แจ้งเอกสารไม่ครบถ้วน, ไม่ตรงกับชื่อเรื่อง หรือมีข้อผิดพลาดเกี่ยวกับเอกสาร ติดต่อที่นี่ ==>
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
Paisan Kittisupakorn. Long short-term memory network based model predictive control for wastewater treatment via reverse osmosis process. (). King Mongkut's University of Technology North Bangkok. Central Library. : , 2022.
Long short-term memory network based model predictive control for wastewater treatment via reverse osmosis process
Name: Chanoknun Worathongchai
Organization :
Chulalongkorn University. Faculty of Engineering
Email :
chanoknun.wora@gmail.com
Name: Paisan Kittisupakorn
Organization :
Chulalongkorn University. Faculty of Engineering
Abstract:
The reverse osmosis (RO) process is widely used to remove undesirable toxic compounds from wastewater. However, the control of reverse process imposes difficulties due to uncertain quality of feed, membrane fouling and process nonlinearity. Nonlinear model predictive control (NMPC) is one of the most effective control systems. The
control performance depends on an accurate internal model used to predict controlled variable over a prediction horizon
to maintain optimum operating conditions, which results in increased productivity and prolongs the life of the membranes. Long short-term memory (LSTM) network constitutes a sub-class of artificial neural network (ANN) that successfully captures complex nonlinear dynamic behavior and circumvent vanishing and exploding gradients. In this
work, an ANN and three LSTM structures that are 1) combining copies of time-invariant features with time series
(LSTM-replicate), 2) concatenating time-invariant feature with output of LSTM (LSTM-concatenate) and 3) initializing
the hidden state of LSTM by time-invariant features (LSTM-initialized) are proposed and applied for NMPC to control the average permeate concentration by manipulating feed pressure. Simulation results show that the LSTM-initialized based NMPC presents satisfactory performance
King Mongkut's University of Technology North Bangkok. Central Library
Address:
BANGKOK
Email:
library@kmutnb.ac.th
Created:
2022
Modified:
2022-11-15
Issued:
2022-11-15
บทความ/Article
application/pdf
BibliograpyCitation :
In King Mongkut's Institute of Technology Ladkrabang. Pure and Applied Chemistry International Conference (PACCON 2022) (pp.430-435). Bangkok : King Mongkut's Institute of Technology Ladkrabang
eng
©copyrights King Mongkut's University of Technology North Bangkok
RightsAccess:
ใช้เวลา
0.029911 วินาที
Chanoknun Worathongchai
| Title | Contributor | Type |
|---|---|---|
| Long short-term memory network based model predictive control for wastewater treatment via reverse osmosis process
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Chanoknun Worathongchai;Paisan Kittisupakorn | บทความ/Article |
Paisan Kittisupakorn
| Title | Contributor | Type |
|---|---|---|
| Long short-term memory network based model predictive control for wastewater treatment via reverse osmosis process
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Chanoknun Worathongchai;Paisan Kittisupakorn | บทความ/Article | |
| Modelling of a benzoxazinone process based on a pilot scale with scale-down approach
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Thitirat Monprapakamon;Wachira Daosud;Paisan Kittisupakorn | บทความ/Article | |
| Heat transfer modeling of deferasirox purification in a batch process
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Naruporn Savetvivat;Weerawun Weerachaipichasgul;Paisan Kittisupakorn | บทความ/Article | |
| Detection and replacement of states with spikes and noise by long short-term memory models or neural networks
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Ittikorn Yutto;Paisan Kittisupakorn | บทความ/Article | |
| Performance of combination ESN and LSTM in prediction of temperature in magnetic heating reactor
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Alkindi, Rasiq Dipta;Paisan Kittisupakorn | บทความ/Article | |
| Optimization of solketal reaction conditions for maximum yield using response surface methodology (RSM) in MATLAB®
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Sittinut Damnoensawat;Paisan Kittisupakorn | บทความ/Article |