A novel dynamic modeling of an industrial gas turbine using condition monitoring data

For some of the existing gas turbines, there is no standard documentation, so non-OEM (Original Equipment Manufacturer) companies will encounter problems for upgrading the systems. The problem even is getting worse for companies focusing on old gas turbines control system retrofit. The main purpose of this paper is to present a gas turbine dynamic modeling procedure in start-up and loading modes, considering some performance information with minimum access to the design and related technical datasheets of the turbine. To specify the characteristics of the shaft speed during system start-up, there are numerous complexities due to uncertainties and unspecified parameters. In this paper, for the start-up mode, the neural network (NN) method and the derived functions of linear regression (LR), shaft dynamic (SD)-based function, and nonlinear auto-regressive exogenous (NARX) and Hammerstein-Wiener (HW) fitted structures are used in addition to the time-delayed transfer functions in order to generate the dynamic model. Also, the operational information of an operating power plant is utilized to generate the dynamic model of the system in loading and unloading modes.