Search Results

Accurately predicting real-world vehicle energy consumption is essential for optimizing vehicle designs, enhancing energy efficiency, and developing effective energy management strategies. This paper presents a data-driven approach that utilizes machine learning techniques and a comprehensive dataset of vehicle parameters and environmental factors to create precise energy consumption prediction models. The methodology involves recording real-world vehicle data using data loggers to extract information from the CAN bus systems for ICE and hybrid electric, as well as hydrogen and battery fuel cell vehicles. Data cleaning and cycle-based analysis are employed to process the dataset for accurate energy consumption prediction. This includes cycle detection and analysis using methods from statistics and signal processing, and then pattern recognition based on these metrics.

The effects of lubricant oil and fuel properties on low speed pre-ignition (LSPI) occurrence in boosted S.I. engines were experimentally evaluated with multi-cylinder engine and de-correlated oil and fuel matrices. Further, the auto-ignitability of fuel spray droplets and evaporated homogeneous fuel/oil mixtures were evaluated in a combustion bomb and pressure differential scanning calorimetry (PDSC) tests to analyze the fundamental ignition process. The work investigated the effect of engine conditions, fuel volatility and various lubricant additives on LSPI occurrence. The results support the validity of aspects of the LSPI mechanism hypothesis based on the phenomenon of droplets of lubricant oil/fuel mixture (caused by adhesion of fuel spray on the liner wall) flying into the chamber and autoigniting before spark ignition.