Considered here are nonlinear autoregressive neural networks (NETs) with exogenous inputs (NARX) as a mathematical model of a steam turbine rotor used for the online prediction of turbine temperature and stress. In this paper, the online prediction is presented on the basis of one critical location in a high-pressure (HP) steam turbine rotor. In order to obtain NETs that will correspond to the temperature and stress the critical rotor location, a finite element (FE) rotor model was built. NETs trained using the FE rotor model not only have FEM accuracy but also include all nonlinearities considered in an FE model. Simultaneous NETs are algorithms which can be implemented in turbine controllers. This allows for the application of the NETs to control steam turbine stress in industrial power plants.

Background This paper presents the experimental and numerical studies of last-stage low-pressure (LP) mistuned steam turbine bladed discs during run-down. Methods The natural frequencies and mode shapes of the turbine bladed disc were calculated using an FE model. The influence of the shaft on the modal properties, such as natural frequencies and mode shapes, was considered. The tip-timing method was used to find the mistuned bladed disc modes and frequencies. Conclusions The experimental results from the tip-timing analysis show that the mistuning in combination with shaft coupling suppresses pure nodal diameter type blade vibrations associated with the fundamental mode shape of a cantilevered blade. Vibration modes emerge when even a single blade is vibrating due to the well-known mode localization caused by mistuning. The numerical results confirm this.

In recent years, organic Rankine cycle (ORC) micro-turbine distributed energy systems have become increasingly popular. Design methods for this type of fluid-flow machinery are still being developed. In this paper, a 2.5-kW radialflow four-stage ORC micro-turbine with HFE7100 is experimentally and numerically analysed. CFX ANSYS was used for the numerical analysis as well as a computational fluid dynamics (CFD) in-house code based on finite volume discretisation with Godunov-type upwind differencing, a high-resolution essentially non-oscillatory (ENO) scheme and a turbulence model with twoequation shear stress transport (SST). The experimental stand and measurements are described. The numerical results are compared with experimental ones and prove to be satisfactory. The developed micro-turbine does not require the use of any traditional lubricant (oil-free technology) because the bearings are lubricated with the vapour of the low-boiling HFE7100. The developed micro-turbine is an innovative solution providing maintenance-free operation and high durability with low friction losses. The experimental studies have also confirmed a considerable reduction in noise and vibration levels.