Optimization and Analysis of Design Parameters, Excess Air Ratio, and Coal Consumption in the Supercritical 660 MW Power Plant Performance using Artificial Neural Network
By: Kumar, Naveen G
.
Contributor(s): Gundabattini, E.
Publisher: Kolkatta Springer 2022Edition: Vol,103(3), June.Description: 445–457p.Subject(s): Mechanical EngineeringOnline resources: Click here
In:
Journal of the institution of engineers (India): Series CSummary: work discusses the supercritical technology that has been instrumental in reducing pollution levels and quick load response from the thermal plant. Various operating parameters such as main steam pressure and temperature; reheat steam pressure and temperature; excess air ratio for a given fuel, feedwater heater bleed steam pressure and temperature are listed. The influence of their optimization is analyzed to reduce the pollution levels to a certain extent. Primarily, this study deals with utilizing artificial intelligence with the existing plant to predict the optimum thermal plant performance. The input parameters that are used in the artificial neural network (ANN) are evaluated to find the energy input through a mixture of coal and air. The ANN algorithm computes different parameters that initiate the optimization, resulting in the least energy input to the plant, as an algorithm fitness function. The built model could also use online optimization in addition to optimizing the design parameters when further modifications are made. This model is used to determine the effect of various excess air ratios and different types of fuels on the performance of the plant. The different boiler losses of boiler from different coal samples and exergy and exergy losses were analyzed at a particular excess air ratio. Finally, this paper predicts that by using ANN tool optimization, around 30% of coal savings are achieved which is equivalent to CO2 pollution reduction, less reduction of NOx and SOx pollutions, and an increase in plant efficiency by 1.3%.
| Item type | Current location | Call number | Status | Date due | Barcode | Item holds |
|---|---|---|---|---|---|---|
Articles Abstract Database
|
School of Engineering & Technology Archieval Section | Not for loan | 2022-1825 |
work discusses the supercritical technology that has been instrumental in reducing pollution levels and quick load response from the thermal plant. Various operating parameters such as main steam pressure and temperature; reheat steam pressure and temperature; excess air ratio for a given fuel, feedwater heater bleed steam pressure and temperature are listed. The influence of their optimization is analyzed to reduce the pollution levels to a certain extent. Primarily, this study deals with utilizing artificial intelligence with the existing plant to predict the optimum thermal plant performance. The input parameters that are used in the artificial neural network (ANN) are evaluated to find the energy input through a mixture of coal and air. The ANN algorithm computes different parameters that initiate the optimization, resulting in the least energy input to the plant, as an algorithm fitness function. The built model could also use online optimization in addition to optimizing the design parameters when further modifications are made. This model is used to determine the effect of various excess air ratios and different types of fuels on the performance of the plant. The different boiler losses of boiler from different coal samples and exergy and exergy losses were analyzed at a particular excess air ratio. Finally, this paper predicts that by using ANN tool optimization, around 30% of coal savings are achieved which is equivalent to CO2 pollution reduction, less reduction of NOx and SOx pollutions, and an increase in plant efficiency by 1.3%.
Click on an image to view it in the image viewer
There are no comments for this item.