论文部分内容阅读
针对故障率时间序列的非线性与非平稳特性,提出一种基于支持向量经验模态分解(SVEMD)的预测方法。首先,将故障率时间序列分解为多个固有模态函数(IMF)与一个余量(RF),利用最小二乘支持向量机(LSSVM)预测时间序列两端的局部极值点,以抑制传统经验模态分解(EMD)的边缘效应;同时以LSSVM回归方式形成包络线,以取代传统EMD中的三次样条插值;然后,建立各IMF与RF的预测模型;最终,将各IMF与RF的预测结果相加以获得故障率时间序列的预测结果。仿真结果表明,该方法的预测精度较传统基于EMD的预测方法与单一预测方法有显著提高,可实现对故障率的准确预测。
Aiming at the nonlinear and non-stationary characteristics of failure rate time series, a prediction method based on Support Vector Empirical Mode Decomposition (SVEMD) is proposed. Firstly, the failure rate time series is decomposed into multiple IMFs and one residual (RF), and the LSSVM is used to predict the local extremum points at both ends of the time series to suppress the traditional experience (EMD). At the same time, the envelope is formed by LSSVM regression to replace the cubic spline interpolation in traditional EMD. Then, the prediction model of each IMF and RF is established. Finally, the IMF and RF The prediction results are summed to obtain the prediction of the failure rate time series. Simulation results show that the prediction accuracy of this method is significantly higher than the traditional EMD-based prediction method and single prediction method, which can accurately predict the failure rate.