### Abstract

Adaptive inverse controllers (AIC) are based on approximate inverse of the system. This approximate inverse system is estimated using-some suitable estimators. They are incorporated in the feed forward path of the plant such that output of the plant tracks some desired signal. In AIC structure finite impulse response filters are used to compensate the effect of the non-cancellable zeros on the output, which avoid the cancellation of unstable poles of the controller with the non-cancellable zeros of the plant. So the boundedness of the input and output signals is assured. In practice the parameters of the controllers change as the frequency components of the reference input signal are changing. This means the parameters of the approximate inverse system designed using AIC method depend on the frequency spectrum of the excitation signal. This property results in highly time variant controller, where the frequency spectrum of the reference signal is not constant with time. In this work, a feed forward NN based structure of the AIC is proposed using the multi layer perceptrons (MLP). Back propagation algorithm is used as the learning algorithm for NN. The proposed structure shows the ability to control non-minimum phase system as well. It has been observed that once NN approximate inverse is learned, it becomes less sensitive to the frequency spectrum of excitation signal. Simulation results for both minimum phase and non-minimum phase plants are presented in the paper.

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

Title of host publication | IASTED International Conference on Modelling Identification and Control |

Editors | M.H. Hamza, M.H. Hamza |

Pages | 595-599 |

Number of pages | 5 |

Publication status | Published - 2003 |

Event | 22nd International Conference on Modelling Identification and Control - Innsbruck, Austria Duration: Feb 10 2003 → Feb 13 2003 |

### Other

Other | 22nd International Conference on Modelling Identification and Control |
---|---|

Country | Austria |

City | Innsbruck |

Period | 2/10/03 → 2/13/03 |

### Fingerprint

### Keywords

- Adaptive Control
- Neural Networks
- Non-minimum Phase

### ASJC Scopus subject areas

- Engineering(all)

### Cite this

*IASTED International Conference on Modelling Identification and Control*(pp. 595-599)

**Adaptive inverse control using a multi layer perceptron neural network.** / Shafiq, Muhammad; Moinuddin, Muhammad.

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

*IASTED International Conference on Modelling Identification and Control.*pp. 595-599, 22nd International Conference on Modelling Identification and Control, Innsbruck, Austria, 2/10/03.

}

TY - GEN

T1 - Adaptive inverse control using a multi layer perceptron neural network

AU - Shafiq, Muhammad

AU - Moinuddin, Muhammad

PY - 2003

Y1 - 2003

N2 - Adaptive inverse controllers (AIC) are based on approximate inverse of the system. This approximate inverse system is estimated using-some suitable estimators. They are incorporated in the feed forward path of the plant such that output of the plant tracks some desired signal. In AIC structure finite impulse response filters are used to compensate the effect of the non-cancellable zeros on the output, which avoid the cancellation of unstable poles of the controller with the non-cancellable zeros of the plant. So the boundedness of the input and output signals is assured. In practice the parameters of the controllers change as the frequency components of the reference input signal are changing. This means the parameters of the approximate inverse system designed using AIC method depend on the frequency spectrum of the excitation signal. This property results in highly time variant controller, where the frequency spectrum of the reference signal is not constant with time. In this work, a feed forward NN based structure of the AIC is proposed using the multi layer perceptrons (MLP). Back propagation algorithm is used as the learning algorithm for NN. The proposed structure shows the ability to control non-minimum phase system as well. It has been observed that once NN approximate inverse is learned, it becomes less sensitive to the frequency spectrum of excitation signal. Simulation results for both minimum phase and non-minimum phase plants are presented in the paper.

AB - Adaptive inverse controllers (AIC) are based on approximate inverse of the system. This approximate inverse system is estimated using-some suitable estimators. They are incorporated in the feed forward path of the plant such that output of the plant tracks some desired signal. In AIC structure finite impulse response filters are used to compensate the effect of the non-cancellable zeros on the output, which avoid the cancellation of unstable poles of the controller with the non-cancellable zeros of the plant. So the boundedness of the input and output signals is assured. In practice the parameters of the controllers change as the frequency components of the reference input signal are changing. This means the parameters of the approximate inverse system designed using AIC method depend on the frequency spectrum of the excitation signal. This property results in highly time variant controller, where the frequency spectrum of the reference signal is not constant with time. In this work, a feed forward NN based structure of the AIC is proposed using the multi layer perceptrons (MLP). Back propagation algorithm is used as the learning algorithm for NN. The proposed structure shows the ability to control non-minimum phase system as well. It has been observed that once NN approximate inverse is learned, it becomes less sensitive to the frequency spectrum of excitation signal. Simulation results for both minimum phase and non-minimum phase plants are presented in the paper.

KW - Adaptive Control

KW - Neural Networks

KW - Non-minimum Phase

UR - http://www.scopus.com/inward/record.url?scp=1542317856&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1542317856&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0889863393

SP - 595

EP - 599

BT - IASTED International Conference on Modelling Identification and Control

A2 - Hamza, M.H.

A2 - Hamza, M.H.

ER -