Fault type determination method and device, computer equipment and readable storage medium

Abstract

The invention relates to a fault type determination method and device, computer equipment and a readable storage medium. The method comprises the following steps: acquiring operation data of an energy internet; determining a target adjacent data quantity and a target dimension M of a local linear embedding algorithm; performing interval dimension reduction processing on the operation data according to the target adjacent data quantity and the target dimension to obtain dimension-reduced operation data; and processing the dimension reduction operation data by using a fault recognition algorithm, and determining a fault type according to a processing result. According to the fault type determination method, the operation data of the energy internet is subjected to dimension reduction processing, and then the fault type is determined according to the dimension-reduced operation data, so that the calculation amount can be reduced, the time can be saved, and the fault diagnosis efficiency can be improved.

Description

technical field [0001] The present application relates to the technical field of Energy Internet, in particular to a fault type determination method, device, computer equipment and readable storage medium. Background technique [0002] With the development of economy and technology, renewable energy sources such as wind energy and solar energy are integrated into the grid on a large scale as distributed power sources. However, the uncertainty, randomness, and volatility of various renewable energy sources will make it very difficult to balance energy supply and demand, and pose challenges to the efficient, safe and stable operation of the Energy Internet. Safe and stable operation is the basis for the construction of the Energy Internet. Because the Energy Internet has distributed faults, large delays, large amounts of information collection, large data dimensions, different time scales caused by strong coupling between electricity and heat, and abnormal Linearity and other...

AI Technical Summary

Problems solved by technology

However, the topology of the Energy Internet is complex, with more and more sensor devices installed, and more and more data volumes and data types available for analysis and mining

When using traditional technology to diagnose a large amount of data obtained from the Energy Internet, it will consume time and energy, making fault diagnosis inefficient

Images