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

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.