Automatic reactor model synthesis with genetic programming

Abstract

Successful modeling of wastewater treatment plant (WWTP) processes requires an accurate description of the plant hydraulics. Common methods such as tracer experiments are difficult and costly and thus have limited applicability in practice; engineers are often forced to rely on their experience only. An implementation of grammar-based genetic programming with an encoding to represent hydraulic reactor models as program trees should fill this gap: The encoding enables the algorithm to construct arbitrary reactor models compatible with common software used for WWTP modeling by linking building blocks, such as continuous stirred-tank reactors. Discharge measurements and influent and effluent concentrations are the only required inputs. As shown in a synthetic example, the technique can be used to identify a set of reactor models that perform equally well. Instead of being guided by experience, the most suitable model can now be chosen by the engineer from the set. In a second example, temperature measurements at the influent and effluent of a primary clarifier are used to generate a reactor model. A virtual tracer experiment performed on the reactor model has good agreement with a tracer experiment performed on-site.

Three-Dimensional Modeling of Hydrodynamics and Biokinetics in EGSB Reactor

“…Then, by the application of activated sludge models to each ideal reactor, effluent quality of a modeled reactor can be obtained. However, the construction of the hydrodynamic model is difficult and relies on experience [20]. Hydrodynamic models regarding anaerobic granular based reactors are much more complex than those regarding aerobic bioreactors [21], which makes modeling anaerobic bioreactors difficult.…”

Modelling of sequencing batch reactor operating at various aeration modes

“…Currently, specialist simulation tools and computer modelling software are a key factor for planning technological changes in WWTPs. It is argued that in the future, the operation of each WWTP will depend on them [1][2][3][4][5]. They enable to gain insights for devices that undergo dynamic changes; thus, the limits and static values taken into account at the designing stage are significantly expanded.…”