Fan blade icing abnormity monitoring method based on fine-grained wind power generation state division

Abstract

The invention discloses a fan blade icing abnormity detection method based on fine-grained wind power generation state division. The fine-grained state division modeling method based on slow feature extraction is provided in a targeted manner after the segmentation characteristic of each variable relationship during variable-working-condition operation of a fan is revealed. Aiming at the dynamic change characteristic of wind power generation, the invention provides a dynamic and static collaborative monitoring method. Data collected by the wind field SCADA system are utilized, the monitoring model of each sub-state is established for the fan by using the method, and the effect of detecting the abnormal output of the fan by using the method provided by the invention is verified offline. Thedynamic characteristic of data when the wind turbine runs is fully utilized, the detection effect is effectively improved, timely diagnosis and processing of the icing condition of the blades by windfield maintenance personnel are facilitated, and therefore normal and stable running of the wind turbine generator set is guaranteed, and meanwhile the safety guarantee coefficient of personnel and property is improved.

Description

technical field [0001] The invention belongs to the field of wind power generation process monitoring, in particular to a method for detecting abnormal icing of fan blades based on fine-grained wind power generation status division. Background technique [0002] According to industry statistics, from January to September 2018, the country's newly added wind power grid-connected capacity was 12.61 million kilowatts, and the cumulative wind power grid-connected capacity reached 176 million kilowatts by the end of September; An increase of 26%; the average utilization hours were 1565 hours, a year-on-year increase of 178 hours; from January to September, the national abandoned wind power was 22.2 billion kWh, a year-on-year decrease of 7.4 billion kWh. [0003] At the same time, economy is still an important factor restricting the development of wind power. Compared with traditional fossil energy power, the cost of wind power generation is still relatively high, and the demand...

AI Technical Summary

Problems solved by technology

However, the icing failure judgment made in this way can usually only be judged in severe icing, and cannot be judged in the early stage of icing

This may be because the previous method cannot effectively utilize the complete information brought by a large number of other measuring points in the fan, and does not consider the characteristics of the variable operating conditions of the fan, as well as the static and dynamic characteristics of the data, so that the overall state of the fan cannot be formed. , accurate and timely monitoring

Images