JF  - Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2019.6499
KW  - identification; data-driven system; closed-loop test rig; hydraulic actuator; neural networks
N2  - This paper presents a data-driven approach that utilizes the gathered experimental data to model and control a test rig constructed for the high-powered gearboxes. For simulating a wide variety of operational conditions, the test rig should be capable of providing different speeds and torques; this is possible using a torque-applying system. For this purpose, Electro-Hydraulic Actuators (EHAs) are used. Since applying accurate torque is a crucial demand as it affects the performance evaluation of the gearboxes, precise modelling of the actuation system along with a high-performance controller are required. In order to eliminate the need to solve complex nonlinear equations of EHA that originate from friction, varying properties of flow, and similar, a data-driven system based on neural networks is used for modelling. In this manner, the model of the system, which captures the whole dynamic of the system, can be obtained without any simplifying assumptions. The model is validated with experimental data, and the learning factors are set to zero to reduce the high computational costs. After that, another network of neurons is used as a controller. The performance of the proposed controller under normal conditions and in the presence of disturbances are investigated. The results show a good tracking of this controller for various reference inputs in different conditions with acceptable characteristics. Additionally, the obtained results are compared with a conventional proportional-integral-derivative (PID) controller results, and the superior features of the proposed scheme are concluded.
UR  - https://www.sv-jme.eu/article/data-driven-model-free-control-of-torque-applying-system-for-a-mechanically-closed-loop-test-rig-using-neural-networks/
@article{{sv-jme}{sv-jme.2019.6499},
	author = {Parvaresh, A., Mardani, M.},
	title = {Data-Driven Model-Free Control of Torque-Applying System for a Mechanically Closed-Loop Test Rig Using Neural Networks},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {66},
	number = {5},
	year = {2020},
	doi = {10.5545/sv-jme.2019.6499},
	url = {https://www.sv-jme.eu/article/data-driven-model-free-control-of-torque-applying-system-for-a-mechanically-closed-loop-test-rig-using-neural-networks/}
}
TY  - JOUR
AU  - Parvaresh, Aida 
AU  - Mardani, Mohsen 
PY  - 2020/05/26
TI  - Data-Driven Model-Free Control of Torque-Applying System for a Mechanically Closed-Loop Test Rig Using Neural Networks
JF  - Strojniški vestnik - Journal of Mechanical Engineering; Vol 66, No 5 (2020): Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2019.6499
KW  - identification, data-driven system, closed-loop test rig, hydraulic actuator, neural networks
N2  - This paper presents a data-driven approach that utilizes the gathered experimental data to model and control a test rig constructed for the high-powered gearboxes. For simulating a wide variety of operational conditions, the test rig should be capable of providing different speeds and torques; this is possible using a torque-applying system. For this purpose, Electro-Hydraulic Actuators (EHAs) are used. Since applying accurate torque is a crucial demand as it affects the performance evaluation of the gearboxes, precise modelling of the actuation system along with a high-performance controller are required. In order to eliminate the need to solve complex nonlinear equations of EHA that originate from friction, varying properties of flow, and similar, a data-driven system based on neural networks is used for modelling. In this manner, the model of the system, which captures the whole dynamic of the system, can be obtained without any simplifying assumptions. The model is validated with experimental data, and the learning factors are set to zero to reduce the high computational costs. After that, another network of neurons is used as a controller. The performance of the proposed controller under normal conditions and in the presence of disturbances are investigated. The results show a good tracking of this controller for various reference inputs in different conditions with acceptable characteristics. Additionally, the obtained results are compared with a conventional proportional-integral-derivative (PID) controller results, and the superior features of the proposed scheme are concluded.
UR  - https://www.sv-jme.eu/article/data-driven-model-free-control-of-torque-applying-system-for-a-mechanically-closed-loop-test-rig-using-neural-networks/
Parvaresh, Aida, AND Mardani, Mohsen.
"Data-Driven Model-Free Control of Torque-Applying System for a Mechanically Closed-Loop Test Rig Using Neural Networks" Strojniški vestnik - Journal of Mechanical Engineering [Online], Volume 66 Number 5 (26 May 2020)

Authors

Affiliations

  • K.N. Toosi University of Technology, Iran 1
  • 2ACECR, Sharif University of Technology Branch, Iran 2

Paper's information

Strojniški vestnik - Journal of Mechanical Engineering 66(2020)5, 337-347

https://doi.org/10.5545/sv-jme.2019.6499

This paper presents a data-driven approach that utilizes the gathered experimental data to model and control a test rig constructed for the high-powered gearboxes. For simulating a wide variety of operational conditions, the test rig should be capable of providing different speeds and torques; this is possible using a torque-applying system. For this purpose, Electro-Hydraulic Actuators (EHAs) are used. Since applying accurate torque is a crucial demand as it affects the performance evaluation of the gearboxes, precise modelling of the actuation system along with a high-performance controller are required. In order to eliminate the need to solve complex nonlinear equations of EHA that originate from friction, varying properties of flow, and similar, a data-driven system based on neural networks is used for modelling. In this manner, the model of the system, which captures the whole dynamic of the system, can be obtained without any simplifying assumptions. The model is validated with experimental data, and the learning factors are set to zero to reduce the high computational costs. After that, another network of neurons is used as a controller. The performance of the proposed controller under normal conditions and in the presence of disturbances are investigated. The results show a good tracking of this controller for various reference inputs in different conditions with acceptable characteristics. Additionally, the obtained results are compared with a conventional proportional-integral-derivative (PID) controller results, and the superior features of the proposed scheme are concluded.

identification; data-driven system; closed-loop test rig; hydraulic actuator; neural networks