Grant: Collaborative Research and Development Grants
University of Alberta
$43,950.00
Finding significant temporal and spatial patterns in industrial process data
FY 2012-13
Summary
Industrial processes, such as those found at Syncrude, generate vast amounts of temporal and spatial. This data is typically generated by sensors used in monitoring the processes in order to maintain safe, reliable operation within the designed envelope of operation. For example, power levels applied to shovel ropes during operation change with both different operators and different locations, or a complex oil extraction process, monitored in terms of flow rates, density, composition, temperature, etc.
In order to improve the processes in terms of reliability and efficiency we need to understand how to model the behaviour of the process. The ability to model these processes given historical data can lead to new insights into the process that allow for further process optimization or lead to the understanding and prediction of failure or process upsets.
In this proposal, we will first investigate how to represent measurement series as (spatial-)temporal sequences of events and develop data mining methods for finding ""significant"" temporal and spatial patterns that can help describe a process, detect and predict unusual events, as well as detect interactions between events.
Program
Collaborative Research and Development Grants
Recipient
Location
Alberta, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
412198-2011
Name nom
Sander, JËrg
Department département
Computing Science
Organization id
9
Institution établissement
University of Alberta
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2012
Competition year année de concours
2011
Award amount
43950
Program id
CRDPJ
Program name en
Collaborative Research and Development Grants
Program name fr
Subventions de recherche et développement coopérative
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
300
Area of application group en
Energy resources
Area of application group fr
Ressources d'énergie
Area of application en
Energy resources (including production, exploration, processing, distribution and use)
Area of application fr
Ressources d'énergie (production, exploration, traitement, distribution et utilisation de l'énergie)
Research subject code
2709
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Other computing methods
Research subject fr
Autres méthodes informatiques
Partie
2
Nb partie
2
Application title
Finding significant temporal and spatial patterns in industrial process data
Keyword
NSERC
Application summary
Industrial processes, such as those found at Syncrude, generate vast amounts of temporal and spatial. This data is typically generated by sensors used in monitoring the processes in order to maintain safe, reliable operation within the designed envelope of operation. For example, power levels applied to shovel ropes during operation change with both different operators and different locations, or a complex oil extraction process, monitored in terms of flow rates, density, composition, temperature, etc.
In order to improve the processes in terms of reliability and efficiency we need to understand how to model the behaviour of the process. The ability to model these processes given historical data can lead to new insights into the process that allow for further process optimization or lead to the understanding and prediction of failure or process upsets.
In this proposal, we will first investigate how to represent measurement series as (spatial-)temporal sequences of events and develop data mining methods for finding ""significant"" temporal and spatial patterns that can help describe a process, detect and predict unusual events, as well as detect interactions between events.