基于多维时间序列模型的内燃机磨损状态预测研究

Research on Prediction of Engine Wear State Based on Multidimensional Time Series Model

现有的油液光谱数据预测方法仅考虑单一数据内部前后间的联系,忽视不同种类数据间的相互影响。多维时间序列模型能够将多种元素光谱数据融合起来同时进行建模,利用所建模型对光谱数据进行预测,提高预报精度。通过内燃机台架实验获得多种元素的光谱数据,选择典型的磨损元素Fe和Al、污染元素Si以及添加剂元素Mg作为分析元素,通过分析找出相关性较大的元素,利用多维时间序列模型对其进行预报,从而对内燃机的磨损状态进行准确判断。结果表明,将多维时间序列模型引入油液光谱数据预报能对内燃机的磨损状态进行准确预测。

The present methods of predicting oil spectrum have the shortage for they only consider the correlation between single kind of data,while exclude the interaction among various data.Spectrum data can be fused using multidimensional time series model and the prediction accuracy is improved.The spectrum data were acquired from the internal-combustion engine test bed and the typical wear elements Fe and Al,the contamination element Si and the lubricant additive element Mg were selected and analyzed,the more correlated elements were found and the engine wear state was diagnosed correctly by predicting the chosen data with multidimensional time series model.Experimental results demonstrate that it is of great help to introduce the multidimensional time series model into oil spectrum prediction to predict engine wear state.