Method and apparatus for detecting delamination in composite panel based on thermal imaging

Abstract

One embodiment of the present disclosure provides a method for detecting delamination of a composite panel based on thermal imaging. The method comprises the steps of receiving thermal imaging data of a panel composed of a composite material and detecting delamination of the composite panel by analyzing temperature differences in a plurality of different regions of the panel based on the thermal imaging data.

Description

Technology Field

[0001] The present invention relates to a method and apparatus for detecting delamination of a thermal imaging-based composite panel, and more specifically, to a technology for detecting thermal performance degradation caused by separation between multiple materials within a heat-generating composite material composed of multiple materials stacked together, based on thermal imaging data. Background Technology

[0002] Recently, composite material panels are being used in various modes of transportation, such as railway vehicles, aircraft, and automobiles, for the purpose of lightweighting. These composite material panels are used in a wide range of applications, including vehicle bodies, bogie frames, and interior materials.

[0003] In addition, the multifunctionalization of composite materials through the mixing of advanced and multifunctional materials is actively underway, and these composite panels are manufactured by incorporating nanomaterials such as CNTs or graphene, or by laminating thin-film carbon fiber heating elements inside.

[0004] In the case of internal lamination of heating elements, forms such as inserting thin-film carbon fiber heating elements between plate-shaped metal materials or inserting carbon fiber heating elements between plate-shaped composite materials can be considered.

[0005] When a composite material containing a carbon fiber heating element is used for a long period, it is exposed to continuous temperature changes of heating and cooling, and thermal deformation due to repeated thermal loading can cause various damages to the composite material.

[0006] In particular, composite materials composed of a multilayer stacked structure are susceptible to interlayer separation, and if delamination occurs over a large area between layers, it is difficult to identify visually from the outside.

[0007] In the case of composite materials embedded with carbon fiber heating elements, there is a concern that mechanical performance may deteriorate if internal interlayer separation occurs. Furthermore, there is a problem where heating performance is severely degraded due to its impact on internal heat flow; additionally, conventional delamination detection techniques using ultrasonic testing require a specialized level of expertise, making it significantly difficult to universally utilize for internal delamination detection.

[0008] Accordingly, there is an increasing need for technology to detect delamination and thermal performance degradation caused by separation between multiple materials within heat-generating composite materials. The problem to be solved

[0009] The present invention aims to solve the problems of the aforementioned prior art and relates to a method and apparatus for detecting delamination of a thermal imaging-based composite panel, which detects thermal performance degradation caused by separation between multiple materials within a heat-generating composite material composed of multiple materials stacked together based on thermal imaging data.

[0010] However, the technical problem that this embodiment aims to solve is not limited to the technical problem described above, and other technical problems may exist. means of solving the problem

[0011] As a technical means for achieving the technical problem described above, an embodiment according to the first aspect of the present disclosure provides a method for detecting delamination of a composite panel based on thermal imaging. The method comprises the steps of receiving thermal imaging data of a panel composed of a composite material and detecting delamination of the composite panel by analyzing the temperature difference between a plurality of different regions of the panel based on the thermal imaging data.

[0012] Additionally, an embodiment according to a second aspect of the present disclosure provides a thermal imaging-based device for detecting delamination of a composite panel. The device comprises at least one processor and a memory electrically connected to the processor and storing at least one code executed by the processor, wherein the memory stores a code that, when executed through the processor, causes the processor to receive thermal imaging data of a panel composed of the composite material and to analyze temperature differences in multiple different regions of the panel based on the thermal imaging data to detect delamination of the composite panel. Effects of the invention

[0013] The present invention can derive a linear correlation of thermal performance degradation according to the peeling area by using a statistical analysis method of thermal images.

