Distribution network equipment health degree dynamic diagnosis method involving credibility evaluation

Abstract

The invention provides a distribution network equipment health degree dynamic diagnosis method involving credibility evaluation. The method comprises the following steps: step (1), obtaining an original feature set of power distribution monitoring quantity; step (2), determining an important status variable through correlation analysis for information of failure equipment and non-failure equipment; step (3), carrying out data quality pretreatment on data of the important status variable determined in the step (2); step (4), marking the important status variable after treated in the step (3); and step (5), inputting a marking result of the important status variable into an evaluation model, and obtaining an evaluation result. The phenomena of data collision and data redundancy appearing in the process of collecting equipment status variables are solved through data credibility evaluation and fusion of different criterial evaluation results, and meanwhile self-updating of the evaluation model is realized through dynamic regulation, so that the method is applicable to power distribution networks with constant development and change.

Description

technical field [0001] The invention relates to the technical field of distribution network equipment, in particular to a method for dynamically diagnosing the health of distribution network equipment considering reliability evaluation. Background technique [0002] Distribution network equipment is the final link of power supply to users and plays an important role in the power grid, so the security and stability of power distribution network is particularly important. With the economic development and urbanization process, the scale of my country's distribution network has become larger and larger, and users have stricter requirements on the reliability of power supply. Compared with the high-voltage power grid, the voltage level of distribution network equipment is low, the number of equipment is large, the grid structure is complex, and the online monitoring equipment is not perfect. Therefore, the state of the distribution network equipment can be evaluated by establis...

AI Technical Summary

Problems solved by technology

[0003] At present, the State Grid Corporation of China has formulated distribution network equipment evaluation standards, but the criteria of these models can only be compared with a certain fixed threshold or a fixed ratio of thresholds.

Because most of the evaluated equipment in the distribution network is in good condition, if a fixed model standard is applied, it may happen that all equipment evaluation results are within the specified threshold for a long time (decades), and no equipment can be repaired; Then, as the equipment aged in batches, the evaluation results of a large number of equipment suddenly exceeded the specified threshold within a few years, resulting in a sharp increase in the maintenance workload in a short period of time, and the equipment maintenance work could not be carried out normally.

Images