燃气轮建模是对其实施控制、性能优化、状态监测等工作的基础。本研究提出了一种基于Hammerstein-Wiener的燃气轮机非线性建模方法，利用传递函数建立了燃气轮机的动态线性模型，分别利用分段线性函数和小波变换网络作为非线性输入环节和输出环节的函数,用来描述燃气轮机的非线性特性，并构建了损失函数。将模型的信息向量与参数向量解耦，基于燃气轮机实际运行数据，利用Gauss-Newton法实现对参数向量的辨识，从而获取到燃气轮机的非线性模型，并与其他模型进行对比，结果表明所建立的非线性模型具有更高的精度。利用测试数据对模型的外延性进行验证，结果显示RMSE最大为0.0109， MAPE最大为 3.3054%， FIT最小为0.9987，表明该模型能够实现对实际燃气轮机监测数据的准确拟合，为燃气轮机状态监测相关工作提供基准。

The modeling of a gas turbine serves as the foundation for its control, performance optimization, and state monitoring. This paper proposes a nonlinear modeling approach for gas turbines based on Hammerstein-Wiener methodology. The dynamic linear model of the gas turbine is established using the transfer function. The piecewise linear function and the wavelet transform network are employed as the functions of the nonlinear input and output links, respectively, to depict the gas turbine"s nonlinear characteristics. And the loss function is constructed. The information vector of the model is decoupled from the parameter vector, and the parameter vector is estimated using the Gauss-Newton method based on actual operational data of the gas turbine, thereby obtaining a nonlinear model for the gas turbine. Comparison with other models demonstrates that the established nonlinear model exhibits enhanced accuracy. The test data is utilized to validate the model"s extensibility. The results demonstrate that the maximum RMSE is 0.0109, the maximum MAPE is 3.3054%, and the minimum FIT is 0.9987, indicating the model"s capability to accurately fit actual gas turbine monitoring data and provide a reference for related gas turbine condition monitoring tasks.

国家科技重大专项