The features of neural networks used for increasing the accuracy of physical quantity measurement are considered by prediction of sensor drift. The technique of data volume increasing for predicting neural network training is offered at the expense of various data types replacement for neural network training and at the expense of the separate approximating neural network use.
This paper presents the approach to research integrated drone-based systems for post emergency monitoring of NPPs as systems with a multi-level degradation. Reliability block diagrams of the systems are built. Degradation levels, conditions which determine them and formulae for calculating the reliability functions of the systems on these levels are proposed. The possibility of using developed models for research systems with a multi-level degradation and using drones are shown.
This paper describes the mobile Ad-Hoc (wireless) network (MANET) for emergency scenarios in nuclear power plant (NPP). Authors proposed the system with such properties as flexibility and a self-forming and self-healing network topology that dynamically adjusts to the moving configuration per each intermediate routing node. It is also proposed to integrate MANET and Bluetooth-like technologies to create an unmanned formation of autonomous quadcopters that provides both indoor and outdoor communications coverage inside and outside of the NPP.
Neural networks models and their training algorithms on a central computer with reference to a previously developed distributed sensor network are considered. The requirements for its intelligent node are formulated. Also the node's structure is offered which realises such intelligent functions, as sensor and other measuring channel components drift prediction using remote reprogramming.
4 January 2016 in International Journal of Thermophysics