Kern, Peter
(2016)
Computational Intelligence Techniques for
Control and Optimization of
Wastewater Treatment Plants.
PhD thesis, National University of Ireland Maynooth.
Abstract
The development of novel, practice-oriented and reliable instrumentation and control strategies for
wastewater treatment plants in order to improve energy efficiency, while guaranteeing process stability and
maintenance of high cleaning capacity, has become a priority for WWTP operators due to increasing
treatment costs. To achieve these ambitious and even contradictory objectives, this thesis investigates a
combination of online measurement systems, computational intelligence and machine learning methods as
well as dynamic simulation models. Introducing the state-of-the-art in the fields of WWTP operation,
process monitoring and control, three novel computational intelligence enabled instrumentation, control
and automation (ICA) methods are developed and presented. Furthermore, their potential for practical
implementation is assessed. The methods are, on the one hand, the automated calibration of a simulation
model for the Rospe WWTP that provides a basis for the development and evaluation of the subsequent
methods, and on the other hand, the development of soft sensors for the WWTP inflow which estimate the
crucial process variables COD and NH4-N, and the estimation of WWTP operating states using Self-
Organising Maps (SOM) that are used to determine the optimal control parameters for each state. These
collectively, provide the basis for achieving comprehensive WWTP optimization. Results show that energy
consumption and cleaning capacity can be improved by more than 50%.
| Item Type: |
Thesis
(PhD)
|
| Keywords: |
Computational Intelligence Techniques; Control and Optimization; Wastewater Treatment Plants; |
| Academic Unit: |
Faculty of Science and Engineering > Electronic Engineering |
| Item ID: |
7586 |
| Depositing User: |
IR eTheses
|
| Date Deposited: |
27 Oct 2016 13:49 |
| URI: |
|
| Use Licence: |
This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available
here |
Repository Staff Only(login required)
 |
Item control page |
Downloads per month over past year
Origin of downloads
Altmetric
Altmetric