Optimizing pH Prediction in Water Treatment Plant Through A Hybrid PSO-SVM Approach With Empirical Mode Decomposition

DOI

10.2991/978-94-6463-478-5_3How to use a DOI?

Keywords

Water Treatment Plant; Support Vector Machine (SVM); Empirical Mode Decomposition (EMD); pH

Abstract

The precise prediction of the outlet ph level of water treatment plants (wtps) is a prerequisite for chemical optimization and process efficiency. It also allows treatment process modifications, protects equipment, and ensures water quality.the main objective of this research is to enhance the accuracy of the outlet ph estimates at the bangabandhu water treatment plant (bwtp) in khulna, bangladesh. This study employed particle swarm optimizer (pso)-based support vector machine (svm) techniques to predict the outlet ph of bwtp. Furthermore, a thorough comparison of conventional and hybrid techniques is carried out in the research. The conventional svm model was executed with a variety of raw water variables, such as temperature, ph, and turbidity. For the model, several sets of input features were considered. In the hybrid approach, the empirical mode decomposition (emd) technique was employed as a pre-processing technique in the svm model. The intrinsic mode functions (imfs) and the residue are the input features of the emd-svm model. This configuration enhances the model’s ability to capture and utilize both the intrinsic oscillatory modes and residual components for improved performance. In this current study, twenty percent (20%) of the whole data set consisted of test data, while the remaining eighty percent (80%) consisted of training data. The pso optimizer was used to determine the models’ optimal hypermeters, including the kernel function and regularization parameters. In between the conventional models, the optimal r2 was 0.72, whereas the hybrid model gives an r2 value of 0.93. The results highlight that the hybrid model performs better than the conventional approach, proving the usefulness of hybrid models in the bwtp ph level prediction task. It may also be used in a related application to enhance ph prediction in other water treatment plants.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Shuvendu Pal Shuvo
AU  - Nasrin Sultana
AU  - M. Mubtasim Fuad Dip
AU  - Shirshendu Pal Shibazee
AU  - Sanjukta Sarker
PY  - 2024
DA  - 2024/07/23
TI  - Optimizing pH Prediction in Water Treatment Plant Through A Hybrid PSO-SVM Approach With Empirical Mode Decomposition
BT  - Proceedings of the 7th International Conference on Civil Engineering for Sustainable Development (ICCESD 2024)
PB  - Atlantis Press
SP  - 18
EP  - 31
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-478-5_3
DO  - 10.2991/978-94-6463-478-5_3
ID  - Shuvo2024
ER  -