Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Collaborative Research and Development Grants

McMaster University

$12,800.00

A hybrid modeling, monitoring and control approach for wastewater treatment plants

FY 2019-20

Summary
Wastewater treatment plants are currently designed using fairly detailed first principles models that are able to capture the dominant dynamics of the process, but not necessarily predict the variables very accurately. The calibration of these models for a new plant site remains a significant challenge. The lack of precise models means that reliable monitoring and optimum operation of these plants is not readily achieved. Plant operation data is becoming increasingly more available, and efforts have been made to use completely data driven approaches to model the plant behaviour. The lack of first principles information in the data driven approaches, however, makes the data driven models susceptible to overfitting and not amenable to extrapolation. Motivated by these considerations, the present proposal will develop hybrid models that seamlessly synergies data driven approaches with first principles models in a way to leverage the information present in the first principles model. This project is a followup to a successful engage grant where a proof of concept for the proposed idea was demonstrated. The present proposal will build on that with real case studies, and generalize to significantly expanded applications of monitoring and feedback control. The direct benefit to the industrial partner Hydromantis is an immensely broadened clientele. Given the broad nature of the tool being developed, additional benefit to Canadian economy will be realized through adaptation of the approach to a broad ranges of production facilities ranging from petrochemicals to pharmaceuticals to steel manufacturing.
Program
Collaborative Research and Development Grants
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
538117-2018
Name nom
Mhaskar, Prashant
Department département
Chemical Engineering
Organization id
27
Institution établissement
McMaster University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2019
Competition year année de concours
2018
Award amount
12800
Program id
CRDPJ
Program name en
Collaborative Research and Development Grants
Program name fr
Subventions de recherche et développement coopérative
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
702
Area of application group en
Transportation systems and services
Area of application group fr
Services et systèmes de transport
Area of application en
Water
Area of application fr
Maritime
Research subject code
1800
Research subject group en
Chemical engineering
Research subject group fr
Génie chimique
Research subject en
Chemical engineering
Research subject fr
Génie chimique
Installment
inst:1 - 1
Partie
1
Nb partie
1
Application title
A hybrid modeling, monitoring and control approach for wastewater treatment plants
Keyword
NSERC
Application summary
Wastewater treatment plants are currently designed using fairly detailed first principles models that are able to capture the dominant dynamics of the process, but not necessarily predict the variables very accurately. The calibration of these models for a new plant site remains a significant challenge. The lack of precise models means that reliable monitoring and optimum operation of these plants is not readily achieved. Plant operation data is becoming increasingly more available, and efforts have been made to use completely data driven approaches to model the plant behaviour. The lack of first principles information in the data driven approaches, however, makes the data driven models susceptible to overfitting and not amenable to extrapolation. Motivated by these considerations, the present proposal will develop hybrid models that seamlessly synergies data driven approaches with first principles models in a way to leverage the information present in the first principles model. This project is a followup to a successful engage grant where a proof of concept for the proposed idea was demonstrated. The present proposal will build on that with real case studies, and generalize to significantly expanded applications of monitoring and feedback control. The direct benefit to the industrial partner Hydromantis is an immensely broadened clientele. Given the broad nature of the tool being developed, additional benefit to Canadian economy will be realized through adaptation of the approach to a broad ranges of production facilities ranging from petrochemicals to pharmaceuticals to steel manufacturing.