中文摘要：

为解决高可靠复杂设备的剩余寿命通常与多个性能参数共同退化相关的实际问题,提出一种多变量灰色误差神经网络预测方法。首先,建立经过背景值优化的多变量灰色预测模型MGM（1,n）,并得到原始数据序列的初始预测值。然后,利用神经网络建立残差序列与原始数据序列之间的映射关系,训练RBF神经网络。最后,将改进的MGM（1,n）模型和RBF神经网络集成,建立多变量灰色误差神经网络预测模型。实例计算结果表明,与单一预测模型相比,该方法能够有效提高预测精度。

英文摘要：

To solve practical ated with common multi -variable optimized bac degradati problems that some residual life of highly reliable complex equipment is usually associ- on of multi-performance parameters, a prediction model of residual life, which is the grey compensating RBF neural network prediction model, was constructed. Firstly, MGM （ 1, n） with kground value was constructed, and initial predictive values of original data sequences were obtained. Secondly, the mapping relationship between residual sequences and original data sequences was established to train RBF neural networks. Finally, the multi-variable grey compensating RBF neural network prediction model was con- strutted to combine improved MGM（ 1, n）with RBF neural network. Results of case study indicate that the presen- ted method effectively improve the prediction accuracy when comparing with the single prediction model.