[0014] In addition, while it is difficult to determine whether delamination has occurred and the area of ​​delamination using only conventional temperature data, the present invention allows for more accurate and easier verification of whether delamination has occurred and the area of ​​delamination. Brief explanation of the drawing

[0015] FIG. 1 is a drawing showing a peel detection device for a composite panel according to one embodiment of the present invention and a thermal imaging terminal connected to the same. Figure 2 is a detailed drawing of the peel detection device of the composite panel in Figure 1. FIG. 3 is a diagram showing the system flow of a peel detection device for a composite panel according to one embodiment of the present invention. FIG. 4 is a diagram showing the peeling process of a composite panel according to one embodiment of the present invention. FIG. 5 is a drawing showing internal peeling of a composite panel according to one embodiment of the present invention. FIGS. 6 to 8 are drawings showing sample configurations of a composite panel according to one embodiment of the present invention. Figures 9 and 10 are drawings showing thermal images of the composite panel sample of Figure 8. FIG. 11 is a graph showing the change in asymmetry according to the peeling area according to one embodiment of the present invention. FIG. 12 is a graph showing the change in kurtosis according to the peeling area according to one embodiment of the present invention. FIGS. 13 and 14 are drawings showing the results of analyzing the peeling area using temperature measurement data according to one embodiment of the present invention. FIG. 15 is a diagram showing the relationship between asymmetry or kurtosis through normalization according to one embodiment of the present invention, the presence of delamination, and the delamination area. FIG. 16 is a flowchart illustrating the sequence of a method for detecting delamination of a composite panel according to another embodiment of the present invention. FIG. 17 is a flowchart illustrating in detail a peeling detection step according to another embodiment of the present invention. Specific details for implementing the invention

[0016] The present disclosure will be described in detail below with reference to the attached drawings. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. Furthermore, the attached drawings are intended only to facilitate understanding of the embodiments disclosed herein, and the technical concept disclosed herein is not limited by the attached drawings. All terms used herein, including technical and scientific terms, should be interpreted in the sense generally understood by those skilled in the art to which the present disclosure pertains. Terms defined in advance should be interpreted as having additional meanings consistent with relevant technical literature and the present disclosure, and should not be interpreted in a highly ideal or restrictive sense unless otherwise defined.

[0017] In order to clearly explain the invention in the drawings, parts unrelated to the explanation have been omitted, and the size, form, and shape of each component shown in the drawings may be varied. Throughout the specification, identical or similar parts are denoted by identical or similar reference numerals.

[0018] Throughout the specification, when it is stated that a part is "connected (connected, contacted, or coupled)" to another part, this includes not only cases where they are "directly connected (connected, contacted, or coupled)," but also cases where they are "indirectly connected (connected, contacted, or coupled)" with other members interposed therebetween. Furthermore, when it is stated that a part "includes (provides, or provides)" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but rather allows for additional "included (provided, or provided)" of other components.

[0019] In this specification, the term "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized by one piece of hardware. Meanwhile, "part" is not limited to software or hardware, and "part" may be configured to reside in an addressable storage medium or configured to run on one or more processors. Accordingly, as an example, "part" includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and "parts" may be combined into a smaller number of components and "parts" or further separated into additional components and "parts." In addition, the components and '~parts' may be implemented to play one or more CPUs within the device or secure multimedia card.

[0020] In the following description, suffixes such as "module" and "part" for components are assigned or used interchangeably solely for the ease of drafting the specification, and do not inherently possess distinct meanings or roles. Furthermore, in describing the embodiments disclosed in this specification, detailed descriptions of related prior art have been omitted where it is determined that such detailed descriptions could obscure the essence of the embodiments disclosed in this specification.

[0021] Terms indicating ordinal numbers, such as first, second, etc., used herein are used solely for the purpose of distinguishing one component from another and do not limit the order or relationship of the components. For example, the first component of the present disclosure may be named the second component, and similarly, the second component may be named the first component. Singular forms used herein should be interpreted to include plural forms unless explicitly to the contrary.

[0022] FIG. 1 is a drawing showing a peel detection device for a composite panel according to one embodiment of the present invention and a thermal imaging terminal connected to the same.

[0023] Referring to FIG. 1, a peel detection device (100) for a composite panel and a thermal imaging terminal (200) can be connected via a communication network. In the following description, the peel detection device (100) for a composite panel may also be implemented in the form of a server. When the peel detection device (100) for a composite panel is implemented as a server, it may be formed as a cloud computing server such as SaaS (Software as a Service), PaaS (Platform as a Service), or IaaS (Infrastructure as a Service). Additionally, the server may be constructed in the form of a private cloud, a public cloud, or a hybrid cloud system, but the scope of the present invention is not limited thereto.

