抽象的な

Surge Detection System Using Gaussian Curve Membership Function

Mohamed A. Waly, Ibrahim F. Tarrad, Mohamed M. Fouad

Problem: Surge is an instability that affects the entire compression system. Surge is characterized by a limit cycle oscillation that results in large amplitude fluctuations of the pressure and flow rate. In contrast to rotating stall, during surge the average mass flow is unsteady but circumferentially uniform. Approach: The attempt to find a simple model structure which can capture in some appropriate sense the key of the dynamical properties of the physical plant, we study the application possibilities of the anti-surge detection system by using Gaussian curve membership function to protect the centrifugal compressor from surge by using Neural fuzzy. Results: By testing the new Neural- Fuzzy system which has been created for demonstrate the validity of proposed control scheme, the new neural-fuzzy system get a good results compared by the used detection system. Conclusion: We can use Neural-Fuzzy system to detect the surge in centrifugal compressor Alternative to current detection system.