Health evaluation method of wind turbines based on diffusion map data dimensionality reduction technology

Abstract

The invention discloses a wind generating set health degree assessment method based on a diffusion diagram data dimension reduction technology. The method comprises the steps of collecting the sampledata, constructing a detection model, determining a health state curved surface, selecting different fault centroids, carrying out data dimension reduction, assessing the health degree of a whole machine and assessing the health degree of the key components of a wind generating set. The beneficial effects of the invention are that the health decline index of the wind generating set is monitored toensure the safe operation of the wind generating set; the inspection and maintenance are arranged in time when the health degree of the wind generating set declines, the unnecessary manpower and material resource loss is avoided, the real-time health degree assessment can be carried out on the wind generating set and the key components thereof; and the diffusion diagram data dimension reduction technology realizes the visualization of the health degree of the wind generating set, monitors the health index decline condition of the wind generating set in advance, has the guiding significance for the on-site maintenance personnel, optimizes a maintenance scheme, and reduces the waste of the manpower and material resources, so that the operation and maintenance cost of the wind generating setis reduced.

Description

technical field [0001] The invention relates to a method for evaluating the health of a wind power generating set, in particular to a method for evaluating the health of a wind generating set based on a diffusion graph data dimensionality reduction technology, and belongs to the technical field of data collection and monitoring of a wind generating set. Background technique [0002] Wind power generation refers to the conversion of wind kinetic energy into electrical energy. Wind energy is a clean and pollution-free renewable energy source. It can compete with conventional energy sources, and wind power technology has also been greatly developed. [0003] At present, wind turbines mainly rely on condition monitoring and fault diagnosis for operation and maintenance, and there is no method for evaluating the health of wind turbines. The health status of wind turbines cannot be monitored effectively in a timely manner. After a fault occurs, the damage is strong, resulting in ...

AI Technical Summary

Problems solved by technology

It is impossible to monitor the health status of wind turbines in a timely and effective manner. After a fault occurs, the damage is strong, resulting in the loss of manpower and material resources, which greatly increases the cost of operation and maintenance.

Images