[0024] The peeling detection device (100) of the composite panel receives thermal image data of the composite panel composed of a composite material. Hereinafter, the composite panel may be referred to as a composite panel.

[0025] The delamination detection device (100) of a composite panel detects delamination of the composite panel by analyzing the temperature difference between multiple different regions of the composite panel based on thermal image data.

[0026] The thermal imaging terminal (200) can photograph a composite material panel and provide thermal image data to a peeling detection device (100) of the composite material panel. The thermal imaging terminal (200) may be specialized equipment for thermal imaging, and may be a terminal including a camera with thermal imaging software installed therein.

[0027] Figure 2 is a detailed drawing of the peel detection device of the composite panel in Figure 1.

[0028] Referring to FIG. 2, the peeling detection device (100) of a composite panel may include a communication module (110), a processor (120), and a memory (130).

[0029] The communication module (110) may include a device comprising hardware and software necessary to transmit and receive signals, such as control signals or data signals, through a wired or wireless connection with another network device.

[0030] The communication module (110) can receive thermal image data from the thermal imaging terminal (200). However, it is not limited thereto, and if necessary, the communication module (110) can receive thermal image data from an external device other than the thermal imaging terminal (200).

[0031] The processor (120) may include various types of devices for controlling and processing data. The processor (120) may refer to a data processing device embedded in hardware having a physically structured circuit to perform a function expressed by code or instructions included in a program.

[0032] In one example, the processor (120) may be implemented in the form of a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), etc., but the scope of the invention is not limited thereto.

[0033] The processor (120) performs operations according to the code stored in memory (130).

[0034] The memory (130) can store at least one of the information and data input to the communication module (110), the information and data required for the function performed by the processor (120), and the data generated according to the execution of the processor (120).

[0035] The term "memory" (130) should be interpreted as a general term for a non-volatile storage device that retains stored information even when power is not supplied, and a volatile storage device that requires power to retain stored information. In addition to a volatile storage device that requires power to retain stored information, the memory (130) may include a magnetic storage medium or a flash storage medium, but the scope of the present invention is not limited thereto.

[0036] Memory (130) is electrically connected to the processor (120) and stores at least one code that is executed by the processor (120). Memory (130) stores code that causes the processor (120) to perform the following functions and procedures when executed through the processor (120).

[0037] The memory (130) stores code that causes the reception of thermal image data of a composite panel composed of a composite material.

[0038] In the memory (130), a code is stored that causes delamination of the composite material panel by analyzing the temperature difference between multiple different regions of the composite material panel based on thermal image data. For example, the temperature of each region may correspond to the temperature of each pixel of the thermal image data. And the asymmetry Sk is a characteristic value that calculates the average temperature for each region and indicates whether the average temperature is higher or lower than the median value of the temperatures of each region. If the average temperature is higher than the temperature of each region, the asymmetry Sk may show a negative value, and if the average temperature is lower than the median value of the temperatures of each region, the asymmetry Sk may show a positive value. And the kurtosis Ku may indicate the density of the temperatures of each region.

[0039] As another example, asymmetry Sk is a characteristic value that calculates the average temperature for each zone and indicates whether the average temperature is higher or lower than the median of the zone temperatures; if the average temperature is higher than the zone temperatures, asymmetry Sk may show a negative value, and if the average temperature is lower than the zone temperatures, asymmetry Sk may show a positive value.

[0040] In memory (130), a code may be stored that analyzes the temperature difference to calculate at least one of asymmetry Sk and kurtosis Ku, and uses at least one of the calculated asymmetry Sk and kurtosis Ku to cause delamination.

[0041] Memory (130) stores code that inputs asymmetry Sk and kurtosis Ku into a pre-set correlation model to calculate whether a peeling zone has occurred and the area. For example, the correlation model has linear characteristics and can be expressed in the form of a two-dimensional linear graph. In this case, the X-axis may be the peeling area and the Y-axis may be the normalized value.

[0042] And, the asymmetry Sk can be calculated based on the following formula.

[0043]

[0044] Kurtosis Ku can be calculated based on the following formula.

