Abstract
With the exponential growth in data collection and storage and the necessity for timely prognostic health monitoring of industrial processes traditional methods of data analysis are becoming redundant. Big data sets and huge volumes of inputs give rise to equally massive computational requirements. In this paper the differences in input parameter selection using a subset of the original variables and using data reduction techniques are compared. Each selection procedure being illustrated by both statistical methods and machine learning techniques. It is shown that the subsequent classification models are highly comparable. Finally the merits of a combined multivariate statistical and wavelet decomposition approach is considered. Techniques are applied to output signals from an experimental compressor rig.
Original language | English |
---|---|
Title of host publication | Proceedings of 2016 7th International Conference on Mechanical and Aerospace Engineering, ICMAE 2016 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 196-201 |
Number of pages | 6 |
ISBN (Electronic) | 9781467388290 |
DOIs | |
Publication status | Published - 23 Aug 2016 |
Event | 7th International Conference on Mechanical and Aerospace Engineering - London, United Kingdom Duration: 18 Jul 2016 → 20 Jul 2016 Conference number: 7 |
Conference
Conference | 7th International Conference on Mechanical and Aerospace Engineering |
---|---|
Abbreviated title | ICMAE 2016 |
Country/Territory | United Kingdom |
City | London |
Period | 18/07/16 → 20/07/16 |
Fingerprint
Dive into the research topics of 'Maintaining model efficiency, avoiding bias and reducing input parameter volume in compressor fault classification'. Together they form a unique fingerprint.Profiles
-
Ann Smith
- Department of Computer Science - Senior Lecturer - Maths
- Centre for Efficiency and Performance Engineering - Member
- Centre for Autonomous and Intelligent Systems - Member
Person: Academic