Interlligent approach for fire - fighting detection in power industry
Coal kept in the coal storage yard spontaneously catches on fire, which results in wastage and can even cause a huge fire to break out. This phenomenon is known as spontaneous combustion of coal. It is a complex process which has nonlinear relationships between its causing variables. Preventive meas...
Saved in:
| Main Author: | |
|---|---|
| Format: | |
| Published: |
2023
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Coal kept in the coal storage yard spontaneously catches on fire, which results in wastage and can even cause a huge fire to break out. This phenomenon is known as spontaneous combustion of coal. It is a complex process which has nonlinear relationships between its causing variables. Preventive measures to combat the fire from spreading to other coal piles in the vicinity have already been put in place. However, predictive aspect before the fire occurs is of great necessity for the power generation sector.
This research studies and considers the different prediction models created for sudden ignition of coal, explicitly in the choice of input and output parameters, to precisely forsee a fire event in the coal stockpiling yard. Emphasis is given to the Feed-Forward Neural Network (FFNN).
The benefits of tuning each parameter in the Neural Network was also discussed. In addition, sensitivity analysis was also dditionally led to to determine the influence of random input variables to their respective response variables. 2HL network was found to be the best prediction with 5 minutes forecast capacity.
From the development of the prediction model followed by the identification of the input parameters for the phenomenon of spontaneous combustion of coal, this will provide precious amount of time for operators involved to hose down the fire before it even occurs. . |
|---|