Glass fiber sleeve quality detection method based on image features

Abstract

The invention belongs to the technical field of glass fiber sleeve quality detection, and particularly relates to a glass fiber sleeve quality detection method based on image features, which comprises the following steps: numbering workpieces, and detecting standard components through a detection assembly, so that a central processing unit in the detection assembly obtains standard image features; placing the detected glass fiber sleeve on the loading platform, immersing the glass fiber sleeve on the loading platform into the gel coupling agent, and vacuumizing the detection box body through a vacuum air pump; starting an ultrasonic generator, and transmitting an ultrasonic signal to the detected glass fiber sleeve by the ultrasonic generator; receiving a signal reflected by the glass fiber sleeve through an ultrasonic receiver, and converting the reflected ultrasonic signal into an electric signal through a signal processor; the image processor is used for imaging an electric signal converted from the reflected ultrasonic signal; and the central processing unit compares detection image features imaged by the image processor with standard image features.

Description

Technical Field

[0001] The present invention belongs to the technical field of glass fiber sleeve quality detection, and in particular relates to a glass fiber sleeve quality detection method based on image features. Background Art

[0002] Patent application number CN202410381639.2 discloses a glass fiber casing quality detection method based on image features, which calculates the color saliency value of each pixel in the casing surface image; obtains the texture smoothness of the pixel according to the LBP value of the pixel and the pixel in the local neighborhood; extracts the texture smoothness co-occurrence matrix of each pixel, and obtains the damage degree of each pixel by combining the texture smoothness of each pixel and the smoothness contrast of the local neighborhood pixel; obtains the smoothness entropy correlation of each pixel according to the smoothness entropy of each pixel and the adjacent pixels, and then obtains the particle value of each pixel; calculates the particle discreteness of each pixel at the same time; obtains the particle saliency value of each pixel according to the particle value and particle discreteness of each pixel, and obtains the visual saliency value of each pixel; extracts abnormal areas, but the disadvantage of this technical solution is that there is no way to realize crack and bubble detection of glass fiber casing. Summary of the Invention

[0003] The present invention aims to provide a glass fiber casing quality detection method based on image features to solve the technical problem that there is no way to detect cracks and bubbles in glass fiber casings.

[0004] To achieve the above objectives, the specific technical solution of the glass fiber sleeve quality detection device based on image features of the present invention is as follows:

[0005] A glass fiber sleeve quality inspection device based on image features includes a detection box, a vacuum air pump, a loading platform and a detection component. The detection box is equipped with a vacuum air pump, which pumps the detection box into a vacuum environment to prevent dust in the air from affecting the inspection. The detection box is equipped with a loading platform, which is used to support the glass fiber sleeve. The detection box is equipped with a detection component, which is used to detect cracks and bubbles in the glass fiber sleeve.

[0006] Furthermore, the glass fiber sleeve placed on the loading platform is immersed in a gel coupling agent.

[0007] Furthermore, the detection component includes an ultrasonic generator, an ultrasonic receiver, a signal processor, an image processor and a central processing unit. The ultrasonic generator communicates with the central processing unit in a one-way manner, the ultrasonic receiver communicates with the signal processor in a one-way manner, the signal processor communicates with the image processor in a one-way manner, and the image processor communicates with the central processing unit in a one-way manner.

[0008] Furthermore, the frequency range of the ultrasonic generator is 1-10 MHz.

[0009] Furthermore, the ultrasonic generator model is DPR300 pulse generator, the ultrasonic receiver model is DPR300 receiver, the signal processor model is ADSP-SC589, the image processor model is ARM Cortex-M4, and the central processing unit model is i.MX RT106.

[0010] Furthermore, a glass fiber casing quality detection method based on image features comprises the following steps:

[0011] S1: Number the workpieces and inspect the standard parts through the inspection component so that the central processor in the inspection component obtains standard image features;

[0012] S2: Place the glass fiber sleeve to be tested on the loading platform and immerse the glass fiber sleeve on the loading platform in the gel coupling agent. The test box is evacuated by a vacuum air pump.

