### Abstract

Original language | English |
---|---|

Title of host publication | 8th Mediterranean Electrotechnical Conference, 1996. MELECON '96. |

Publisher | IEEE |

Pages | 1461-1464 |

Number of pages | 5 |

ISBN (Print) | 0-7803-3109-5 |

DOIs | |

Publication status | Published - 1996 |

### Fingerprint

### Keywords

- Adaptive control systems
- Algorithms
- Calculations
- Computer control
- Computer simulation
- Electric control equipment
- Electric currents
- Electric resistance
- Mathematical models
- Neural networks
- Nonlinear equations
- Vectors, Electromagnetic torque
- Feedforward type architecture
- Neuro-control approach
- Nonlinear voltage equations
- Positioning system
- Real time control
- Sliding mode controller
- Switched reluctance motor drives
- Torque equation
- Vector control drives
- Reluctance motors

### Cite this

*8th Mediterranean Electrotechnical Conference, 1996. MELECON '96.*(pp. 1461-1464). IEEE. https://doi.org/10.1109/MELCON.1996.551225

**Neuro-control approach of switched reluctance motor drives.** / Trifa, V.; Gaura, Elena; Moldovan, L.; De Sario M., Maione B. (Editor); Pugliese P., Savino M. (Editor).

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding

*8th Mediterranean Electrotechnical Conference, 1996. MELECON '96..*IEEE, pp. 1461-1464. https://doi.org/10.1109/MELCON.1996.551225

}

TY - GEN

T1 - Neuro-control approach of switched reluctance motor drives

AU - Trifa, V.

AU - Gaura, Elena

AU - Moldovan, L.

A2 - De Sario M., Maione B.

A2 - Pugliese P., Savino M.

PY - 1996

Y1 - 1996

N2 - The purpose of the paper is to present several studies on neural networks used for modelling a switched reluctance motor (SRM) with variable structure control. A positioning system with four-phase SRM is presented, in which the position error is processed by a sliding-mode controller. The control unit represents the subject of a neural network based model. The proposed network system has a feed-forward type architecture, structured on three layers of processing units. The networks are trained using the BKP algorithm. Once the network system is trained, it is integrated as a part of the positioning system. The training and testing sets of examples are obtained by numerical simulation of the positioning system using the Matlab environment.

AB - The purpose of the paper is to present several studies on neural networks used for modelling a switched reluctance motor (SRM) with variable structure control. A positioning system with four-phase SRM is presented, in which the position error is processed by a sliding-mode controller. The control unit represents the subject of a neural network based model. The proposed network system has a feed-forward type architecture, structured on three layers of processing units. The networks are trained using the BKP algorithm. Once the network system is trained, it is integrated as a part of the positioning system. The training and testing sets of examples are obtained by numerical simulation of the positioning system using the Matlab environment.

KW - Adaptive control systems

KW - Algorithms

KW - Calculations

KW - Computer control

KW - Computer simulation

KW - Electric control equipment

KW - Electric currents

KW - Electric resistance

KW - Mathematical models

KW - Neural networks

KW - Nonlinear equations

KW - Vectors, Electromagnetic torque

KW - Feedforward type architecture

KW - Neuro-control approach

KW - Nonlinear voltage equations

KW - Positioning system

KW - Real time control

KW - Sliding mode controller

KW - Switched reluctance motor drives

KW - Torque equation

KW - Vector control drives

KW - Reluctance motors

U2 - 10.1109/MELCON.1996.551225

DO - 10.1109/MELCON.1996.551225

M3 - Conference proceeding

SN - 0-7803-3109-5

SP - 1461

EP - 1464

BT - 8th Mediterranean Electrotechnical Conference, 1996. MELECON '96.

PB - IEEE

ER -