Research On Reliability Evaluation For Transformer Based On Operating State And Insulation Life

The reliability of a power transformer refers to its ability to continue safe and stable operation in the power system.As one of the key equipments of the power grid,the health status of power transformer is related to the safety and stability of the entire power grid.In the event of a failure,it is highly likely to cause a power outage and huge economic losses.Considering multiple factors to comprehensively evaluate the reliability of the transformer and timely formulate corresponding maintenance strategies can avoid losses and hazards caused by abnormal operation of the transformer as much as possible,which is of great significance for the safe and stable operation of the power system.Therefore,this paper firstly diagnoses and evaluates the life of the transformer,and considers the operating state score and insulation life of the transformer at the same time.The reliability evaluation model based on the operating state and insulation aging is established,and the reliability evaluation of the transformer is realized.Firstly a new method of transformer fault diagnosis based on artificial bee colony correlation vector machine is proposed to eliminate the influence of the randomness of parameter selection on the classification accuracy of the algorithm.The method takes DGA data as the feature input,the correlation vector machine kernel function parameters as the food source,and the correct rate as the fitness.The artificial bee colony algorithm is used to find the food source position with the highest fitness,so as to obtain the optimal kernel function parameters and improve the parameters.Compared with the traditional optimization algorithm,the artificial bee colony algorithm seeks the optimal solution through iterative and neighborhood search strategies,which largely avoids the parameters falling into local optimum and improves the classification accuracy rate.Secondly,in order to improve the insulation aging degree and moisture content evaluation accuracy of transformer oil paper,the insulation life of transformer is accurately evaluated.Based on the correction factor algorithm,a new evaluation method of oil paper insulation state is proposed,and the degree of polymerization and water content are explored in the correction factor algorithm.On the basis of the transformer's equivalent hot spot temperature,an insulation life assessment model under the combined influence of aging,moisture and temperature is established,and a life assessment method is proposed.The example is verified by applying the correction factor method to evaluate the moisture content and polymerization value of the main insulation of the field transformer,and calculate the insulation life.The effectiveness of the insulation life assessment model is preliminarily verified.Finally,in order to comprehensively consider the influence of transformer primary insulation aging development and operating state on the failure rate,a transformer reliability evaluation model based on insulation aging and operating state is established to improve the accuracy of transformer reliability assessment.By establishing the relationship between operating state and life expectancy,the operating state score is introduced into the aging life assessment model,and a new model of insulation aging and operating state to characterize the failure rate is proposed.The new failure rate model is fitted based on historical sample data,which proves that the new model has the ability to characterize the actual failure rate.