Advances in Brain-Computer Interfaces and Neural Integration
Predicting Off-Design Performance of Axial Compressors Using Multilayer Neural Network Model for Surge Control
Abstract
Mostafa A. Elhosseini, Mohamed A. Elmelegy, Amira Y. Haikal and Hesham Arafat Ali
The incidence of surge within axial compressors profoundly influences the efficacy and reliability of aeroengines. Conventional methodologies in engine design have predominantly concentrated on the precise and efficient forecasting of critical characteristics during such occurrences. This paper presents a novel approach for predicting the surge phenomenon in axial compressors. Surge is a major issue in the operation of axial compressors, causing reduced performance, increased wear and tear, and in some cases, complete machine failure. The proposed approach utilizes a neural network model based on the compressor’s design data to forecast the behavior of the compressor’s working map under off-design conditions. The model is verified using real data collected over five years during compressor operation, including the opening angle of the Inlet Guided Van (IGV), an important parameter often ignored or assumed to be fixed in previous studies.
The results show that the neural network-based approach effectively predicts the compressor’s behavior under different operating conditions, providing valuable insights into the onset of surge and offering a real-time surge prediction and control tool. The ability to predict the compressor’s working map enables optimizing its performance and controlling instability. This model was validated by comparing its predictions with real operating conditions observed over five years across various compressor operating modes. As a result, this predictive model enables the safe operation of axial compressors by mitigating instability risks during operation. This study’s findings highlight the model’s effectiveness, as evidenced by the minimal error observed between the predicted and actual data collected across various compressor operating modes. The model exhibits a strong performance, characterized by a high regression factor of 0.92667 and a low mean squared error of 3.04465 x 10^-3. These numerical values underscore the reliability and precision of the proposed approach in predicting the operation of the axial compressor under diverse conditions, ultimately contributing to enhanced stability and safety during compressor operations.