This decommissioned ERA site remains active temporarily to support our final migration steps to https://ualberta.scholaris.ca, ERA's new home. All new collections and items, including Spring 2025 theses, are at that site. For assistance, please contact erahelp@ualberta.ca.
Search
Skip to Search Results- 6Process Control
- 3Machine Learning
- 2Reinforcement Learning
- 1Data-driven
- 1Distributed Parameter Systems
- 1Dynamic tuning
-
Data-driven development of advanced controllers for complex reaction systems with minimal prior information
DownloadFall 2024
In the realm of complex reactive systems where full knowledge of ongoing reactions is unattainable, the adoption of data-driven inferential models based on mixture spectra has gained significant traction. Spectra-based online monitoring has shown promise due to the rapidity, non-invasiveness,...
-
Spring 2010
In this thesis, a Reinforcement Learning (RL) method called Sarsa is used to dynamically tune a PI-controller for a Continuous Stirred Tank Heater (CSTH) experimental setup. The proposed approach uses an approximate model to train the RL agent in the simulation environment before implementation...
-
Spring 2024
Advanced process control has been considered as a promising tool for addressing various control objectives for complex industrial applications, including ensuring safe operation, reducing operational cost, improving process efficiency, achieving more environmentally friendly practices, etc....
-
From Continuous Modelling to Discrete Constrained Optimal Control of Distributed Parameter Systems
DownloadSpring 2022
Distributed parameter systems (DPS) are systems that have their evolution through time and in space. These systems are present in every type of industrial process, from chemical to electrical applications. Thus, proper modeling and control of DPS are indispensable for the optimization and control...
-
Monitoring of Industrial Processes via Non-stationary Probabilistic Slow Feature Analysis Machine Learning Algorithm
DownloadSpring 2020
This research develops a first of its kind machine learning (ML) algorithm, called probabilistic slow feature analysis (PSFA), that monitors and detects faults for non-stationary industrial processes. The novelty of this ML algorithm is that it can monitor and detect faults for non-stationary...
-
Spring 2020
Reinforcement learning (RL) has received wide attention in various fields lately. Model-free RL brings data-driven solutions that learn the control strategy directly from interaction with process data without the need for a process model. This is especially beneficial in the case of nonlinear...