[0045]

[0046] In the above formulas for calculating asymmetry Sk and kurtosis Ku, X is the temperature data value of each pixel, N is the total number of derived data, It can represent the average value of the entire pixel temperature data.

[0047] FIG. 3 is a diagram showing the system configuration and flow of a peel detection device for a composite panel according to one embodiment of the present invention.

[0048] Referring to FIG. 3, power is supplied to a composite panel (301) by a power supply (302) to emit heat, and when a thermal imaging terminal (200) transmits thermal imaging data to a peeling detection device (100) of the composite panel, the peeling detection device (100) of the composite panel can visualize the thermal imaging data and provide it to a manager terminal (304).

[0049] FIG. 4 is a diagram showing the peeling process of a composite panel according to one embodiment of the present invention.

[0050] Referring to FIG. 4, when a composite panel (301) containing a heating element is exposed to temperature changes due to continuous heating and cooling (401), thermal deformation (402) occurs at a point that receives a concentrated thermal load, and delamination (403) occurs internally over time. When delamination occurs internally, it is difficult to detect from the outside, and due to the separation between internal layers, the thermal conductivity is lowered, which can lead to a combination of mechanical and thermal performance degradation.

[0051] FIG. 5 is a drawing showing internal peeling of a composite panel according to one embodiment of the present invention.

[0052] Referring to FIG. 5, when delamination (504) occurs inside the composite panel (301), the temperature of the delamination area may be lower (502), unlike the high temperature (501) of the points where delamination did not occur. This is because, due to the occurrence of internal delamination (504), the heat source cannot pass through the composite material entirely due to the low thermal conductivity of the air generated in the delamination area, and some heat loss occurs.

[0053] FIGS. 6 to 8 are drawings showing sample configurations of a composite panel according to one embodiment of the present invention.

[0054] Referring to FIGS. 6 and 7, a sample of a composite panel (301) for verifying a temperature change due to the peeling of the composite material may include a carbon fiber (601), a Teflon film (602), an electrode portion (603), and a substrate portion (604). The carbon fiber (601) acts as a heating element, and the Teflon film (602) may be attached to simulate peeling. The electrode portion (603) provides power to the carbon fiber, and the substrate portion (604) may be configured to wrap the carbon fiber (601), the Teflon film (602), and the electrode portion (603).

[0055] Referring to FIG. 7, a sample of the composite panel (301) is described in more detail as follows: carbon fibers (601) are inserted between glass fibers composed of a plurality of yarn cloths (701, Yan cloth) and roving cloths (702, Roving cloth) made of glass fibers, and a Teflon film (602) may be inserted as a peeling simulation film for a peeling test.

[0056] Referring to FIG. 8, Teflon films (602) of various sizes can be prepared by inserting them between glass fibers and carbon fiber (601) films. For example, when a sample of a composite panel (301) has a width and length of 150 x 150 mm, Teflon films (602) can be prepared for 0% (802), 7% (40 x 40 mm) (803), 11% (50 x 50 mm) (804), and 16% (60 x 60 mm) (805) of the total area.

[0057] Figures 9 and 10 are drawings showing thermal images of the composite panel sample of Figure 8.

[0058] Referring to FIG. 9, power is supplied to a sample of the composite panel (301) prepared in FIG. 8, and when the surface temperature reaches a quasi-equilibrium state, a thermal imaging terminal (200) is used to take a picture. The Teflon film (602) corresponding to 0% of the total area (802) shows a constant surface temperature of 109 degrees, the area corresponding to 7% (40X40mm) (803) shows a peeled area of ​​99 degrees when the surface temperature is 105 degrees, the area corresponding to 11% (50X50mm) (804) shows a peeled area of ​​100 degrees when the surface temperature is 110 degrees, and the area corresponding to 16% (60X60mm) (805) shows a peeled area of ​​97 degrees when the surface temperature is 108 degrees.

[0059] Referring to FIG. 10, in order to analyze the uniformity of the heat generation shown in FIG. 9, arbitrary thermal image data (1001) can be extracted in pixel units (1002) to analyze pixel-unit temperature data.

[0060] FIGS. 11 and 12 are graphs showing the change in asymmetry and kurtosis according to the peeling area according to one embodiment of the present invention.

