基于BP神经网络与时间序列分析的柴油机故障诊断

Diesel engine fault diagnosis based on BP neural network and time series analysis

将时间序列分析和神经网络相结合应用于柴油机振动故障诊断.从时间序列分析的结果中提取柴油机故障的特征参数,然后以此建立相应的神经网络,识别柴油机的运行故障,大大提高诊断的准确性.讨论柴油机气阀间隙异常的诊断和柴油机负荷状态的识别,并给出振动特征参数与柴油机工作状态之间的关系.

An investigation on diesel engine vibration fault diagnosis is conducted based on the combination of neural network and time series analysis. The characteristic parameters obtained from time series analysis are used to build a suitable BP neural network in order to detect the engine operating faults and improve the diagnosis accuracy. The diagnoses of variations in valve clearances and engine cylinder loads are discussed. The relationships between vibration characteristics and engine working conditions are presented.