Neural network model comparison on the indicators of quality

摘要

The proposed control system is designed to build models of objects of regulation on the basis of quality indicators. Technical result is achieved by the neural network model comparing a quality indicator, which includes a control object, the input of which is fed the input signal, a control object output is connected to an input unit for calculating the quality metric input of the adder connected to the output quality index calculating unit and the output of neural network model, output of the adder connected to the input of the learning algorithm, a neural network model input coupled to the output of the learning algorithm and the input signal consists of preparing neural mod Is a Quality Score of the control object is not worse than that of the control object on the basis of which it is built.