Identification of Two-shaft Gas Turbine Variables Using a Decoupled Multi-model Approach With Genetic Algorithm

Abstract

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.

Identification of twin-shaft gas turbine based on hybrid decoupled state multiple model approach

“…The form of a multi-pattern decoupled state proposed by [16,22,28], which describes the system of the application presented in this paper can be expressed as follows:…”

“…The aim is to identify and optimize the parameters of the local model in order to accurately reproduce the dynamic behavior of the system. The parametric estimation method is based on minimizing the function of the quadratic error presenting the difference between the estimated output of the multiple model ( ) k y ˆ and the measured output of the considered nonlinear system ( ) k y which is defined as follows [15,16,22,28]:…”

“…Parametric modelling of gas compressor plants using real data have studied by Yang Chen et al in [33] and the modelling the dynamics of flow with a probabilistic method have studied by Yu Zhang in [34]. The hierarchical modelling approach to characterize the dynamics of the drive system of a gas turbine and monitoring system of the gas turbine based on the acquisition of real data of onsite gas turbine vibration measurement have studied by Guolian Hou et al in [12] and by many others research in modelling [23,[27][28][29]. In fact, the gas turbine research field has covered control and many others such as fault diagnosis and maintenance, under the assumption that the system operates around a single operation point.…”