摘要
针对具有非线性和时变关系的涡轮试验多通道信号偏差检测问题,建立了自关联神经网络估计器和预报器方法。分析了自关联神经网络结构及输入-输出参数与测量变量之间的关联关系,提出了不同输入参数的涡轮试验传感器数据估计器和预报器,实现了对数据偏差的检测、分离及数据重构。
A neural network model based approach is presented to handle the bias detection and correction problem with data correlated by nonlinear and time-varying relations in gas turbine test. A special architecture of the auto-associative neural network is defined with different input and output parameters. Novel estimators and predictors based on auto-associative neural network are devised and evaluated with practical test data. A scheme integrating operations of error detection, fault isolation and data reconstruction is presented based on auto-associative neural network.
出处
《燃气涡轮试验与研究》
2008年第2期27-32,共6页
Gas Turbine Experiment and Research
基金
湖南省优秀博士学位论文基金资助项目(2003011)
中国燃气涡轮研究院先进试验技术研究资助项目
关键词
燃气涡轮发动机
传感器数据证实
自关联神经网络
估计与预报
gas turbine engine
sensor data validation（SDV）
auto-associative neural network（AANN）
estimate and prediction
