Polyester film mechanical property detection device based on optical recognition

Abstract

According to the optical identification-based polyester film mechanical property detection device, a cushion film is arranged between a clamping roller and a to-be-stretched polyester film, and the material and the thickness of the cushion film are optimized, so that uniform stress stretching is realized; meanwhile, the clamping rollers rotate while moving in the horizontal direction, so that the problem that the detection precision is reduced due to rigid stretching is solved; and the mechanical property of the polyester film is quickly and accurately judged in a mode of combining machine vision and a neural network.

Description

technical field [0001] The invention relates to the field of mechanical performance detection of polyester film materials. Background technique [0002] The mechanical properties of polyester film materials are an important factor to measure their usability. The stress of the polyester film material during use will accelerate the aging of the material, so it is necessary to test the mechanical properties of the material. [0003] In the prior art, the stress field analysis method is mainly used to detect the mechanical properties of the membrane, but the equipment and algorithm of this method are relatively complicated, difficult to operate, and the detection time is long, so it can only be used in scientific research experiments and is not suitable for production lines. in the application. Most of its testing equipment are tensile testing machines, which are too complicated and professional to be suitable for automatic operation. [0004] Moreover, the stretching device ...

AI Technical Summary

Problems solved by technology

This will require a higher step resolution of the stretching device, otherwise the mechanical properties of the film will suddenly drop at a certain moment, and the detection system cannot respond in time at this time, resulting in detection failure

To ensure a timely response requires a costly detection system

In addition, rigid clamping will cause uneven stress on local contact parts, resulting in an increased probability of local cracks during stretching

However, the occurrence of such cracks does not fully reflect the mechanical properties of the polyester film, and it is more caused by clamping.

[0005] In the prior art, image processing methods are also used to detect mechanical properties, but most algorithms have not found suitable detection features, such as using elongation as indicators, which cannot accurately reflect the mechanical properties of the film

Moreover, the current image processing algorithm is not mature enough to accurately detect

Therefore, it can only be used for auxiliary detection and cannot be applied to the production line

Although the neural network model has been applied in other fields, there is still no special model structure applicable in the field of membrane mechanical performance testing. Other models cannot adapt to the characteristics of high light transmission and diffuse light of polyester film images, and cannot accurately detect and judge

Images