Feature classification-based power distribution network voltage loss fault intelligent identification method

Abstract

The invention relates to a feature classification-based power distribution network voltage loss fault intelligent identification method. The method comprises the following steps that: learning data and prediction data are acquired, and data cleaning is carried out; a fault evaluation index system is constructed based on a voltage loss fault type, wherein the fault evaluation index system comprisesa sudden change voltage loss characteristic, a trend voltage loss characteristic and a jump voltage loss characteristic, and a learning sample and a prediction sample are formed; the learning sampleis divided into a training set and a test set, a voltage loss fault identification model is learnt by using the training set, and the effect of the model is evaluated based on the test set; and finally, with the prediction sample adopted as the input quantity of the voltage loss fault identification model, the voltage loss fault suspicion coefficient of each user is outputted, and a fault suspicion user is locked. According to the method, voltage loss fault types including sudden change voltage loss, trend voltage loss and jump voltage loss are refined; the suspicion of the voltage loss faultsof the users is analyzed according to the different types of voltage loss faults, so that the effective and accurate identification of the voltage loss faults can be realized; and a fault detection management mode is improved to a management level of pre-event prevention and in-event control.

Description

Technical field [0001] The invention relates to the technical field of power distribution network loss of voltage fault identification, and in particular to a method for intelligently identifying a power loss fault of a distribution network based on feature classification. Background technique [0002] In the three-phase power supply system, the electric energy metering device often has various failures due to factors such as fuse fusing. Among them, the loss of voltage is the most prominent. The abnormal measurement of the electric energy metering device caused by the failure not only causes power loss to the power enterprise, but also to the subsequent Electricity tracking brings certain difficulties. In order to avoid and reduce such losses, it is necessary to quickly and accurately discover metering faults and deal with them in a timely and effective manner to ensure the reliable and normal operation of the metering device. [0003] Traditional metering failure detection metho...

AI Technical Summary

Problems solved by technology

[0002] In the three-phase power supply system, the electric energy metering device often has various faults due to factors such as fuse blown, among which the failure of voltage loss is the most prominent. Battery replenishment brings certain difficulties

[0004] In the current research on the identification of voltage loss faults based on data mining technology, although classification models such as neural networks can be used to classify fault users and normal users at a certain level, they generally classify voltage loss into one type analysis, there is a high rate of missed judgment

Images