An abnormal monitoring method for fan blade icing based on fine-grained wind power generation state division

Abstract

The invention discloses a method for detecting abnormal icing of fan blades based on fine-grained wind power generation status division. After revealing the segmental characteristics of the relationship between variables in the variable operating conditions of the wind turbine, a fine-grained state partition modeling method based on slow feature extraction is proposed. Aiming at the dynamic characteristics of wind power generation, a dynamic and static monitoring method is proposed. Using the data collected by the SCADA system of the wind farm, the above method is used to establish the monitoring model of each sub-state of the wind turbine, and the effect of the method proposed in this paper to detect the abnormal output of the wind turbine is verified offline. It makes full use of the dynamic characteristics of the data when the wind turbine is running, effectively improves the detection effect, and helps the wind farm maintenance personnel to diagnose and deal with the blade icing in a timely manner, thus ensuring the normal and stable operation of the wind turbine. The safety factor of personnel and property has been 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