Gas Source Localization Using physics Guided Neural Networks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910437051727872 |
|---|---|
| author | Ruiz, Victor Scott Prieto Hinsen, Patrick Wiedemann, Thomas Christof, Constantin Shutin, Dmitriy |
| author_facet | Ruiz, Victor Scott Prieto Hinsen, Patrick Wiedemann, Thomas Christof, Constantin Shutin, Dmitriy |
| contents | This work discusses a novel method for estimating the location of a gas source based on spatially distributed concentration measurements taken, e.g., by a mobile robot or flying platform that follows a predefined trajectory to collect samples. The proposed approach uses a Physics-Guided Neural Network to approximate the gas dispersion with the source location as an additional network input. After an initial offline training phase, the neural network can be used to efficiently solve the inverse problem of localizing the gas source based on measurements. The proposed approach allows avoiding rather costly numerical simulations of gas physics needed for solving inverse problems. Our experiments show that the method localizes the source well, even when dealing with measurements affected by noise. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_04151 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Gas Source Localization Using physics Guided Neural Networks Ruiz, Victor Scott Prieto Hinsen, Patrick Wiedemann, Thomas Christof, Constantin Shutin, Dmitriy Machine Learning This work discusses a novel method for estimating the location of a gas source based on spatially distributed concentration measurements taken, e.g., by a mobile robot or flying platform that follows a predefined trajectory to collect samples. The proposed approach uses a Physics-Guided Neural Network to approximate the gas dispersion with the source location as an additional network input. After an initial offline training phase, the neural network can be used to efficiently solve the inverse problem of localizing the gas source based on measurements. The proposed approach allows avoiding rather costly numerical simulations of gas physics needed for solving inverse problems. Our experiments show that the method localizes the source well, even when dealing with measurements affected by noise. |
| title | Gas Source Localization Using physics Guided Neural Networks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2405.04151 |