Fault prediction of fire control system based on Grey rough set and BP neural network

Abstract

The tank fire control system plays a very important role in today's war. With the development of science and technology, the fire control system has become more modern. Taking the fire control computer as an example, this paper proposes a fault prediction method using rough set and neural network. First, according to the grey relational analysis technology and rough set theory, the original fault decision table is reduced by attributes. Then delete the redundant and invalid attribute data in the original data, and finally use the reduced rough set data as the input of the BP neural network to complete the failure prediction of the fire control computer. This method not only improves the efficiency and accuracy of failure prediction, but also reduces the maintenance cost of the fire control system.