Detection of Water Content in Transformer Oil Using Multi Frequency Ultrasonic with PCA-GA-BPNN

The water content in oil is closely related to the deterioration performance of an insulation system, and accurate prediction of water content in oil is important for the stability and security level of power systems. A novel method of measuring water content in transformer oil using multi frequency ultrasonic with a back propagation neural network that was optimized by principal component analysis and genetic algorithm (PCA-GA-BPNN), is reported in this paper. 160 oil samples of different water content were investigated using the multi frequency ultrasonic detection technology. Then the multi frequency ultrasonic data were preprocessed using principal component analysis (PCA), which was implemented to obtain main principal components containing 95% of original information. After that, a genetic algorithm (GA) was incorporated to optimize the parameters for a back propagation neural network (BPNN), including the weight and threshold. Finally, the BPNN model with the optimized parameters was trained with a random 150 sets of pretreatment data, and the generalization ability of the model was tested with the remaining 10 sets. The mean squared error of the test sets was 8.65 × 10−5, with a correlation coefficient of 0.98. Results show that the developed PCA-GA-BPNN model is robust and enables accurate prediction of a water content in transformer oil using multi frequency ultrasonic technology.

[1]  Fei He,et al.  Prediction model of end-point phosphorus content in BOF steelmaking process based on PCA and BP neural network , 2018, Journal of Process Control.

[2]  Min Deng,et al.  Study of Partial Discharge Localization Using Ultrasonics in Power Transformer Based on Particle Swarm Optimization , 2008, IEEE Transactions on Dielectrics and Electrical Insulation.

[3]  Sunil Kumar,et al.  Artificial neural network based modeling to evaluate methane yield from biogas in a laboratory-scale anaerobic bioreactor. , 2016, Bioresource technology.

[4]  N. Lelekakis,et al.  Measuring Paper Water Content of Transformers: A New Approach Using Cellulose Isotherms in Nonequilibrium Conditions , 2013, IEEE Transactions on Power Delivery.

[5]  Shun-ichi Amari,et al.  Network information criterion-determining the number of hidden units for an artificial neural network model , 1994, IEEE Trans. Neural Networks.

[6]  A. Roli.  Artificial Neural Networks , 2012, Lecture Notes in Computer Science.

[7]  Jianhua Mo,et al.  Springback prediction of high-strength sheet metal under air bending forming and tool design based on GA–BPNN , 2011 .

[8]  Rajesh Kumar,et al.  Pt nanoparticles decorated SnO2 nanoneedles for efficient CO gas sensing applications , 2018 .

[9]  Mohammad Reza Meybodi,et al.  A learning automata-based algorithm for determination of the number of hidden units for three-layer neural networks , 2009, Int. J. Syst. Sci..

[10]  Olav Krause,et al.  Measuring the Pressboard Water Content of Transformers Using Cellulose Isotherms and the Frequency Components of Water Migration , 2017, IEEE Transactions on Power Delivery.

[11]  Nie Peng,et al.  Prediction of tool VB value based on PCA and BP neural network , 2011 .

[12]  Lei Wu,et al.  Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and GA-BP neural network method , 2016 .

[13]  Shuzhi Sam Ge,et al.  Highly Accurate Time-of-Flight Measurement Technique Based on Phase-Correlation for Ultrasonic Ranging , 2017, IEEE Sensors Journal.

[14]  Chao Ren,et al.  Research on soil moisture inversion method based on GA-BP neural network model , 2018, International Journal of Remote Sensing.

[15]  M. M. Youssef,et al.  Applications of ultrasound in analysis, processing and quality control of food: A review , 2012 .

[16]  P Jacquemart.  [A progressive method of medical examination: ultrasonic echotomography]. , 1974, L' Information dentaire.

[17]  Shuyi Cheng,et al.  Use of ultrasonic array method for positioning multiple partial discharge sources in transformer oil. , 2014, The Review of scientific instruments.

[18]  M. Duval,et al.  Monitor for Hydrogen Dissolved in Transformer Oil , 1977, IEEE Transactions on Electrical Insulation.

[19]  Shifei Ding,et al.  An optimizing BP neural network algorithm based on genetic algorithm , 2011, Artificial Intelligence Review.

[20]  Jae-Chul Kim,et al.  The analysis of ultrasonic signals by partial discharge and noise from the transformer , 2005 .

[21]  Weigen Chen,et al.  Highly sensitive carbon monoxide (CO) gas sensors based on Ni and Zn doped SnO2 nanomaterials , 2018 .

[22]  M.K. Pradhan,et al.  Assessment of the status of insulation during thermal stress accelerated experiments on transformer prototypes , 2006, IEEE Transactions on Dielectrics and Electrical Insulation.

[23]  Daniel Martin,et al.  Fundamental concepts of using water activity probes to assess transformer insulation water content , 2016, IEEE Electrical Insulation Magazine.

[24]  K. Torkos,et al.  A New Analytical Method for the Determination of the Water Content of Transformer Oils , 1982, IEEE Transactions on Electrical Insulation.

[25]  J. Dayhoff,et al.  Artificial neural networks , 2001, Cancer.

[26]  James L. Kirtley,et al.  An improved transformer top oil temperature model for use in an on-line monitoring and diagnostic system , 1997 .

[27]  Ch. Ratnam,et al.  Ultrasonic based structural damage detection using combined finite element and model Lamb wave propagation parameters in composite materials , 2013 .

[28]  Tapan K. Saha,et al.  Understanding the impact of moisture and ageing of transformer insulation on frequency domain spectroscopy , 2014, IEEE Transactions on Dielectrics and Electrical Insulation.

[29]  L. Lundgaard,et al.  Ageing of Mineral Oil Impregnated Cellulose by Acid Catalysis , 2008, IEEE Transactions on Dielectrics and Electrical Insulation.

[30]  J. Rubio-Serrano,et al.  Electro-acoustic detection, identification and location of partial discharge sources in oil-paper insulation systems , 2012, IEEE Transactions on Dielectrics and Electrical Insulation.

[31]  Liu Ke,et al.  Research on the Forecast Model of Electricity Power Industry Loan Based on GA-BP Neural Network , 2012 .

[32]  J. A. Alvarez-Chavez,et al.  Direct optical techniques for the measurement of water content in oil–paper insulation in power transformers , 2011 .

[33]  Dian Zheng Zhuang,et al.  Application and Study of BP Neural Network and Genetic Algorithm for Optimizational Parameters Based on MATLAB , 2013 .

[34]  Saeed Mohajeryami,et al.  Estimation of water content in a power transformer using moisture dynamic measurement of its oil , 2017 .