0
Research Papers

Assessment of Charge-Air Cooler Health in Diesel Engines Using Nonlinear Time Series Analysis of Intake Manifold Temperature

[+] Author and Article Information
Alok A. Joshi1

 Cummins Inc., 1900 McKinley Avenue, MC 50174, Columbus, IN 47201alok.a.joshi@cummins.com

Scott James, Peter Meckl, Galen King

Ray W. Herrick Laboratories, School of Mechanical Engineering, Purdue University, West Lafayette, IN 47907-2031

Kristofer Jennings

Department of Statistics, College of Science, Purdue University, West Lafayette, IN 47907-2067

1

Corresponding author.

J. Dyn. Sys., Meas., Control 131(4), 041009 (May 18, 2009) (11 pages) doi:10.1115/1.3023142 History: Received June 20, 2007; Revised August 24, 2008; Published May 18, 2009

Degradation in the cooling effectiveness of a charge-air cooler (CAC) in a medium-duty turbocharged diesel engine has significant impact on engine performance. This degradation lowers the boost pressure and raises the intake manifold temperature. As a result, the engine provides lower horsepower and higher hydrocarbon levels than the rated values. The objective of this research is to monitor the health of the charge-air cooler by analyzing the intake manifold temperature signal. Experiments were performed on a Cummins ISB series turbocharged diesel engine, a 6-cylinder inline configuration with a 5.9 l displacement volume. Air flowing over the cooler was blocked by varying amounts, while various engine temperatures and pressures were monitored at different torque-speed conditions. Similarly, data were acquired without the introduction of any fault in the engine. For the construction of the manifold temperature trajectory vector, average mutual information estimates and a global false nearest neighbor analysis were used to find the optimal time parameter and embedding dimensions, respectively. The prediction of the healthy temperature vector was done by local linear regression using torque, speed, and their interaction as exogenous variables. Analysis of residuals generated by comparing the predicted healthy temperature vector and the observed temperature vector was successful in detecting the degradation of the charge-air cooler. This degradation was quantified by using box plots and probability density functions of residuals generated by comparing intake manifold temperature of healthy and faulty charge-air coolers. The general applicability of the model was demonstrated by successfully diagnosing a fault in the exhaust gas recirculation cooler of a different engine.

FIGURES IN THIS ARTICLE
<>
Copyright © 2009 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

Communication system for the engine setup in the laboratory

Grahic Jump Location
Figure 2

Experimental setup for monitoring charge-air cooler health

Grahic Jump Location
Figure 3

Schematic of intake-air handling system

Grahic Jump Location
Figure 4

Sensor readings retrieved from the engine control module. Sample interval τs=200 ms.

Grahic Jump Location
Figure 5

Average mutual information plotted as a function of delay units, both on the log-log scale

Grahic Jump Location
Figure 6

Time series for intake manifold temperature sampled at τs=200 ms and a time series derived using a factor of k=20 for data set h1

Grahic Jump Location
Figure 7

Percentage of global false nearest neighbors plotted as a function of increasing embedding dimension for intake manifold temperature using different test data sets

Grahic Jump Location
Figure 8

Solid line in upper row of figures is actual intake manifold temperature measurement and dashed line is the response of local linear regression model predicting healthy signal behavior when the ISB 1998 engine and the model are driven by the same torque-speed points defined by modified AVL-8 test-cycle. The lower row of figures shows residuals generated by comparing actual signal and predicted healthy signal by the solid line and the dotted lines indicate median, tenth, and ninetieth percentile for the residuals. (a) Engine without fault (train data—h1, h2, h6, and test data—h3). (b) Engine with grade-3 CAC fault (train data—h1, h2, h6, and test data—f3).

Grahic Jump Location
Figure 9

Box plots of intake manifold temperature residuals for various data sets used for training and testing the state of CAC health

Grahic Jump Location
Figure 10

Probability density function estimates for intake manifold temperature residuals to evaluate the state of charge-air cooler

Grahic Jump Location
Figure 11

Solid line in upper row of figures is actual intake manifold temperature measurement and dashed line is the response of local linear regression model predicting healthy signal behavior when ISB 2007 engine and the model are driven by the same torque-speed points defined by SET drive cycle. The lower row of figures shows residuals generated by comparing actual signal and predicted healthy signal by the solid line and the dotted lines indicate median, tenth, and ninetieth percentile for the residuals. (a) Engine with fault. (b) Engine with 40% restriction in the coolant path of EGR cooler.

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In