A novel plugged tube detection and identification approach for final super heater in thermal power plant using principal component analysis

Abstract During startup or normal operations, tube monitoring systems for steam boilers can considerably improve efficiency and reliability in thermal power plants (TPPs). Although several attempts have been made to detect and locate boiler tube leaks, what seems to be lacking is the study for tube plugging, one of the fundamental causes of the leaks and other tube failures. Scale and deposit formations on inner surfaces of tubes cause the tubes to be plugged. Although the formations can be suppressed and removed by chemical treatments for boiler water and steam blowing during startup procedures, it is still difficult to monitor and prevent tube plugging during startup or normal operations. In this paper, a novel plugged tube detection and identification approach is proposed for final super heater (FSH) tube banks. Principal component analysis is applied to tube temperature data for plugging detection and identification. The data are collected from thermocouples installed on the FSH outlet header section. To identify plugged tubes, contribution analysis and the characteristics of plugged tube temperatures are employed. To verify the performance of the proposed method, tube temperature data from an 870 MW supercritical coal-fired TPP are used. The experiment results show that the proposed method can successfully detect and identify plugged tubes. The proposed method can help to decide how many times steam blowing should be performed, whether startup procedures should be delayed or stopped, and which tubes should be maintained. Furthermore, severe tube failures can be prevented by avoiding damage from overheating due to tube plugging.

[1]  John E Oakey Power plant life management and performance improvement , 2011 .

[2]  Socrates Dokos,et al.  Multiscale Two-Directional Two-Dimensional Principal Component Analysis and Its Application to High-Dimensional Biomedical Signal Classification , 2016, IEEE Transactions on Biomedical Engineering.

[3]  Lei Tian,et al.  A genetic-algorithm-based selective principal component analysis (GA-SPCA) method for high-dimensional data feature extraction , 2003, IEEE Trans. Geosci. Remote. Sens..

[4]  Ali Ajami,et al.  Data driven approach for fault detection and diagnosis of turbine in thermal power plant using Independent Component Analysis (ICA) , 2012 .

[5]  Yu Liu,et al.  Image Denoising Using Quadtree-Based Nonlocal Means With Locally Adaptive Principal Component Analysis , 2016, IEEE Signal Processing Letters.

[6]  Chun-Chin Hsu,et al.  An Adaptive Forecast-Based Chart for Non-Gaussian Processes Monitoring: With Application to Equipment Malfunctions Detection in a Thermal Power Plant , 2011, IEEE Transactions on Control Systems Technology.

[7]  Samarendra Dandapat,et al.  Multichannel ECG Data Compression Based on Multiscale Principal Component Analysis , 2012, IEEE Transactions on Information Technology in Biomedicine.

[8]  Farid Kadri,et al.  Improved principal component analysis for anomaly detection: Application to an emergency department , 2015, Comput. Ind. Eng..

[9]  Naim Afgan,et al.  Boiler tube leakage detection expert system , 1998 .

[10]  Liansuo An,et al.  Power station boiler furnace water-cooling wall tube leak locating method based on acoustic theory , 2015 .

[11]  Haitao Zhao,et al.  A novel incremental principal component analysis and its application for face recognition , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[12]  Dawid Taler,et al.  Thermal simulation of superheaters taking into account the processes occurring on the side of the steam and flue gas , 2015 .

[13]  Muhammad Riaz,et al.  An improved PCA method with application to boiler leak detection. , 2005, ISA transactions.

[14]  Damian Flynn,et al.  Thermal Power Plant Simulation and Control , 2003 .

[15]  June Ho Park,et al.  A Clustering-Based Fault Detection Method for Steam Boiler Tube in Thermal Power Plant , 2016 .

[16]  Dipak K. Sarkar,et al.  Thermal Power Plant: Design and Operation , 2015 .

[17]  A. K Raja,et al.  Power Plant Engineering , 1998 .

[18]  Ahmet Palazoglu,et al.  A data-driven multidimensional visualization technique for process fault detection and diagnosis , 2016 .

[19]  Minyoung Kim,et al.  Greedy Learning of Sparse Eigenfaces for Face Recognition and Tracking , 2014, Int. J. Fuzzy Log. Intell. Syst..

[20]  Hongwei Liu,et al.  Noise Reduction Method Based on Principal Component Analysis With Beta Process for Micro-Doppler Radar Signatures , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[21]  Tongwen Chen,et al.  Efficient model-based leak detection in boiler steam-water systems , 2002 .

[22]  Shuang Liu,et al.  Coupled principal component analysis based face recognition in heterogeneous sensor networks , 2016, Signal Process..

[23]  Qing Li,et al.  Fault detection and isolation for self powered neutron detectors based on Principal Component Analysis , 2015 .

[24]  Liang Zhao,et al.  Fault detection in time-varying chemical process through incremental principal component analysis , 2016 .

[25]  Erik Dotzauer,et al.  Bayesian network-based early-warning for leakage in recovery boilers , 2008 .

[26]  Hazem Nounou,et al.  Statistical fault detection using PCA-based GLR hypothesis testing , 2013 .

[27]  G. H. Babcock,et al.  Steam / its generation and use , 1972 .

[28]  Augusto Sarti,et al.  Hyperbolic boiler tube leak location based on quaternary acoustic array , 2011 .

[29]  Anna Jankowska,et al.  Early detection and prediction of leaks in fluidized-bed boilers using artificial neural networks , 2015 .

[30]  Weihua Gui,et al.  Latent space transformation based on principal component analysis for adaptive fault detection , 2010 .

[31]  Baligh Mnassri,et al.  Reconstruction-based contribution approaches for improved fault diagnosis using principal component analysis , 2015 .

[32]  Hazem Nounou,et al.  PLS-based EWMA fault detection strategy for process monitoring , 2015 .