Controlling a Turbine with a Recurrent Neural Network

摘要

The invention relates to a method for controlling a turbine which is characterized by a hidden state at each point in time of the control. The dynamic behavior of the turbine is modeled using a recurrent neural network comprising a recurrent hidden layer. The recurrent hidden layer is formed by vectors of neurons which describe the hidden state of the turbine at the points in time of the control. For each point in time, two vectors are connected chronologically to a first connection which bridges one point in time, and two vectors are additionally connected chronologically to a second connection which bridges at least two points in time. Short-term effects can be corrected by means of the first connections, and long-term effects can be corrected by means of the second connections. Emissions and occurring dynamics can be minimized in the turbine by means of the latter. The invention further relates to a control device and a turbine comprising such a control device.

主权项

1. A method for controlling a turbine, the turbine comprising plurality of sensors for providing sensor values ascertained on the turbine and a plurality of actuators for actuating the turbine, the turbine being characterized at each instant from a plurality of chronological instants of control by a hidden state that is derivable by sensor values and a rating signal for the hidden state and is influenceable by alterable actuator values for the plurality of actuators, the method comprising:
modeling dynamic behavior of the turbine with a recurrent neural network comprising an input layer, a recurrent hidden layer, and an output layer based on training data comprising sensor values of the plurality of sensors, actuator values of the plurality of actuators, and rating signals, wherein the input layer is formed from first vectors of neurons that describe sensor values, actuator values, or sensor values and actuator values at the instants, wherein the recurrent hidden layer is formed from second vectors of neurons that describe the hidden state of the turbine at the instants, wherein chronologically, for all the instants, two respective vectors from the second vectors are connected to a first connection that spans one instant, and, chronologically, two respective vectors from the second vectors are connected to a second connection that spans at least two instants, and wherein the output layer is formed from at least one third vector of neurons that describe the rating signal or at least one portion of the sensor values, at least one portion of the actuator values, or the at least one portion of the sensor values and the at least one portion of the actuator values at the instants; performing a learning method, an optimization method, or a learning and optimization method on the hidden states in order to provide a set of rules having optimized actuator values for each of the hidden states; ascertaining the current hidden state using the recurrent neural network and currently ascertained sensor values from the plurality of sensors; ascertaining current actuator values; and actuating the plurality of actuators using the provided set of rules and the current hidden state.