摘要
电控高压共轨技术的采用使得船用柴油机性能及排放具有了更大的优化空间,但同时柴油机控制参数增多使得柴油机性能的预测变得更为复杂。为建立精确的柴油机性能预测模型,利用回归支持向量机,通过对试验数据的学习以获得预测模型。支持向量机的预测精度会因其参数的选择出现一定的差异,所以需要对支持向量机参数选择进行研究和优化。以某型船用高速大功率电控高压共轨柴油机为研究对象,建立支持向量机预测模型,分析其预测性能受参数选择的影响,并利用人工鱼群算法对其进行优化。结果表明,基于人工鱼群算法优化的回归支持向量机能够建立精度较高的柴油机性能预测模型,且人工鱼群算法具有很好的寻优性能。
The introduction of common rail direct injection system(CRDI)has extended the optimization space of marine diesel engine by performance and commission.But meanwhile,the prediction of engine performance became more complex due to the increase of control parameters.In order to establish an accurate model for the engine performance,the support vector regression(SVR)is employed to get the predictive model by studying the test data.The predictive accuracy of SVR will be varied due to the selection of parameters,so the research and optimization of these parameters are necessary.Based on a CRDI-assisted marine diesel engine,the SVR predictive model is developed;the parameters of SVR are investigated and optimized using artificial fish school algorithm(AFSA).The results indicate that the SVR predictive model optimized by AFSA has the ability to develop perfect engine performance predictive models.In addition,AFSA has an excellent performance of optimization.
作者
牛晓晓
刘文斌
聂志斌
焦会英
NIU Xiaoxiao;LIU Wenbin;NIE Zhibin;JIAO Huiying(Henan Diesel Engine Industry Co.,Ltd.,Henan Luoyang 471000,China)
出处
《船舶工程》
CSCD
北大核心
2019年第7期44-48,79,共6页
Ship Engineering
关键词
船用柴油机
高压共轨
预测模型
回归支持向量机
人工鱼群算法
marine diesel engine
common rail direct injection system(CRDI)
predictive model
support vector regression(SVR)
artificial fish school algorithm(AFSA)