[0013] S3: Start the ultrasonic generator, which sends ultrasonic wave signals to the glass fiber casing to be tested;

[0014] S4: The ultrasonic receiver receives the signal reflected by the glass fiber casing, and the signal processor converts the reflected ultrasonic signal into an electrical signal;

[0015] S5: The image processor converts the reflected ultrasonic signal into an electrical signal to form an image;

[0016] S6: The central processing unit compares the detection image features generated by the image processor with the standard image features;

[0017] S7: If the detected image features are compared with the standard image features and the image features show a multi-peak phenomenon with wide amplitude and branched peaks, and the main peak is sharp and accompanied by secondary small peaks, then the glass fiber sleeve has cracks;

[0018] S8: If the detected image features are compared with the standard image features and the image features show a low echo height, a rounded peak, a single pulse shape, and a stable waveform, then the glass fiber sheath has a single bubble;

[0019] S9: If the detected image features are compared with the standard image features and the image features show a family of reflected waves with wave heights varying with bubble sizes, then the glass fiber sleeve contains dense bubble clusters.

[0020] S10: If the detected image features are compared with the standard image features, and the image features show a smooth amplitude without sudden changes, a single peak and steep front and back edges, then the glass fiber sleeve does not have cracks or single bubbles or dense bubble groups and is a qualified product.

[0021] The advantages of the present invention are:

[0022] The ultrasonic generator transmits an ultrasonic signal to the glass fiber casing, the ultrasonic receiver receives the signal reflected by the glass fiber casing, the signal processor converts the reflected ultrasonic signal into an electrical signal, the image processor images the electrical signal converted from the reflected ultrasonic signal, and the central processing unit performs quality inspection on the inspected glass fiber casing according to the detection image features imaged by the image processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of the glass fiber casing quality detection method based on image features of the present invention;

[0024] Figure 2 Schematic diagram of the detection component structure of the present invention; DETAILED DESCRIPTION

[0025] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of the present invention.

[0026] In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0027] Example 1

[0028] like Figure 1-2As shown, a glass fiber sleeve quality inspection device based on image features includes a detection box, a vacuum air pump, a loading platform and a detection component. The detection box is equipped with a vacuum air pump, which pumps the detection box into a vacuum environment to prevent the dust in the air from affecting the detection. The detection box is equipped with a loading platform, which is used to support the glass fiber sleeve. The detection box is equipped with a detection component, which is used to detect cracks and bubbles in the glass fiber sleeve.

[0029] Wherein, the glass fiber sleeve placed on the loading platform is immersed in the gel coupling agent.

[0030] Example 2

[0031] like Figure 2 As shown, the detection component includes an ultrasonic generator, an ultrasonic receiver, a signal processor, an image processor and a central processing unit. The ultrasonic generator communicates with the central processing unit in a one-way manner, the ultrasonic receiver communicates with the signal processor in a one-way manner, the signal processor communicates with the image processor in a one-way manner, and the image processor communicates with the central processing unit in a one-way manner. In this configuration, the ultrasonic generator transmits an ultrasonic signal to the glass fiber casing, the ultrasonic receiver receives the signal reflected by the glass fiber casing, the signal processor converts the reflected ultrasonic signal into an electrical signal, the image processor images the electrical signal converted from the reflected ultrasonic signal, and the central processing unit performs quality inspection on the detected glass fiber casing according to the detection image features imaged by the image processor.

[0032] Wherein, the frequency range of the ultrasonic generator is 1-10 MHz.

[0033] Among them, the signal processor model is ADSP-SC589, the image processor model is ARM Cortex-M4, and the central processing unit model is i.MX RT106.

[0034] Example 3

[0035] like Figure 1 As shown in FIG, a glass fiber casing quality detection method based on image features comprises the following steps:

[0036] S1: Number the workpieces and inspect the standard parts through the inspection component so that the central processor in the inspection component obtains standard image features;

[0037] S2: Place the glass fiber sleeve to be tested on the loading platform and immerse the glass fiber sleeve on the loading platform in the gel coupling agent. The test box is evacuated by a vacuum air pump.

[0038] S3: Start the ultrasonic generator, which emits ultrasonic signals to the glass fiber casing to be tested;

[0039] S4: The ultrasonic receiver receives the signal reflected by the glass fiber casing, and the signal processor converts the reflected ultrasonic signal into an electrical signal;

[0040] S5: The image processor converts the reflected ultrasonic signal into an electrical signal to form an image;

[0041] S6: The central processing unit compares the detection image features generated by the image processor with the standard image features;

[0042] S7: If the detected image features are compared with the standard image features and the image features show a multi-peak phenomenon with wide amplitude and branched peaks, and the main peak is sharp and accompanied by secondary small peaks, then the glass fiber sleeve has cracks;

[0043] S8: If the detected image features are compared with the standard image features and the image features show a low echo height, a rounded peak, a single pulse shape, and a stable waveform, then the glass fiber sheath has a single bubble;

[0044] S9: If the detected image features are compared with the standard image features and the image features show a family of reflected waves with wave heights varying with bubble sizes, then the glass fiber sleeve contains dense bubble clusters.

