论文部分内容阅读
利用飞机的性能参数对飞机进行故障预报和状态监控是非常重要的。飞机的性能参数不仅具有非线性而且往往包含噪声,使得故障预测结果具有不确定性。针对这些问题,研究了利用非线性支持向量机处理飞机性能参数的预测问题,通过增加线性约束的方式解决了噪声带来的不确定性问题。此种方法不仅提高了预测的精度,而且模型可以利用适用于处理大规模二次规划的序列最小最优化算法进行求解,使得其可以解决大数据量的预测问题。利用仿真数据以及实际飞机性能参数对该方法进行了实验分析,实验结果表明此方法在精度上较不考虑噪声影响的模型有所提高,对于进一步提高飞机故障预测的精度,从而提高飞机的安全性具有重要意义。
The use of aircraft performance parameters of aircraft failure prediction and status monitoring is very important. Aircraft performance parameters are not only nonlinear but often contain noise, making the prediction of the fault uncertain. In order to solve these problems, this paper studies the prediction of aircraft performance parameters by using nonlinear support vector machines, and solves the problem of noise caused by noise by adding linear constraints. This method not only improves the prediction accuracy, but also solves the problem of forecasting large data by using the minimum sequence optimization algorithm which is suitable for large-scale quadratic programming. The method is experimentally analyzed by using the simulation data and the actual aircraft performance parameters. The experimental results show that this method has higher accuracy than the model without considering the influence of noise, and improves the aircraft’s flight safety to further improve the accuracy of aircraft fault prediction It is of great significance.