A. Roubaud**, V. Mahulkar, P. Leyland and D. Favrat Laboratory for Industrial Energy systems, Swiss Federal Institute of Technology of Lausanne, Switzerland J.B. Vos CFS engineering, Scientific Park, Lausanne, Switzerland Abstract This paper deals with the simulation of HCCI combustion based on a generic rapid compression machine experiment as a test bed, and using a coupled CFD code-chemical k...

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...

High Chromium Cast Iron (HCCI) is mostly utilised in environments under severe abrasion and corrosion wear conditions, research on this material with added niobium obtained positive results regarding resistance. The casting process has surface finish dimensional accuracy limitations compared to machining processes. There are too few studies about HCCI machinability no one additions. may allow n...

We propose a model based control strategy to adapt the injection settings according to the air path dynamics on a Diesel HCCI engine. This approach complements existing airpath and fuelpath controllers, and aims at accurately controlling the start of combustion. For that purpose, start of injection is adjusted based on a Knock Integral Model and intake manifold conditions. Experimental results ...

Three-dimensional imaging of fuel tracer planar laser-induced fluorescence in a homogeneous charge compression ignition (HCCI) engine is presented. A high-speed multiple Nd:YAG laser and detection system, in combination with a scanning mirror, are used to collect eight images, with an equidistant separation of 0.5 mm. Three-dimensional isoconcentration surfaces calculated from the data are visu...

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, ...