The control device includes a feedforward method learning device that includes a first feedforward neural network for predicting a change in a control state quantity of the controlled object from the malfunction in the controlled object by learning learning data as a combination of the control state quantity due to the control of the controlled object and the disturbance to the controlled object, and a feedforward execution device that predicts the change in the control state quantity of the controlled object from the disturbance in the controlled object based on the first neural network for feedforward control and the control operation amount based on the change corrected the control state variable directly or indirectly.
展开▼