Wind turbine generator measuring and control system and method based on edge computing and deep learning

Abstract

The invention discloses a wind turbine generator measuring and control system and method based on edge computing and deep learning. The system comprises a main server, end sensors, end controllers, end servers and fan main controllers, wherein the end sensors, the end controllers, the end servers and the fan main controllers are installed on fans. The end sensors are located at the potions of to-be-monitored parts of the fans. The end controllers are connected with the end sensors and the end servers. The end controllers store deep learning models. The end controllers are used for obtaining collected data of the end sensors, performing edge computing treatment on the collected data through the deep learning models, storing treatment results in the end servers and generating fan control instructions. The end servers are connected with the main server. The main server is used for obtaining the treatment results through the end servers and issuing the deep learning models to the end controllers. The fan main controllers are connected with the end controllers or the end servers to obtain the fan control instructions and control the fans according to the instructions. All the fans can be rapidly and independently controlled in real time, and a wind turbine generator is more efficiently and intelligently controlled.

Description

technical field [0001] The invention relates to the technical field of wind power generation, in particular to a wind turbine measurement and control system and measurement and control method based on edge computing and deep learning. Background technique [0002] During the development of wind turbines in the direction of intelligence, the requirements for condition monitoring of wind turbines are also continuously increasing. Compared with the past, the type and quantity of current wind turbine status monitoring points have increased significantly, and the installation of monitoring systems for blades, towers, foundations, bolts and other components has become very common. [0003] The current wind turbine monitoring system is mainly based on data collection and real-time status display. The next decision is made by manually reading the operating status. Although it can be operated remotely, it cannot be instant and fast. In addition, manual operation uses the same and si...

AI Technical Summary

Problems solved by technology

[0003] The current wind turbine monitoring system is mainly based on data collection and real-time status display. The next decision is made by manually reading the operating status. Although it can be operated remotely, it cannot be instant and fast.

In addition, manual operation uses the same and single countermeasures for each unit, and it is impossible to coordinate the operation of the entire wind farm in combination with other wind turbines, which is likely to cause a certain loss of resources. Therefore, a more intelligent control method is needed to allow wind farms to operate reliably and efficiently, and to maximize the benefits of wind farms

Images