A method and system for electrical load classification based on load characteristic visualization

Abstract

The invention discloses a method for classifying electrical loads based on load characteristic visualization, which includes: collecting voltage data and current data of electrical equipment in a steady state, and performing filtering and sampling processing on the voltage and current data; The current data and voltage data of one cycle are retained as the starting point of zero rise, and a self-incrementing sequence whose length is the number of sampling points in one cycle is added as time data to obtain the current data, voltage data and time data of the electrical equipment after processing. The processed current data, voltage data and time data are subjected to Min-max standardization processing successively, and further arranged into a two-dimensional matrix according to the order of the time domain, and three processed grayscale images are obtained through the PIL library. The invention can solve the technical problems of lack of time information, large image redundancy, low recognition accuracy, complicated calculation process and long judgment time existing in the existing electrical load classification method.

Description

technical field [0001] The invention belongs to the technical field of deep learning and pattern recognition, and more specifically relates to an electrical load classification method and system based on load characteristic visualization. Background technique [0002] With the development of economy and society, there are more and more types of electrical loads such as household appliances. By classifying and managing different electrical loads and applying Internet of Things technology to smart homes, it is the key to realize energy saving and improve power utilization in smart homes. [0003] The existing electrical load classification is mainly realized in the following two ways. The first is to use short-time Fourier transform, wavelet transform and other technologies to analyze the transient characteristics of the electrical load such as instantaneous power, transient current waveform and duration, and According to the analysis results, the classification of electrical...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the above defects or improvement needs of the prior art, the present invention provides a method and system for classifying electrical loads based on visualization of load characteristics. Monitoring, which will increase the technical problem of energy consumption, and the technical problem that the traditional wavelet algorithm cannot achieve real-time classification due to the slow calculation speed and long time consumption, and the lack of time information due to the electrical load characteristics and the redundancy of the voltage-current trajectory image. Large technical problems that affect the classification accuracy, as well as the technical problems that the actual classification effect is poor due to the low recognition rate of the model calculated by the machine learning algorithm and the poor robustness and practicability of the model

Images