[0061] Referring to Fig. 11, the degree of asymmetry Sk is calculated to analyze the pixel-unit temperature data extracted from Fig. 10, and a graph showing the change in the degree of asymmetry Sk according to the peeling area can be obtained based on the degree of asymmetry Sk. To this end, the formula for calculating the degree of asymmetry Sk is as follows.

[0062]

[0063] In the formula above for calculating the asymmetry Sk, X is the temperature data value of each pixel, N is the total number of derived data, represents the average value of the total pixel temperature data.

[0064] The asymmetry Sk indicates the skewness of the mean value relative to the median of the total temperature data. When compared to a normal distribution with a normal distribution value of Sk=0 (1102), if the mean value is higher than the median, a negative value appears, indicating that there is a lot of high-temperature data. In this case, the graph appears skewed toward the high-temperature side. Conversely, if the mean value is lower than the median, a positive value appears, indicating that there is a lot of low-temperature data, and the graph appears skewed toward the low-temperature side.

[0065] When the asymmetry Sk is calculated through each sample of the composite panel (301) in FIGS. 8 and FIG. 9 above, it is -1.5, -1.25, -1.01, and -0.89 (1101), and when represented as a graph, it is as shown in FIG. 11. As shown in the graph of FIG. 11, the asymmetry Sk of all samples is negative, and the average value is higher than the median value, showing a characteristic of having a large amount of high-temperature data. In addition, it can be seen that as the peeling area increases, it gradually approaches the normal distribution value (1102), which can be inferred to be because the number of low-temperature pixels increases within a certain number of pixels as the heat generation performance decreases due to the increase in the peeling area, thereby lowering the proportion of high-temperature data.

[0066] Referring to Fig. 12, kurtosis Ku is calculated to analyze the pixel-unit temperature data extracted from Fig. 10, and a graph of the change in kurtosis Ku according to the peeling area can be obtained based on kurtosis Ku. To this end, the formula for calculating kurtosis Ku is as follows.

[0067]

[0068] In the formula above for calculating kurtosis Ku, X is the temperature data value of each pixel, N is the total number of derived data, represents the average value of the total pixel temperature data.

[0069] Kurtosis Ku indicates how dense the temperature data is, and depending on the density, the kurtosis Ku of the graph appears as a peak or a flat shape. Based on the normal distribution value (1201) Ku=3, if the distribution is dense, it appears as a value higher than 3, and if the distribution is dispersed, it appears as a value lower than 3.

[0070] When the kurtosis Ku is calculated for each sample of the composite panel (301) in FIGS. 8 and FIG. 9 above, it is 4.1, 3.86, 3.78, and 3.67 (1202), and when represented as a graph, it is as shown in FIG. 12. As shown in the graph of FIG. 12, the kurtosis of all samples is positive, indicating that the temperature data is concentrated in a specific range. Similar to the asymmetry graph of FIG. 11, as the peeling area increases, it approaches the normal distribution value (1201), because the heat generation performance decreases in the peeling area, causing the overall temperature distribution to disperse.

[0071] FIGS. 13 and 14 are drawings showing the results of analyzing the peeling area using temperature measurement data according to one embodiment of the present invention.

[0072] Referring to FIG. 13 and FIG. 14, FIG. 13 estimates the relationship (1302) of the temperature reached relative to the peeling area (1301), and FIG. 14 estimates the relationship (1402) of the heating rate relative to the peeling area (1401). Both show non-linearity, making it difficult to derive an accurate relationship.

[0073] FIG. 15 is a diagram showing the relationship between asymmetry or kurtosis through normalization according to one embodiment of the present invention, the presence of delamination, and the delamination area.

[0074] Referring to Fig. 15, according to the statistical analysis method of thermal imaging data, the relationship between the peeling areas through normalization can be derived more clearly. In addition, as shown, it can be confirmed that the sensitivity is higher because the slope of the asymmetry Sk (1501, 2.64) is greater than the slope of the kurtosis Ku (1502, 0.65).

[0075] Accordingly, the presence of delamination and the delamination area can be determined through the relationship between asymmetry Sk and the delamination area. Alternatively, the presence of delamination and the delamination area can be determined through the relationship between kurtosis Ku and the delamination area.

