The Fault Diagnosis of Bora Engine CH Emissions based on Neural network

Tie Wang

Abstract


Along with an increase of the automobile possession quantity, the air pollution caused by the pollutant of the automobile emissions is serious day by day. The emission diagnosis become the important technology for guaranteeing the human sustainable development. The article introduces the reasons of CH excessive emissions in vehicle discharge of pollutants, the impact which CH excessive emissions have on our environment, expounds the advantages of SOM neural network and BP neural network, briefly describes why these two tools are applied to the project. In the article, diagnostic procedures are written by MATLAB software, parameters are analyzed which influence CH emission of a particular model engine. In the article, Volkswagen Bora acts as experimental models, the data stream is extracted, then the data are classified, trained and operated, the diagnostic results and diagnostic accuracy are finally obtained. Through SOM, the accuracy rate of fault sample data diagnostic is 73.3% and BP is 65.1%. The results of sample show that: SOM neural network can quickly and accurately diagnose the reasons of the CH excessive emissions in vehicle discharge of pollutants.

 

DOI: http://dx.doi.org/10.11591/telkomnika.v10i8.1702


Full Text:

PDF
Total views : 39 times

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

shopify stats IJEECS visitor statistics