Model predictive engine air-ratio control using online sequential extreme learning machine

摘要: Air-ratio is an important engine parameter that relates closely to emissions, power, and brake-specific fuel consumption. Model predictive controller (MPC) a well-known technique for air-ratio control. This paper utilizes advanced modelling technique, called online sequential extreme learning machine (OSELM), develop MPC (OEMPC) regulation according various loads. The proposed OEMPC was implemented on real verify its effectiveness. Its control performance also compared with the latest control, namely diagonal recurrent neural network MPC, conventional proportional---integral---derivative (PID) controller. Experimental results show superiority of over other two controllers, which can more effectively regulate specific target values under external disturbance. Therefore, promising scheme replace PID