Research on Power Transformer Fault Forecast
To forecast power transformer fault, this paper proposed a integrated algorithm. Research found that discrete time series of power transformer dissolved gases concentration have 2 main types: the s type and the monotone increasing type. The gray verhulst model was chosen for forecasting the s type series, while the gray model predicted the monotone increasing type data. The two models combined a new integrated forecast model. The fault diagnosis method combines the improved three-ratio method and gray artificial immune algorithm, so it can diagnoses both single and multi power transformer faults, and give the fault location. Experiments show that the power transformer fault forecast algorithm is effective and reliable.
Helen Zhang, Gang Shen and David Jin
R. R. Zheng et al., "Research on Power Transformer Fault Forecast", Advanced Materials Research, Vols. 204-210, pp. 1553-1558, 2011