论文部分内容阅读
液体火箭发动机试验台故障预测问题实际上是与试验台相关的参数预测问题,通过预测相关参数在试验台运行过程中的变化趋势,可以判断试验台未来某一时刻是否可能发生故障。由于液体火箭发动机试验台系统复杂、不易建模,提出了一种相关向量机(relevancevector machine,RVM)故障预测模型。在模型的训练阶段,根据数据序列的特征,分别采用单参量、相空间重构和多参量的方法进行了模型的训练,然后利用训练好的模型对试验台总体健康度和启动过程推力进行了趋势预测。预测结果表明,该方法能有效地跟踪试验台可能发生的故障及故障发展趋势。
The fault prediction of liquid rocket engine test bed is actually a parameter prediction problem related to the test rig. By predicting the trend of the relevant parameters during the operation of the test rig, it is possible to determine whether a failure of the test rig is possible at a certain point in the future. Due to the complexity and difficulty of modeling the liquid rocket engine test bed, a fault prediction model of relevance vector machine (RVM) is proposed. In the training phase of the model, the training of the model was carried out according to the characteristics of the data series using single parameters, phase space reconstruction and multi-parameters respectively, and then the trained model was used to test the overall health of the test rig and the thrust of the starting process Trend forecast. The prediction results show that this method can effectively track the possible failure of the test bench and the trend of fault development.