Analysis of sequence batch reactor for COD and TSS removal identification from septic sludge treatment plant using bio inspired algorithm: a case study in Sarawak
This study focuses on the prediction of effluent removal through Sequence Batch Reactor (SBR) in Septic Sludge Treatment Plant (SSTP) located in Sarawak. The SBR is a fill-and-draw activated sludge system for wastewater treatment plant. The current system practiced has successfully produced a h...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2012
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/28356/ http://irep.iium.edu.my/28356/ http://irep.iium.edu.my/28356/1/EP161%281%29.pdf |
| Summary: | This study focuses on the prediction of effluent
removal through Sequence Batch Reactor (SBR) in
Septic Sludge Treatment Plant (SSTP) located in
Sarawak. The SBR is a fill-and-draw activated sludge
system for wastewater treatment plant. The current
system practiced has successfully produced a high
efficiency of effluent removal, namely Chemical Oxygen
Demand (COD) and Total Suspended Solids (TSS).
However, a direct cause-effect relationship to
wastewater treatment performance is rarely established.
Conversely, experimental results could lead to
contradictory conclusions. Therefore, this hinders the
formulation of deterministic cause-effect relationship
that could be used as prediction model. In this study,
Artificial Immune System (AIS) technique named Clonal
Selection Algorithm (CSA) is introduced in the
development of a prediction model to forecast the
performance of the SSTP. In order to attain this
objective, the Root Mean Square Error (RMSE), Mean
Absolute Percentage Error (MAPE) and Correction
Coefficient (R) are used as performance indexes. The
main outcome is to achieve a satisfactory prediction of
effluent removal as in accordance to “The
Environmental Quality Act 1974, Environmental Quality
(Sewage) Regulation 2009: Standard A” for effluent
discharge. Results of this study, exhibits a small
percentage of predicted effluent error successfully
modeled. Thus, the pattern recognition of effluent
obtained from using CSA has shown a successful novel
predictive model that could be used as an engineering
tool for environmental planning, |
|---|