Relationship Prediction Based on Graph Model for Steam Turbine Control Valve
The control valve is an important piece of equipment in the steam turbine, which frequently suffers from the fault of the dead zone. The graph model is a promising method for dead zone detection, yet establishing an accurate and completed graph topology is not an easy task due to limited mechanism k...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Actuators |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-0825/10/5/91 |
| _version_ | 1797536179709542400 |
|---|---|
| author | Yi-Jing Zhang Li-Sheng Hu |
| author_facet | Yi-Jing Zhang Li-Sheng Hu |
| author_sort | Yi-Jing Zhang |
| collection | DOAJ |
| description | The control valve is an important piece of equipment in the steam turbine, which frequently suffers from the fault of the dead zone. The graph model is a promising method for dead zone detection, yet establishing an accurate and completed graph topology is not an easy task due to limited mechanism knowledge. Hence, a graph model is proposed to predict the links in the graph and estimate the relationship between variables of related equipment of the control valve. The graph convolution is conducted on the uncompleted graph to learn the low-level representations of the graph nodes, and the score function is used to evaluate the probability of the existence of links between a pair of graph nodes. Results demonstrate a test accuracy of 99.2% for the link prediction, and follow the principles of thermodynamics in the steam turbine. Consequently, the proposed graph model is capable of estimating the relationships for the steam turbine control valve, and other inter-connected industrial systems. |
| first_indexed | 2024-03-10T11:55:58Z |
| format | Article |
| id | doaj.art-6dc580aee9d2432d9fd203e8a01916b8 |
| institution | Directory Open Access Journal |
| issn | 2076-0825 |
| language | English |
| last_indexed | 2024-03-10T11:55:58Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Actuators |
| spelling | doaj.art-6dc580aee9d2432d9fd203e8a01916b82023-11-21T17:18:01ZengMDPI AGActuators2076-08252021-04-011059110.3390/act10050091Relationship Prediction Based on Graph Model for Steam Turbine Control ValveYi-Jing Zhang0Li-Sheng Hu1Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, ChinaDepartment of Automation, Shanghai Jiao Tong University, Shanghai 200240, ChinaThe control valve is an important piece of equipment in the steam turbine, which frequently suffers from the fault of the dead zone. The graph model is a promising method for dead zone detection, yet establishing an accurate and completed graph topology is not an easy task due to limited mechanism knowledge. Hence, a graph model is proposed to predict the links in the graph and estimate the relationship between variables of related equipment of the control valve. The graph convolution is conducted on the uncompleted graph to learn the low-level representations of the graph nodes, and the score function is used to evaluate the probability of the existence of links between a pair of graph nodes. Results demonstrate a test accuracy of 99.2% for the link prediction, and follow the principles of thermodynamics in the steam turbine. Consequently, the proposed graph model is capable of estimating the relationships for the steam turbine control valve, and other inter-connected industrial systems.https://www.mdpi.com/2076-0825/10/5/91graph convolutionlink predictionrelationship predictionscore functionsteam turbine control valve |
| spellingShingle | Yi-Jing Zhang Li-Sheng Hu Relationship Prediction Based on Graph Model for Steam Turbine Control Valve Actuators graph convolution link prediction relationship prediction score function steam turbine control valve |
| title | Relationship Prediction Based on Graph Model for Steam Turbine Control Valve |
| title_full | Relationship Prediction Based on Graph Model for Steam Turbine Control Valve |
| title_fullStr | Relationship Prediction Based on Graph Model for Steam Turbine Control Valve |
| title_full_unstemmed | Relationship Prediction Based on Graph Model for Steam Turbine Control Valve |
| title_short | Relationship Prediction Based on Graph Model for Steam Turbine Control Valve |
| title_sort | relationship prediction based on graph model for steam turbine control valve |
| topic | graph convolution link prediction relationship prediction score function steam turbine control valve |
| url | https://www.mdpi.com/2076-0825/10/5/91 |
| work_keys_str_mv | AT yijingzhang relationshippredictionbasedongraphmodelforsteamturbinecontrolvalve AT lishenghu relationshippredictionbasedongraphmodelforsteamturbinecontrolvalve |