In this article, a stochastic gradient based online learning algorithm for Extreme Learning Machines (ELM) is developed (SG-ELM). A stability criterion based on Lyapunov approach is used to prove both asymptotic stability of estimation error and stability in the estimated parameters suitable for identification of nonlinear dynamic systems. The developed algorithm not only guarantees stability, ...

The alternative HCCI combustion mode presents a possible means for decreasing the pollution with respect to the conventional gasoline or diesel engines, while maintaining the efficiency of a diesel engine or even increasing it. This paper investigates the possibility of using gasoline in an HCCI engine and analyses the auto-ignition of gasoline in such an engine. The compression ratio that has ...

Modeling engines using physics-based approaches is a traditional and widely-accepted method for predicting in-cylinder pressure the start of combustion (SOC). However, developing such intricate models typically demands significant effort, time, knowledge about underlying physical processes. In contrast, machine learning techniques have demonstrated their potential building that are not only rap...

To characterize the ignition process in homogeneous charge compression ignition engines, high fidelity simulations are performed to study the effects of different initial temperature distributions on the autoignition of a turbulent homogeneous mixture at high pressure. The effects of the initial temperature distribution on the ignition and subsequent heat release are studied by comparison of si...