In industrial practice, the representation of the dynamics of nonlinear systems by models linking their different operating variables requires an identification procedure to characterize their behavior from experimental data. This article proposes the identification of the variables of a two-shafts gas turbine based on a decoupled multi-model approach with genetic algorithm. Hence the multi-model is determined in the form of a weighted combination of the decoupled linear local state space sub-models, with optimization of an objective cost function in different modes of operation of this machine. This makes it possible to have robust and reliable models using input / output data collected on the examined system, limiting the influence of errors and identification noises.

No abstract

The work presented in this paper focuses on presenting an hybrid identification method for a nonlinear dynamic gas turbine, from a real time input and outputs data exploitation, with the fuel flow as the input and the rotational speed of high pressure and low pressure turbine as outputs. The multi model, which are in the form of a weighted combination of local linear state space models, offer an interesting alternative of the nonlinear models because it takes into account a several operating modes. The models are identified with the help of decoupled models using a hybrid approach between parametric estimation using artificial intelligence algorithms.

No abstract

The work presented in this paper focuses on presenting an hybrid identification method for a nonlinear dynamic gas turbine, from a real time input and outputs data exploitation, with the fuel flow as the input and the rotational speed of high pressure and low pressure turbine as outputs. The multi model, which are in the form of a weighted combination of local linear state space models, offer an interesting alternative of the nonlinear models because it takes into account a several operating modes. The models are identified with the help of decoupled models using a hybrid approach between parametric estimation using artificial intelligence algorithms.