• Vol 7, No 4 (2016)
  • Electrical, Electronics, and Computer Engineering

Performance Analysis of an Automatic Green Pellet Nuclear Fuel Quality Classification using Modified Radial Basis Function Neural Networks

Benyamin Kusumoputro, Dede Sutarya, Akhmad Faqih

Corresponding email: kusumo@ee.ui.ac.id


Published at : 29 Apr 2016
IJtech : IJtech Vol 7, No 4 (2016)
DOI : https://doi.org/10.14716/ijtech.v7i4.3138

Cite this article as:

Kusumoputro, B., & Sutarya, D.& Faqih, A. 2016. Performance Analysis of an Automatic Green Pellet Nuclear Fuel Quality Classification using Modified Radial Basis Function Neural Networks. International Journal of Technology. Volume 7(4), pp.709-719

209
Downloads
Benyamin Kusumoputro Computational Intelligence and Intelligent System Research Group, Dept. of Electrical Engineering, Faculty of Engineering, Universitas Indonesia, Kampus Baru UI, Depok 16424, Indonesia
Dede Sutarya Center of Technology for Nuclear Fuels, Badan Tenaga Atom Nasional, Kompleks PUSPIPTEK Serpong, Serpong 15314, Indonesia
Akhmad Faqih Computational Intelligence and Intelligent System Research Group, Dept. of Electrical Engineering, Faculty of Engineering, Universitas Indonesia, Kampus Baru UI, Depok 16424, Indonesia
Email to Corresponding Author

Abstract
image

Cylindrical uranium dioxide pellets, which are the main components for nuclear fuel elements in light water reactors, should have a high density profile, a uniform shape, and a minimum standard quality for their safe use as a reactor fuel component. The quality of green pellets is conventionally monitored by laboratory measurement of the physical pellet characteristics; however, this conventional classification method shows some drawbacks, such as difficult usage, low accuracy, and high time consumption. In addition, the method does not address the non-linearity and complexity of the relationship between pellet quality variables and pellet quality. This paper presents the development and application of a modified Radial Basis Function neural network (RBF NN) as an automatic classification system for green pellet quality. The weight initialization of the neural networks in this modified RBF NN is calculated through an orthogonal least squared method, and in conjunction with the use of a sigmoid activation function on its output neurons. Experimental data confirm that the developed modified RBF NN shows higher recognition capability when compared with that of the conventional RBF NNs. Further experimental results show that optimizing the quality classification problem space through eigen decomposition method provides a higher recognition rate with up to 98% accuracy.

Green pellet quality classification, Nuclear fuel cell, Orthogonal least squared method, RBF NN, Weight initialization

References

Alotaibi, F.D., Abdennour, A., Ali, A.A., 2007. A Robust Prediction Model using ANFIS based on Recent TETRA Outdoor RF Measurements Conducted in Riyadh City-Saudi Arabia. International Journal of Electronic Communication (AEU), Volume X(x), pp. X-x

Batan, 2007. Safety Analysis Report-IEBE, Center of Nuclear Fuel Technology, no.doc. KK20J09003

Briyatmoko, B., Rachmawati, M., Yulianto, T., 2010. Current Status of R&D of Nuclear Fuel Elements for PWR in Indonesia. In: Advanced Fuel Pellet Materials and Fuel Rod Design for Water Cooled Reactors, IAEA-TTECDOC-1654, pp. 99–104

Fukunaga, K. 1990. Introduction to Statistical Pattern Recognition. Academic Press, San Diego, California, USA

Garcia, A., Luviano-Juarez, A., Chaires, A., Poznyak, A., Poznyak, T., 2011. Projectional Dynamic Neural Networks Identifier for Chaotic Systems: Applications to Chua Circuit. International Journal of Artificial Intelligence, Volume 6, S11, pp. 1–18

Haykin, S., 1996. Adaptive Filter Theory, 3rd ed., Prentice-Hall, Upper Saddle River, New Jersey, USA

Hornik, K., Stinchcombe, M., White, H., 1989. Multilayer Feedforward

Networks are Universal Approximators, Neural Networks, Volume 2(5), pp. 359–366

Jayaraj, R.N., Ganguly, C., 2003. Recent Developments in Design and Manufacture of Uranium Dioxide Fuel Pellets for PHWRs in India. In: Proceedings of a Technical Committee Meeting, IAEA-TECDOC-1416, Brussels, Belgium, pp. 13–20

Jothiprakash, V., Magar, R.B., Kalkuthi, S., 2009. Rainfalls-runoffs Models using Adaptive Neuro-Fuzzy Inference System (ANFIS) for an Intermittent River. International Journal of Artificial Intelligence, Volume 3, A03, pp. 1–23

Kusumoputro, B., Faqih, A., Sutarya, D., Lina, 2013. Quality Classification of Green Pellet Nuclear Fuels using Radial Basis Function Neural Networks. In: IEEE Proceedings of the 12th International Conference of Machine Learning and Applications, Florida, USA, pp. 194–198

Kusumoputro, B., Lina, Kresnaraman, B., 2011. Improvement of Recognition Capability of Fuzzy-Neuro LVQ using Fuzzy Eigen Decomposition for Discriminating Three-Mixture Fragrances Odor. Information Technology Journal, Volume 10(12), pp. 2385–2391

Nguyen, D., Widrow, B., 1990. Improving the Learning Speed of the 2-Layer Neural Networks by Choosing Initial Values of Adaptive Weights. In: Proceedings of the IJJN, Volume 3, San Diego, California, USA, pp. 21–26

Pramanik, D., Ravindran, M., Rao, G.V.S.H, Jararaj, R.N., 2010. Innovative Process Techniques to Optimize Quality and Microstructure of UO2 Fuel for PHWRs in India. In: Advanced Fuel Pellet Materials and Fuel Rod Design for Water Cooled Reactors, IAEA-TTECDOC-1654, pp. 13–34

Sarma, K.K., 2009. Neural Network Based Feature Extraction for Assamese Character and Numeral Recognition. International Journal of Artificial Intelligence, Volume 2, S09, pp. 37–56

Sutarya, D., Kusumoputro, B., 2011. Quality Classification of Uranium Dioxide Pellets for PWR Reactor using ANFIS. IEEE Tencon 2011, Bali, Indonesia, pp. 314–318

Swets, D.L., Weng, J., 1996. Using Discriminant Eigenfeatures for Image Retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 18, pp. 831–836

Table of Contents