Fluorescent oil film gray scale and thickness modeling method based on neural network

Abstract

The invention discloses a fluorescent oil film gray scale and thickness modeling method based on a neural network. The method comprises the following steps: step 1, collecting fluorescent oil film gray scale and thickness data; step 2, training a BP neural network model, and carrying out structure construction on the BP neural network model; step 3, carrying out precision inspection, adjusting thetraining frequency, and repeating the step 2; if 1) the effect is not optimal, adjusting the network structure, adjusting the training frequency, and repeating the step 2; and finally forming a BP neural network structure. The method has the advantages that a large amount of cost and time are saved, operation is convenient and easy, and the method has great military and economic significance in accurately calculating the air friction resistance value.

Description

technical field [0001] The invention relates to the technical field of aerodynamics, in particular to a method for modeling the gray scale and thickness of a fluorescent oil film based on a neural network. Background technique [0002] Surface friction stress is one of the most important physical quantities in aerodynamics and an important part of the total resistance of aircraft flight. It can well describe the state of the turbulent boundary layer, and it is also one of the most difficult physical quantities to determine. Reducing friction can not only reduce the fuel consumption of the aircraft and increase the endurance of the aircraft, but also means that the heat flow on the surface of the supersonic aircraft is reduced, the weight of the heat-resistant material is reduced, and the payload is increased. [0003] The traditional methods of measuring surface friction stress are mostly local indirect measurement methods, such as hot wire method, hot film method, boundary ...

AI Technical Summary

Problems solved by technology

[0004] (1) The measurement accuracy is greatly affected by environmental factors, and the measurement steps are mostly operated by humans. The measurement results are mainly judged by human subjective consciousness. Based on the above factors, the resulting errors are relatively large;

[0005] (2) The cost is high, the requirements for traditional manufacturing are high, and a fixed geometric shape mold is required to perform friction measurement well

[0007] (1) At present, relevant research is still in the initial stage of exploration, which only provides theoretical basis and research modeling direction, and cannot be really applied to engineering practice;

[0008] (2) There is no systematic model establishment of the relationship between the gray scale and thickness of the fluorescent oil film, nor is there a systematic discussion on the accuracy and error of the model

However, this solution also has certain defects and limitations, as follows: In fact, the initial UV light intensity can be simply calculated according to the UV lamp power provided by the manufacturer, but if you want to get the fluorescence efficiency coefficient, you need to do it in the fluorescent oil film configuration process. In this paper, the ratio and concentration of silicone oil and fluorescent molecules are calibrated. This calibration experiment requires a large number of fluorescent oil film materials with different ratios for comparison, and the preparation of oil films with different concentrations of fluorescent molecules is time-consuming and labor-intensive, and requires high-precision stirring equipment. , which increases the experimental cost

Images