[0045] S10: If the detected image features are compared with the standard image features, and the image features show a smooth amplitude without sudden changes, a single peak and steep front and back edges, then the glass fiber sleeve does not have cracks or single bubbles or dense bubble groups and is a qualified product.

[0046] It will be understood that the present invention is described by way of some embodiments, and it will be appreciated by those skilled in the art that various changes or equivalent substitutions may be made to these features and embodiments without departing from the spirit and scope of the present invention. In addition, under the teachings of the present invention, these features and embodiments may be modified to adapt to specific circumstances and materials without departing from the spirit and scope of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of this application are intended to be protected by the present invention.

Claims

1. A glass fiber casing quality detection device based on image features, comprising a detection box, characterized in that: It also includes a vacuum air pump, a loading platform and a detection component. The vacuum air pump is installed in the detection box, and the vacuum air pump draws the detection box into a vacuum environment to prevent the dust in the air from affecting the detection. The loading platform is installed in the detection box, and the loading platform is used to support the glass fiber sleeve. The detection component is installed in the detection box, and the detection component is used to detect cracks and bubbles in the glass fiber sleeve.

2. The device for detecting quality of glass fiber sleeves based on image features according to claim 1, characterized in that: The glass fiber sleeve placed on the object carrying platform is immersed in the gel coupling agent.

3. The device for detecting quality of glass fiber sleeves based on image features according to claim 1, characterized in that: The detection component includes an ultrasonic generator, an ultrasonic receiver, a signal processor, an image processor and a central processing unit. The ultrasonic generator communicates with the central processing unit in a one-way manner, the ultrasonic receiver communicates with the signal processor in a one-way manner, the signal processor communicates with the image processor in a one-way manner, and the image processor communicates with the central processing unit in a one-way manner.

4. The device for detecting quality of glass fiber sleeves based on image features according to claim 3, characterized in that: The frequency range of the ultrasonic generator is 1-10 MHz.

5. The device for detecting quality of glass fiber sleeves based on image features according to claim 3, characterized in that: The ultrasonic generator model is DPR300 pulse generator, the ultrasonic receiver model is DPR300 receiver, the signal processor model is ADSP-SC589, the image processor model is ARM Cortex-M4, and the central processing unit model is i.MXRT106.

6. A method for detecting quality of a glass fiber sleeve based on image features according to the device for detecting quality of a glass fiber sleeve based on image features according to any one of claims 1 to 5, characterized in that: The steps are: S1: Number the workpieces and inspect the standard parts through the inspection component so that the central processor in the inspection component obtains standard image features; S2: Place the glass fiber sleeve to be tested on the loading platform and immerse the glass fiber sleeve on the loading platform in the gel coupling agent. The test box is evacuated by a vacuum air pump. S3: Start the ultrasonic generator, which sends ultrasonic wave signals to the glass fiber casing to be tested; S4: The ultrasonic receiver receives the signal reflected by the glass fiber casing, and the signal processor converts the reflected ultrasonic signal into an electrical signal; S5: The image processor converts the reflected ultrasonic signal into an electrical signal to form an image; S6: The central processing unit compares the detection image features generated by the image processor with the standard image features; S7: If the detected image features are compared with the standard image features and the image features show a multi-peak phenomenon with wide amplitude and branched peaks, and the main peak is sharp and accompanied by secondary small peaks, then the glass fiber sleeve has cracks; S8: If the detected image features are compared with the standard image features and the image features show a low echo height, a rounded peak, a single pulse shape, and a stable waveform, then a single bubble exists in the glass fiber sheath; S9: If the detected image features are compared with the standard image features and the image features show a family of reflected waves with wave heights varying with bubble sizes, then the glass fiber sleeve contains dense bubble clusters. S10: If the detected image features are compared with the standard image features, and the image features show a smooth amplitude without sudden changes, a single peak and steep front and back edges, then the glass fiber sleeve does not have cracks or single bubbles or dense bubble groups and is a qualified product.

Images