【摘要】 应用径向基函数网络(RBFNN)和压缩映射遗传算法(CMGA)的融合理论,提出了车用催化转化器劣化的在线预测策略。利用催化转化器劣化试验数据作为RBFNN的输入,影响催化转化器劣化的性能参数作为RBFNN的输出,进行了车用催化转化器劣化的模糊预测。利用RBF-CMGA融合预测策略,进行了车用催化转化器的空燃比特性、起燃比特性的劣化试验。结果表明:CO、HC和NOx的劣化系数分别为1.27、1.48、1.03,验证了该融合预测策略具有较好的分辨率,可用于车用催化器在线劣化预测。更多还原

【Abstract】 Based on the synergetic theory of the radial basal function neural network(RBFNN) and the contractive mapping genetic arithmetic(CMGA),an on-line forecast strategy for aging prediction of catalytic converter was proposed.The performance datas of catalytic converter were obtained by the aging test of the catalytic converter,the sampling datas were used as the inputs of the RBFNN,and the aging parameters of the catalytic converter were used as the outputs of the RBFNN,and the forecast strategy of aging prediction for catalytic converter was educated and studied by RBF-CMGA.The on-line aging tests of the catalytic converter,such as the air/fuel ratio and the light-off behavior of the catalytic converter,were performed by the RBF-CMGA synergetic theory on a vehicle.The test results show that the aging coefficient for CO,HC and NOx is 1.27,1.48 and 1.03 respectively;the prediction theory has a better resolving power and can be used for the aging prediction of automotive catalytic converter.更多还原