Wind turbine replacement schedule
A technology of wind turbines and schedules, applied in the direction of wind turbines, control of wind turbines, monitoring of wind turbines, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0049] According to one embodiment, at least one failure condition of at least one component (eg a bearing) of the wind turbine is detected. After a failure state is identified (for example using values of vibration or noise as measured by a microphone or accelerometer), the remaining producible energy (also referred to as residual power generation (RGP)) is estimated. In this context, the RGP can be considered as the distribution of kWh remaining until component failure at a given instance of time. In contrast to conventional considerations of remaining useful life (RUL), RGP is independent of the need for continuous operation. Thus, according to embodiments of the present invention, RGP may be directly associated with performance gains, and thus, with costs involved in operation and maintenance.
[0050] The basic method for estimating remaining producible energy (RGP) can be based on deep learning architectures known as recurrent neural networks (RNNs), such as figure 1...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 