[0076] FIG. 16 is a flowchart illustrating the sequence of a method for detecting delamination of a composite panel according to another embodiment of the present invention, and FIG. 17 is a flowchart illustrating in detail the delamination detection step according to another embodiment of the present invention.

[0077] The method for detecting delamination of a thermal imaging-based composite panel described below can be performed by the delamination detection device described above with reference to FIGS. 1 to 15. Accordingly, the description of the embodiment of the present disclosure described above with reference to FIGS. 1 to 15 can be applied in the same way to the embodiment described below, and any content that overlaps with the description above will be omitted. The steps described below do not necessarily have to be performed in order, the order of the steps can be set in various ways, and the steps may be performed almost simultaneously.

[0078] Referring to FIGS. 16 and 17, a method for detecting delamination of a composite panel includes a thermal image data reception step (S100) and a delamination detection step (S200).

[0079] The data reception step (S100) receives thermal image data of a composite material panel composed of a composite material.

[0080] The delamination detection step (S200) is a step of detecting delamination of the composite material panel by analyzing the temperature difference between multiple different regions of the composite material panel based on the thermal image data. For example, the temperature per region may correspond to the temperature per pixel of the thermal image data. The asymmetry Sk is a characteristic value that indicates whether the average temperature is higher or lower than the temperature per region by calculating the average temperature for each region; if the average temperature is higher than the temperature per region, the asymmetry Sk may show a negative value, and if the average temperature is lower than the temperature per region, the asymmetry Sk may show a positive value. The kurtosis Ku may represent the density of the temperature per region.

[0081] The delamination detection step (S200) may include a step (S210) of calculating at least one of asymmetry Sk and kurtosis Ku by analyzing the temperature difference, and a step (S220) of detecting delamination using at least one of the calculated asymmetry Sk and kurtosis Ku.

[0082] Then, code is stored that inputs the asymmetry Sk and kurtosis Ku into a pre-configured correlation model to calculate the occurrence and area of ​​the delamination zone. For example, the correlation model has linear characteristics and can be represented in the form of a two-dimensional linear graph. In this case, the X-axis may represent the delamination area and the Y-axis may represent the normalized value.

[0083] The degree of asymmetry Sk can be calculated based on the following formula.

[0084]

[0085] Kurtosis Ku can be calculated based on the following formula.

[0086]

[0087] In the above formulas for calculating asymmetry Sk and kurtosis Ku, X is the temperature data value of each pixel, N is the total number of derived data, It can represent the average value of the entire pixel temperature data.

[0088] One embodiment of the present invention may also be implemented in the form of a recording medium comprising computer-executable instructions, such as program modules executed by a computer. A computer-readable medium may be any available medium accessible by a computer and includes both volatile and non-volatile media, and both removable and non-removable media. Additionally, a computer-readable medium may include all computer storage media. A computer storage medium includes both volatile and non-volatile, removable and non-removable media implemented by any method or technique for storing information, such as computer-readable instructions, data structures, program modules, or other data.

[0089] Although the method and system of the present invention have been described in relation to specific embodiments, some or all of their components or operations may be implemented using a computer system having a general-purpose hardware architecture.

[0090] A person skilled in the art to which this disclosure pertains will understand that, based on the foregoing description, other specific forms can be easily modified without altering the technical spirit or essential features of this disclosure. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. The scope of this disclosure is defined by the claims set forth below, and all modifications or variations derived from the meaning and scope of the claims and equivalents thereof should be interpreted as being included within the scope of this disclosure. The scope of this application is defined by the claims set forth below rather than by the foregoing detailed description, and all modifications or variations derived from the meaning and scope of the claims and equivalents thereof should be interpreted as being included within the scope of this application. Explanation of the symbols

[0091] 100: Delamination detection device for composite panels 110: Communication module 120: Processor 130: Memory 200: Thermal imaging terminal 301: Composite panel 302: Power supply 303: Administrator terminal

