### Abstract

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

Pages | 955-960 |

Number of pages | 6 |

DOIs | |

Publication status | Published - Jun 2005 |

Event | American Control Conference 2005 (ACC) - Portland, United States Duration: 8 Jun 2005 → 10 Jun 2005 |

### Conference

Conference | American Control Conference 2005 (ACC) |
---|---|

Country | United States |

City | Portland |

Period | 8/06/05 → 10/06/05 |

### Fingerprint

### Keywords

- molecular-weight distribution
- equation
- distributions
- emulsion polymerization
- stochastic-systems
- particle-size distribution
- probability density-function

### Cite this

*Periodic learning of b-spline models for output PDF control: application to MWD control*. 955-960. Paper presented at American Control Conference 2005 (ACC) , Portland, United States. https://doi.org/10.1109/ACC.2005.1470083

}

**Periodic learning of b-spline models for output PDF control : application to MWD control.** / Wang, H.; Zhang, Z.J.; Yue, H.

Research output: Contribution to conference › Paper

TY - CONF

T1 - Periodic learning of b-spline models for output PDF control

T2 - application to MWD control

AU - Wang, H.

AU - Zhang, Z.J.

AU - Yue, H.

PY - 2005/6

Y1 - 2005/6

N2 - Periodic learning of B-spline basis functions model for the output probability density function (PDF) control of non-Gaussian systems is studied in this paper using the recursive least square algorithm. Within each control interval, the basis functions are fixed and the control input design is performed that controls the shape of the output PDFs. However, between each control interval, periodic learning techniques are used to tune the shape of the basis functions. This has been shown to be able to improve the accuracy of the B-spline approximation model. As such, the overall B-spline model of the output PDFs becomes a dual-model related to both time and space variables. The algorithm has been applied to a simulation study of the molecular weight distribution (MWD) control of a styrene polymerization process, leading to some interesting results.

AB - Periodic learning of B-spline basis functions model for the output probability density function (PDF) control of non-Gaussian systems is studied in this paper using the recursive least square algorithm. Within each control interval, the basis functions are fixed and the control input design is performed that controls the shape of the output PDFs. However, between each control interval, periodic learning techniques are used to tune the shape of the basis functions. This has been shown to be able to improve the accuracy of the B-spline approximation model. As such, the overall B-spline model of the output PDFs becomes a dual-model related to both time and space variables. The algorithm has been applied to a simulation study of the molecular weight distribution (MWD) control of a styrene polymerization process, leading to some interesting results.

KW - molecular-weight distribution

KW - equation

KW - distributions

KW - emulsion polymerization

KW - stochastic-systems

KW - particle-size distribution

KW - probability density-function

U2 - 10.1109/ACC.2005.1470083

DO - 10.1109/ACC.2005.1470083

M3 - Paper

SP - 955

EP - 960

ER -