Visual detection-based base cloth surface detection method for manufacturing inflatable false target

Abstract

The invention relates to the technical field of new material detection, and discloses a base cloth surface detection method for inflatable false target manufacturing based on visual inspection, and the method comprises the following steps: carrying out tension leveling treatment on composite coating base cloth; visible light and thermal radiation images are synchronously collected through a high-resolution industrial camera and a thermal infrared imager; a multi-modal algorithm fusing YOLOv5 crack detection, U-Net bonding defect identification and CIELAB color difference analysis is adopted; the emissivity uniformity and the temperature difference standard reaching condition are verified, and environment interference compensation is carried out through a polynomial fitting algorithm; and establishing a three-level judgment system, and outputting a detection report containing defect types, coordinates and maintenance suggestions. According to the invention, integrated detection of the air tightness, the structural strength and the camouflage performance of the base cloth can be realized, the limitation of traditional manual detection is broken through, the detection precision and efficiency are improved, and the method is particularly suitable for surface defect detection of the composite coating base cloth in the manufacturing process of military inflatable simulation false targets.

Description

Technical Field

[0001] The present invention relates to the technical field of new material detection, in particular to a surface detection method of a base cloth used for manufacturing an inflatable false target based on visual detection. Background Art

[0002] In modern military training and combat, inflatable decoys are widely used due to their low cost and flexible deployment. As a key material for decoys, the base fabric must possess excellent airtightness, structural strength, and camouflage properties to simulate real targets and confuse enemy reconnaissance and attack.

[0003] Early fabric materials and surface characteristics were relatively simple, and traditional fabric defect detection relied heavily on manual visual inspection, a method that is inefficient and susceptible to subjective factors. When inspecting inflatable decoy fabrics, manual inspections struggle to accurately identify tiny cracks and bonding defects. Inspection accuracy is even lower for fabrics that have been used in complex environments. Furthermore, manual inspections cannot meet the demands of large-scale production and rapid testing, making them difficult to adapt to the efficient production and rapid deployment of modern military equipment.

[0004] As the application scenarios of inflatable decoys expand, automated inspection technology is gradually emerging and being applied in the industrial field. While automated inspection technology improves inspection efficiency, it still faces challenges in detection accuracy and functional integrity. Some conventional fabric inspection technologies based on machine vision can only detect obvious surface defects on the base fabric and are unable to effectively inspect the special structure and performance requirements of the base fabric of inflatable decoys. As a core component of modern battlefield deception systems, the base fabric of inflatable simulated decoys must simultaneously meet airtightness, structural strength, and camouflage properties.

[0005] Chinese invention patent CN116385426A discloses a textile surface defect detection method based on an improved YOLOv7 model. The invention collects a test set of textile surface defect images and inputs them into the improved YOLOv7 network for training to obtain the optimal target detection model. This invention only solves the single defect detection problem of civilian textiles, and its technical means cannot adapt to the composite coating structure and extreme environmental stability requirements of military decoy targets.

[0006] Chinese invention patent CN116309367A discloses a method for detecting surface defects of fiber fabrics based on machine vision. This invention is based on machine vision and uses the periodic characteristics of alternating light and dark presented in the image and related algorithms for detection. It does not involve the base fabric used in the manufacture of inflatable decoys, which has a special multi-layer composite structure.

[0007] Therefore, the present invention proposes a surface detection method for a base fabric used in manufacturing an inflatable decoy based on visual detection. Summary of the Invention

[0008] The purpose of the present invention is to solve the problems of low detection accuracy, single function, poor environmental adaptability and reliance on subjective experience in the existing surface defect detection technology for base fabrics used in the manufacture of inflatable decoys. A surface defect detection method for base fabrics used in the manufacture of inflatable decoys based on visual detection is proposed. The method is particularly suitable for surface defect detection of composite coated fabric base fabrics in the manufacturing process of military simulation decoys.

