Search Results

We have developed an artificial neural network (ANN) based combustion model and have integrated it into a fluid mechanics code (KIVA3V) to produce a new analysis tool (titled KIVA3V-ANN) that can yield accurate HCCI predictions at very low computational cost.

In this paper, we propose to use Artificial Neural Networks (ANN) to model the air flow rate through a 2.4 liter VVT engine with independent intake and exhaust camshaft phasers.

A cylindrical combustion bomb with dynamic charging system and electro-hydraulic sampling valve is used to study the effects of turbulence on hydrocarbon (HC) emissions from a quench layer and from artificial crevices. The turbulence level is varied by changing the delay time between induction of combustible charge and ignition. ...Upper limit estimates of the residual wall layer HC concentration show that residual quench layer hydrocarbons are only a small fraction of the exhaust HC emission. Artificial crevice experiments show that the exhaust HC emission is directly proportional to crevice volume and that the initial equivalence ratio strongly influences the species distribution in the exhaust.

The recognition module extracts features from these traces and feeds them to an artificial neural network (ANN). After training on different tracks, the ANN successfully distinguishes traces originating from the original vehicles as well as traces taken from modified vehicles.

The NOx and smoke emission models adopt an artificial neural network (ANN) approach with Multi-Layer Perceptron (MLP) architectures. The networks are trained and validated using experimental data collected from engine bench tests.

The emissions of in-use vehicles were compared to the EPA certification standards at 50,000 and 100,000 miles, enabling evaluation of the artificial aging process of vehicles tested in the FTP. Tailpipe and engine-out emissions data are used to model the Catalyst Pass Fractions (CPFs) and cold start performance.

In both studies, stimulus sets were created by artificially introducing a controlled degree of non-linearity into a nominally linear powertrain sound.

The results show that these artificially augmented labels can significantly improve the prediction accuracy both in terms of MAE and time shift metrics.

Since the end of W.W.II, many countries have embarked on various to develop a national automobile industry to spur the economic growth of the country, to meet the rising domestic demand for automobiles, and to compete in the world markets. Can these countries achieve these objectives and at the same time retain their national independence in the automobile industry from the domination of the foreign multinational automobile manufacturers? This paper addresses these questions by examining first, the records of Latin America (Argentina, Brazil, Mexico), South Korea and Taiwan in Asia Pacific Region; it then attempts to determine to what extent their experiences may be transferrable to the Chinese automobile industry which is currently undergoing modernization. For the purpose of this paper, the automobile industry encompasses only passenger vehicles.