Search Results

SAE 2011 High Efficiency IC Engines Symposium - Session 1- Pathways to High Efficiency Presenter Rolf D. Reitz, Univ. of Wisconsin

The fatty acid methyl esters (FAME's) - in Europe mostly RME (Rapeseed methyl ester) - are used in several countries as alternative biogene Diesel fuels in various blending ratios with fossil fuels (Bxx). Questions often arise about the influences of these biocomponents on the modern exhaust aftertreatment systems and especially on the regeneration of Diesel particle filters (DPF). In the present work different regeneration procedures of DPF systems were investigated with biofuels B0, B20 & B100. The tested regeneration procedures were: passive regenerations: DOC + CSF; CSF alone, active regenerations: standstill burner; fuel injections & DOC. During each regeneration on-line measurements of regulated and unregulated emission components (nanoparticles & FTIR) were conducted. It can be stated that the increased portion of RME in fuel provokes longer time periods to charge the filter with soot.

The 14 papers in this technical paper collection discuss high efficiency IC engines. Topics covered include engine downsizing, pressure boosting and turbocharging, intelligent combustion, low temperature and stratified charge, advanced fuel injection technologies, and more. The 15 papers in this technical paper collection discuss high efficiency IC engines. Topics covered include engine downsizing, pressure boosting and turbocharging, intelligent combustion, low temperature and stratified charge, advanced fuel injection technologies, and more.

The 25 papers in this technical paper collection focus on fuel injection and sprays. Topics covered include spray characterization, cavitation, multi-phase jet modeling, CFD models for spray processes, wall films and impingement, hydraulic circuit analysis, dissolved gas effects, and more. The 25 papers in this technical paper collection focus on fuel injection and sprays. Topics covered include spray characterization, cavitation, multi-phase jet modeling, CFD models for spray processes, wall films and impingement, hydraulic circuit analysis, dissolved gas effects, and more.

The 8 technical papers in this collection are devoted to experimental and computational work in the area of fuel injection systems and sprays. Topics include: spray characterization, cavitation, multi-phase jet modeling, CFD models for spray processes, wall films and impingement, hydraulic circuit analysis, and dissolved gas effects. Studies of gasoline, diesel and alternative fuel sprays and fuel injection equipment are encouraged.

This technical paper collection is devoted to experimental and computational work in the area of fuel injection systems and sprays. Topics include: spray characterization, cavitation, multi-phase jet modeling, CFD models for spray processes, wall films and impingement, hydraulic circuit analysis, and dissolved gas effects.

This technical paper collection is devoted to experimental and computational work in the area of fuel injection systems and sprays. Topics include: spray characterization, cavitation, multi-phase jet modeling, CFD models for spray processes, wall films and impingement, hydraulic circuit analysis, and dissolved gas effects

This technical paper collection is devoted to experimental and computational work in the area of fuel injection systems and sprays. Topics include: spray characterization, cavitation, multi-phase jet modeling, CFD models for spray processes, wall films and impingement, hydraulic circuit analysis, and dissolved gas effects.

This collection is devoted to experimental and computational work in the area of fuel injection systems and sprays. Topics include: spray characterization, cavitation, multi-phase jet modeling, CFD models for spray processes, wall films and impingement, hydraulic circuit analysis, and dissolved gas effects.

This collection is devoted to experimental and computational work in the area of fuel injection systems and sprays. Topics include: spray characterization, cavitation, multi-phase jet modeling, CFD models for spray processes, wall films and impingement, hydraulic circuit analysis, and dissolved gas effects.

Abstract Lane changes are stressful maneuvers for drivers, particularly during high-speed traffic flows. However, modeling driver’s lane-changing decision and implementation process is challenging due to the complexity and uncertainty of driving behaviors. To address this issue, this article presents a personalized Lane-Changing Model (LCM) for Advanced Driver Assistance System (ADAS) based on deep learning method. The LCM contains three major computational components. Firstly, with abundant inputs of Root Residual Network (Root-ResNet), LCM is able to exploit more local information from the front view video data. Secondly, the LCM has an ability of learning the global spatial-temporal information via Temporal Modeling Blocks (TMBs). Finally, a two-layer Long Short-Term Memory (LSTM) network is used to learn video contextual features combined with lane boundary based distance features in lane change events.

Abstract Gasoline particulate filters (GPFs) are important aftertreatment components that enable gasoline direct injection (GDI) engines to meet European Union (EU) 6 and China 6 particulate number emissions regulations for nonvolatile particles greater than 23 nm in diameter. GPFs are rapidly becoming an integral part of the modern GDI aftertreatment system. The Active Exhaust Tuning (EXTUN) Valve is a butterfly valve placed in the tailpipe of an exhaust system that can be electronically positioned to control exhaust noise levels (decibels) under various vehicle operating conditions. This device is positioned downstream of the GPF, and variations in the tuning valve position can impact exhaust backpressures, making it difficult to monitor soot/ash accumulation or detect damage/removal of the GPF substrate. The purpose of this work is to present a unique example of subsystem control and diagnostic architecture for an exhaust system combining GPF and EXTUN.

