An Effective Strategy on Anomaly Monitoring of Oil Quality in Heavy-Duty Diesel Engine

Yong Dong Zhao; Wen Zhu Zhao; Xian Cheng Wang; Mu He

doi:10.4028/www.scientific.net/AMM.543-547.1078

Paper Titles

Study of Intelligent Fault Diagnosis Method for Turbo-Generator Unit Based on Support Vector Machine and Knowledge
p.1057

The Application of BP Neural Network in Diagnosing the Short Circuit Fault of Winding
p.1064

Research and Application on Fault Diagnosis for Steam Turbine Using Multi-Parameter Fusion
p.1068

Data Fusion in Environment Monitoring Systems with Extended Dempster-Shafer Theory
p.1074

An Effective Strategy on Anomaly Monitoring of Oil Quality in Heavy-Duty Diesel Engine
p.1078

Fault Diagnosis of Gearbox Based on Information Fusion Technique
p.1083

Auto-Detecting System for Circulating Tumor Cells Based on LabView
p.1087

FTA-Based Reliability Measurement with Support of TRA
p.1091

Applying Simulation to Equipment Test and Evaluation
p.1095

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 543-547An Effective Strategy on Anomaly Monitoring of Oil...

An Effective Strategy on Anomaly Monitoring of Oil Quality in Heavy-Duty Diesel Engine

Abstract:

When the engine is working, the oil may be mixed with diesel once there isnt any burning diesel flowing into the crank case or there is a diesel leak in the joint of the oil atomizer and the high-pressure oil pipe. Once it happens, the oil degradation will appear, which can cause serious accidents such as drawing cylinder and tile burning when it appears to be severe. At the present moment, the quality of oil in the real vehicle cant be monitored. In this paper, a model used to monitor the quality of the oil was built by means of matching experiment, which took advantage of the neural network. Through the test of the real vehicle, it came to a conclusion that the mode could monitor the viscosity of the oil in real time and accurately calculate the volume fraction of diesel that is mixed into the oil, which could provide an effective means for the replacement of oil.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 543-547)

Pages:

1078-1082

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.543-547.1078

Citation:

Cite this paper

Online since:

March 2014

Authors:

Yong Dong Zhao*, Wen Zhu Zhao, Xian Cheng Wang, Mu He

Keywords:

Anomaly Monitoring, Heavy-Duty Diesel Engine, Neural Network (NN), Oil Quality

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Z. Defeng. Matlab Neural Network Application Design [M]. Beijing: China Machine Press, pp.171-180, (2011).

Google Scholar

[2] Z. Gengyun, F. Licheng. Diesel Engine Oil Quality Monitoring Based on Viscosity and Dielectric Constant [J]. Journal of Academy of Armored Force Engineering, Vol. 26, pp.30-33, (2012).

Google Scholar

[3] Bishop C M. Neural Networks for Pattern Recognition [M]. Oxford Clarendon Press, pp.118-123, (1995).

Google Scholar

[4] Z. Xu. Engine Oil Degradation and Its Law [J]. Industry Technology, Vol. 11, pp.127-128, (2009).

Google Scholar

[5] G. Changjun. Reasons for Diesel Engine Oil Degradation and Its Testing Means [J]. Friends of Agricultural Implements, Vol. 7, pp.22-23, (2005).

Google Scholar

[6] M. Fukang. Analysis of Diesel Engine Oil Dilution Reasons and Its Guard Methods [J]. Modern Vehicle Power, Vol. 2, pp.39-42, (2008).

Google Scholar

[7] He. Fengqin. Oil Quality Testing Design Based on Oil Viscosity [J]. Journal of Shanghai Normal University, Vol. 38, pp.626-629, June (2009).

Google Scholar

[8] G. Juan. Artificial Neural Network Principle and Simulation Examples [M], Beijing: China Machine Press, pp.155-160, (2003).

Google Scholar