Abstract:
This article substantiates the need for deep integration in the form of convolution of artificial intelligence methods and measurement theory at all levels of information acquisition and processing to improve the efficiency, stability, consistency, transparency, traceability and quality control of measurement and neural network solutions, intellectualization of data transmission and storage systems (IIoT), and the construction of highly efficient cyberphysical systems.
The paper considers the approach and methodological principles of creating a new type of neural networks, called Bayesian measurement networks. The concept and formalization of a new type of Bayesian neurons implementing Bayesian convolution based on the regularizing Bayesian approach is given. Three types of Bayesian neurons that implement the convolution of the values of quantitative and qualitative features are considered. An architectural scheme and metrological justification of BIN solutions, a platform for rapid development of applied BIN solutions, are proposed. Examples of solutions to applied problems based on BIN are given.
The concept is given and a practical example of an intelligent industrial IoT is given. The expediency and experience of using BITS and cognitive measurements for the construction of CPSS are noted.
Keywords:
Artificial intelligence, Measurement theory, Neural network, Regularizing Bayesian approach, Industrial internet of things
_______________________________________________________________________
