Assessment Of Electric Power Equipment Aging Trend Based On Robust Locally Weighted Regression Algorithm

As usual equipment aging phenomenon,a great many number of power companies have gradually pay close attention to it.Until now,most of power companies by means of deterministic method based on engineering judgment have still judged electric power equipment out of service for aging.According to causing a lot of malpractice for engineering judgment,a method based on robust locally weighted regression algorithm is proposed to evaluate the aging trend of electric power equipment in the paper.The method using robust locally weighted regression algorithm combined with the actual operation state and the actual operation characteristics of electric power equipment analyze the aging state of electric power equipment,which is able to approach the aging process of electric power equipment,make out very lively estimation to the electric power equipment aging trend and build model of electric power equipment aging.Thereby,it can provide an early forecasted for equipment aging causing equipment fault and provide a scientific basis of equipment out of service for equipment aging causing equipment maintainability and equipment fault.In the paper,the transforms in one actual power system are analyzed according to the method;the analysis result is basic in accord with actual operation state of transformers,which verify effectiveness of the method. The method has an important guiding significance for power system planning,analysis of reserving electric power equipment and pushes forward the electric power market-based process.