State Monitoring of Chemical Plants using Normal Operation Historical Data and Application to Soft Sensors
| Project/Area Number |
26420781
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Reaction engineering/Process system
|
|---|
| Research Institution | Kyushu University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
Fiscal Year 2016: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2015: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2014: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
|
|---|
| Keywords | 化学プラント / 運転監視 / 正常状態予測 / ソフトセンサー / データベースモデル |
|---|
| Outline of Final Research Achievements |
In a chemical plant, the values of the state variables are measured in real time for operation and monitoring and are stored as the operation historical data at the same time. But most of them are the historical data during normal operation. In this study, we have developed a method to accurately predict the current normal state by referring to historical data during past normal operation which has been accumulated in large quantities. Its usefulness has been demonstrated by applying it to the boiler plant whose normal states are uncertainly varied. Furthermore, we showed that the proposed method can be applied to soft sensors widely used for estimating values of variables that are difficult to be measured in real time by numerical experiments based on operational data in actual plant.
|
Report
(4 results)
Research Products
(1 results)