[0009] In order to achieve the above-mentioned object, the present invention adopts the following technical solution: a method for detecting the surface of a base fabric for manufacturing an inflatable decoy based on visual detection, comprising the following steps: Step S1, pre-treatment of the base fabric, laying the composite coated base fabric used for the military inflatable decoy on the detection platform, and eliminating surface wrinkles through a tension adjustment device; Step S2, multispectral image acquisition, capturing a visible light image of the surface of the base fabric by a high-resolution industrial camera, and capturing a thermal radiation image of the surface of the base fabric by an infrared thermal imager; Step S3, defect detection, uses a multimodal algorithm to identify coating cracks, bonding defects, and camouflage anomalies, verifies emissivity uniformity and temperature difference compliance, and compensates for environmental interference using a polynomial fitting algorithm; Step S4: Based on the impact of the defect on airtightness, structural strength, and camouflage performance, a three-level standard is used to determine the defect, and a test report including the defect type, coordinates, and repair suggestions is output.

[0010] The beneficial effects brought about by the technical solution provided by the present invention include at least: The present invention can comprehensively capture the visible light and thermal radiation information of the base fabric surface through multispectral image acquisition combined with a high-resolution industrial camera and an infrared thermal imager.

[0011] The present invention uses a multimodal algorithm to identify coating cracks, bonding defects and camouflage anomalies, while verifying the uniformity of emissivity, effectively avoiding the missed detection that may occur in traditional single detection methods, and ensuring that even tiny defects on the surface of the base fabric can be accurately identified.

[0012] The present invention compensates for the offset error of the infrared thermal imager caused by ambient temperature through blackbody three-point calibration and quadratic polynomial fitting algorithm, so that the detection method can be adapted to extreme military environments and the detection accuracy is not affected by temperature fluctuations.

[0013] The present invention, by targeting the special needs of military inflatable decoys, can effectively detect surface defects of the base fabric, ensure the airtightness, structural strength and camouflage performance of the decoy, provide reliable protection for military training and combat, and improve the quality and performance of military equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0015] Figure 1 A flow chart of a method for detecting the surface of a base fabric used in manufacturing an inflatable decoy target based on visual detection provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] To further illustrate the technical means and effectiveness of the present invention in achieving its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effectiveness of a visual inspection-based surface inspection method for a base fabric used in the manufacture of inflatable decoys. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0017] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0018] The following examples are for illustrative purposes only and are not intended to limit the scope of the present invention.

[0019] The following describes in detail a specific scheme of a method for detecting the surface of a base fabric for manufacturing an inflatable decoy based on visual detection provided by the present invention in conjunction with the accompanying drawings.

[0020] See also Figure 1 , which shows a method flow chart of a method for detecting the surface of a base fabric for manufacturing an inflatable decoy based on visual detection according to an embodiment of the present invention, the method comprising the following steps: Step S1, pre-treatment of the base fabric, laying the composite coated base fabric used for the military inflatable decoy on the detection platform, and eliminating surface wrinkles through a tension adjustment device; Wherein, step S1 further includes the following sub-steps: S1-1, confirm that the base fabric meets the requirements of a four-layer composite structure; the four-layer composite structure includes, from the inside to the outside, a textile base material layer, a metallized reflective layer, an airtight coating, and a camouflage spray layer; S1-2, platform calibration, use a high-precision level to adjust the platform level and clean the surface with ethanol; S1-3, applying tension to the edge of the base fabric through a pneumatic tension adjustment device to eliminate residual wrinkles on the surface of the base fabric; S1-4, use a vacuum adsorption fixture to align and fix the edge of the base fabric with the platform reference line.

[0021] It should be noted that the textile base material layer is made of metal fiber blended polyester fabric.

[0022] The thickness of the adhesive layer of the airtight coating is 0.3±0.1mm, ensuring an adhesion strength of >5kN / m.

[0023] The metallized reflective layer adopts a composite metal film with a breaking strength of ≥8kN / m, ensuring the structural integrity under the air chamber pressure of 700Pa after inflation.

[0024] The camouflage spray coating is PVC ink, the camouflage spray defect judgment threshold ΔE>3.0, and the defect judgment threshold setting standard complies with GJB 7987-2012.

