Revolution Control for Diesel Engines by Neural Networks

2004-01-1361

03/08/2004

Event
SAE 2004 World Congress & Exhibition
Authors Abstract
Content
The performance of various types of control systems for an electric governor of a diesel engine was examined. The amount of fuel injection of a diesel engine is usually controlled by an electric governor system in these decades, and a PID controller is installed for the electric governor. Even when the optimal parameters for PID controller are well tuned, it is difficult to keep constant rotation speed of the engine, because the applied load to generators may vary according to its running conditions. In this study, a neural network was applied to regulate the parameters in the PID controller for the axial-moving DC motor to control the amount of fuel injection. Experimental studies show that the parameter regulation system using neural network presented here showed good performance under various running conditions. Furthermore, it was shown that various types of training algorithms were applied to neural network control systems and their performance was compared.
Meta TagsDetails
DOI
https://doi.org/10.4271/2004-01-1361
Pages
8
Citation
Mitsuhashi, K., Tsuchiya, T., Morishita, S., Shiraishi, T. et al., "Revolution Control for Diesel Engines by Neural Networks," SAE Technical Paper 2004-01-1361, 2004, https://doi.org/10.4271/2004-01-1361.
Additional Details
Publisher
Published
Mar 8, 2004
Product Code
2004-01-1361
Content Type
Technical Paper
Language
English