Dynamic model development for submerged membrane filtration process using recurrent artificial neural network with control application
Modeling of membrane filtration process is challenging task because it is involves many interactions from biological and physical operation behavior. Membrane fouling in filtration process is too complex to understand and to derive a robust model is not possible. The aim of this paper is to study th...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2015
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/61996/1/NorhalizaAbdWahab2015_DynamicModelDevelopmentforSubmergedMembrane.pdf http://eprints.utm.my/id/eprint/61996/ http://www.utm.my/iicist/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Modeling of membrane filtration process is challenging task because it is involves many interactions from biological and physical operation behavior. Membrane fouling in filtration process is too complex to understand and to derive a robust model is not possible. The aim of this paper is to study the potential of neural network based dynamic model for submerged membrane filtration process. The purpose of the model is to represent the dynamic behavior of the filtration process therefore suitable control strategy and tuning can be developed to control the filtration process more effectively. In this work, a recurrent neural network (RNN) structure was employed to perform the dynamic model of the filtration process. The random step was applied to the suction pump to obtained the permeate flux and Transmembrane Pressure (TMP) dynamic. The model was evaluated in term of %R2, root mean square error (RMSE,) and mean absolute deviation (MAD). Proportional integral derivative (PID) controller was implemented to the model for different control strategies and several tuning gains were tested for the effective filtration control. The result of proposed modeling technique showed that the RNN structure is able to model the dynamic behavior of the filtration process below critical flux condition. The developed model also can be a reliable assistance for the control strategy development in the filtration process. |
|---|