Power equipment diagnosis method integrating negative selection algorithm and radial basis function

Abstract

The invention relates to the technical field of artificial intelligence, in particular to a power equipment diagnosis method integrating a negative selection algorithm and a radial basis function. Themethod comprises the following steps: S1, preprocessing fault data through a negative selection algorithm, and classifying different fault samples; s2, performing a machine learning algorithm througha radial basis function to realize fault diagnosis of the power distribution equipment; fault data are preprocessed through a negative selection algorithm, different fault samples are classified, machine learning is carried out through a radial basis function neural network function, and finally fault diagnosis of the power distribution equipment is achieved.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a method for diagnosing electric power equipment that combines a negative selection algorithm and a radial basis function. Background technique [0002] The existing fault diagnosis methods always have their own limitations, so a single diagnosis technique cannot solve all problems. Fault diagnosis based on expert system diagnoses random events by learning multi-expert knowledge, but it is difficult to acquire knowledge, the ability to update the knowledge base is poor, and the contradiction between expert knowledge in multiple fields is difficult to handle. Capabilities are very limited, making rule-based expert systems very limited. Fault diagnosis based on artificial neural network has nonlinear large-scale parallel distributed processing, self-organization, and self-learning capabilities, but its own learning requires typical fault samples, and it is difficul...

AI Technical Summary

Problems solved by technology

[0002] The existing fault diagnosis methods always have their own limitations, so it is not possible to solve all problems with a single diagnosis technique

Fault diagnosis based on expert system diagnoses random events by learning multi-expert knowledge, but it is difficult to acquire knowledge, the ability to update the knowledge base is poor, and the contradiction between expert knowledge in multiple fields is difficult to handle. Capabilities are very limited, making rule-based expert systems very limited

Fault diagnosis based on artificial neural network has nonlinear large-scale parallel distributed processing, self-organization, and self-learning capabilities, but its own learning requires typical fault samples, and it is difficult to collect fault data of power equipment, and it is not easy to classify faults

Images