Reliability And Chaotic Risk Modeling For Real Time Data Driven Smart Systems

Reliability and chaotic risk modeling for a real time data driven smart system is an important problem of systems engineering. A real time data driven smart system is a multicomponent chaotic mechatronic system, such as driveless car with thousands of components. It uses physically sensors for its components and real time data for functioning of components. Its components having increasing, constant or decreasing risk functions. Reliability and chaotic risk modeling in a multicomponent chaotic system uses the reliability block diagrams. Mixture distribution models with weight functions are proposed for modeling reliability and chaotic risk of reliability block diagrams for real time data driven smart systems. Non-linear reliability and hazard functions for real time data driven smart systems are transformed to mixture reliability and hazard functions respectively. Mixture reliability and hazard functions are expressed as linear functions of component functions with non-linear weight functions. Mixture reliability and hazard functions for real time data driven smart systems are obtained as finite sum of products of component’s non-linear weight functions with component pure reliability and hazard functions respectively. It is shown that the number of terms in mixture reliability and hazard functions for real time data driven smart systems are equal to the number of components in multicomponent chaotic systems. The effect of the structure of reliability block diyagram of a multicomponent chaotic system is reflected to the component’s non-linear weight functions. Mixture distribution models with non-linear weight functions and pure component functions are used both for prediction of reliability or life times and risk of multicomponent chaotic system and its components concurrently. The working principle and computational steps of the proposed mixture model reliability and chaotic risk analysis of reliability block diagram of a multicomponent chaotic system were explained on an application for complex event processing.