This paper presents novel research on the development of a generic intelligent oil fraction sensor based on Electrical Capacitance Tomography (ECT) data. An artificial Neural Network (ANN) has been employed as the intelligent system to sense and estimate oil fractions from the cross-sections of two-component flows comprising oil and gas in a pipeline. Previous works only focused on estimating the oil fraction in the pipeline based on fixed ECT sensor parameters. With fixed ECT design sensors, an oil fraction neural sensor can be trained to deal with ECT data based on the particular sensor parameters, hence the neural sensor is not generic. This work focuses on development of a generic neural oil fraction sensor based on training a Multi-Layer Perceptron (MLP) ANN with various ECT sensor parameters. On average, the proposed oil fraction neural sensor has shown to be able to give a mean absolute error of 3.05% for various ECT sensor sizes.
References
[1]
Ismail, I.; Gamio, J.C.; Bukhari, S.F.A.; Yang, W.Q. Tomography for multi-phase flow measurement in the oil industry. Flow Meas. Instrum. 2005, 16, 145–155.
[2]
Xie, D.; Li, W.; Wang, F.; Zheng, J.; Zheng, Y.; Liang, G. A new method for the flowrate measurement of gas-liquid two-phase flow. IEEE Trans. Instrum. Meas. 2007, 56, 1495–1500.
[3]
York, T.A.; Ukpong, A.; Mylvaganam, S.; Yu, R. Parameter Estimation from Tomographic Data Using Self-Organising Maps. Proceedings of the 2012 IEEE International Conference on Imaging Systems and Techniques, Manchester, UK, 16–17 July 2012; pp. 112–116.
[4]
Yi, L.; Yang, W.Q.; Wu, Z.P.; Tsamakis, D.; Xie, C.G.; Huang, S.M.; Lenn, C. Gas/Oil/Water Flow Measurement by Electrical capacitance Tomography. Proceedings of the 2012 IEEE International Conference on Imaging Systems and Techniques, Manchester, UK, 16–17 July 2012; pp. 83–88.
[5]
Soleimani, M.; Stewart, V.J.; Budd, C.J. Crack detection in dielectric objects using electrical capacitance tomography imaging. Insight Non-destr. Test. Cond. Monit. 2011, 53, 21–24.
[6]
Jablonka, K.; Glovnea, R.; Bongaerts, J. Evaluation of EHD films by electrical capacitance. J. Phys. D Appl. Phys. 2012, 45, 1–8.
[7]
Grudzien, K.; Chaniecki, Z.; Romanowski, A.; Niedostatkiewicz, M.; Sankowski, D. ECT image analysis methods for shear zone measurements during silo discharging process. Chin. J. Chem. Eng. 2012, 20, 337–345.
[8]
Elmy, J.M.; Ruzairi, A.R.; Ling, L.P.; Hafiz, F.R.M.; Omar, M.F.M.; Muzakkir, A.N. Visualization of recovered palm oil using portable ECT imager in extraction palm oil process. Flow Meas. Instrum. 2013. Available online: http://www.sciencedirect.com/science/article/pii/S0955598612001173 (accessed on 22 February 2013).
[9]
Wang, H.; Yang, W. Scale-up of an electrical capacitance tomography sensor for imaging pharmaceutical fluidized beds and validation by computational fluid dynamics. Meas. Sci. Technol. 2011, 22, 1–11.
[10]
Rezvanpour, A.; Wang, C.-H.; Liang, Y.C.; Yang, W. Investigation of droplet distribution in electrohydrodynamic atomization (EHDA) using an ac-based electrical capacitance tomography (ECT) system with an internal-external electrode sensor. Meas. Sci. Technol. 2012, 23, 1–10.
[11]
Yang, W.Q.; Peng, L. Image reconstruction algorithms for electrical capacitance tomography. Meas. Sci. Technol. 2003, 14, R1–R13.
[12]
Kjaergaard-Rasmussen, J.; Yang, W.Q. A Compact Electrical capacitance Tomography System. Proceedings of the IEEE International Workshop on Imaging Systems and Techniques, Crete, Greece, 10–12 September 2008; pp. 175–180.
[13]
Ying, J. Design and implementation of hardware system for electrical capacitance tomography. Proceedings of First International Workshop on Education Technology and Computer Science ETCS 2009, Hubei, China, 7–8 March 2009; pp. 588–593.
[14]
Olmos, A.M.; Carvajal, M.A.; Morales, D.P.; Garcia, A.; Palma, A.J. Development of an electrical capacitance tomography system using four rotating electrodes. Sens. Actuat. A-Phy. 2008, 148, 366–375.
[15]
Duggan, P.M.; York, T.A. Tomographic Image Reconstruction using RAM-based Neural Networks. Proceedings of the Process Tomography—Implementation for Industrial Processes—PROC. European Concerted Action on Process Tomography (ECAPT): Bergen, Norway, 1995; pp. 411–419.
