Improved Elman neural network with ant colony algorithm and its applications in fault diagnosis

Abstract

In the power plant, the blower fans running conditions related to the power plant production directly, as well as the security situation. This article introduced embedded system monitoring to the Auxiliary power plant machinery diagnostics systems. An on-line mechanical fault diagnosis system was developed based on ant colony algorithm and Elman neural network. This system integrated data acquisition, signal processing, network communications, on-line fault diagnosis and other functions into one. Experiments show that this method is simple and effective. It can also be applied to other fault diagnosis of complex systems and has certain portability.