Latent-Space Dynamics for Prediction and Fault Detection in Geothermal Power Plant Operations
This paper presents a latent-space dynamic neural network (LSDNN) model for the multi-step-ahead prediction and fault detection of a geothermal power plant’s operation. The model was trained to learn the dynamics of the power generation process from multivariate time-series data and the effects of e...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/7/2555 |
| _version_ | 1827623649415266304 |
|---|---|
| author | Yingxiang Liu Wei Ling Robert Young Jalal Zia Trenton T. Cladouhos Behnam Jafarpour |
| author_facet | Yingxiang Liu Wei Ling Robert Young Jalal Zia Trenton T. Cladouhos Behnam Jafarpour |
| author_sort | Yingxiang Liu |
| collection | DOAJ |
| description | This paper presents a latent-space dynamic neural network (LSDNN) model for the multi-step-ahead prediction and fault detection of a geothermal power plant’s operation. The model was trained to learn the dynamics of the power generation process from multivariate time-series data and the effects of exogenous variables, such as control adjustment and ambient temperature. In the LSDNN model, an encoder–decoder architecture was designed to capture cross-correlation among different measured variables. In addition, a latent space dynamic structure was proposed to propagate the dynamics in the latent space to enable prediction. The prediction power of the LSDNN was utilized for monitoring a geothermal power plant and detecting abnormal events. The model was integrated with principal component analysis (PCA)-based process monitoring techniques to develop a fault-detection procedure. The performance of the proposed LSDNN model and fault detection approach was demonstrated using field data collected from a geothermal power plant. |
| first_indexed | 2024-03-09T11:53:33Z |
| format | Article |
| id | doaj.art-9ef53ca94ef140f0990bd6f56fb1dc84 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T11:53:33Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-9ef53ca94ef140f0990bd6f56fb1dc842023-11-30T23:11:47ZengMDPI AGEnergies1996-10732022-03-01157255510.3390/en15072555Latent-Space Dynamics for Prediction and Fault Detection in Geothermal Power Plant OperationsYingxiang Liu0Wei Ling1Robert Young2Jalal Zia3Trenton T. Cladouhos4Behnam Jafarpour5Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA 90089, USAMork Family Department of Chemical Engineering and Materials Science, University of Southern California, Los Angeles, CA 90089, USAMork Family Department of Chemical Engineering and Materials Science, University of Southern California, Los Angeles, CA 90089, USACyrq Energy Inc., Salt Lake City, UT 84101, USACyrq Energy Inc., Salt Lake City, UT 84101, USAMork Family Department of Chemical Engineering and Materials Science, University of Southern California, Los Angeles, CA 90089, USAThis paper presents a latent-space dynamic neural network (LSDNN) model for the multi-step-ahead prediction and fault detection of a geothermal power plant’s operation. The model was trained to learn the dynamics of the power generation process from multivariate time-series data and the effects of exogenous variables, such as control adjustment and ambient temperature. In the LSDNN model, an encoder–decoder architecture was designed to capture cross-correlation among different measured variables. In addition, a latent space dynamic structure was proposed to propagate the dynamics in the latent space to enable prediction. The prediction power of the LSDNN was utilized for monitoring a geothermal power plant and detecting abnormal events. The model was integrated with principal component analysis (PCA)-based process monitoring techniques to develop a fault-detection procedure. The performance of the proposed LSDNN model and fault detection approach was demonstrated using field data collected from a geothermal power plant.https://www.mdpi.com/1996-1073/15/7/2555fault detectionneural networklatent space dynamicsgeothermal operationspower plant |
| spellingShingle | Yingxiang Liu Wei Ling Robert Young Jalal Zia Trenton T. Cladouhos Behnam Jafarpour Latent-Space Dynamics for Prediction and Fault Detection in Geothermal Power Plant Operations Energies fault detection neural network latent space dynamics geothermal operations power plant |
| title | Latent-Space Dynamics for Prediction and Fault Detection in Geothermal Power Plant Operations |
| title_full | Latent-Space Dynamics for Prediction and Fault Detection in Geothermal Power Plant Operations |
| title_fullStr | Latent-Space Dynamics for Prediction and Fault Detection in Geothermal Power Plant Operations |
| title_full_unstemmed | Latent-Space Dynamics for Prediction and Fault Detection in Geothermal Power Plant Operations |
| title_short | Latent-Space Dynamics for Prediction and Fault Detection in Geothermal Power Plant Operations |
| title_sort | latent space dynamics for prediction and fault detection in geothermal power plant operations |
| topic | fault detection neural network latent space dynamics geothermal operations power plant |
| url | https://www.mdpi.com/1996-1073/15/7/2555 |
| work_keys_str_mv | AT yingxiangliu latentspacedynamicsforpredictionandfaultdetectioningeothermalpowerplantoperations AT weiling latentspacedynamicsforpredictionandfaultdetectioningeothermalpowerplantoperations AT robertyoung latentspacedynamicsforpredictionandfaultdetectioningeothermalpowerplantoperations AT jalalzia latentspacedynamicsforpredictionandfaultdetectioningeothermalpowerplantoperations AT trentontcladouhos latentspacedynamicsforpredictionandfaultdetectioningeothermalpowerplantoperations AT behnamjafarpour latentspacedynamicsforpredictionandfaultdetectioningeothermalpowerplantoperations |