### Abstract

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

Title of host publication | Proceedings of the Twenty-ninth (2019) International Ocean and Polar Engineering Conference |

Publisher | International Society of Offshore & Polar Engineers |

Publication date | 2019 |

Pages | 951-958 |

ISBN (Print) | 978-1 880653 85-2 |

Publication status | Published - 2019 |

Event | 29th International Ocean and Polar Engineering Conference (ISOPE 2019) - Honolulu, United States Duration: 16 Jun 2019 → 21 Jun 2019 |

### Conference

Conference | 29th International Ocean and Polar Engineering Conference (ISOPE 2019) |
---|---|

Country | United States |

City | Honolulu |

Period | 16/06/2019 → 21/06/2019 |

Series | Proceedings of the International Offshore and Polar Engineering Conference |
---|---|

ISSN | 1098-6189 |

### Keywords

- Model Reduction
- System simulation
- Machine Learning
- Hull-propeller-engine simulation
- 0D engine model
- Propulsion simulation

### Cite this

*Proceedings of the Twenty-ninth (2019) International Ocean and Polar Engineering Conference*(pp. 951-958). International Society of Offshore & Polar Engineers. Proceedings of the International Offshore and Polar Engineering Conference

}

*Proceedings of the Twenty-ninth (2019) International Ocean and Polar Engineering Conference.*International Society of Offshore & Polar Engineers, Proceedings of the International Offshore and Polar Engineering Conference, pp. 951-958, 29th International Ocean and Polar Engineering Conference (ISOPE 2019), Honolulu, United States, 16/06/2019.

**Model Reduction through Machine Learning Tools Using Simulation Data with High Variance.** / Koosup Yum, Kevin ; Taskar, Bhushan; Pedersen, Eilif.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Model Reduction through Machine Learning Tools Using Simulation Data with High Variance

AU - Koosup Yum, Kevin

AU - Taskar, Bhushan

AU - Pedersen, Eilif

PY - 2019

Y1 - 2019

N2 - Enhancing the computational speed through model reduction can facilitate the use of a complex system model for a design task. A part of the system model that is demanding in numerical calculation can be replaced by a surrogate model using machine learning tools such as support vector machine (SVM) and artificial neural network (ANN), which may be an effective way to find a highly nonlinear regression model with a multi-dimensional input. However, obtaining a proper dataset for training the model is one of the biggest challenges to find such a model, especially when the input of the model has a high dimension. In this regard, running a system simulation with a high-fidelity model in the possible operational mode can provide a relevant and appropriate size of the data-set with high variance. In this paper, a propulsion simulation of a marine vessel system based on the first principle models is used to generate a synthetic data-set for training ANN and SVM models for a cylinder model of a main engine. The trained models were tested with a static data-set, an open-loop dynamic simulation, and a closed-loop dynamic simulation, and compared to the original models. The results show that the outputs from the surrogate models agree well with the 0D models except some load increasing situation in the closed-loop dynamic simulation. The system model using the surrogate models showed an order-higher simulation speed than the 0D model, and the gap will increase as the rated shaft speed of the diesel engine increases.

AB - Enhancing the computational speed through model reduction can facilitate the use of a complex system model for a design task. A part of the system model that is demanding in numerical calculation can be replaced by a surrogate model using machine learning tools such as support vector machine (SVM) and artificial neural network (ANN), which may be an effective way to find a highly nonlinear regression model with a multi-dimensional input. However, obtaining a proper dataset for training the model is one of the biggest challenges to find such a model, especially when the input of the model has a high dimension. In this regard, running a system simulation with a high-fidelity model in the possible operational mode can provide a relevant and appropriate size of the data-set with high variance. In this paper, a propulsion simulation of a marine vessel system based on the first principle models is used to generate a synthetic data-set for training ANN and SVM models for a cylinder model of a main engine. The trained models were tested with a static data-set, an open-loop dynamic simulation, and a closed-loop dynamic simulation, and compared to the original models. The results show that the outputs from the surrogate models agree well with the 0D models except some load increasing situation in the closed-loop dynamic simulation. The system model using the surrogate models showed an order-higher simulation speed than the 0D model, and the gap will increase as the rated shaft speed of the diesel engine increases.

KW - Model Reduction

KW - System simulation

KW - Machine Learning

KW - Hull-propeller-engine simulation

KW - 0D engine model

KW - Propulsion simulation

M3 - Article in proceedings

SN - 978-1 880653 85-2

SP - 951

EP - 958

BT - Proceedings of the Twenty-ninth (2019) International Ocean and Polar Engineering Conference

PB - International Society of Offshore & Polar Engineers

ER -