[0025] Step S2, multispectral image acquisition, using a high-resolution industrial camera to acquire a visible light image of the base fabric surface, and using an infrared thermal imager to acquire a thermal radiation image of the base fabric surface; Wherein, in step S2, the following sub-steps are also included: S2-1, equipment calibration, geometric distortion correction of high-resolution industrial cameras using a checkerboard calibration plate; blackbody calibration of infrared thermal imagers at -40°C, 25°C, and 120°C, corresponding to the low temperature limit, normal temperature, and high temperature operating points, respectively; S2-2, visible light image acquisition, including: Use a high-resolution industrial camera with a resolution of ≥20 million pixels to capture the surface image of the base fabric under standard light source D65; The movement is controlled by the XYZ three-axis linkage platform to maintain the overlap rate of adjacent images at 10-15%; Laser displacement sensor assists autofocus to ensure depth of field consistency; S2-3, infrared image acquisition, including: Use infrared thermal imager to collect thermal radiation images; Synchronously record ambient temperature and humidity data for real-time compensation of polynomial fitting algorithm; S2-4, image synchronization alignment, pixel-level alignment of visible light and infrared images through SIFT feature matching.

[0026] It should be noted that an overlap rate of 10-15% meets the minimum overlap requirement of SIFT feature matching, ensuring that there is no detection blind area on the surface of the base fabric.

[0027] The D65 light source was selected based on the need for military battlefield daylight simulation.

[0028] Ambient temperature and humidity affect the thermal conductivity of the air, which in turn interferes with the temperature measurement of thermal radiation images.

[0029] The SIFT feature matching error is ≤0.5 pixels, ensuring the crack positioning accuracy of 0.1mm.

[0030] Step S3, defect detection, uses a multimodal algorithm to identify coating cracks, bonding defects, and camouflage anomalies, verifies emissivity uniformity and temperature difference compliance, and compensates for environmental interference using a polynomial fitting algorithm; Wherein, in step S3, the following sub-steps are also included: S3-1, airtight coating crack detection, including: Crack detection uses the YOLOv5 target detection model trained on a military fabric crack sample library, with a detection sensitivity of cracks ≥ 0.1 mm in width. Defect analysis: measuring the actual width and cumulative length of cracks, and simultaneously analyzing temperature anomalies in the crack area; Quality assessment: when a single crack width > 0.3mm or the cumulative length of cracks > 10cm and the temperature standard deviation > 1.5℃ is detected, it is judged as "scrap"; the remaining cracks are judged as "repairable"; S3-2, Adhesion Defect Detection, including: Image segmentation detection uses the U-Net neural network model to process the base fabric image and identify the bonding defect area through multi-scale feature fusion; Defect quantification analysis, calculation of the actual area of the bonding defect area, and analysis of the edge irregularity of the defect area; Quality assessment: when the bonding defect area is greater than 10cm² or the defect penetrates the critical stress-bearing area, it is judged as "scrap"; other defects with an area greater than 5cm² are judged as "repairable"; S3-3, camouflage spray defect detection, including: Color consistency testing: collect RGB images of the base fabric surface and convert them into CIELAB color space, and calculate the ΔE color difference between the tested area and the standard sample; Missing spray area detection uses the reflectivity difference between the metallized base fabric and the coating, adopts semantic segmentation algorithm to extract the outline of the missing spray area, and calculates the actual area of the missing spray area; Defect judgment: when the ΔE color difference is greater than 3.0 or the missed spraying area is greater than 2cm², an early warning is triggered; S3-4, Emissivity Uniformity Analysis, including: Image preprocessing: using median filtering to eliminate thermal image noise and using Otsu's adaptive threshold algorithm to segment the effective detection area of the base fabric; Temperature analysis: collect 10 frames of temperature data continuously within a 5-minute monitoring window and calculate the temperature standard deviation of the effective area of each frame; Uniformity determination: when the standard deviation of more than 30% of the frames is greater than 2°C, it is determined that the emissivity is non-uniform; S3-5, determination of temperature difference compliance, including: Background temperature measurement: automatically select a uniform area ≥5cm away from the edge of the base fabric as the background and calculate the average temperature of the background area; Temperature difference analysis: continuously monitor the highest temperature point on the surface of the base fabric and calculate the real-time difference between the highest temperature and the background temperature; Quality assessment: when the temperature difference is continuously greater than 50°C and the fluctuation is ≤±5°C, it is judged as "qualified"; when the temperature difference is between 45-50°C or the fluctuation is greater than ±5°C, it is judged as "repairable"; S3-6, Environmental Disturbance Compensation, including: Temperature calibration uses a surface source blackbody to regularly calibrate the infrared thermal imager, and a polynomial fitting algorithm is used to compensate for the offset error of the ambient temperature on the infrared thermal imager. The calibration formula is:

