Identification and classification of operating flow regimes and prediction of stall in a contra-rotating axial fan using machine learning

Abstract

Prediction of stall before it occurs, or detection of stall is crucial for smooth and lasting operation of fans and compressors. In order to predict the stall, it is necessary to distinguish the operational and stall regions based on certain parameters. Also, it is important to observe the variation of those parameters as the fan transitions towards stall. Experiments were performed on a contra-rotating fan setup under clean inflow conditions, and unsteady pressure data were recorded using seven high-response sensors circumferentially arranged on the casing, near the first rotor leading edge. Windowed Fourier analysis was performed on the pressure data, to identify different regions, as the fan transits from the operational to stall region. Four statistical parameters were identified to characterise the pressure data and reduce the number of data points. K-means clustering was used on these four parameters to algorithmically mark different regions of operation. Results obtained from both the analyses are in agreement with each other, and three distinct regions have been identified. Between the no-activity and stall regions, there is a transition region that spans for a short duration of time characterised by intermittent variation of abstract parameters and excitations of Fourier frequencies. The results were validated with five datasets obtained from similar experiments at different times. All five experiments showed similar trends. Neural Network models were trained on the clustered data to predict the operating region of the machine. These models can be used to develop control systems that can prevent the stalling of the machine.

Hybrid optimal deep learning with IoT based smart based monitoring and maintenance system for axial flow fan using feature optimization

“…To validate their approach, an experimental study established an operational state model for the LAF by fusing vibration and electric data. [26] analyzed pressure data using windowed Fourier analysis to distinguish operational regions as a fan transitioned from its operational state to stall. They identified four statistical parameters to effectively describe pressure data and reduce complexity.…”

“…Simultaneously, managing noise production is crucial, particularly in applications where noise reduction is a primary consideration, demanding the design of fans that operate quietly while maintaining peak performance [25]. Aerodynamic performance is another vital aspect, requiring the optimization of blade shapes, angles, and curvature to attain desired characteristics such as high airflow rates and pressure rises [26]. In certain applications involving the use of axial flow fans with liquids, the risk of cavitations, phenomenon where local pressure drops below the fluid's vapor pressure needs to be addressed through design considerations.…”