Experimental Data Processing Techniques to Map the Performance of a Spark Ignition Engine

摘要: Mapping the performance of an internal combustion engine over a wide range operating conditions is common procedure during development. The generation and post-processing data are high-cost activities. Two approaches which offer advantages parametric test plans have been investigated. A statistically designed matrix tests has employed to map stability parameters. This approach minimizes number required techniques provide valuable insight relationships exist between variables. particularly useful efficient when qualitative trends prime interest. When large sets necessarily acquired quantitative variables particular concern, then processing using neural networks shown be effective approach. use this technique illustrated by application evaluate engine-out emissions state