Method research of noise diagnosis based on fuzzy neural network

In this paper, a new noise diagnosis method is presented, and its algorithm deduced, based on a fuzzy neural network. As a practical example, the noise field intensity is diagnosed and the coupling noise is identified for the noise from a steam turbine unit. The results show that the fuzzy neural network has a good capacity for pattern recognition, fast convergence and good stability in dealing with uncertain or ambiguous data at the classification boundary. The noise radiated from the steam turbines unit is diagnosed accurately and the noise node is suppressed effectively and is restructured.