Equipment type identification method combining electric power fingerprint knowledge and neural network

Abstract

The invention discloses an equipment type identification method combining electric power fingerprint knowledge and a neural network. The method comprises the following steps: S1, acquiring voltage and current sampling data when equipment is used; S2, setting a time interval, and segmenting the data obtained in S1; S3, converting the data obtained in the step S2 into common electrical characteristic quantities; S4, inputting the electrical characteristic quantity obtained in the S3 into a knowledge extraction model to obtain electric power fingerprint knowledge points of the equipment; S5, encoding the electric power fingerprint knowledge points obtained in the step S4, and splicing the electric power fingerprint knowledge points with the electric characteristic quantities obtained in the step S3 to obtain a total characteristic vector; And S6, inputting the total feature vector obtained in the step S5 into a trained neural network to obtain the equipment type. Compared with a traditional load identification method, the invention has the advantages that a machine learning method and a knowledge-driven method are organically combined, the requirement for the data size can be greatly reduced, the convergence data and judgment speed of the model can be increased, and the accuracy of the model can be improved.

Description

technical field [0001] The invention relates to a device type identification method combined with power fingerprint knowledge and a neural network, and belongs to the technical field of load identification. Background technique [0002] With the gradual improvement of the electrical measurement system of the power grid, more and more electrical measurement devices are put into use, and it becomes possible to use monitoring data for load identification. At present, there are many load identification methods proposed, but they mainly focus on completely data-driven machine learning methods, and few people consider combining expert experience and knowledge for load identification. Such as the Chinese patent application (publication number CN105974219B) proposes to use voltage, current and power factor to carry out load identification, is based on the identification method of complete data drive, the shortcoming is that these three equipments with relatively close data volume ca...

AI Technical Summary

Problems solved by technology

Such as the Chinese patent application (publication number CN105974219B) proposes to use voltage, current and power factor to carry out load identification, is based on the identification method of complete data drive, the disadvantage is that these three devices with relatively close data volume cannot be identified; such as Chinese patent (publication number CN111914899A) proposes to combine artificial rules and machine learning for identification, although it is combined with partial knowledge for identification, but the knowledge comes from a data-driven decision tree and does not belong to interpretable expert experience and knowledge

Images