### Abstract

This paper presents active control of acoustic noise using radial basis function (RBF) networks and its digital signal processor (DSP) real-time implementation. The neural control system consists of two stages: first, identification (modeling) of secondary path of the active noise control using RBF networks and its learning algorithm, and secondly neural control of primary path based on neural model obtained in the first stage. A tapped delay line is introduced in front of controller neural, and another tapped delay line is inserted between controller neural networks and model neural networks. An algorithm referred to as FX-RBF is proposed to account for secondary path effects of the control system arising in active noise control. The resulting algorithm turns out to be the filtered-X version of the standard RBF learning algorithm. We address centralized and decentralized controller configuration and their DSP implementation is carried out. Effectiveness of the neural controller is demonstrated by applying the algorithm to active noise control within a 3 dimension enclosure to generate quiet zones around error microphones. Results of the real-time experiments shows that 10-30 dB noise attenuation is obtained, are better than those obtained by classical least mean-square technique, such as FX-LMS.

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

Title of host publication | IEEE International Symposium on Intelligent Control - Proceedings |

Pages | 460-466 |

Number of pages | 7 |

Publication status | Published - 2002 |

Event | Proceedings of the 2002 IEEE International Symposium on Intelligent Control - Vancouver Duration: 2002 Oct 27 → 2002 Oct 30 |

### Other

Other | Proceedings of the 2002 IEEE International Symposium on Intelligent Control |
---|---|

City | Vancouver |

Period | 02/10/27 → 02/10/30 |

### Fingerprint

### Keywords

- Active noise control
- Adaptive nonlinear control
- DSP
- Radial basis function networks

### ASJC Scopus subject areas

- Hardware and Architecture
- Control and Systems Engineering

### Cite this

*IEEE International Symposium on Intelligent Control - Proceedings*(pp. 460-466)

**DSP based RBF neural modeling and control for active noise cancellation.** / Bambang, Riyanto T.; Anggono, Lazuardi; Uchida, Kenko.

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

*IEEE International Symposium on Intelligent Control - Proceedings.*pp. 460-466, Proceedings of the 2002 IEEE International Symposium on Intelligent Control, Vancouver, 02/10/27.

}

TY - GEN

T1 - DSP based RBF neural modeling and control for active noise cancellation

AU - Bambang, Riyanto T.

AU - Anggono, Lazuardi

AU - Uchida, Kenko

PY - 2002

Y1 - 2002

N2 - This paper presents active control of acoustic noise using radial basis function (RBF) networks and its digital signal processor (DSP) real-time implementation. The neural control system consists of two stages: first, identification (modeling) of secondary path of the active noise control using RBF networks and its learning algorithm, and secondly neural control of primary path based on neural model obtained in the first stage. A tapped delay line is introduced in front of controller neural, and another tapped delay line is inserted between controller neural networks and model neural networks. An algorithm referred to as FX-RBF is proposed to account for secondary path effects of the control system arising in active noise control. The resulting algorithm turns out to be the filtered-X version of the standard RBF learning algorithm. We address centralized and decentralized controller configuration and their DSP implementation is carried out. Effectiveness of the neural controller is demonstrated by applying the algorithm to active noise control within a 3 dimension enclosure to generate quiet zones around error microphones. Results of the real-time experiments shows that 10-30 dB noise attenuation is obtained, are better than those obtained by classical least mean-square technique, such as FX-LMS.

AB - This paper presents active control of acoustic noise using radial basis function (RBF) networks and its digital signal processor (DSP) real-time implementation. The neural control system consists of two stages: first, identification (modeling) of secondary path of the active noise control using RBF networks and its learning algorithm, and secondly neural control of primary path based on neural model obtained in the first stage. A tapped delay line is introduced in front of controller neural, and another tapped delay line is inserted between controller neural networks and model neural networks. An algorithm referred to as FX-RBF is proposed to account for secondary path effects of the control system arising in active noise control. The resulting algorithm turns out to be the filtered-X version of the standard RBF learning algorithm. We address centralized and decentralized controller configuration and their DSP implementation is carried out. Effectiveness of the neural controller is demonstrated by applying the algorithm to active noise control within a 3 dimension enclosure to generate quiet zones around error microphones. Results of the real-time experiments shows that 10-30 dB noise attenuation is obtained, are better than those obtained by classical least mean-square technique, such as FX-LMS.

KW - Active noise control

KW - Adaptive nonlinear control

KW - DSP

KW - Radial basis function networks

UR - http://www.scopus.com/inward/record.url?scp=0036911823&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036911823&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0036911823

SP - 460

EP - 466

BT - IEEE International Symposium on Intelligent Control - Proceedings

ER -