Fault diagnosis method of peak-load-regulation steam turbine based on improved PCA-HKNN artificial neural network

Abstract

Clean energy is now developing rapidly, especially in the United States, China, the Britain and the European Union. To ensure the stability of power production and consumption, and to give higher priority to clean energy, it is essential for large power plants to implement peak shaving operation, which means that even the 1000 MW steam turbines in large plants will undertake peak shaving tasks for a long period of time. However, with the peak load regulation, the steam turbines operating in low capacity may be much more likely to cause faults. In this paper, aiming at peak load shaving, a fault diagnosis method of steam turbine vibration has been presented. The major models, namely hierarchy-KNN model on the basis of improved principal component analysis (Improved PCA-HKNN) has been discussed in detail. Additionally, a new fault diagnosis method has been proposed. By applying the PCA improved by information entropy, the vibration and thermal original data are decomposed and classified into a finite number of characteristic parameters and factor matrices. For the peak shaving power plants, the peak load shaving state involving their methods of operation and results of vibration would be elaborated further. Combined with the data and the operation state, the HKNN model is established to carry out the fault diagnosis. Finally, the efficiency and reliability of the improved PCA-HKNN model is discussed. It’s indicated that compared with the traditional method, especially handling the large data, this model enhances the convergence speed and the anti-interference ability of the neural network, reduces the training time and diagnosis time by more than 50%, improving the reliability of the diagnosis from 76% to 97%.

Keywords

Steam turbine fault diagnosis peak load regulation large data

Get full access to this article

View all access options for this article.

References

Lee

C-H

Huang

S-C

Chang

C-A

, et al. Operation of steam turbines under blade failures during the summer peak load periods. Energies 2014; 7: 7415–7433.

Feili

Akar

Lotfizadeh

, et al. Risk analysis of geothermal power plants using Failure Modes and Effects Analysis (FMEA) technique. Energy Convers Manag 2013; 72: 69–76.

Kazemzadeh

M-R

Amjadian

Amraee

. A hybrid data mining driven algorithm for long term electric peak load and energy demand forecasting. Energy 2020; 204: 117948.

Karimi

Akhavan Niaki

Miriha

, et al. A weighted K-means clustering approach to solve the redundancy allocation problem of systems having components with different failures. Proc IMechE, Part O: J Risk and Reliability 2019; 233(6): 925–942.

Tian

Duan

Fan

, et al. Fault diagnostic strategy of multivalued attribute system based on growing algorithm. Proc IMechE, Part O: J Risk and Reliability 2019; 233(2): 235–245.

Michau

Palme

, et al. Feature learning for fault detection in high-dimensional condition monitoring signals. Proc IMechE, Part O: J Risk and Reliability 2020; 234(1): 104–115.

Yang

Z-D

Zhang

Z-Y

. Fault diagnosis of steam turbine rotor based on multi feature extractions and Kernel extreme learning machine. Turbine Technol 2020; 62(2): 137–142.

Tian

Wei

. Vibration fault diagnosis of steam turbines based on VMD and optimized LSSVM. J Chin Soc Power Eng 2019; 39(10): 818–825.

Tamilselvan

Wang

. Failure diagnosis using deep belief learning based health state classification. Reliab Eng Syst Saf 2013; 115: 124–135.

10.

Tran

Althobiani

Ball

. An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks. Expert Syst Appl 2014; 41(9): 4113–4122.

11.

Kuremoto

Kimura

Kobayashi

. Time series forecasting using a deep belief network with restricted Boltzmann machines. Neurocomputing 2014; 137(15): 47–56.

12.

Hrasko

Pacheco

AGC

Krohling

. Time series prediction using restricted Boltzmann machines and back propagation. Procedia Comput Sci 2015; 55: 990–999.

13.

Yuan

Lin

. Fault diagnosis and remaining useful life estimation of aero engine using LSTM neural network. In: IEEE international conference on aircraft utility system, Beijing, China, 10–12 October 2016, pp.135–140. New York: IEEE.

14.

Wang

. Study on signal recognition and diagnosis for spacecraft based on deep learning method. In: Prognostics and system health management conference, Beijing, China, 21–23 October 2016, pp.1–5. New York: IEEE.

15.

Chen

Sánchez

. Multi-layer neural network with deep belief network for gearbox fault diagnosis. J Vibro Eng 2015; 17(5): 2379–2392.

16.

Sun

Shao

Zhao

. A sparse auto-encoder-based deep neural network approach for induction motor faults classification. Measurement 2016; 89: 171–178.

17.

Wang

Xia

. Fault detection and self-learning identification based on PCA-PDBNs. Chin J Sci Instrum 2015; 36(5): 1147–1154.

18.

Chuan

Sánchez

R-V

Zurita

, et al. Fault diagnosis for rotating machinery using vibration measurement deep statistical feature learning. Sensors 2016; 16(6): 895–914.

19.

Yang

Zhou

, et al. Research on fault diagnosis of steam turbine flow passage based on EMD and PNN. J Vib Meas Diagn 2018, 38(6): 1138-1142.

20.

Duan

Liu

Y-L

, et al. An efficient realization of deep learning for traffic data imputation. Transp Res C Emerg Technol 2016; 72: 168–181.

21.

Geng

L-J

X-Y

. Improvements of KNN algorithm for big data classification. Appl Res Comput 2014; 31(5): 1342–1344+1373.

22.

Zhou

Shen

Zhao

, et al. Health management of mechanical equipment based on deep learning: review and prospect. Mod Mach 2018; 4: 19–27.

23.

Zhou

Liu

Yang

, et al. Method for estimating harmonic parameters based on measurement data without phase angle. Energies 2020; 13: 879.

24.

Assaad

Boné

Cardot

. A new boosting algorithm for improved time-series forecasting with recurrent neural networks. Inf Fusion 2006; 9(1): 41–55.