论文部分内容阅读
状态特征指标对机械的状态监测和故障诊断具有重要意义。本文提出应用机械设备工作状态下噪声信号自回归模型的关联维数来描述设备在不同工作状态下的特征 ,进而实现对状态的监测、识别和分类。文中通过实验证明 ,设备在相同工作状态下 ,噪声信号的AR模型参数具有相近的关联维数 ,在不相同状态下则有明显不同的关联维数。因此关联维数不仅可以作为状态监测与识别和分类的重要依据 ,而且可以作为其他特征提取方法的补充。此方法对设备状态监测准确率的提高具有明显的作用
State characteristics of the indicators of the state of the machine monitoring and fault diagnosis is of great significance. This paper proposes to use the correlation dimension of the autoregressive model of the noise signal under the working condition of the mechanical equipment to describe the characteristics of the equipment under different working conditions so as to realize the monitoring, identification and classification of the condition. The experimental results show that the AR model parameters of the noise signal have similar correlation dimensions under the same working condition and obviously different correlation dimensions under different states. Therefore, the correlation dimension not only serves as an important basis for condition monitoring and identification and classification, but also can be used as a complement to other feature extraction methods. This method has an obvious effect on the improvement of equipment condition monitoring accuracy