Real-Time Hybrid Modeling of Francis Hydroturbine Dynamics via a Neural Controlled Differential Equation Approach
In recent years, deep learning has been widely applied to learning nonlinear dynamic models for the development of a digital twin system. However, most traditional deep learning frameworks, such as recurrent neural networks, convolutional neural networks, and multilayer perceptrons, find it difficul...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10347184/ |
| _version_ | 1797322595608035328 |
|---|---|
| author | Hong Wang Zhun Yin Zhong-Ping Jiang |
| author_facet | Hong Wang Zhun Yin Zhong-Ping Jiang |
| author_sort | Hong Wang |
| collection | DOAJ |
| description | In recent years, deep learning has been widely applied to learning nonlinear dynamic models for the development of a digital twin system. However, most traditional deep learning frameworks, such as recurrent neural networks, convolutional neural networks, and multilayer perceptrons, find it difficult to learn continuous-time and nonlinear system models. To address this challenge, in this paper, a novel deep learning method called neural controlled differential equation has been proposed to model the unknown nonlinear dynamics of controlled continuous-time systems seen in Francis hydroturbines of hydropower systems. Following the development of discretized-model structures for the system using the first principles, a detailed learning algorithm is formulated that is integrated with the physical model of the hydroturbine. As a result, a hybrid modeling with effective learning capability is obtained. To test the effectiveness of the proposed learning algorithm, a set of operational data has been collected and used to train the nonlinear dynamics of the Francis hydroturbine, where the learning results of the two nonlinear dynamics, namely the mechanical torque and water flow dynamics, using the real data have indicated that the proposed method can accurately learn these unknown nonlinear dynamics in an online, adaptive way. Moreover, to address the overfitting problem that appears during the online training phase, we propose to apply a meta-learning technique to pre-train a meta-initial value for each parameter of the proposed neural controlled differential equations. It has been shown that the use of the meta-learning technique can reduce the prediction mean square error significantly by more than 60%. |
| first_indexed | 2024-03-08T05:16:35Z |
| format | Article |
| id | doaj.art-f1f977a810934cafbba07880db4b8c71 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T05:16:35Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-f1f977a810934cafbba07880db4b8c712024-02-07T00:01:33ZengIEEEIEEE Access2169-35362023-01-011113913313914610.1109/ACCESS.2023.334062710347184Real-Time Hybrid Modeling of Francis Hydroturbine Dynamics via a Neural Controlled Differential Equation ApproachHong Wang0https://orcid.org/0000-0002-9876-0176Zhun Yin1https://orcid.org/0000-0002-3159-7319Zhong-Ping Jiang2https://orcid.org/0000-0002-4868-9359Energy and Transportation Science Division, Oak Ridge National Laboratory, Oak Ridge, TN, USADepartment of Electrical and Computer Engineering, New York University, Brooklyn, NY, USADepartment of Electrical and Computer Engineering, New York University, Brooklyn, NY, USAIn recent years, deep learning has been widely applied to learning nonlinear dynamic models for the development of a digital twin system. However, most traditional deep learning frameworks, such as recurrent neural networks, convolutional neural networks, and multilayer perceptrons, find it difficult to learn continuous-time and nonlinear system models. To address this challenge, in this paper, a novel deep learning method called neural controlled differential equation has been proposed to model the unknown nonlinear dynamics of controlled continuous-time systems seen in Francis hydroturbines of hydropower systems. Following the development of discretized-model structures for the system using the first principles, a detailed learning algorithm is formulated that is integrated with the physical model of the hydroturbine. As a result, a hybrid modeling with effective learning capability is obtained. To test the effectiveness of the proposed learning algorithm, a set of operational data has been collected and used to train the nonlinear dynamics of the Francis hydroturbine, where the learning results of the two nonlinear dynamics, namely the mechanical torque and water flow dynamics, using the real data have indicated that the proposed method can accurately learn these unknown nonlinear dynamics in an online, adaptive way. Moreover, to address the overfitting problem that appears during the online training phase, we propose to apply a meta-learning technique to pre-train a meta-initial value for each parameter of the proposed neural controlled differential equations. It has been shown that the use of the meta-learning technique can reduce the prediction mean square error significantly by more than 60%.https://ieeexplore.ieee.org/document/10347184/Deep learningdigital twinhydroturbine systemneural controlled differential equation |
| spellingShingle | Hong Wang Zhun Yin Zhong-Ping Jiang Real-Time Hybrid Modeling of Francis Hydroturbine Dynamics via a Neural Controlled Differential Equation Approach IEEE Access Deep learning digital twin hydroturbine system neural controlled differential equation |
| title | Real-Time Hybrid Modeling of Francis Hydroturbine Dynamics via a Neural Controlled Differential Equation Approach |
| title_full | Real-Time Hybrid Modeling of Francis Hydroturbine Dynamics via a Neural Controlled Differential Equation Approach |
| title_fullStr | Real-Time Hybrid Modeling of Francis Hydroturbine Dynamics via a Neural Controlled Differential Equation Approach |
| title_full_unstemmed | Real-Time Hybrid Modeling of Francis Hydroturbine Dynamics via a Neural Controlled Differential Equation Approach |
| title_short | Real-Time Hybrid Modeling of Francis Hydroturbine Dynamics via a Neural Controlled Differential Equation Approach |
| title_sort | real time hybrid modeling of francis hydroturbine dynamics via a neural controlled differential equation approach |
| topic | Deep learning digital twin hydroturbine system neural controlled differential equation |
| url | https://ieeexplore.ieee.org/document/10347184/ |
| work_keys_str_mv | AT hongwang realtimehybridmodelingoffrancishydroturbinedynamicsviaaneuralcontrolleddifferentialequationapproach AT zhunyin realtimehybridmodelingoffrancishydroturbinedynamicsviaaneuralcontrolleddifferentialequationapproach AT zhongpingjiang realtimehybridmodelingoffrancishydroturbinedynamicsviaaneuralcontrolleddifferentialequationapproach |