No abstract

Taking into account the digital transformation, the prospects for the development of intelligent complex security management system FEC are revealed. For the first time a definition of intelligent complex security management system FEC is given, also, its generalized structure is developed, considering the development of the Russian human-machine concept, as a complex information-energy system, on the basis of intellectualization of theoretical principles of human physiology and psychology. Its main elements are defined: a core, subsystems and components and mathematical dependencies implementing management functions are given. The core, subsystems and components are represented by the protected system at the level of security threat management in the form of a block-functional system scheme with elements of artificial intelligence that differ in the detail level. The mutual influence mechanism of separate subsystems and components is defined through simple, hybrid and complex threats. Besides, system threats of FEC were classified and their definitions were given. As an example, we consider the complex threat related to security of critical information FEC infrastructure. What is more, the basic intelligent management principles of complex FEC security are formulated, based on the block-functional system scheme with artificial intelligence elements and operator state security Identification in real time. We obtained general equations of the output state variables vector, which is equivalent to the security model of the operator, vectors of output state variables in case of hybrid, complex, and system FEC threats.

The paper proposes a forecasting technique of radio information system characteristics for optimal technical condition of space control system components, using a recurrent neural network and information tools from an early-warning radar stations group and Russian Aerospace Forces optical-electronic stations when determining the optimal technical condition of the Space Monitoring System (SMS) components. Analyzing values of time series by a recurrent neural network LSTM-based model with various parameters, we propose an algorithm for solving problem of forecasting characteristics of a radio information complex. The network architecture is a two-layer network with one layer of LSTM cells and one fully connected layer. There are results of experimental forecasting by pre-training the recurrent neural network (RNN) model sampling 1080 normalized measurements of a conditional sensor of 30 minutes apart. The training sample is made of conditional sensor normalized values for 9 hours continuous operation. The algorithm for the model training and creation is implemented in Python language using open source library TensorFlow. Experiments were performed with different values of the forecast horizon and the length of the input sequence of time series values. We obtained: the total average error for each combination of parameters, the dependence of the average forecast error on the used parameters and the dependence of the average (for all forecast values) forecast error on the period of the analyzed sensor values.

The analysis, detailing, theoretical and technological justifcation of the concept of fre and electric damage. It is proposed to use the electric meter suppressor of fire and electric damage and fire hazards in the residential sector. The cognitive model taking into account possibilities of influence of the electric meter of the suppressor on decrease in damage for the electrical reasons and the functional model of electric power quality system are constructed. The cognitive model is considered as one of the components describing the external impact in the neurograph as a model to support control over the comprehensive objects safety for reducing fire risks in the residential sector associated with electrical causes of fires.