This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Advanced Engine Diagnostics Using Universal Process Modeling
Annotation ability available
Sector:
Language:
English
Abstract
There are many benefits in monitoring the health of an internal combustion engine, whether it be a spark-ignition, compression-ignition, or gas turbine. These benefits include detecting faulty or failing engine sensors and detecting subtle problems which could, if left undetected, cause serious engine damage. While there are many benefits to monitoring engine health, the challenge becomes how to determine if an engine is healthy or not.
Universal Process Modeling (UPM) is a new and unique multivariate modeling technique which can accurately determine the health of complex equipment such as an internal combustion engine. UPM is an inductive technique which uses a reference library of example data to describe how an engine normally operates. UPM calculates an overall “system” health and the health of each variable monitored. The healths are expressed in how many standard deviations they are away from their expected values. Engine-related problems are revealed when the system health falls outside a statistical limit. Insight into the nature of the problem may be gained by examining those variables which have deviated the most from their expected values. This paper discusses the features and benefits of UPM and describes its application to advanced engine diagnostics.
Authors
Topic
Citation
O'Sullivan, P., "Advanced Engine Diagnostics Using Universal Process Modeling," SAE Technical Paper 961706, 1996, https://doi.org/10.4271/961706.Also In
References
- Arnolds, S. 1981 “The Theory of Linear Models and Multivariate Analysis” John Wiley & Sons New York, NY
- Box, G. E. P. Hunter, J. S. 1987 “Empirical Model Building and Response Surfaces” John Wiley & Sons New York, NY
- Flury, B. Dayal, B. S. MacGregor, J. F. Taylor, P. A. Kildaw, R. Marcikic, S. “Application of Feedforward Neural Networks and Partial Least Squares Regression for Modelling Kappa Number in a Continuous Kamyr Digester” Pulp and Paper Canada 95 1 1994
- Riedwyl, H. 1988 “Multivariate Statistics: A Practical Approach” Chapman and Hall New York, NY
- MacGregor, J. F. Jaeckle, C. Kiparissides, C. Koutoudi, M. “Process Monitoring and Diagnosis by Multiblock PLS Methods” AIChE Journal May 1994
- Milliken, G. A. Johnson, D. E. 1992 “Analysis of Messy Data: Volume 1” Chapman and Hall New York, NY
- Murphy, B. 1978 “Selecting Out of Control Variables with the T 2 Multivariate Quality Control Procedure” The Statistician 36 571 582
- O'Sullivan, P. J. “Application of a New Technique for Modeling System Behavior” ISA Symposium Proceedings Edmonton May 1991