Setup, Validation and Probabilistic Robustness Estimation of a Model for Prediction of LCF in Steam Turbine Rotors

Author(s):  
David Pusch ◽  
Matthias Voigt ◽  
Konrad Vogeler ◽  
Peter Dumstorff ◽  
Henning Almstedt

Flexibility and availability together with fast startup times become more and more important for steam turbine operation. Exact knowledge about the turbine components stresses and lifetime consumption during transient operation is a prerequisite in order to meet these requirements. A transient FE model of an intermediate pressure steam turbine rotor was generated, allowing the prediction of temperature and elastic stress field during turbine startup, load changes and shutdown. Operating data of the steam parameters and of a thermocouple inside the wall of the turbine inner casing were used to indirectly validate the thermal FE model in order to reproduce the measured metal temperatures in a proper accuracy. Subsequently a probabilistic sensitivity study was performed in order to identify the influence of scattering or not well known boundary conditions on the calculated lifetime consumption of the steam turbine rotor during a cold start. This in fact provides information about the accuracy of the prediction. The results of the sensitivity study also help to improve the model accuracy by identifying the boundary conditions with the largest impact on lifetime prediction uncertainty, i.e. the boundary conditions that need further investigation.

Author(s):  
Krzysztof Dominiczak ◽  
Romuald Rządkowski ◽  
Wojciech Radulski ◽  
Ryszard Szczepanik

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.


2021 ◽  
Vol 3 (2) ◽  
Author(s):  
Vital Kumar Yadav Pillala ◽  
B. V. S. S. S. Prasad ◽  
N. Sitaram ◽  
M. Mahendran ◽  
Debasish Biswas ◽  
...  

AbstractThe paper presents details of a unique experimental facility along with necessary accessories and instrumentation for testing steam turbine cascade blades in wet and nucleating steam. A steam turbine rotor tip cascade is chosen for flow investigations. Cascade inlet flow measurements show uniform conditions with dry air and steam and dry air mixture of different ratios. Exit flow surveys indicate that excellent flow periodicity is obtained. Blade surface static pressure and exit total pressure distributions are also presented with dry air and with steam and dry air mixture of different ratios as the working medium at an exit Mach number of 0.52.


2019 ◽  
Vol 76 ◽  
pp. 263-278 ◽  
Author(s):  
Xuanchen Zhu ◽  
Haofeng Chen ◽  
Fuzhen Xuan ◽  
Xiaohui Chen

2017 ◽  
Vol 46 (3) ◽  
pp. 612-616
Author(s):  
Guo Shirui ◽  
Shang Huichao ◽  
Cui Lujun ◽  
Guo Xiaofeng ◽  
Yao Jianhua

2021 ◽  
Author(s):  
Chongyu Wang ◽  
Di Zhang ◽  
Yonghui Xie

Abstract The steam turbine rotor is still the main power generation equipment. Affected by the impact of new energy on the power grid, the steam turbine needs to participate in peak load regulation, which will make turbine rotor components more prone to failure. The rotor is an important equipment of a steam turbine. Unbalance and misalignment are the normal state of rotor failure. In recent years, more and more attention has been paid to the fault detection method based on deep learning, which takes rotating machinery as the object. However, there is a lack of research on actual steam turbine rotors. In this paper, a method of rotor unbalance and parallel misalignment fault detection based on residual network is proposed, which realizes the end-to-end fault detection of rotor. Meanwhile, the method is evaluated with numerical simulation data, and the multi task detection of rotor unbalance, parallel misalignment, unbalanced parallel misalignment coupling faults (coupling fault called in this paper) is realized. The influence of signal-to-noise ratio and the number of training samples on the detection performance of neural network is discussed. The detection accuracy of unbalanced position is 93.5%, that of parallel misalignment is 99.1%. The detection accuracy for unbalance and parallel misalignment is 89.1% and 99.1%, respectively. The method can realize the direct mapping between the unbalanced, parallel misalignment, coupling fault vibration signals and the fault detection results. The method has the ability to automatically extract fault features. It overcomes the shortcoming of traditional methods that rely on signal processing experience, and has the characteristics of high precision and strong robustness.


Sign in / Sign up

Export Citation Format

Share Document