涡轮机
计算机科学
人工智能
工程类
机械工程
计算科学
模拟
作者
Yanzhao Wu,Ran Tao,Di Zhu,Ruofu Xiao
标识
DOI:10.1080/19942060.2024.2443122
摘要
In order to analyse and master the force characteristics of the prototype bulb turbine under critical cavitation condition, this study compared the force characteristics of the turbine under different operating conditions, and finally the problems of the DMD method in the low dimensional reduction application of one-dimensional time-series signals were clarified. A Hankel-DMD method was proposed to analyse the force characteristics under different operating conditions, and the linearization advantage of the DMD method was utilized, Further temporal prediction was conducted on the variation law of the force characteristics of the tubular turbine. In order to accurately predict the future changes in the force characteristics of the turbine, this study analysed the prediction error of the linear Hankel-DMD method and proposed a new time series prediction model based on the Hankel-DMD-LSTM method, which provides a new means for predicting the force characteristics of tubular turbine. To a certain extent, it could provide diagnostic insights into abnormal events with distinct periodic changes in time-series signals, and provide certain assistance in signal interpretability.
科研通智能强力驱动
Strongly Powered by AbleSci AI