A5068935902- Fault Detection and Control Systems
- Spectroscopy and Chemometric Analyses
- Mineral Processing and Grinding
- Advanced Statistical Process Monitoring
- Reservoir Engineering and Simulation Methods
- Advanced Control Systems Optimization
- Oil and Gas Production Techniques
- Heavy Metal Exposure and Toxicity
- Reconstructive Surgery and Microvascular Techniques
- Surgical Simulation and Training
- Control Systems and Identification
- Surgical site infection prevention
- Cardiac, Anesthesia and Surgical Outcomes
- Water Systems and Optimization
- Neural Networks and Applications
- Arsenic contamination and mitigation
- Analytical chemistry methods development
- Anatomy and Medical Technology
- Neural Networks and Reservoir Computing
- Machine Fault Diagnosis Techniques
- Machine Learning and ELM
- Body Contouring and Surgery
University of Alberta
2016-2021
All India Institute of Medical Sciences
2013
In this brief, we propose the mixtures of probabilistic principal component analyzers with latent bases having a common structure for modeling and monitoring multimodal processes. The proposed framework attributes joint distribution to each element across all bringing consistent local models that correspond various operating modes. Hierarchical prior distributions are attributed regularize parameters obtaining sparse model structures. We employ variational Bayesian expectation-maximization...
In this paper, a hybrid model is proposed to simultaneously mine causal connections and features responsible for contemporaneous correlations in multivariate process. The developed by combining the vector auto-regressive exogenous factor analysis model. parameters of resulting are regularized using hierarchical prior distributions pruning insignificant/irrelevant ones from It then estimated under variational Bayesian expectation maximization framework. estimation initiated with complex which...
Data-driven causal modeling approaches find application in process data analysis and control. Process systems can be time-varying nature; however, the existing literature for data-driven hardly accounts this. In this article, we present a approach systems. It relies on parameter models (TVPMs), estimated under variational Bayesian expectation-maximization (VBEM) framework. We incorporate hypothesis switching procedure followed by estimation that allows us to infer strengths of influence...
Mixture of probabilistic principal component analyzers (MPPCA) has been used for modeling non-Gaussian process data and monitoring in the past. However, appropriate model structure selection case MPPCA is a challenging task. Previously, variational Bayesian expectation maximization (VBEM) estimation to handle this VBEM can be computationally expensive practical purposes also, may converge spurious estimates. In article, collapsed technique with new collapsing scheme as an alternative...
Electrical submersible pump (ESP) is one of the preferred artificial lift systems in upstream oil production because its wide operating range and endurance to harsh environments. In Alberta Canada, about two-thirds steam assisted gravity drainage (SAGD) wells are equipped with ESPs. Keeping ESPs long-term operational primary challenges faced by operators. ESP failures a common problem due various reasons, such as, conditions, improper installations, etc. Therefore, real-time monitoring...
The present study arose from the need of to determine inorganic arsenic (iAs) at low levels in rice. Ultra-high performance liquid chromatography coupled with inductively plasma mass spectrometry (UHPLC-ICPMS) using Kinetic Energy Discrimination (KED) mode eliminate spectral interferences was used for analysis iAs. Sample preparation involves extraction (sum As3+ and As5+) water by heating 90 °C 5 min bath. Separation is accomplished a reversed-phase ion pack column gradient chromatographic...
Steam assisted gravity drainage (SAGD) is a widely adopted oil extraction technique for heavy reservoirs in Alberta, Canada. One of the common approaches by which producers optimize production from SAGD controlling emulsion level above producer well bores, strategy known as subcool control within industry. In this study, we assess and compare performances two strategies, one makes use classic (PID) other advanced (model predictive controller (MPC)). As controlled process case non-linear...