Abstract
Large sized transformers are an important part of global power systems and industrial infrastructures. An unexpected failure of a power transformer can cause severe production damage and significant loss throughput the power grid. In order to prevent power facilities from malfunctions and breakdowns, the development of real-time monitoring and health prediction tools are of great interests to both researchers and practitioners. An advanced monitoring tool performs real-time monitoring of key parameters to detect signals of potential failure through data mining techniques and prediction models. Asset managers use the result to develop a suitable maintenance and repair strategy for failure prevention. Principal component analysis (PCA) and back-propagation artificial neural network (BP-ANN) are the algorithms adopted in the research. This chapter utilizes industrial power transformers’ historical data from Taiwan and Australia to train and test the failure prediction models and to verify the proposed methodology. First, PCA detects the conditions of transformers by identifying the state of dissolved gasses. Then, the BP-ANN health prediction model is trained using the key factor values. The integrated engineering asset management database includes nine gases in oil as input factors (N2, O2, CO2, CO, H2, CH4, C2H4, C2H6, and C2H2). After applying the principal components algorithm, the research identifies five factors from the Taiwan operational transformer data and six factors from the Australia data. The integrated PCA and BP-ANN fault diagnosis system yields effective and accurate predictions when tested using Taiwan and Australia data. The accuracy rates are much higher (i.e., 92 and 96 % respectively) when compared to previous result of 69 and 75 %. This research is benchmarked against the DGA heuristic approaches including IEEE’s Doernenburg and Rogers and IEC’s Duval Triangle for the experimental fault diagnoses.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abu-Elanien AEB, Salama MMA (2010) Asset management techniques for transformers. Electr Power Syst Res 80(4):456–464
Bhalla D, Bansal RK, HiO Gupta (2012) Function analysis based rule extraction from artificial neural networks for transformer incipient fault diagnosis. Electr Power Energy Syst 43(1):1196–1203
Cybenko G (1989) Approximation by superpositions of a sigmoidal function. Math Control Signals Syst 5(4):303–314
Elangovan M, Babu Devasenapati S, Sakthivel NR, Ramachandran KI (2011) Evaluation of expert system for condition monitoring of a single point cutting tool using principle component analysis and decision tree algorithm. Expert Syst Appl 38(4):4450–4459
El-Hag AH, Saker YA, Shurrab IY (2011) Online oil condition monitoring using a partial- discharge signal. IEEE Trans Power Deliv 26(2):1288–1289
Ghunem RA, El-Hag AH, Assaleh K (2010) Prediction of furan content in transformer oil using artificial neural networks (ANN). In: IEEE international symposium on electrical insulation (ISEI), San Diego, CA, USA, June 6–9, 1–4
Hair J, Anderson R, Tathan R, Black W (1998) Multivar data anal. Macmillan, NJ
Hastings NAJ (2010) Physical asset management. Springer, London
Hornik K, Stinchcombe M, White H (1989) Multi-layer feedforward networks are universal approximations. Neural Netw 2(5):336–359
Ma C, Tang WHT, Yang Z, Wu QH, Fitch J (2007) Asset managing the power dilemma. IEEE Control Autom Mag 18(5):40–45. IEEE Press, October–November
Ma L (2007) Condition monitoring in engineering asset management. Asia-Pacific Vibration Conference (APVC), August 6–9, Sapporo, Japan, pp 1–16
Parkes D (1978) Terotechnology handbook. Her Majesty’s Stationery Office, London
PAS 55-1 (2008) Asset management: specification for the optimized management of physical assets. British Standards Institution, UK
Roberts C, Dassanayake HPB, Lehrasab N, Goodman CJ (2002) Distributed quantitative and qualitative fault diagnosis: railway junction case study. Control Eng Pract 10(4):419–429
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning internal representations by error propagation. Parallel Distrib Process: Explor Microstruct Cognit 1:318–363
Sakthivel NR, Sugumaranb V, Nair BB (2010) Comparison of decision tree-fuzzy and rough set-fuzzy methods for fault categorization of mono-block centrifugal pump. Mech Syst Signal Process 24(6):1887–1906
Shintemirov A, Tang W, Wu QH (2009) Power transformer fault classification based on dissolved gas analysis by implementing bootstrap and genetic programming. IEEE Trans Syst Man Cybern-Part C: Appl Rev 39(1):69–79
Trappey AJC, Trappey CV, Ni WC (2013) A multi-agent collaborative maintenance platform applying game theory negotiation strategies. J Intell Manuf 24(3):613–623
Werbos P (1974) The roots of backpropagation. Wiley, Canada
Wu ML (1999) SPSS & the application and analysis of statistics. Wu Nan Publishing Company, Taiwan
Xiao F, Wang SW, Xu XH, Ge G (2009) An isolation enhanced PCA method with expert-based multivariate decoupling for sensor FDD in air-conditioning systems. Appl Therm Eng 29(4):712–722
Zurada JM (1992) Introduction to artificial neural systems. West Publishing Company, Minnesota
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Trappey, A.J.C., Trappey, C.V., Ma, L., Chang, J.C. (2015). Integrating Real-Time Monitoring and Asset Health Prediction for Power Transformer Intelligent Maintenance and Decision Support. In: Tse, P., Mathew, J., Wong, K., Lam, R., Ko, C. (eds) Engineering Asset Management - Systems, Professional Practices and Certification. Lecture Notes in Mechanical Engineering. Springer, Cham. https://doi.org/10.1007/978-3-319-09507-3_46
Download citation
DOI: https://doi.org/10.1007/978-3-319-09507-3_46
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-09506-6
Online ISBN: 978-3-319-09507-3
eBook Packages: EngineeringEngineering (R0)