[16]
Williams, P.; York, T. Hardware implementation of RAM-based neural networks for tomographic data processing. IEE Proc. Comput. Digit. Tech. 1999, 146, 114–118.
[17]
Yang, W.Q.; York, T.A. New AC-based capacitance tomography system. IEE Proc. Sci. Meas. Technol. 1999, 146, 47–53.
[18]
Yang, W.Q. Further developments in an ac-based capacitance tomography system. Rev. Sci. Instr. 2001, 72, 3902–3907.
[19]
Jing, L.; Liu, S.; Li, Z.; Meng, S. An image reconstruction algorithm based on the extended Tikhonov regularisation method for electrical capacitance tomography. Measurement 2009, 42, 368–376.
[20]
Jing, L. A Novel Image Reconstruction Algorithm for Electrical capacitance Tomography. Proceedings of the 2010 International Conference on Intelligent System Design and Engineering Application, Changsha, China, 13–14 October 2010; pp. 120–123.
[21]
Jing, L.; Shi, L.; Wang, X.; Liu, Q. An image reconstruction algorithm for electrical capacitance tomography based on robust principal component analysis. Sensors 2013, 13, 2076–2092.
[22]
Wang, L.; Du, X.; Shao, X. A hybrid ECT image reconstruction based in Tikhonov regularisation theory and SIRT algorithm. J. Phys. Conf. Ser. 2006, 48, 1453–1458.
[23]
Nooralahiyan, A.Y.; Hoyle, B.S.; Bailey, A.J. Pattern and Association and Feature Extraction in Electrical capacitance Tomography. Proceedings of the European Concerted Action on Process Tomography (ECAPT), Oporto, Portugal, 24–26 March 1994.
Nooralahiyan, A.Y.; Hoyle, B.S.; Bailey, A.J. Neural networks for pattern association in electrical capacitance tomography. IEE Proc. Circuits Devices Syst. 1994, 141, 517–521.
[26]
Nooralahiyan, A.Y.; Hoyle, B.S.; Bailey, A.J. Performance of neural network in capacitance-based tomographic process measurement systems. Meas. Control 1995, 28, 109–112.
[27]
Wang, W. Voidage measurement of gas-oil two-phase flow. Chin. J. Chem. Eng. 2007, 15, 339–344.
[28]
Chen, Y.; Song, Y.; Zhang, J. A Novel Principal Component Analysis Flow Pattern Identification Algorithm for Electrical capacitance Tomography System. Proceedings of 2010 International Conference on Machine Vision and Human-machine Interface, Kaifeng, China, 24–25 April 2010; pp. 235–238.
[29]
Yang, W.Q.; Wu, Z.; Tsamakis, D.; Cheng-Gang, X.; Huang, S.; Lenn, C.; Learmonth, D.; Cutler, A. Multiphase Flow Measurement by Electrical capacitance Tomography. Proceedings of 2011 IEEE International Conference on Imaging Systems and Techniques, Penang, Malaysia, 17–18 May 2011; pp. 108–111.
[30]
Qiu, C.; Hoyle, B.S.; Podd, F.J.W. Engineering and application of a dual-modality process tomography system. Flow Meas. Instrum. 2007, 18, 247–254.
[31]
Xie, C.G.; Plaskowski, A.; Beck, M.S. 8-electrode capacitance system for two-component flow identification. Part 1: Tomographic flow imaging. IEE Proc-G. 1989, 136, 173–183.
[32]
Yang, W.Q.; Spink, D.M.; York, T.A.; McCann, H. An image reconstruction algorithm based on Landweber's iteration for electrical-capacitance tomography. Meas. Sci. Technol. 1999, 10, 1065–1069.
Li, Y.; Yang, W.Q. Image reconstruction by nonlinear Landweber iteration for complicated distribution. Meas. Sci. Technol. 2008, 19, 1–8.
[35]
Lee, S.H.; Lee, S.B.; Kim, Y.S.; Kim, J.H.; Choi, B.Y.; Kim, K.Y. A Filtering Approach of Iterative Tikhonov Regularization Method in ECT. Proceedings of the 5th IEEE Conference on Sensors, Daegu, Korea, 22–25 October 2006; pp. 919–922.
[36]
Xie, C.G.; Huang, S.M.; Hoyle, B.S.; Thorn, R.; Lenn, C.; Snowden, D.; Beck, M.S. Electrical capacitance tomography for flow imaging—system model for development of image reconstruction algorithms and design of primary sensors. IEE Proc-G. 1992, 139, 89–98.
[37]
Mohamad Saleh, J.; Hoyle, B.S. Determination of multi-component flow process parameters based on electrical capacitance tomography data using artificial neural network. Meas. Sci. Technol. 2002, 13, 1815–1821.
