Abstract: Provided is learning device that is a learning device of a neural network model whose bond strength between multiple neurons is represented as a weighting coefficient. The learning device is configured to optimize the weighting coefficient by using an evaluation function that includes a model reliability based on the degree of firing of each neuron of the multiple neurons and a prediction error obtained using the neural network model.

Abstract: A model optimization device is configured to optimize a prediction model configured to generate predicted values of a target variable for an explanatory variable. The model optimization device includes a generating unit configured to generate expanded MR data by transforming training data, and an optimization unit configured to cause the prediction model to learn and optimize the prediction model based on a first predicted value generated by the prediction model based on the training data, and a second predicted value generated by the prediction model based on the MR data.

Abstract: A model evaluating device is configured to evaluate performance of a prediction model configured to generate predicted values of a target variable for an explanatory variable. The model evaluating device includes a generating unit configured to generate expanded MR data by transforming evaluation data, and an evaluating unit configured to evaluate the performance of the prediction model based on a first predicted value generated by the prediction model based on the evaluation data, and a second predicted value generated by the prediction model based on the MR data.

Abstract: An operating condition of a wind turbine facility or at least one wind turbine is acquired, and an estimated value of a measurable physical quantity corresponding to the operating condition is calculated. It is determined whether an abnormality is present in the wind turbine by comparing the estimated value and the actual value.