[0031] in, Indicates the actual temperature value of the target surface after ambient temperature compensation; Indicates the surface temperature of the base fabric directly measured by the infrared thermal imager; Indicates the ambient temperature collected in real time; a represents the quadratic coefficient of the ambient temperature, b represents the linear coefficient, and c represents the zero offset compensation; Distance compensation: synchronously collect target distance data and automatically adjust the focus of the thermal imager according to the distance change; Geometric correction: real-time correction of temperature measurement errors caused by viewing angle deviation.

[0032] It should be noted that the military base fabric crack sample library contains more than 2,000 labeled samples, covering cracks with a width of 0.1mm-2mm, different directions and environmental damage, and uses data enhancement technology to improve the model generalization ability.

[0033] By using the feature pyramid network of YOLOv5 to fuse multi-scale features, pixel-level positioning of 0.1mm cracks is achieved, with a bounding box regression error of ≤0.5 pixels, meeting the needs of military base fabric micro-defect detection.

[0034] Adopting an encoding-decoding architecture, the encoding stage uses convolutional layers to extract features of different scales, and the decoding stage uses skip connections to fuse shallow texture information with deep semantic information, accurately identifying adhesion defect areas larger than 5cm².

[0035] Canny edge detection is used to extract the defect outline and calculate the ratio of the circumference to the equivalent circle circumference. Irregularity greater than 1.5 is considered an edge fuzzy defect, which helps distinguish process stitching lines from real bonding defects.

[0036] Convert RGB to CIELAB to eliminate device color deviation. The calculation formula for ΔE is:

[0037] in, Indicates the brightness difference between the measured area and the standard sample, reflecting the difference between light and dark; Indicates the color difference between the red and green axes, positive values indicate that the sample is reddish, and negative values indicate that the sample is greenish; Indicates the color difference between the yellow and blue axes. Positive values indicate that the sample is yellowish, and negative values indicate that the sample is bluish.

[0038] A single crack >0.3mm will result in air leakage >10% / h under a pressure difference of 500Pa, causing the inflatable structure to become unstable within 2 hours.

[0039] The temperature standard deviation is greater than 1.5°C, which corresponds to the minimum detectable temperature difference of the thermal infrared module, ensuring the camouflage requirement of a temperature difference greater than 50°C from the background environment.

[0040] When the area of bonding defects in the critical stress-bearing area exceeds 10 cm², the tensile strength decreases by more than 20%, making it impossible to withstand a load with a snow-bearing capacity of 20 kg / m².

[0041] More than 30% of the frames with a standard deviation greater than 2°C indicate that the metallization layer is partially damaged, resulting in uneven thermal infrared radiation and affecting the camouflage effect.

[0042] The Otsu segmentation threshold is adjusted according to the theoretical emissivity of the metallization layer to avoid local emissivity anomalies caused by coating damage.

[0043] In the temperature difference standard determination, the background area is selected to avoid the edge of the metallized layer to prevent the heat conduction difference at the edge joint from interfering with the reference temperature calculation.

[0044] The coefficients a, b, and c in the temperature calibration formula are obtained by fitting the blackbody calibration experiment.

[0045] Step S4: Determine the defect according to the three-level standard based on its impact on airtightness, structural strength, and camouflage performance, and output a test report containing the defect type, coordinates, and repair recommendations; Wherein, in step S4, the following sub-steps are also included: S4-1, defect classification, divides the test results into three levels: Qualified, no defects that affect use, and the temperature difference is continuously greater than 50℃ and the fluctuation is ≤±5℃; Repairable, with defects that can be repaired through standard maintenance packages; Scrap, serious defects affecting airtightness, structural strength or camouflage performance; S4-2, report generation, automatically outputs a test report containing the following contents: Defect type and coordinates; Defect size and severity; Repair recommendations for “repairable” defects; S4-3, data storage, stores the test data in association with the product number in the database; records the environmental data during the test, which includes temperature and humidity data.

