UDC 519.7: 62.506
DOI: 10.36871/2618-9976.2022.01.001
Authors
Prokopchina S.V.
Professor, Doctor of Technical Sciences, Financial University under the Government
of the Russian Federation, Moscow, Russia
Abstract
Within the framework of the Industry 4.0 concept, intensive development
of the processes of intellectualization of sensor systems
is envisaged.
Among the most important specific properties of real measuring
processes in complex systems is, first of all, their implementation
under conditions of considerable uncertainty. The uncertainty
is caused by a priori incompleteness, inaccuracy, vagueness
of information about a complex measuring object and its
functioning environment, which does not allow to build an adequate
model of the object before the measurement experiment,
to identify and formalize the influencing factors of the external
environment and to develop effective algorithms for the functioning
of information and measurement systems.
The report proposes an approach to the intellectualization
of measurement systems in conditions of uncertainty by creating
intelligent sensor networks based on Bayesian intelligent technologies
(BIT) and means of their implementation. Typical modules
of such networks are considered, which are integrated sets
of various sensors and intelligent measurement information
processing systems. The results of the networks are comprehensive
assessments of the state of complex objects and recommendations
for providing of their sustainable functioning. An important
part of such systems is the builtin
means of a complete
metrological justification of all received solutions. The systems
have a hierarchical architecture, according to the levels of management
of complex objects, which has the possibility of selfdevelopment
based on newly received information. This is
achieved thanks to models and scales with dynamic constraints
on which all BIT algorithms are built. The report provides examples
of the use of intelligent sensor networks for monitoring and
control of power generation and water supply systems.
Keywords
Intelligent measurements, Bayesian approach, Sensors network