Search Results

Autonomous vehicles are currently a subject of great interest and there is heavy research on creating and improving algorithms for detecting objects in their vicinity. A ROS-based deep learning approach has been developed to detect objects using point cloud data. With encoded raw light detection and ranging (LiDAR) and camera data, several basic statistics such as elevation and density are generated. The system leverages a simple and fast convolutional neural network (CNN) solution for object identification and localization classification and generation of a bounding box to detect vehicles, pedestrians and cyclists was developed. The system is implemented on an Nvidia Jetson TX2 embedded computing platform, the classification and location of the objects are determined by the neural network. Coordinates and other properties of the object are published on to various ROS topics which are then serviced by visualization and data handling routines.

The influence of fuel aromatics type on the particulate matter (PM) and NOx exhaust emissions of a heavy-duty, single-cylinder, DI diesel engine was investigated. Eight fuels were blended from conventional and oil sands crude oil sources to form five fuel pairs with similar densities but with different poly-aromatic (1.6 to 14.6%) or total aromatic (14.3 to 39.0%) levels. The engine was tuned to meet the U.S. EPA 1994 emission standards. An eight-mode, steady-state simulation of the U.S. EPA heavy-duty transient test procedure was followed. The experimental results show that there were no statistically significant differences in the PM and NOx emissions of the five fuel pairs after removing the fuel sulphur content effect on PM emissions. However, there was a definite trend towards higher NOx emissions as the fuel density, poly-aromatic and total aromatic levels of the test fuels increased.

Diesel-fueled heavy-duty vehicles (HDVs) can be retrofitted with conversion kits to operate as dual-fuel vehicles in which partial diesel usage is offset by a gaseous fuel such as compressed natural gas (CNG). The main purpose of installing such a conversion kit is to reduce the operating cost of HDVs. Additionally, replacing diesel partially with a low-carbon fuel such as CNG can potentially lead to lower carbon dioxide (CO2) emissions in the tail-pipe. The main issue of CNG-diesel dual-fuel vehicles is the methane (CH4, the primary component of CNG) slip. CH4 is difficult to oxidize in the exhaust after-treatment (EAT) system and its slip may offset the advantage of lower CO2 emissions of natural gas combustion as CH4 is a strong greenhouse gas (GHG). The objective of this study is to compare the emissions of an HDV with a CNG conversion kit operating in diesel and dual-fuel mode during highway operation.

In North America, heavy-duty diesel engines for on-road use have to meet strict regulations for their emissions of nitric oxide and nitrogen dioxide (cumulatively referred to as ‘NOx’) besides other criteria pollutants. Over the next decade, regulations for NOx emissions are expected to becoming more stringent in North America. One of the major technical barriers for achieving in-use NOx emissions commensurate with the levels determined from in-laboratory test procedures required by regulations is controlling NOx emissions during cold start and engine idling. Since the exhaust gas temperature can be low during these conditions, the effectiveness of the exhaust after-treatment (EAT) system may be reduced. Under colder climate conditions like in Canada, the impact may be even more significant.