Multi-level direct current fault arc detection method based on parameter matching

Abstract

The invention discloses a multi-level direct current fault arc detection method based on parameter matching, and the method comprises the steps: obtaining a system signal in real time, improving the fault arc component proportion through signal filtering processing, then carrying out the fault arc feature analysis and state learning, and using training time as a core evaluation target in the fault arc state identification training process; testing a trained fault arc state identification model, and taking the comprehensive judgment accuracy, the response time, the detection sensitivity and the parameter optimization time of direct current fault arc generation detection through the model as DC fault arc detection performance evaluation targets; adopting a particle swarm optimization to carry out multi-objective optimization, so that multi-link detection parameters in the whole process of direct-current fault arc detection achieve global optimal matching, and the detection effect is cooperatively improved. Therefore, urgent demands of reliable detection of various complex fault arcs caused by multi-noise source interference and operation environment difference in different direct current power supply scenes is dynamically met.

Description

technical field [0001] The invention belongs to the technical field of electrical fault detection, and relates to a DC fault arc detection method, in particular to a multi-dimensional fault arc detection performance evaluation target group constructed by applying a particle swarm optimization algorithm to globally optimize and match the detection parameters of a multi-level classification model, thereby It meets the requirements for accurate detection of various and complex DC fault arcs under the interference of multiple noise sources and different operating environments that can dynamically adapt to application scenarios. Background technique [0002] The arc fault protection device is one of the core equipments to ensure the safety and reliability of DC power supply. It fundamentally guarantees the reliable operation of the system and the safety of power consumption. It is also one of the bottlenecks restricting the rapid development of DC systems. The "dual carbon" goal ...

AI Technical Summary

Problems solved by technology

However, at present, there is no method to optimize and match the multi-link parameters of the multi-level DC arc fault detection process by using the particle swarm optimization algorithm, and there is no multi-dimensional target for comprehensive evaluation of the DC fault arc detection performance.

Images