Transformer fault prediction method based on monitoring data of dissolved gas in oil of transformer

Abstract

The invention provides a transformer fault prediction method based on monitoring data of a dissolved gas in the oil of a transformer. The method includes the following steps of: optimization of historical online data of the dissolved gas in the oil of the transformer, model identification of the optimized data, estimation of auto-regression moving average model parameters, model checking and establishment. With the transformer fault prediction method adopted, the content of the characteristic gas in the oil of the transformer at any time point in the future can be predicted, and therefore, the faults of the transformer can be judged, and maintenance measures can be put forward. Compared with the prior art, the method can improve sample quality, embody individual characteristics of the transformer and reflect a characteristic that the dissolved gas in the oil changes with time. Since data obtained through adopting the method do not change abruptly, the method can make more stable and concise physical interpretation compared with a prediction model which is established through adopting traditional machine learning. With the transformer fault prediction method adopted, the accuracy of online data prediction of the dissolved gas in the oil of the transformer can be improved, and fault prediction and maintenance measures can be more accurate and reliable; a reliable guarantee can be provided for the maintenance and use of the transformer; and the service life of the transformer can be prolonged.

Description

technical field [0001] The invention relates to a power equipment fault prediction technology, in particular to a transformer fault prediction method based on monitoring data of dissolved gas in transformer oil. Background technique [0002] As a main transformation equipment in the power grid, the transformer plays a pivotal role in the power grid. Therefore, the research on condition-based maintenance technology of transformers is particularly important. On-line monitoring technology is an important part of condition-based maintenance technology, and on-line monitoring of dissolved gas in oil, as a comprehensive and highly sensitive monitoring method, has been rapidly applied and promoted. , At the same time, it has also become an effective means of transformer maintenance and evaluation. On-line monitoring of dissolved gas in transformer oil can be used in two aspects of fault diagnosis and prediction. Among them, the fault prediction technology requires that some fault ...

AI Technical Summary

Problems solved by technology

The biggest feature of these methods is to iterate repeatedly according to the sample until a suitable model is found. The main problem caused by this feature is the unknowability of the iterative process, that is, the iterated mathematical model lacks physical explanation and cannot reflect the time-domain characteristics of the data.

Moreover, the machine learning method has high requirements on the data quality of the iterative samples. Since the online monitoring equipment will be affected by on-site interference and environmental factors, the data quality is difficult to guarantee. Using these problematic data as machine learning training samples will lead to prediction model failure. Changes drastically with the length of time, which will directly lead to unstable prediction results and cannot guarantee the accuracy of the prediction

Images