Fault line selection method for power distribution network containing distributed generation based on deep belief network

Abstract

The invention discloses a fault line selection method for a power distribution network containing distributed generation based on a deep belief network. The method comprises the steps of acquiring zero-sequence current and voltage signals of the head end of each feeder line under different single-phase grounding fault conditions; extracting steady-state and transient-state characteristic quantities contained in the zero-sequence current and voltage signals; performing data and polarity pretreatment on the original characteristic quantity; and performing fault line selection and positioning byadopting a deep belief network algorithm. According to the invention, the deep learning theory is applied to small-current grounding fault positioning containing the distributed generation, better fault tolerance is achieved, the accuracy of small-current grounding fault line selection can be improved, and the reliability and the safety of the operation of the power distribution network are improved at the same time.

Description

technical field [0001] The invention relates to the technical field of distribution network fault location, in particular to a fault line selection method for a distribution network containing distributed power sources based on a deep belief network. Background technique [0002] Among all kinds of faults in the distribution network, 80% are single-phase to ground short-circuit faults. In my country, the 6-35kV medium and low-voltage distribution network often adopts two small-current grounding methods: neutral point ungrounded or arc suppression coil grounded. When a single-phase short-circuit fault occurs, the fault current amplitude is very small, making the fault The characteristic information is not obvious, but if the single-phase fault in the distribution network is not dealt with in time, it will lead to further phase-to-phase short circuit and expand the impact of the fault. And with the addition of distributed power, the situation will be more complicated. Therefo...

AI Technical Summary

Problems solved by technology

[0005] (1) Expert system: This method is to use the relay protection in the power grid, the action principle of the circuit breaker and the past fault finding experience of the dispatcher to form the knowledge base of the expert system in the fault diagnosis, and obtain the inference result according to the real-time alarm signal according to the knowledge base , but this method is slow, poor in fault tolerance, and cannot learn independently

[0006] (2) Fault location method based on support vector machine: This method simplifies the usual classification and regression problems, and the learning speed is fast, but its disadvantage is that it is difficult to implement for large-scale training samples

[0007] (3) Fault location method based on artificial neural network: This method uses fault signals to carry out self-learning, its nonlinear mapping and fault tolerance are very strong, and it is good at solving more complicated problems of solving the potential relationship between input and output, but the disadvantage is The neural network has a slow convergence speed, a large amount of calculation, and it is easy to fall into a local optimum

Images