الفهرس 
Reactive model
Transformer Condition AssessmentOnly 14 pages are availabe for public view
 |  | from | 227 |  |  |
| | | from | 227 | | |
Abstract
In this thesis, a new methodology is adopted to develop an enhanced transformer predictive Asset Management (AM) model. The increase in the distribution networks load demand is the major motivation for this work. The distribution networks performance is highly affected by the condition and the lifetime of the working transformers.
The proposed strategy relies upon assessing the present condition of transformers by calculating the Health Indices (HI). Calculating the transformer (HI) score is undertaken utilizing (14) distinct oil transformer measurements. The measurements were acquired in the field for a total of 804 transformers. One major research step was the calculation of HI by optimizing and identifying the most significant diagnostic measurements and developing a model using Binary Cat Swarm Optimization (BCSO) with Support Vector Machines (SVM) for this purpose. A Self-Adaptive Neuro-Fuzzy Interference System (ANFIS) predictor model is adopted using the Particle Swarm Optimization (PSO) technique and utilized for the prediction of the optimized HI. The study is undertaken by processing two actual field measurements for working distribution transformers (≤69kV) within the network of industrial facilities.
The Institute of Electrical and Electronics Engineers (IEEE) Transformer Life Expectancy (TLE) model is utilized in the following step in the current research to build an enhanced life expectancy model. The enhanced model is developed relying on the calculated transformer HI in addition to the transformer loading conditions. A direct relationship between the IEEE ageing factors and the HI ageing factors is identified and projected. The enhanced model is capable of integrating factors affecting transformers. Faults and maintenance that the transformer is subjected to are amongst factors taken into consideration to improve the life expectancy model.
The reliability score calculation is applied as a Key Performance Indicator (KPI) for assessing the transformers as well as the distribution network. The calculated transformer HI score with the aid of historical failure rate are utilized during the calculation of the distribution network reliability score. An application on distribution network with transformers and loads is analyzed to verify the strategy effectiveness. The results of this research are the basis for an enhancement for the smart grids performance estimation.