ITC/USA 2005 Conference Proceedings / The Forty-First Annual International Telemetering Conference and Technical Exhibition / October 24-27, 2005 / Riviera Hotel & Convention Center, Las Vegas, Nevada / This paper suggests a reconfigurable sensor network (data bus) which is well suited for telemetry mission of rockets and launch vehicles. Reconfiguration of sensors’ channel information can be achieved without additional software and hardware. The proposed network consists of a central unit and multiple remote units with RS-485 data bus. Since those units need only an FPGA and a programmable ROM to be implemented, the network can provide minimum costs and high reliability. And this paper also presents reliability prediction result of a unit based on MIL-HDBK-217F and Monte Carlo simulation.

This thesis deals with the possibility of using neural networks in the analysis of a racing vehicle telemetry data. The analysis consists of finding and classifying the driving states of the vehicle as well as reconstruction and prediction of the data signal. The thesis consists of a research of machine learning focusing on neural networks. It describes the main types of the most commonly used neural networks with the description of their structure and their learning process. It also deals with the problem of classification and an in-depth analysis of the signal prediction and reconstruction. The conclusion is devoted to the implementation of the network into a TeleMatrix application.