Process Monitoring for the Flow Field of Wind Tunnel Systems with a One-Class Classifier Ensemble

作     者：Zhang, Meng Chen, Yiheng Ren, Weijie 

作者机构：Shenyang Aerosp Univ Sch Artificial Intelligence 37Daoyi South St Shenyang 110136 Peoples R China Harbin Engn Univ Coll Intelligent Syst Sci & Engn 145 Nantong St Harbin 150001 Peoples R China 

出 版 物：《JOURNAL OF AEROSPACE ENGINEERING》 (J Aerosp Eng)

年 卷 期：2025年第38卷第2期

核心收录：

学科分类：08[工学] 0813[工学-建筑学] 0814[工学-土木工程] 0825[工学-航空宇航科学与技术] 

基　　金：Doctoral Research Foundation of Liaoning Science and Technology Department [2022-BS-220] National Natural Science Foundation of China Aviation Science Foundation of China 

主　　题：Wind tunnel Flow field Process monitoring One-class classifier Ensemble learning 

摘      要：The process monitoring system for wind tunnel flow fields enables real-time monitoring of anomalies and faults within the flow field, allowing for the implementation of necessary adjustments to ensure the normal operation of the wind tunnel. Because of the performance limitations of single models, many ensemble monitoring models based on ensemble learning have been proposed. To ensure diversity within the ensemble, a large number of base learners are generated. However, it has been discovered that the redundancy resulting from a large number of base learners not only harms the performance of the ensemble model but also increases computational burden and storage overhead. To address this, this paper presents an ensemble monitoring model based on ensemble pruning. Specifically, given the unavailability of data labels in the wind tunnel flow-field data sets, one-class classifiers are employed as the base learners. After the ensemble generation stage, the performance of each base learner is estimated based on its correlation with the proxy model. Then, using the estimated performance, a dedicated base learner selection mechanism is proposed based on statistical testing to filter out redundant individuals. To validate the effectiveness of the proposed monitoring model, nine data sets from real wind tunnels were used for model training, and an additional nine data sets were used for testing. Experimental results demonstrated the significance of ensemble pruning in enhancing ensemble performance.