基于BP神经网络的信息融合发动机故障诊断的研究

Study on the Diagnosing for Engine In-cylinder Faults Based on Multi-sensor Information Fusion

本文为了解决发动机喷油器故障诊断中基于单传感器信息的方法诊断精度低的缺点。在神经网络分析的基础上,提出了一种基于气缸压和,缸盖振动信号和燃油压力等多传感器信息融合的喷油器故障诊断新方法该方法能有效地提高其故障诊断精度。

In this article,based on theory of Bpneural network analysis,in order to solve the non-linear and uncertain faults of engine problems, a new in - cylinder faults of engine diagnosis method based on multi-sensor information fusion is presented.Two kinds of signals are sampled,and are analyzed using load identification and wavelet packet methods.Eight features are extracted, and are put into Bpnerual networks system, Through this method,the fault diagnosis accuracy is improved effectively.