基于神经网络和LSSVM的点火提前角组合预测研究

A Research on Ignition Advance Angle Combined Prediction Based on Neural Network and LSSVM

针对传统插值法确定汽油机点火提前角精度较低的问题,提出了根据发动机负荷变化的可变最优加权方法,并建立了基于BP-LSSVM的汽油机可变最优加权点火提前角组合预测模型,通过点火提前角预测结果的对比与分析,验证了提出的基于神经网络和LSSVM的汽油机点火提前角组合预测模型的准确性和有效性。

Aiming at the problem that the precision of the ignition advance angle of the gasoline engine determined by the traditional interpolation method is low, a variable optimal weighting method is proposed according to the variation of engine load and a variable optimal weighted combination model of BP-LSSVM ignition advance angle is established. By comparing and analyzing the resuhs of other prediction model, the accuracy and validity of the BP-LSSVM ignition advance angle combined prediction model based on neural networks and LSSVM is verified.