基于FNER性能退化指标及IDRSN的滚动轴承寿命状态识别方法

Recognition of Rolling Bearing Life Status Based on FNER Performance Degradation Indicator and IDRSN

针对滚动轴承退化性能难以评估、寿命状态难以识别的问题,提出一种基于特征噪声能量比(Feature-to-noise energy ratio,FNER)指标及改进深度残差收缩网络(Improved deep residual shrinkage network,IDRSN)的滚动轴承寿命状态识别新方法。首先,将全寿命轴承信号进行希尔伯特(Hilbert)变换和快速傅里叶变换(Fast fourier transform,FFT)得到包络谱,根据故障特征频率及其倍频计算包络谱幅值的特征能量比(Feature energy ratio,FER);然后,根据自相关函数(Autocorrelation function,AF)得到包络信号的总能量,将故障特征能量和噪声能量的比值作为轴承性能退化指标,之后按照FNER指标曲线划分轴承寿命状态和实现样本标签化;随后,使用标签化样本训练引入了密集连接网络的IDRSN得到轴承寿命状态识别模型。为了提高抗干扰能力,将DropBlock层引入第一个大型卷积内核,在全局平均池化之前引入Dropout技术。最后,运用两个滚动轴承全寿命周期数据集验证FNER指标和IDRSN模型的实用性和有效性,结果表明所提方法能更准确地实现滚动轴承寿命状态识别。

Aiming at the difficulty in evaluating the degradation performance of rolling bearing and identifying bearing running state,a new method based on feature-to-noise energy ratio(FNER)indicator and improved deep residual shrinkage network(IDRSN)model is proposed.Firstly,Hilbert transform and fast fourier transform(FFT)are used to obtain the envelope spectrum of bearing run-to-failure test signal and the fault feature energy of the envelope spectrum amplitude is calculated.The feature energy ratio of the envelope spectrum amplitude is calculated according to the fault characteristic frequency and its frequency multiplication.Subsequently,the total energy of the signal is obtained according to the autocorrelation function(AF).After that,the ratio of the fault feature energy and the noise energy is used as the bearing performance degradation indicator.Moreover,the bearing running state is divided according to FNER indicator and tagged bearing samples realized.Then,tagged samples are used to train the IDRSN which introduces the densely connected network to obtain the bearing running state recognition model.In order to improve the anti-interference ability,the DropBlock layer is introduced into the first large convolution kernel and the Dropout technique is introduced before the global average pooling layer(GPA).Finally,two life cycle data sets of rolling bearings are used to verify the practicability and validity of FNER indicator and IDRSN model.The results show that the proposed method can more accurately identify the life state of rolling bearings.