On-Line Prediction of Temperature and Stress in Steam Turbine Components Using Neural Networks

Abstract

Considered here are Nonlinear Auto-Regressive neural networks with exogenous inputs (NARX) as a mathematical model of a steam turbine rotor used for the on-line prediction of turbine temperature and stress. In this paper on-line prediction is presented on the basis of one critical location in a high pressure steam turbine rotor, according to power plant common measurements, i.e., turbine speed, turbine load as well as steam temperature and pressure before turbine control valve. In order to obtain neural networks that will correspond to the temperature and stress the critical rotor location, an FE rotor model was built. Neural networks trained using the FE rotor model not only have FEM accuracy, but also include nonlinearity related to nonlinear steam turbine expansion, nonlinear heat exchange inside the turbine and nonlinear rotor material properties during transient conditions. Simultaneous neural networks are algorithms which can be implemented in turbine controllers. This allows for the application of neural networks to control steam turbine stress in industrial power plants.

Archives of Thermodynamics

“…For the analysis of the heating method, a part of the high pressure (HP) turbine shaft was selected, in which [1,2] critical stress has been found due to the phenomena described above. The location of its occurrence is the bottom of the groove for fixing the blades.…”

“…On line information regarding relative stress allows to start up the steam turbine in the shortest possible time and in the same time maintain requested design life of the turbine. It might be concluded that the steam turbine lifetime consumption of the steam turbine due to thermal low cyclic fatigue is minimized for given preconditions as turbine initial condition and thermal boundary conditions during the turbine startup [1,2]. The course of start-up planning is also relevant for the process of turbine start-up.…”

“…AG methods are used to plan the optimal start-up and heating path of the steam turbine shaft. A part of the real turbine shaft has been selected for testing on the basis of [1,2]. This part is a steam turbine rotor blade groove, which is a critical location for reaction type blading steam turbine rotors.…”

Optimization of Control Parameters of Magnetorheological Squeeze Film Dampers to Minimize the Vibration Amplitude of Rotors Passing the Critical Speed

“…Optimization of the technological or operation parameters of rotating machines is needed to meet rising demands put on their design or accomplish the technological processes. Du et al [31] and Dominiczak et al [32] reported on the optimization of the start-up procedure of large steam turbines, focusing on heat parameters. Saldarriaga and Steffen [33], Mohammadzadeh and Ghoddoosian [34], and Yao et al [35] dealt with balancing the rotors based on the utilization of different optimization methods.…”