摘要
为克服非线性误差,提高航空发动机上传感器系统的测量精度,采用基于函数链神经网络的非线性校正技术,弥补了传统方法计算量大、精度不高的不足,减小了非线性误差.仿真结果表明此方法速度快,计算精度高,绝对误差不超过0.07o,完全满足测量要求,已在发动机地面试验系统中得到应用,该方法可应用于航空发动机全权限数字式电子控制(FADEC)系统中.
In order to correct the non-linearity error and improve the measuring precision of aeroengine sensors system, non-linearity correction based on Functional-link neural network makes up for the traditional methods’ disadvantages, such as much calculation and low precision, it reduced the non-linearity error, Simulation results indicated that this method has merits of high precision and speediness, absolute error does not surpass 0.07 degree, completely meets the measurement request, it is already adopted in A...
出处
《电子器件》
CAS
2007年第6期2163-2165,共3页
Chinese Journal of Electron Devices
基金
陕西省基础研究计划资助项目(2005E1115)
空军科研基金资助项目(2003KJ01705)
