Method for constructing cascading Bayesian network for solving combinatorial explosion problem

Abstract

The invention discloses a method for constructing a cascading Bayesian network for solving a combinatorial explosion problem. The method comprises two core parts: A) a method for constructing the topological structure of a cascading Bayesian network by a system access, and B) an intermediate node probability parameter setting method of the cascading Bayesian network. Firstly, the construction of the topological structure of the Bayesian network is finished, wherein the topological structure of the Bayesian network is consistent with a fault cascading configuration in engineering practice, then, the setting of each node condition probability table of the Bayesian network is finished, and finally, the construction of the cascading Bayesian network is jointly finished. When the cascading Bayesian network finishes being constructed, any existing Bayesian network reasoning technology can be applied to carry out reasoning calculation on the cascading Bayesian network so as to obtain system reliability. While a reliability calculation result of the system can be guaranteed to be correct, the probability parameters in the network are effectively reduced, specifically, the number of the probability parameters on each access can be lowered to a linear order from an exponential order, calculation efficiency is improved, and a combinatorial explosion problem is solved.

Description

technical field [0001] The invention relates to the field of system engineering reliability analysis, in particular to a method for converting a system reliability block diagram into a Bayesian network. Background technique [0002] Reliability block diagram is an important tool for studying system reliability. For a complex system, the logic diagram that uses the components of the system to frame each component and uses connections to describe the influence of the state of each component on the state of the system is called a reliability block diagram, and the reliability block diagram is referred to as RBD. According to the connection mode between the blocks, the reliability block diagram is divided into series connection, parallel connection, hybrid connection and bridge connection, etc. The system task reliability model established by the reliability block diagram is concise and intuitive, and it is also the easiest for engineers to grasp. It is one of the most widely u...

AI Technical Summary

Problems solved by technology

However, the three-layer node BN network has the problem of conditional probability parameter combination explosion: when any path in the system contains too many elements, for the second layer Bayesian network node representing the state of the path, the conditional probability parameter in the conditional probability table The number will increase exponentially with the number of components contained in the path, and the exponential growth method will inevitably lead to a sharp increase in the number of conditional probability parameters of the three-layer Bayesian network with the increase in the number of elements on the path, and finally appear due to the data Too many explosion problems that cannot be stored, making Bayesian network reasoning impossible

Images