Because of its high NOx reduction efficiency, selective catalyst reduction (SCR) has become an indispensable part of diesel vehicle aftertreatment. This paper presents a control strategy for SCR systems that is based on an on-line radial basis function neural network (RBFNN) and an on-line backpropagation neural network (BPNN). In this control structure, the radial basis function neural network is employed as an estimator to provide Jacobian information for the controller; and the backpropagation neural network is utilized as a controller, which dictates the appropriate urea-solution to be injected into the SCR system. This design is tested by simulations based in Gamma Technologies software (GT-ISE) as well as MATLAB Simulink. The results show that the RBF-BPNN control technique achieves a 1–5 % higher NOx reduction efficiency than a PID controller.
- Dynamic Systems and Control Division
SCR Control System Design Based on On-Line Radial Basis Function and Backpropagation Neural Networks
Sui, W, & Hall, CM. "SCR Control System Design Based on On-Line Radial Basis Function and Backpropagation Neural Networks." Proceedings of the ASME 2017 Dynamic Systems and Control Conference. Volume 3: Vibration in Mechanical Systems; Modeling and Validation; Dynamic Systems and Control Education; Vibrations and Control of Systems; Modeling and Estimation for Vehicle Safety and Integrity; Modeling and Control of IC Engines and Aftertreatment Systems; Unmanned Aerial Vehicles (UAVs) and Their Applications; Dynamics and Control of Renewable Energy Systems; Energy Harvesting; Control of Smart Buildings and Microgrids; Energy Systems. Tysons, Virginia, USA. October 11–13, 2017. V003T34A002. ASME. https://doi.org/10.1115/DSCC2017-5095
Download citation file: