00000ctm a22000004a 4500 UP-99796217611306123 Buklod 20230215105418.0 m |o d | ta 140609s xx d r |||| u| (iLib)UPD-00221205173 DENGII rda eng DMLUC LG 995 2014 E64 M35 Malabanan, Daniel R. author. Power transformer condition assessment using an immune neural network approach to dissolved gas analysis Daniel R. Malabanan. Quezon City College of Engineering, University of the Philippines Diliman 2014. xiv, 163 leaves color illustrations 28 cm text rdacontent unmediated rdamedia volume rdacarrier Thesis (M.S. Electrical Engineering)--University of the Philippines, Diliman. One commonly used engineering tool for condition assessment of power transformers is Dissolved Gas Analysis (DGA), which can detect internal and incipient faults and can be done without disrupting the operation of the transformer. The drawback of DGA is that the conventional methods used to interpret DGA test results have limitations. To address the limitations of the conventional methods, this paper proposes a combined Artificial Immune System (AIS) and Artificial Neural network (ANN), called an Immune Neural Network, to provice an alternative approach for condition assessment of transformers. The paper used a Radial Basis Function Neural Network (RBFNN) for non-linear mapping of DGA data inputs, such as gas concentrations of five dissolved gases (hydrogen, methane, ethane, ethylene, and acetylene) in transformer oil, rate of increase of gas concentrations in ppm/day, and gas ratios, to different transformer health conditions such as normal condition and faulty conditions involving internal arcing, localized overheating, partial discharge activity, or multiple faults. An immune system-inspired model known as the aiNet model was used to determine the centers of the RBFNN. The aiNet was compared to random selection and k-means clustering in determining the RBFNN hidden centers. It was proven in the study that the aiNet has better training convergence, and has an advantage over k-means due to non-empty clusters results. The study also showed that unlike conventional methods, the Immune Neural Network approach always gives a definite diagnosis and has better diagnosis accuracy for normal, single-fault, and multi-fault transformer conditions. Electric transformers. Gases Analysis. Neural networks (Computer science). Thesis FI UP UPD DARCHIVES LG 995 2014 E64 M35 UPD DENG-II LG 995 2014 E64 M35 Thesis