Grants and Contributions:

Back to search

Title:

Clustering and dimensionality reduction based techniques for low latency big data feature extraction applications

Agreement Number:

EGP

Agreement Value:

$25,000.00

Agreement Date:

Mar 7, 2018 -

Organization:

Natural Sciences and Engineering Research Council of Canada

Location:

Saskatchewan, CA

Reference Number:

GC-2017-Q4-00035

Agreement Type:

Grant

Report Type:

Grants and Contributions

Additional Information:

Grant or Award spanning more than one fiscal year (2017-2018 to 2018-2019).

Recipient's Legal Name:

Al-Anbagi, Irfan (University of Regina)

Program:

Engage Grants for universities

Program Purpose:

The Mercedes-Benz Fuel Cell Division (MBFC) in Burnaby, Canada develops and runs the manufacturingx000D
processes required for the assembly of Fuel Cell Stack prototypes. MBFC uses the Manufacturing Executionx000D
System (MES) to collect and analyze data from the manufacturing lines to the database system. The size of thex000D
collected data is very high and MBFC is not able to detect certain fuel cell defects in a timely manner.x000D
This Engage grant project aims to develop and evaluate a mechanism that reduces the time taken to search thex000D
Mercedes-Benz Fuel Cell (MBFC's) big data and detect a failure in the manufacturing process in a real-timex000D
fashion. This will be done by critically studying and understanding MBFC's database schema and analysing ax000D
graph version of this database. A dimensionality reduction and feature extraction mechanism will be developedx000D
to search a specific cluster of the MBFC big data set and identify defective fuel cells using the Gas Diffusionx000D
Layer (GDL) bleed through method. Finally, a mechanism will be proposed to detect defective fuel cells in ax000D
total data dump scenario.x000D
The proposed research is innovative because it will devise a novel real-time big data feature extractionx000D
technique that combines a low latency and high efficiency dimensionality reduction technique with a clusteringx000D
graph-based database mechanism. Potential pitfalls and risks will be identified, mitigated and managed throughx000D
enhanced research methodologies, using diverse dimensionality reduction models and providing alternativex000D
approaches to detect features in big data.x000D
MBFC will be involved in the project by providing technical support, consultation and advice on issuesx000D
related to their database schema, Manufacturing Execution Systems (MES) interface and their GDL bleedx000D
through testing processes. This research will enable MBFC to establish a presence in fuel cell manufacturingx000D
and help establish Canada as a global leader in innovative green technologies.