Secondary system defect data mining method based on top-k and pso

Abstract

The invention discloses a secondary system defect data mining method based on top-k and pso, and the method comprises the following steps: 1, recording the abnormal condition of equipment: in an intelligent station, secondary equipment is equipment which assists primary equipment, the reliability of the secondary equipment affects the performance of a whole power grid, and most of the equipment can achieve an online self-checking function; when equipment is abnormal, data can be uploaded through a station control layer network, meanwhile, the data can be stored in a local database, and the data can be used for mining frequent item sets and association rules after being preprocessed. According to the method, the support degree of each set is recorded through the set data dictionary, and then the confidence is solved by utilizing the pso algorithm and combining the target function formed by the rule number and the average confidence, so the parameter optimization is realized, and the data is not deleted as much as possible while the overall result is ensured to have higher confidence.

Description

technical field [0001] The invention relates to the technical field of system data mining, in particular to a secondary system defect data mining method based on top-k and pso. Background technique [0002] PSO is the English abbreviation of particle swarm optimization algorithm (ParticleSwarmOptimization), which is a population-based stochastic optimization technique proposed by Eberhart and Kennedy in 1995. Particle swarm algorithm imitates the flocking behavior of insects, herds of animals, birds and fish, etc. These groups look for food in a cooperative way, and each member of the group constantly changes by learning its own experience and the experience of other members. its search mode. [0003] Under normal circumstances, there are a large amount of defect data of the substation secondary system at the intelligent station terminal. These data can use correlation analysis to mine the hidden relationship behind them, so as to provide auxiliary strategies. The tradition...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the need to set support, confidence and other indicators to screen the appropriate rules in order to overcome the existence of the prior art. The indicators need to be manually set. For the problem of a large amount of manpower, a secondary system defect data mining method based on top-k and pso is provided. The secondary system defect data mining method based on top-k and pso has the effect of simple process and no need for a large amount of manpower

Images