Abstract Real-time reconstruction of 3D environment attributed with semantic information is significant for a variety of applications, such as obstacle detection, traffic scene comprehension and autonomous navigation. The current approaches to achieve it are mainly using stereo vision, Structure from Motion (SfM) or mobile LiDAR sensors. Each of these approaches has its own limitation, stereo vision has high computational cost, SfM needs accurate calibration between a sequences of images, and the onboard LiDAR sensor can only provide sparse points without color information. This paper describes a novel method for traffic scene semantic segmentation by combining sparse LiDAR point cloud (e.g. from Velodyne scans), with monocular color image. The key novelty of the method is the semantic coupling of stereoscopic point cloud with color lattice from camera image labelled through a Convolutional Neural Network (CNN).

Abstract More than a decade ago, we proposed combined use of direct injection (DI) and jet ignition (JI) to produce high efficiency, high power-density, positive-ignition (PI), lean burn stratified, internal combustion engines (ICEs). Adopting this concept, the latest FIA F1 engines, which are electrically assisted, turbocharged, directly injected, jet ignited, gasoline engines and work lean stratified in a highly boosted environment, have delivered peak power fuel conversion efficiencies well above 46%, with specific power densities more than 340 kW/liter. The concept, further evolved, is here presented for unmanned aerial vehicle (UAV) applications. Results of simulations for a new DI JI ICE with rotary valve, being super-turbocharged and having gasoline or methanol as working fuel, show the opportunity to achieve even larger power densities, up to 430 kW/liter, while delivering a near-constant torque and, consequently, a nearly linear power curve over a wide range of speeds.

Abstract The main focus of this article is the online estimation of the terminal airspace sector capacity from the Air Traffic Controller 0ATC) dynamical neural model using Neural Partial Differentiation (NPD) with permissible safe separation and affordable workload. For this purpose, a primarily neural model of a multi-input-single-output (MISO) ATC dynamical system is established, and the NPD method is used to estimate the model parameters from the experimental data. These estimated parameters have a less relative standard deviation, and hence the model validation results show that the predicted neural model response is well matched with the intervention of the ATC workload. Moreover, the proposed neural network-based approach works well with the experimental data online as it does not require the initial values of model parameters, which are unknown in practice.

Abstract This article serves as a proof-of-concept and feasibility analysis regarding a variable compression ratio (VCR) engine design utilizing an exhaust valve opening during the compression stroke to vary the compression ratio instead of the traditional method of changing the cylinder or piston geometry patented by Ford, Mercedes-Benz, Nissan, Peugeot, Gomecsys, et al. [1]. In this concept, an additional exhaust valve opening was used to reduce the virtual compression ratio of the engine, without geometric changes. A computational fluid dynamic model in ANSYS Forte was used to simulate a single-cylinder, cold flow, four-stroke, direct injection engine cycle. In this model, the engine was simulated at a compression ratio of 10:1. Then, the model was modified to a compression ratio of 17:1. Then, an additional valve opening at the end of the compression stroke was added to the 17:1 high compression model.

Abstract This paper presents a machine learning application of the force/torque sensor in a human-robot collaborative manufacturing scenario. The purpose is to simplify the programming for physical interactions between the human operators and industrial robots in a hybrid manufacturing cell which combines several robotic applications, such as parts manipulation, assembly, sealing and painting, etc. A multiclass classifier using Light Gradient Boosting Machine (LightGBM) is first introduced in a robotic application for discriminating five different contact states w.r.t. the force/torque data. A systematic approach to train machine-learning based classifiers is presented, thus opens a door for enabling LightGBM with robotic data process. The total task time is reduced largely because force transitions can be detected on-the-fly. Experiments on an ABB force sensor and an industrial robot demonstrate the feasibility of the proposed method.

Abstract In an automated machining process, monitoring the conditions of the tool is essential for deciding to replace or repair the tool without any manual intervention. Intelligent models built with sensor information and machine learning techniques are predicting the condition of the tool with good accuracy. In this study, statistical models are developed to identify the conditions of the abrasive grinding wheel using the Acoustic Emission (AE) signature acquired during the surface grinding operation. Abrasive grinding wheel conditions are identified using the abrasive wheel wear plot established by conducting experiments. The piezoelectric sensor is used to capture the AE from the grinding process, and statistical features of the abrasive wheel conditions are extracted in time and wavelet domains of the signature. Machine learning algorithms, namely, Classification and Regression Trees (CART) and Support Vector Classifiers (SVC), are used to build statistical models.

This technical paper collection is devoted to experimental and computational work in the area of fuel injection systems and sprays. Topics include: spray characterization, cavitation, multi-phase jet modeling, CFD models for spray processes, wall films and impingement, hydraulic circuit analysis, and dissolved gas effects.

The 32 papers in this technical paper collection cover topics such as spray characterization, cavitation, multi-phase jet modeling, CFD models for spray processes, wall films and impingement, hydraulic circuit analysis, and dissolved gas effects.