Stored Grain Inventory Management Using Neural-Network-Based Parametric Electromagnetic Inversion
| Autor: | Nicholas Geddert, Ryan Kruk, Colin Gilmore, Joe LoVetri, Kennedy Krakalovich, Ian Jeffrey, Keeley Edwards, Mohammad Asefi |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Normalization (statistics)
Permittivity Electromagnetics General Computer Science Computer science 0211 other engineering and technologies 02 engineering and technology Synthetic data Data modeling 0202 electrical engineering electronic engineering information engineering General Materials Science parametric inversion grain storage monitoring 021101 geological & geomatics engineering Parametric statistics phaseless imaging Training set Artificial neural network General Engineering Experimental data 020206 networking & telecommunications Electromagnetic inverse scattering calibration machine learning lcsh:Electrical engineering. Electronics. Nuclear engineering Algorithm lcsh:TK1-9971 |
| Zdroj: | IEEE Access, Vol 8, Pp 207182-207192 (2020) |
| ISSN: | 2169-3536 |
| Popis: | We present a neural network architecture to determine the volume and complex permittivity of grain stored in metal bins. The neural networks output the grain height, cone angle and complex permittivity of the grain, using the input of experimental field data ( $S$ -parameters) from an electromagnetic imaging system consisting of 24 transceivers installed in the bin. Key for practical applications, the neural networks are trained on synthetic data sets but generate the parametric information using experimental data as input, without the use of calibration objects or open-short-load measurements. To accomplish this, we formulate a data normalization scheme that enables the use of a loss function that directly compares measured $S$ -parameters and simulation model fields. The normalization strategy and the ability to train on synthetic data means we do not need to collect experimental training data. We demonstrate the applicability of this synthetically trained neural network to experimental data from two different bin geometries, and discuss the ability of these neural networks to successfully infer parameters that can be used for grain inventory management. Our neural-network-based approach enables rapid inference, providing a more cost-effective long-term solution than existing optimization-based parametric inversion methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|