Wind turbine generator state monitoring method based on OC-RKELM

Abstract

The invention discloses a wind turbine generator state monitoring method based on OC-RKELM. The method comprises the following steps of 1, acquiring operation data and environmental parameter data of a wind turbine generator; 2, cleaning the acquired data of the wind turbine generator; and establishing a health data set of the normal operation data of the wind turbine generator; 3, based on the health data set of the wind turbine generator, establishing mathematical description for the health data set by utilizing an OCRKELM model; 4, determining a health threshold based on analysis of historical normal data so as to judge whether the operation data belongs to the health data set of the wind turbine generator or not; and 5, correspondingly processing real-time operation data of the wind turbine generator, judging whether the real-time operation data of the wind turbine generator is normal operation data or not based on the OCRKELM model, and carrying out early warning and shutdown inspection on the wind turbine generator when an early warning condition is met. The method is less in intervention and simple to implement, can effectively detect abnormality of a running state of the wind turbine generator, and can provide technical support for operation and maintenance of a wind power plant.

Description

technical field [0001] The invention relates to the technical field of wind power, in particular to an OC-RKELM-based wind power unit state monitoring method. Background technique [0002] In order to deal with problems such as environmental pollution and energy crisis, countries around the world are vigorously developing the wind power industry, and the cumulative installed capacity of wind turbines continues to grow. As of the end of 2019, the global installed capacity of wind turbines has reached 651GW, and hundreds of thousands of wind turbines are being connected to the grid. The design life of a wind turbine is usually 20 years. During its service life cycle, due to the adverse effects of various environments, loads, materials and other factors, all components of the wind turbine will inevitably produce cumulative damage, resistance attenuation and functional degradation, and even Serious malfunctions may occur. Condition monitoring technology can detect abnormalitie...

AI Technical Summary

Problems solved by technology

[0003] Existing data acquisition and supervisory control and control (SCADA) system status monitoring technology is only realized by setting thresholds for one-dimensional characteristic parameters, and can only find extreme abnormal data; the existing wind power data visualization analysis technology requires professional analysts to analyze The power curve and other graphs of wind turbines are analyzed or the wind farm is monitored by experienced personnel. The labor cost is high and the real-time performance is poor; the existing condition monitoring technology based on neural network modeling has strong parameters. Randomness, the generalization and stability of the model are difficult to guarantee

Images