[0046] Repair recommendations include: Repair area and coating thickness for coating cracks; Re-bonding solutions for bonding defects; The color number and range of the re-spray for camouflage spray defects.

[0047] It should be noted that the temperature difference is continuously greater than 50°C and the fluctuation is ≤±5°C to ensure that the false target presents a stable thermal signature on the infrared reconnaissance equipment, avoiding being identified by the enemy due to insufficient temperature difference or excessive fluctuation.

[0048] The standard maintenance package includes: Repair coating cracks by providing airtight coating patches made of the same material as the base fabric and special adhesives; Adhesive defect repair, including two-component fast-curing adhesive and pressure fixture; Camouflage re-spraying, pre-stored standard color number database, support matching re-spraying color number.

[0049] Coordinate positioning is based on the XYZ three-axis linkage platform coordinate system, combined with the global coordinate system after image stitching, to meet the precise positioning needs during maintenance.

[0050] In this way, a surface detection method for a base fabric used in the manufacture of an inflatable decoy based on visual detection can be realized.

[0051] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for detecting the surface of a base fabric used in the manufacture of an inflatable decoy based on visual inspection, characterized in that: The following steps are involved: Step S1, pre-treatment of the base fabric, laying the composite coated base fabric used for the military inflatable decoy on the detection platform, and eliminating surface wrinkles through a tension adjustment device; Step S2, multispectral image acquisition, capturing a visible light image of the surface of the base fabric by a high-resolution industrial camera, and capturing a thermal radiation image of the surface of the base fabric by an infrared thermal imager; Step S3, defect detection, uses a multimodal algorithm to identify coating cracks, bonding defects, and camouflage anomalies, verifies emissivity uniformity and temperature difference compliance, and compensates for environmental interference using a polynomial fitting algorithm; Step S4: Based on the impact of the defect on airtightness, structural strength, and camouflage performance, a three-level standard is used to determine the defect, and a test report including the defect type, coordinates, and repair suggestions is output.

2. The method for detecting the surface of a base fabric for manufacturing an inflatable decoy based on visual inspection according to claim 1, characterized in that: Wherein, step S1 further includes the following sub-steps: S1-1, confirm that the base fabric conforms to a four-layer composite structure; the four-layer composite structure includes, from the inside to the outside, a textile base material layer, a metallized reflective layer, an airtight coating, and a camouflage spray coating; S1-2, platform calibration, use a high-precision level to adjust the platform level and clean the surface with ethanol; S1-3, applying tension to the edge of the base fabric through a pneumatic tension adjustment device to eliminate residual wrinkles on the surface of the base fabric; S1-4, use a vacuum adsorption fixture to align and fix the edge of the base fabric with the platform reference line.

3. The method for detecting the surface of a base fabric for manufacturing an inflatable decoy based on visual inspection according to claim 1, characterized in that: Wherein, in step S2, the following sub-steps are also included: S2-1, equipment calibration, geometric distortion correction of high-resolution industrial cameras using a checkerboard calibration plate; blackbody calibration of infrared thermal imagers at -40°C, 25°C, and 120°C, corresponding to the low temperature limit, normal temperature, and high temperature operating points, respectively; S2-2, visible light image acquisition, including: Use a high-resolution industrial camera with a resolution of ≥20 million pixels to capture the surface image of the base fabric under standard light source D65; The movement is controlled by the XYZ three-axis linkage platform to maintain the overlap rate of adjacent images at 10-15%; Laser displacement sensor assists autofocus to ensure depth of field consistency; S2-3, infrared image acquisition, including: Use infrared thermal imager to collect thermal radiation images; Synchronously record ambient temperature and humidity data for real-time compensation of polynomial fitting algorithm; S2-4, image synchronization alignment, pixel-level alignment of visible light and infrared images through SIFT feature matching.