[38]
Mohamad Saleh, J.; Hoyle, B.S.; Podd, F.J.W.; Spink, D.M. Direct process estimation from tomographic data using artificial neural systems. J. Electron. Imaging 2001, 10, 646–652.
[39]
Yan, H.; Shao, F.; Wang, S. Simulation Study of capacitance Tomography Sensors. Proceedings of the 1st World Congress on Industrial Process Tomography, Buxton, Greater Manchester, UK, 14–17 April 1999; pp. 388–394.
[40]
Somerville, A.; Evans, I.; York, T. Preliminary Studies of Planar capacitance Tomography. Proceedings of the 1st World Congress on Industrial Process Tomography, Buxton, Greater Manchester, 14–17 April 1999; pp. 522–529.
[41]
Osman–Ali, N.; Mohamad–Saleh, J.; Abdul–Aziz, Z.; Talib, H. Optimization of electrical capacitance tomography sensor using design of experiment method. J. Teknologi. 2012, 55, 87–99.
Mohamad, E.J.; Marwah, O.M.F.; Rahim, R.A.; Rahiman, M.H.F.; Muji, S.Z.M. Electronic Design for Portable Electrical capacitance Sensor: A Multiphase Flow Measurement. Proceedings of the 4th International Conference on Mechatronics (ICOM), Kuala Lumpur, Malaysia, 17–19 May 2011; pp. 1–8.
[44]
Donthi, S.S. capacitance Based Tomography for Industrial Applications. M. Tech. Credit Seminar Report; Electronic Systems Group, IIT Bombay, 2004; pp. 1–18.
[45]
Spink, D.M. Direct finite element solution for the capacitance, conductance or inductance, and force in linear electrostatic and magnetostatic problems. COMPEL-Int. J. Comput. Math. Elec. 1996, 15, 70–84.
[46]
Mohamad Saleh, J. Neural Computation Applied to Process Interpretation from Tomographic Data. PhD Thesis, University of Leeds, United Kingdom, 2001.
[47]
Kotsianis, S.B. Supervised machine learning: A review of classification technique. Informatica 2007, 31, 249–268.
[48]
Lin, W.-J.; Chen, J.J. Class-imbalaced classifiers for high dimensional data. Brief. Bioinform. 2013, 14, 13–26.
[49]
Wefky, A.M.; Espinosa, F.; Jiménez, J.A.; Santiso, E.; Rodríguez, J.M.; Fernández, A.J. Alternative sensor system and MLP neural network for vehicle pedal activity estimation. Sensors 2010, 10, 3798–3814.
[50]
Pan, C.H.; Hsieh, H.Y.; Tang, K.T. An analog multilayer perceptron neural network for a portable electronic nose. Sensors 2013, 13, 193–207.
[51]
Mohamad Saleh, J.; Jamaludin, R.; Talib, H. Capacitance-based tomography flow pattern classification using intelligent classifiers with voting technique. J. Teknologi. 2011, 55, 75–85.
[52]
Rumelhart, D.E.; McClelland, J.L. Parallel Distributed Processing; MIT Press: Cambridge, MA, USA, 1987.
[53]
Saracoglu, ？.G. An artificial neural network approach for the prediction of absorption measurements of an evanescent field fiber sensor. Sensors 2008, 8, 1585–1594.
[54]
Sarigiannis, D.A.; Karakitsios, S.P.; Gotti, A.; Papaloukas, C.L.; Kassomenos, P.A.; Pilidis, G.A. Bayesian algorithm implementation in a real time exposure assessment model on benzene with calculation of associated cancer risks. Sensors 2009, 9, 731–755.
[55]
Efendioglu, H.S.; Yildirim, T.; Fidanboylu, K. Prediction of force measurements of a microbend sensor based on an artificial neural network. Sensors 2009, 9, 7167–7176.
[56]
Sapon, M.A.; Ismail, K.; Zainudin, S. Prediction of Diabetes by Using Artificial Neural Network. Proceedings of the 2011 International Conference on Circuits, System and Simulation, Singapore, 28–29 May 2011; pp. 299–303.
[57]
Saric, A.; Xiao, J. Efficient Levenberg-Marquardt Minimization of the Cross-Entropy Error Function. Proceedings of the 2011 International Joint Conference on Neural Networks, San Jose, CA, USA, 31 July–5 August 2011; pp. 1–8.
[58]
Plumb, P.; Rowe, R.C.; York, P.; Brown, M. Optimization of the predictive ability of artificial neural network (ANN) model: A comparison of three ANN programs and four classes of training algorithms. Eur. J. Pharm. Sci. 2005, 25, 395–405.
[59]
Makhfi, S.; Velasco, R.; Habak, M.; Haddouche, K.; Vantomme, P. An optimized ANN approach for cutting forces prediction in AISI 52100 bearing steel hard turning. Sci. Technol. 2013, 3, 24–32.
