Developing a soft sensor to monitor water quality
ApplyProject Description
Ensuring the performance of wastewater treatment processes is important to guarantee that the
final treated wastewater quality is safe for reuse. However, bacterial concentration present along the different stages of treatment process is not easily measured routinely for the plant operators. A moving horizon sensing approach based on neural networks has been proposed in [1] for measuring the bacteria concentration from easy to measure variables. The obtained model has been successfully tested on KAUST wastewater plant. In this project, the student will test and extend the model to other sets of data. A particular interest will be on incorporating self-calibration or self-training strategies to guarantee good performance of the proposed algorithm.
[1] Mohammed Alharbi, Pei-Ying Hong, Taous-Meriem Laleg-Kirati. Sliding window neural network based sensing of bacteria in wastewater treatment plants, Journal of process control, Volume 110, February 2022, Pages 35-44
Program -
Applied Mathematics and Computer Science
Division -
All Divisions
Faculty Lab Link -
https://www.kaust.edu.sa/en/study/faculty/peiying-hong
Field of Study -
Applied mathematics
About the
Researcher
Peiying Hong
Desired Project Deliverables
We expect the student to test the existing model on a new dataset. Various neural network configurations will be also tested and compared.