船用燃气轮机状态趋势预测算法研究

Study on the Method of Tendency Forecast for Marine Gas Turbine

摘要:

燃气轮机是船舶动力系统的重要组成部分,为了提高船舶性能,需对其进行状态趋势预测;首先研究了常用的几种预测算法,总结了各自优缺点和适用范围,对常见预测方法的技术特点进行了详细分析;为提高船用燃气轮机状态预测精度,提出了组合优选和虚拟预测的思想,通过研究组合预测方法实现了燃汽轮机状态的趋势预测,验证了组合优选和虚拟预测的可操作性和正确性,将预测结果同直接预测相比较,验证了其优越性。

Abstract:

Gas turbine is an important part of the ship’s power system. In order to protect the ship's safe navigation and perform tasks, we should monitoring and predict the state of the gas turbine. This paper studies several commonly used predictive algorithms, test and verify them and analyzes the advantages and disadvantages of these predictive algorithms. In order to predict with greater accuracy, we use a combination of preferred and virtual predictable algorithm, which are used to predict the state of gas turbine. The paper verifies the operability and correctness of the combination of preferred and virtual predict by the Gas turbine’s date prediction. It also shows the superiority of the preferred and virtual predictable algorithm compared to the direct prediction. 