基于Hankel阵的荧光油膜灰度与厚度预测模型改进

Improved prediction model of gray and thickness of fluorescent oil film based on Hankel matrix

针对荧光油膜灰度与厚度关系数据采集方法较为繁琐、耗时耗力这一问题,研究了基于Hankel阵的系统辨识算法,并在此基础提出了Hankel阵误差修正模型和Hankel阵高阶迭代误差修正模型等两种改进方法,利用了极少数据量建立模型,实现了对其余未知荧光油膜厚度值的预测,且保持了较高的精度。试验结果表明:基于极少数据量建模以预测该数据量外的数据点这一特殊背景下,插值法的外插能力显得并不适用。而传统Hankel阵预测模型的预测精度为76.69%,Hankel阵误差修正模型和Hankel阵高阶迭代误差修正模型的预测精度分别为85.69%和89.25%,较之传统方法预测精度分别提高了9%和12.56%,为荧光油流技术领域针对荧光油膜灰度与厚度建模问题提供了一种可行技术路线,具有一定的实际工程应用意义。

In order to solve the problem of tedious and time-consuming data collection methods for the relationship between gray and thickness of fluorescent oil film,the system identification algorithm of Hankel matrix was studied,and two improved methods such as Hankel array error correction model and Hankel array high order iterative error correction model were proposed accordingly,which can achieve the prediction of the remaining unknown fluorescent oil film thickness values by using a very small amount of data to build the models.The prediction of the remaining unknown fluorescent oil film thickness values was achieved with high accuracy.The test results showed that the interpolation capability of the interpolation method seemed not applicable in the particular context of modelling a very small amount of data to predict data points outside that amount of data,while the prediction accuracy of the traditional Hankel array prediction model was 76.69%;the Hankel array error correction model and the Hankel array high order iterative error correction model had a prediction accuracy of 85.69% and 89.25%,respectively,9% and 12.56% higher than those of the traditional method.This has provided a feasible technical route for modelling the gray and thickness of fluorescent oil film in the field of fluorescent oil flow technology with certain practical engineering application significance.