The Pre-Stall Behavior of a 4-Stage Transonic Compressor and Stall Monitoring Based on Artificial Neural Networks

摘要

Current research concerned with the aerodynamic instabilityof compressors aims at an extension of the operatingrange of the compressor towards decreased massflow. Inpractice, a safety margin is maintained between operatingpoint and stability limit to prevent the compressor from goinginto stall and surge. In this article, we analyze the behaviorof a 4-stage transonic axial compressor before enteringthe unstable range and present an approach to identifying incipientsurge and stall using artificial neural networks. Thismethod is based on measurements of the unsteady static wallpressure in front of the first rotor.Analyzing the static pressure signals by using the FastFourier Transform shows that peripheral disturbances(modal waves) can only be identified in a small range closeto nominal speed (at 95%). At lower speeds (60 to 80% ofnominal speed), the investigated compressor flow enters instabilityby spike-type stall.Monitoring stability over the entire speed range of the compressor relies on artificial neural networks using the unsteady wall pressure signal. In the present case, artificial neural networks show to be the most useful tool to indicate approaching instability. The method works reliably for both types of instabilities, spike-type stall as well as modal waves.