公开(公告)号：WO2005116413A1

公开(公告)日：2005-12-08

申请号：PCT/EP2005/005601

申请日：2005-05-24

Applicant: UMICORE AG & CO. KG ,  LANDGRAF, Christian ,  HOHENBERG, Günter ,  VAN SETTEN, Barry ,  SÖGER, Nicola ,  PFEIFER, Marcus ,  SPURK, Paul

Inventor： LANDGRAF, Christian ,  HOHENBERG, Günter ,  VAN SETTEN, Barry ,  SÖGER, Nicola ,  PFEIFER, Marcus ,  SPURK, Paul

IPC: F01N9/00

CPC classification number: F01N9/002 ,  F01N9/007 ,  F01N11/002 ,  F01N2550/04 ,  F02D41/029 ,  F02D41/1405 ,  F02D2200/0812 ,  Y02T10/47

Abstract: The invention provides a method for determining the loading of a particulate filter, in particular of a particulate filter arranged in the exhaust-gas purification system of a diesel engine. First of all, a characteristic diagram for the particulate filter in a known state of loading is provided, and an artificial neural network is trained using this characteristic diagram. It is preferable for the characteristic diagram to describe the pressure difference caused by the filter as a function of the exhaust-gas temperature and of the exhaust-gas mass flowing through the filter. The loading of the particulate filter can then be determined by the artificial neural network from measured variables which characterize the operating state of the engine, such as the pressure difference caused by the filter, the exhaust-gas temperature and the exhaust-gas mass flowing through the filter.

Abstract translation: 本发明提供一种用于确定颗粒过滤器，特别是布置在柴油发动机的废气净化系统中的颗粒过滤器的负载的方法。 首先，提供了在已知装载状态下的微粒过滤器的特性图，并且使用该特性图来训练人造神经网络。 特征图优选地描述作为废气温度的函数的过滤器和流过过滤器的废气质量的压力差。 颗粒过滤器的装载然后可以通过人造神经网络从表征发动机的运行状态的测量变量确定，例如由过滤器引起的压力差，排气温度和废气质量流过 过滤器。