80results about "Neural network algorithms" patented technology

A method for controlling operation of a wind turbine includes collecting training data, training a machine learning model, obtaining recent data, and applying the machine learning model the recent data to output a reference power or reference power differential corresponding to the recent data. The machine learning model is then applied to the recent data to output at least one of estimated power or estimated power differential corresponding to values of the pitch setpoints and the tip speed ratio setpoints which differ from the recent data. A turbine setting is determined by comparing the estimated power or estimated power differential to the reference power or reference power differential, and then applying the turbine setting to the wind turbine if the estimated power or estimated power differential is greater than or equal to a threshold amount above the reference power or reference power differential.

The invention provides a real-time variable pitch robust control system and a method for a wind turbine based on reinforcement learning. The system comprises a wind speed collection system, a fan information collection module, an enhanced signal generation module, a variable pitch robust control module and a control signal generation module, wherein the wind speed acquisition system is used for collecting the wind speed value in a wind field; the fan information collection module is used for collecting the angular speed of a wind wheel; the enhanced signal generation module can generate an enhanced signal according to the collected wind wheel angular speed and rated wind wheel angular speed; the variable pitch robust control module comprises an action network and an evaluation network, theaction network generates an action value according to the wind speed value in the wind field and the wind wheel angular speed and outputs the action value to the evaluation network, the evaluation network performs learning and training according to the enforced signal and the action value and generates a cumulative return value which is output to the action network, and the action network performs learning and training according to the cumulative return value to update and output the action value; the control signal generation module is connected with the action network to generate the received action value and a corresponding control signal; the wind turbine can adjust the pitch angle according to the control signal, the adjustment of the angular speed of the wind wheel is achieved, andthe smooth output power of a fan is ensured.

The invention relates to a method (200) for monitoring a status of at least one wind turbine. The method (200) comprises: detecting first measurement signals via one or more sensors (210), wherein thefirst measurement signals provide one or more parameters relating to at least one rotor blade of the at least one wind turbine in a normal status; training a trainable algorithm based on the first measurement signals of the normal status (220); detecting second measurement signals via the one or more sensors (230); and recognising an undetermined anomaly via the trainable algorithm trained in thenormal status, if a current status of the wind turbine, determined based on the second measurement signals, deviates from the normal status (240).