In the existing fire alarm system, create a BP neural network simulation model which is based on Wuhan Zhongshan Road Tunnel project, access to actual operation data as the training sample data,.

Control parameter gotten by dynamic neural network is used to control the model's output in simulation. The result concludes that the controller can get better control result.

This paper brings the fuzzy neural network algorithms into the call admission control in ATM networks. The simulation result shows that it has better effect than usual algorithms.