Claims

Claim 1 A method for detecting delamination of a composite panel based on a thermal image, performed by at least one processor, comprising: a) receiving thermal image data of a composite panel composed of a composite material; and b) detecting delamination of the composite panel by analyzing the temperature difference between a plurality of different regions of the composite panel based on the thermal image data, wherein step b) comprises: b-1) calculating at least one of asymmetry Sk and kurtosis Ku by analyzing the temperature difference; and b-2) detecting delamination using at least one of the calculated asymmetry Sk and kurtosis Ku, wherein the asymmetry Sk is calculated based on the following formula, and In the above formula, X is the temperature data value of each pixel, N is the total number of derived data, A thermal imaging-based method for detecting delamination of a composite panel, wherein represents the average value of the total pixel temperature data. Claim 2 A method for detecting delamination of a thermal image-based composite panel, wherein, in claim 1, the temperature per region corresponds to the temperature per pixel of the thermal image data. Claim 3 delete Claim 4 A method for detecting delamination of a thermal image-based composite panel, wherein, in claim 1, step b-2) includes the step of inputting the asymmetry Sk and kurtosis Ku into a pre-set correlation model to calculate the occurrence and area of ​​a delamination zone, which is a part where delamination has occurred inside the composite panel. Claim 5 A method for detecting delamination of a thermal image-based composite panel, wherein, in claim 1, the asymmetry Sk is a characteristic value indicating whether the average temperature is higher or lower than the median value of the temperatures for each region by calculating the average temperature for each region, and if the average temperature is higher than the temperatures for each region, the asymmetry Sk indicates a negative value, and if the average temperature is lower than the median value of the temperatures for each region, the asymmetry Sk indicates a positive value. Claim 6 A method for detecting delamination of a thermal image-based composite panel, wherein, in claim 1, the kurtosis Ku represents the density of temperature in each region. Claim 7 delete Claim 8 In claim 1, the kurtosis Ku is calculated based on the following formula, and In the above formula, X is the temperature data value of each pixel, N is the total number of derived data, A thermal imaging-based method for detecting delamination of a composite panel, wherein represents the average value of the total pixel temperature data. Claim 9 A method for detecting delamination of a thermal image-based composite panel, wherein, in claim 4, the correlation model has linear characteristics. Claim 10 The apparatus comprises at least one processor; and a memory electrically connected to the processor and storing at least one code executed by the processor, wherein the memory stores a code that, when executed through the processor, causes the processor to receive thermal image data of a composite panel composed of a composite material, analyze temperature differences in multiple different regions of the composite panel based on the thermal image data, and detect delamination of the composite panel, wherein the memory further stores a code that, when executed through the processor, causes the processor to analyze temperature differences to calculate at least one of asymmetry Sk and kurtosis ku, and uses at least one of the calculated asymmetry Sk and kurtosis ku to detect delamination, wherein the asymmetry Sk is calculated based on the following formula, and In the above formula, X is the temperature data value for each region, N is the total number of derived data, A delamination detection device for a composite panel, which represents the average value of temperature data across the entire area. Claim 11 A thermal imaging-based composite panel peeling detection device, wherein, in claim 10, the temperature per region corresponds to the temperature per pixel of the thermal imaging data. Claim 12 delete Claim 13 A thermal imaging-based delamination detection device for a composite panel, wherein, in claim 10, the memory further stores a code that causes the processor, when executed through the processor, to input the asymmetry Sk and kurtosis Ku into a preset correlation model to calculate the occurrence and area of ​​a delamination zone, which is a part where delamination has occurred inside the composite panel. Claim 14 A thermal imaging-based composite panel delamination detection device, wherein, in claim 10, the asymmetry Sk is a characteristic value that calculates the average temperature for each region and indicates whether the average temperature is higher or lower than the median value of the temperatures for each region, and if the average temperature is higher than the median value of the temperatures for each region, the asymmetry Sk indicates a negative value, and if the average temperature is lower than the temperatures for each region, the asymmetry Sk indicates a positive value. Claim 15 A thermal imaging-based composite panel delamination detection device according to claim 10, wherein the kurtosis Ku represents the density of temperature per region. Claim 16 delete Claim 17 In Clause 10, the kurtosis Ku is calculated based on the following formula, and In the above formula, X is the temperature data value for each region, N is the total number of derived data, A thermal imaging-based composite panel delamination detection device, which represents the average value of the temperature data across the entire area. Claim 18 A thermal imaging-based composite panel delamination detection device according to claim 13, wherein the correlation model has linear characteristics.

Images