基于改进凌日搜索算法的风洞天平载荷预测方法  

A Wind Tunnel Balance Load Prediction Method Based on ITS Algorithm

作　　者：王碧玲 周灏 沈力华 刘博宇[1,2] 王奔 WANG Biling;ZHOU Hao;SHEN Lihua;LIU Boyu;WANG Ben(AVIC Aerodynamics Research Institute,Shenyang 110034,China;Aviation Key Laboratory of Science and Technology of High Speed and High Reynolds,Shenyang 110034,China;School of Mechatronics Engineering,Shenyang Aerospace University,Shenyang 110136,China)

机构地区：[1]中国航空工业空气动力研究院,沈阳110034 [2]高速高雷诺数气动力航空科技重点实验室,沈阳110034 [3]沈阳航空航天大学机电工程学院,沈阳110136

出　　处：《计算机测量与控制》2024年第11期25-33,共9页Computer Measurement &Control

摘　　要：风洞天平是在风洞测试中使用的测力传感器,在使用之前需要进行校准以测量缩比模型受到的气动载荷;传统的方法使用预设的多项式函数进行拟合,忽略了某些变量的存在对测量载荷的负面影响,导致数据处理结果的失真;在此,提出了一种改进的凌日搜索算法(ITS),选择对测量载荷更具重要性的特征;然后,使用贝叶斯线性回归算法(BLR)建立预测模型测量天平载荷,最后,在两个天平数据集上测试了该方法,结果表明ITS-BLR方法评估确定了对预测目标具有较高贡献的特征,进而降低了预测误差,与最小二乘法得到的综合加载误差相比,降幅最高达到60%,说明提出的方法可以实现对天平载荷的准确预测。A wind tunnel balance is a force sensor used in wind tunnel testing,which needs to be calibrated to measure the aerodynamic load on the scale model before use.Traditional methods use preset polynomial function for fitting,ignoring the negative influence of some variables on the measured load,which leads to the distortion of data processing results.Based on this,an improved transit search(ITS)algorithm is proposed to select more important features for load measurement.Then,Bayesian linear regression algorithm(BLR)is used to build a prediction model to measure the balance load.Finally,the method is verified on two balance datasets.The results show that the ITS-BLR method evaluates and identifies features with a higher contribution to the prediction target,thereby reducing the prediction error.Compared with the comprehensive loading error that obtained by the least squares method,the error of the ITS-BLR method is reduced up to 60%,which shows that the proposed method can provide an accurate prediction for the balance load.

关 键 词：风洞天平 载荷预测 优化算法 特征选择 凌日搜索 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置]