A wind power generator failure early warning and alarm method

Abstract

The invention relates to a failure early warning and alarming method for a wind-driven generator. The method comprises the following steps of (1) reading the historical data of a sensor; (2) preprocessing the historical data; (3) establishing a normal sensor data sequence library; (4) reading a real-time sensor data sequence; (5) normalizing the sensor data sequence; (6) performing data sequence correlation operation; and (7) performing failure early warning and alarming. Compared with the conventional failure alarming method for the wind-driven generator, the method has the advantages that failure marking over massive sensor data of the wind-driven generator is not required, and a finite-length sensor data sequence corresponding to the normal running state of the wind-driven generator is only required to be extracted, so that the implementation workload and the implementation difficulty are effectively reduced; and in addition, the sensor data sequence required by analysis is finite in length, so that the operational efficiency is effectively improved, and an alarm about a failure of the wind-driven generator can be given in real time.

Description

technical field [0001] The invention relates to a wind power generator, in particular to a fault warning and alarm method for a wind power generator. Background technique [0002] With the country's great investment in the wind power energy industry, the scale of wind farms has expanded rapidly, causing the operation and management of wind power companies to face enormous pressure, especially in the management and maintenance of wind power generators. At the same time, wind power generator failures and shutdowns occur from time to time, and wind power companies are worried about sudden accidents. At present, the operation and maintenance methods of wind turbines used have a certain lag, and the technical level of the maintenance and repair personnel of wind turbines on site is generally low, so it is difficult to maintain and repair wind turbines in a timely and effective manner. [0003] Due to the continuous construction and operation of wind farms and the rapid increase ...

AI Technical Summary

Problems solved by technology

Due to the shortage of wind turbine maintenance resources and limited technical conditions, it is difficult to maintain and repair wind turbines in a timely manner, so that timely maintenance and repair of wind turbines cannot be carried out during the inspection interval. It will not be repaired until the wind turbine fails, which will not only cause maintenance downtime losses, but also increase the maintenance cost of wind turbines

[0004] Since the wind turbine is in normal operation most of the time, it is easy to find the sensor data sequence corresponding to the normal operation state of the wind turbine, but it is relatively difficult to find the sensor data sequence corresponding to the fault state of the wind turbine

Finding the sequence of sensor data corresponding to the fault state of the wind turbine is more difficult, especially in the case of imperfect records of wind turbine faults

Images