### Abstract

This paper introduces the use of the Adaptive Particle Swarm Optimization (APSO) for adapting the weights of Fuzzy Neural Networks (FNN). The fuzzy network is used for the identification of the dynamics of a DC motor with nonlinear load torque. Then the speed of the motor is controlled using an inverse controller to follow a required sinusoidal speed trajectory. The parameters of the DC motor are assumed unknown as well as the nonlinear load torque characteristics. In the first stage a nonlinear fuzzy neural network FNN is used to approximate the motor voltage as a function of the motor speed samples. In the second stage, the above mentioned approximator is used to calculate the control signal (the motor voltage) as a function of the speed samples and the required reference trajectory. Unlike the conventional back-propagation technique, the adaptation of the weights of the FNN approximator is done on-line (at each iteration) using adaptive particle swarm optimization based on the least squares error minimization with random initial condition without any offline pre-training. The adaptive particle swarm algorithm is used to track the changes in the nonlinear load torque.

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

Pages (from-to) | 469-476 |

Number of pages | 8 |

Journal | Alexandria Engineering Journal |

Volume | 46 |

Issue number | 4 |

Publication status | Published - Jul 2007 |

### Fingerprint

### Keywords

- Fuzzy Neural Networks (FNN)
- Inverse Control (IC)
- Least Squares (LS)
- Particle Swarm Optimization (PSO)
- System identification

### ASJC Scopus subject areas

- Engineering(all)

### Cite this

*Alexandria Engineering Journal*,

*46*(4), 469-476.

**Adaptive fuzzy APSO based inverse tracking-controller for DC motors.** / Youssef, Karim H.; Wahba, Manai A.; Yousef, Hasan A.; Sebakhy, Omar A.

Research output: Contribution to journal › Article

*Alexandria Engineering Journal*, vol. 46, no. 4, pp. 469-476.

}

TY - JOUR

T1 - Adaptive fuzzy APSO based inverse tracking-controller for DC motors

AU - Youssef, Karim H.

AU - Wahba, Manai A.

AU - Yousef, Hasan A.

AU - Sebakhy, Omar A.

PY - 2007/7

Y1 - 2007/7

N2 - This paper introduces the use of the Adaptive Particle Swarm Optimization (APSO) for adapting the weights of Fuzzy Neural Networks (FNN). The fuzzy network is used for the identification of the dynamics of a DC motor with nonlinear load torque. Then the speed of the motor is controlled using an inverse controller to follow a required sinusoidal speed trajectory. The parameters of the DC motor are assumed unknown as well as the nonlinear load torque characteristics. In the first stage a nonlinear fuzzy neural network FNN is used to approximate the motor voltage as a function of the motor speed samples. In the second stage, the above mentioned approximator is used to calculate the control signal (the motor voltage) as a function of the speed samples and the required reference trajectory. Unlike the conventional back-propagation technique, the adaptation of the weights of the FNN approximator is done on-line (at each iteration) using adaptive particle swarm optimization based on the least squares error minimization with random initial condition without any offline pre-training. The adaptive particle swarm algorithm is used to track the changes in the nonlinear load torque.

AB - This paper introduces the use of the Adaptive Particle Swarm Optimization (APSO) for adapting the weights of Fuzzy Neural Networks (FNN). The fuzzy network is used for the identification of the dynamics of a DC motor with nonlinear load torque. Then the speed of the motor is controlled using an inverse controller to follow a required sinusoidal speed trajectory. The parameters of the DC motor are assumed unknown as well as the nonlinear load torque characteristics. In the first stage a nonlinear fuzzy neural network FNN is used to approximate the motor voltage as a function of the motor speed samples. In the second stage, the above mentioned approximator is used to calculate the control signal (the motor voltage) as a function of the speed samples and the required reference trajectory. Unlike the conventional back-propagation technique, the adaptation of the weights of the FNN approximator is done on-line (at each iteration) using adaptive particle swarm optimization based on the least squares error minimization with random initial condition without any offline pre-training. The adaptive particle swarm algorithm is used to track the changes in the nonlinear load torque.

KW - Fuzzy Neural Networks (FNN)

KW - Inverse Control (IC)

KW - Least Squares (LS)

KW - Particle Swarm Optimization (PSO)

KW - System identification

UR - http://www.scopus.com/inward/record.url?scp=50149096276&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50149096276&partnerID=8YFLogxK

M3 - Article

VL - 46

SP - 469

EP - 476

JO - AEJ - Alexandria Engineering Journal

JF - AEJ - Alexandria Engineering Journal

SN - 1110-0168

IS - 4

ER -