Five phase multi-layer drive with fault tolerant neuro-fuzzy features for safety critical applications

Alessio Di Tullio, Marco Tursini, Francesco Parasiliti, Kan Akatsu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This article presents a method for control of a multiphase motor drive based on the use of a cognitive network that is capable of modelling nonlinearities of the system in fault conditions. To obtain a faithful model of the drive, a neural network (trained with the results of simulated faults) is used in the control algorithm in order to predict the system performance and adapt the control. A new multiphase motor with variable characteristics, particularly suited to applications in which a very wide variability of the speed range is required, will be described and presented in its structure. The technique to remedy failure adopted for this drive will be presented and described in its characteristics. The effectiveness of the control technique lastly will be highlighted by simulations that put it in comparison with classical solutions that employ PID controllers.

Original languageEnglish
Title of host publication2017 20th International Conference on Electrical Machines and Systems, ICEMS 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538632468
DOIs
Publication statusPublished - 2017 Oct 2
Event20th International Conference on Electrical Machines and Systems, ICEMS 2017 - Sydney, Australia
Duration: 2017 Aug 112017 Aug 14

Other

Other20th International Conference on Electrical Machines and Systems, ICEMS 2017
CountryAustralia
CitySydney
Period17/8/1117/8/14

Fingerprint

Neural networks
Controllers

Keywords

  • Fault tolerant
  • Multi-layer motor
  • Multiphase motor
  • Neural network
  • Neuro-fuzzy control
  • Safety critical application

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering
  • Mechanical Engineering
  • Control and Optimization

Cite this

Di Tullio, A., Tursini, M., Parasiliti, F., & Akatsu, K. (2017). Five phase multi-layer drive with fault tolerant neuro-fuzzy features for safety critical applications. In 2017 20th International Conference on Electrical Machines and Systems, ICEMS 2017 [8056487] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICEMS.2017.8056487

Five phase multi-layer drive with fault tolerant neuro-fuzzy features for safety critical applications. / Di Tullio, Alessio; Tursini, Marco; Parasiliti, Francesco; Akatsu, Kan.

2017 20th International Conference on Electrical Machines and Systems, ICEMS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. 8056487.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Di Tullio, A, Tursini, M, Parasiliti, F & Akatsu, K 2017, Five phase multi-layer drive with fault tolerant neuro-fuzzy features for safety critical applications. in 2017 20th International Conference on Electrical Machines and Systems, ICEMS 2017., 8056487, Institute of Electrical and Electronics Engineers Inc., 20th International Conference on Electrical Machines and Systems, ICEMS 2017, Sydney, Australia, 17/8/11. https://doi.org/10.1109/ICEMS.2017.8056487
Di Tullio A, Tursini M, Parasiliti F, Akatsu K. Five phase multi-layer drive with fault tolerant neuro-fuzzy features for safety critical applications. In 2017 20th International Conference on Electrical Machines and Systems, ICEMS 2017. Institute of Electrical and Electronics Engineers Inc. 2017. 8056487 https://doi.org/10.1109/ICEMS.2017.8056487
Di Tullio, Alessio ; Tursini, Marco ; Parasiliti, Francesco ; Akatsu, Kan. / Five phase multi-layer drive with fault tolerant neuro-fuzzy features for safety critical applications. 2017 20th International Conference on Electrical Machines and Systems, ICEMS 2017. Institute of Electrical and Electronics Engineers Inc., 2017.
@inproceedings{812efb47404a4f3faf5db42f453f19c0,
title = "Five phase multi-layer drive with fault tolerant neuro-fuzzy features for safety critical applications",
abstract = "This article presents a method for control of a multiphase motor drive based on the use of a cognitive network that is capable of modelling nonlinearities of the system in fault conditions. To obtain a faithful model of the drive, a neural network (trained with the results of simulated faults) is used in the control algorithm in order to predict the system performance and adapt the control. A new multiphase motor with variable characteristics, particularly suited to applications in which a very wide variability of the speed range is required, will be described and presented in its structure. The technique to remedy failure adopted for this drive will be presented and described in its characteristics. The effectiveness of the control technique lastly will be highlighted by simulations that put it in comparison with classical solutions that employ PID controllers.",
keywords = "Fault tolerant, Multi-layer motor, Multiphase motor, Neural network, Neuro-fuzzy control, Safety critical application",
author = "{Di Tullio}, Alessio and Marco Tursini and Francesco Parasiliti and Kan Akatsu",
year = "2017",
month = "10",
day = "2",
doi = "10.1109/ICEMS.2017.8056487",
language = "English",
booktitle = "2017 20th International Conference on Electrical Machines and Systems, ICEMS 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Five phase multi-layer drive with fault tolerant neuro-fuzzy features for safety critical applications

AU - Di Tullio, Alessio

AU - Tursini, Marco

AU - Parasiliti, Francesco

AU - Akatsu, Kan

PY - 2017/10/2

Y1 - 2017/10/2

N2 - This article presents a method for control of a multiphase motor drive based on the use of a cognitive network that is capable of modelling nonlinearities of the system in fault conditions. To obtain a faithful model of the drive, a neural network (trained with the results of simulated faults) is used in the control algorithm in order to predict the system performance and adapt the control. A new multiphase motor with variable characteristics, particularly suited to applications in which a very wide variability of the speed range is required, will be described and presented in its structure. The technique to remedy failure adopted for this drive will be presented and described in its characteristics. The effectiveness of the control technique lastly will be highlighted by simulations that put it in comparison with classical solutions that employ PID controllers.

AB - This article presents a method for control of a multiphase motor drive based on the use of a cognitive network that is capable of modelling nonlinearities of the system in fault conditions. To obtain a faithful model of the drive, a neural network (trained with the results of simulated faults) is used in the control algorithm in order to predict the system performance and adapt the control. A new multiphase motor with variable characteristics, particularly suited to applications in which a very wide variability of the speed range is required, will be described and presented in its structure. The technique to remedy failure adopted for this drive will be presented and described in its characteristics. The effectiveness of the control technique lastly will be highlighted by simulations that put it in comparison with classical solutions that employ PID controllers.

KW - Fault tolerant

KW - Multi-layer motor

KW - Multiphase motor

KW - Neural network

KW - Neuro-fuzzy control

KW - Safety critical application

UR - http://www.scopus.com/inward/record.url?scp=85034628216&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85034628216&partnerID=8YFLogxK

U2 - 10.1109/ICEMS.2017.8056487

DO - 10.1109/ICEMS.2017.8056487

M3 - Conference contribution

BT - 2017 20th International Conference on Electrical Machines and Systems, ICEMS 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -