Intelligent photovoltaic-power-station fault diagnosis method based on similarity of layered KPI (Key Performance Indicator)

Abstract

The invention discloses an intelligent photovoltaic-power-station fault diagnosis method based on the similarity of layered KPI (Key Performance Indicator). The intelligent photovoltaic-power-station fault diagnosis method comprises the following steps of: dividing centralized operation and maintenance management objects of a photovoltaic power station into a group-layer management object, a power-station-layer management object and an equipment-layer management object; extracting KPIs of the power-station-layer management object and the equipment-layer management object as feature quantities, and setting feature weights of the feature quantities according to the levels of the management objects and the importance degree of equipment; then carrying out normalization processing on the feature quantities of all management objects in a layered model according to the weights and obtaining normalization values of all layers of the centralized operation and maintenance; then, judging whether the equipment at the layer has a fault according to similarity of the normalization values of the management objects at all the layers and the optimum normalization value at the layer, and finally positioning faulted positions by a mode of layer-layer progressive comparison. The intelligent photovoltaic-power-station fault diagnosis method disclosed by the invention is applicable to photovoltaic power generation groups for centralized operation and maintenance systems of the photovoltaic power stations, and has general adaptability in fault diagnosis; the intelligent photovoltaic-power-station fault diagnosis method is intuitive in vision and easy in use, and has the advantages that the faulted positions can be rapidly positioned, the operation and maintenance efficiency can be effectively improved and the operation and maintenance cost can be reduced.

Description

technical field [0001] The invention belongs to the technical field of new energy, and in particular relates to a fault diagnosis method for an intelligent photovoltaic power station based on hierarchical KPI similarity. Background technique [0002] At present, the photovoltaic industry is developing rapidly. It is estimated that by 2020, my country's photovoltaic installed capacity will reach 150GW. Due to the openness of its industry, the photovoltaic industry has basically formed a group operation model, and a group has multiple photovoltaic power plants under its jurisdiction. Moreover, with favorable policies and markets, enterprise groups continue to enter the photovoltaic industry. After the completion of photovoltaic power plants under the group, the biggest problem is operation and maintenance. In order to increase power generation and reduce operation and maintenance costs, each enterprise group needs to Centralized operation and maintenance of photovoltaic power...

AI Technical Summary

Problems solved by technology

[0003] In the current operation and maintenance of smart photovoltaic power plants, the fault location of equipment lacks effective means and methods, mainly relying on the experience of operation and maintenance personnel, which is inefficient and relatively high cost

Images