Artificial neural network approach using Levenberg-Marquardt algorithm in the use of bottom ash waste in concrete hollow block design
Neural Network modeling was applied for the prediction of compressive strength of Coal Bottom Ash (CBA). Levenberg-Marquardt was used for the different neural network architectures to find acceptable models than can accurately predict the compressive strength of CHB's and realistically model th...
Saved in:
| Main Author: | |
|---|---|
| Format: | text |
| Language: | English |
| Published: |
Animo Repository
2003
|
| Subjects: | |
| Online Access: | https://animorepository.dlsu.edu.ph/etd_masteral/3046 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | De La Salle University |
| Language: | English |
| Summary: | Neural Network modeling was applied for the prediction of compressive strength of Coal Bottom Ash (CBA). Levenberg-Marquardt was used for the different neural network architectures to find acceptable models than can accurately predict the compressive strength of CHB's and realistically model the behavior of CHB's with CBA as partial substitute to sand. In addition, the maximum percentage of CBA content was derived from the ANN (Artificial Neural Network) model based on PNS (Philippine National Standards) types. CBA is a waste by-product of coal-fired power plant. An experimental study utilizing CBA as a partial substitute to sand in the production of CNB's was conducted. Around 429 pieces of four-inch thick CHB's were tested with such variable mix proportions as: water-cement ratio (w/c), cement-aggregate ratio (c/a), weight of the specimen (wt), slump (sl), and coal bottom ash percent substitution (CBA) taken into consideration. |
|---|