一种新的混合智能预测模型及其在故障诊断中的应用

针对机电设备运行状态受多因素影响且变化趋势复杂、难以用单一预测方法进行有效预测的问题，提出了一种新的基于经验模式分解、支持向量机和自适应线性神经网络的混合智能预测模型．首先，利用经验模式分解方法将非平稳时间序列按其内在的时间特征尺度自适应地分解为多个本征模式分量，然后根据这些分量各自趋势变化的剧烈程度选择合适的核函数，用支持向量机对其进行预测，最后通过自适应线性神经网络对这些预测分量进行自适应加权组合，得到原始序列的预测值．研究结果表明，对于标准算例和某机组振动趋势的预测，不论是单步预测还是多步预测，该模型的预测性能均好于单一的支持向量机预测方法。

Novel Hybrid Intelligent Forecasting Model and Its Application to Fault Diagnosis

Due to the fluctuation and complexity of electromechanical equipment operation condition affected by various factors, it is difficult to use a single forecasting method to accurately describe the moving tendency. So a novel hybrid intelligent forecasting model based on empirical mode decomposition (EMD), support vector machines (SVMs) and adaptive linear neural network (ALNN), is proposed, where these intrinsic mode components (IMCs) are adaptively extracted via EMD from a nonstationary time series (according) to the intrinsic characteristic time scales. Tendencies of these IMCs are forecasted with SVMs (respectively,) in which the kernel functions are appropriately chosen with these different fluctuations of IMCs. These forecasting results of IMCs are combined with ALNN to output the forecasting result of the original time series. The proposed model is applied to the tendency forecasting of a benchmark example and a vibration signal from machine sets, and the simulated results show that the forecasting performance (of the) hybrid model outperforms SVMs with the single-step ahead forecasting or the multi-step ahead (forecasting.)