4. The method for detecting the surface of a base fabric for manufacturing an inflatable decoy based on visual inspection according to claim 1, characterized in that: Wherein, in step S3, the following sub-steps are also included: S3-1, airtight coating crack detection, including: Crack detection uses the YOLOv5 target detection model trained on a military fabric crack sample library, with a detection sensitivity of cracks ≥ 0.1 mm in width. Defect analysis: measuring the actual width and cumulative length of cracks, and simultaneously analyzing temperature anomalies in the crack area; Quality assessment: when a single crack width > 0.3mm is detected, it is judged as "scrapped"; when the cumulative length of cracks detected is > 10cm and the temperature standard deviation is > 1.5℃, it is judged as "scrapped"; the remaining cracks are judged as "repairable"; S3-2, Adhesion Defect Detection, including: Image segmentation detection uses the U-Net neural network model to process the base fabric image and identify the bonding defect area through multi-scale feature fusion; Defect quantification analysis, calculation of the actual area of the bonding defect area, and analysis of the edge irregularity of the defect area; Quality assessment: If the bonding defect area is greater than 10cm² or the defect penetrates the critical stress-bearing area, it will be considered "scrapped"; if the defect area is greater than 5cm², it will be considered "repairable"; S3-3, camouflage spray defect detection, including: Color consistency testing: collect RGB images of the base fabric surface and convert them into CIELAB color space, and calculate the ΔE color difference between the tested area and the standard sample; Missing spray area detection uses the reflectivity difference between the metallized base fabric and the coating, adopts semantic segmentation algorithm to extract the outline of the missing spray area, and calculates the actual area of the missing spray area; Defect judgment: when the ΔE color difference is greater than 3.0 or the missed spraying area is greater than 2cm², an early warning is triggered; S3-4, Emissivity Uniformity Analysis, including: Image preprocessing: using median filtering to eliminate thermal image noise and using Otsu's adaptive threshold algorithm to segment the effective detection area of the base fabric; Temperature analysis: collect 10 frames of temperature data continuously within a 5-minute monitoring window and calculate the temperature standard deviation of the effective area of each frame; Uniformity determination: when the standard deviation of more than 30% of the frames is greater than 2°C, it is determined that the emissivity is non-uniform; S3-5, determination of temperature difference compliance, including: Background temperature measurement: automatically select a uniform area ≥5cm away from the edge of the base fabric as the background and calculate the average temperature of the background area; Temperature difference analysis: continuously monitor the highest temperature point on the surface of the base fabric and calculate the real-time difference between the highest temperature and the background temperature; Quality assessment: when the temperature difference is continuously greater than 50°C and the fluctuation is ≤±5°C, it is judged as "qualified"; when the temperature difference is between 45-50°C or the fluctuation is greater than ±5°C, it is judged as "repairable"; S3-6, Environmental Disturbance Compensation, including: Temperature calibration uses a surface source blackbody to regularly calibrate the infrared thermal imager, and a polynomial fitting algorithm is used to compensate for the offset error of the ambient temperature on the infrared thermal imager. The calibration formula is: in, Indicates the actual temperature value of the target surface after ambient temperature compensation; Indicates the surface temperature of the base fabric directly measured by the infrared thermal imager; Indicates the ambient temperature collected in real time; a represents the quadratic coefficient of the ambient temperature, b represents the linear coefficient, and c represents the zero offset compensation; Distance compensation: synchronously collect target distance data and automatically adjust the focus of the thermal imager according to the distance change; Geometric correction: real-time correction of temperature measurement errors caused by viewing angle deviation.

5. The method for detecting the surface of a base fabric for manufacturing an inflatable decoy based on visual inspection according to claim 1, characterized in that: Wherein, in step S4, the following sub-steps are also included: S4-1, defect classification, divides the test results into three levels: Qualified, no defects that affect use, and the temperature difference is continuously greater than 50℃ and the fluctuation is ≤±5℃; Repairable, with defects that can be fixed through standard maintenance packages; Scrap, serious defects affecting airtightness, structural strength or camouflage performance; S4-2, report generation, automatically outputs a test report containing the following contents: Defect type and coordinates; Defect size and severity; Repair recommendations for "repairable" defects; S4-3, data storage, storing the detection data in association with the product number in the database; recording the environmental data during the detection, the environmental data including temperature and humidity data.

6. The method for detecting the surface of a base fabric for manufacturing an inflatable decoy based on visual inspection according to claim 5, characterized in that: The repair recommendations include: Repair area and coating thickness for coating cracks; Re-bonding solutions for bonding defects; The color number and range of the re-spray for camouflage spray defects.

Images