Přístupnostní navigace
E-application
Search Search Close
Bachelor's Thesis
Author of thesis: Bc. Jan Kočařík
Acad. year: 2025/2026
Supervisor: Ing. Dominik Řičánek
Reviewer: Ing. Tomáš Zemčík
This bachelor’s thesis deals with the design, implementation, and evaluation of regression models functioning as soft sensors in the biological stage of wastewater treatment plants. The main objective is the prediction of technological variables based on real operational data from the experimental SBR reactor of the Brno-Modřice wastewater treatment plant and the comparison of the performance of three regression methods: linear regression, ridge regression, and polynomial regression. The thesis provides a detailed discussion of the process of feature space transformation for capturing nonlinear relationships, optimization of regression method selection for parameters affected by multicollinearity, and the impact of integrating delayed variables. Significant attention is devoted to testing the models in two distinct operational modes — offline prediction mode and autonomous real-time online prediction mode. The achieved results demonstrate that, in offline mode, polynomial regression achieves high accuracy in estimating dissolved oxygen concentration, oxidation-reduction potential, and nitrogen species. The thesis also addresses the limitations and implementation of the aforementioned regression methods and their mutual comparison in the simulation of online deployment. In this mode, the regression methods achieve high accuracy in predicting dissolved oxygen concentration, oxidation-reduction potential, liquid level in the accumulation tank, and airflow rate into the bioreactor. The thesis also contains a proposition of soft-sensor networks capable of compensating for failures of physical probes or directly replacing them for economic reasons while maintaining monitoring quality.
Wastewater treatment plant, SBR reactor, soft-sensor, linear regression, ridge regression, polynomial regression, online prediction, time-lagged variables.
Date of defence
17.06.2026
Result of the defence
Defended (thesis was successfully defended)
Grading
B
Process of defence
Student obhájil bakalářskou práci. Komise neměla žádné námitky k řešené práci. V průběhu odborné rozpravy student odpověděl na dotazy oponenta. Navazující otázka komise směřovala k naměřenémým a využitým datasetům. Proč byla v dodaných měřených datech perioda vzorkování 60,5 s? Probíhá v práci samotná predikce koncentrace látek nebo je to spíše myšleno jako virtuální snímač? Student odpověděl na položené otázky komise.
Language of thesis
Czech
Faculty
Fakulta elektrotechniky a komunikačních technologií
Department
Department of Control and Instrumentation
Study programme
Automation and Measurement (BPC-AMT)
Composition of Committee
doc. Ing. Jan Mikulka, Ph.D. (předseda) doc. Ing. Petr Blaha, Ph.D. (místopředseda) Ing. Ilona Janáková, Ph.D. (člen) Ing. Lukáš Kopečný, Ph.D. (člen) Ing. Tomáš Macho, Ph.D. (člen) Ing. Soňa Šedivá, Ph.D. (člen)
Supervisor’s reportIng. Dominik Řičánek
Grade proposed by supervisor: A
Reviewer’s reportIng. Tomáš Zemčík
Grade proposed by reviewer: C
Responsibility: Mgr. et Mgr. Hana Odstrčilová