Structural stress monitoring system based on color difference identification of pressure-sensitive paint

Abstract

The invention relates to the technical field of pressure-sensitive paint, in particular to a structural stress monitoring system based on color difference identification of pressure-sensitive paint, which comprises an image analysis module, a frequency identification module, a rhythm extraction module, a path comparison module and an early warning judgment module. According to the method, dynamic tracking and response feature extraction of a color difference abnormal area in a time sequence are achieved through combination of image color difference gradient density analysis and physical response frequency information, and the color difference abnormal area is obtained through continuous extraction and comparison of the color evolution trend and the gravity center track direction. The method improves the recognition precision of the path change of the abnormal region and the judgment capability of the structure deviation trend, enhances the recognition sensitivity of the accelerated evolution state of the region through the synchronous analysis of the frequency change and the sudden change time point, and optimizes the matching relation between the color difference response and the stress evolution. And by using trend sequence and direction consistency analysis, crack early warning has time continuity and space positioning capability, and the abnormal behavior identification effect in a complex environment is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of pressure-sensitive coatings, and in particular to a structural stress monitoring system based on color difference recognition of pressure-sensitive coatings. Background Art

[0002] The technical field of pressure-sensitive coatings primarily involves the development and application of functional coatings that are sensitive to changes in external pressure. These coatings express the physical stimuli they perceive through color changes. Their microstructures possess physical or chemical response properties, enabling them to produce visible color differences under specific stress conditions. Key issues within this technical field include the material composition mechanism, color response mechanism, external stress perception mechanism, and integration with optical imaging technology of pressure-sensitive coatings. These coatings have been extensively researched and applied in areas such as engineering structure monitoring, mechanical failure warning, and aerospace material inspection. Traditional structural stress monitoring systems for color difference recognition of pressure-sensitive coatings use manual or single image sensing devices to visually observe or perform static image analysis of color difference changes in the pressure-sensitive coating on a structure's surface to determine the stress distribution state. The technical objective of these devices is to spatially identify stress concentrations or potential crack risks in critical structural areas. These devices typically employ an image acquisition device to acquire coating images and determine the stress state by comparing the average values ​​of the RGB channels within the area. Preliminary crack analysis is then performed based on changes in pixel distribution. Physical response data on the structure's surface is measured using strain sensors to assist in determining stress changes.

[0003] Traditional structural stress monitoring technology based on pressure-sensitive coatings relies on the static acquisition of single-frame images and the change in the average value of the RGB channels to judge color difference. It lacks the ability to identify continuous evolution trends in the time dimension, resulting in the inability to accurately capture abnormal evolution paths in periodic or weak gradient stress response processes. Misjudgment occurs when the mutation points are dense but the average value fluctuations are not significant. It is difficult to achieve quantitative analysis of the spatial offset between the directional trend of the abnormal color difference area and the structural design model. If irregular stress concentration or early crack offset evolution occurs in a certain area of ​​the structure, it is difficult to effectively respond and identify through static data, resulting in stress identification errors and delayed crack trend response, limiting the adaptability and response sensitivity in multi-cycle dynamic monitoring scenarios. Summary of the Invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a structural stress monitoring system based on color difference recognition of pressure-sensitive coatings.

[0005] In order to achieve the above-mentioned object, the present invention adopts the following technical solution: A structural stress monitoring system based on color difference recognition of pressure-sensitive coatings comprises: The image analysis module collects images of the paint area, analyzes the color gradient changes of each pixel and its neighboring pixels in the image, identifies pixel mutation points and uses them as the center to establish multi-radius concentric ring areas, analyzes the distribution density trend of mutation points, detects color abnormality areas, and generates density aggregation trends; The frequency identification module uses the density aggregation trend to obtain response data of the color difference abnormal area using stress and temperature sensors, records the number of peak occurrences as the response frequency value, analyzes the consistency between the stress and temperature response frequencies, evaluates the regional resonance response state, and establishes response frequency information; The rhythm extraction module calls the response frequency information, identifies the paint color difference in adjacent frames in the image sequence of the color difference abnormal area, identifies the trend of color change, evaluates the trend consistency of regional color evolution in the time series, and generates evolution rhythm information; The path comparison module calls the evolution rhythm information, constructs the center of gravity evolution path according to the coordinates of the center of gravity of the mutation point in the abnormal area in each cycle, and compares it with the stress path in the target structure design model, analyzes the consistency of the direction change trend and the offset angle, and generates offset direction information.

[0006] As a further solution of the present invention, the density aggregation trend includes the distribution density of pixel mutation points, the scale level of concentric ring areas, and the density change ratio sequence; the response frequency information includes the stress response frequency, the temperature response frequency, and the frequency consistency state; the evolution rhythm information includes the color difference change time series, the color change trend between image frames, and the time rhythm consistency level; the offset direction information is specifically the color difference center of gravity evolution path, the theoretical stress path direction, and the center of gravity path offset angle.

[0007] As a further solution of the present invention, the image analysis module includes: The pixel gradient extraction submodule collects images of the pressure-sensitive coating area, obtains the RGB channel value of each pixel in the image, calculates the RGB difference between the pixel point and the neighboring pixels, analyzes the color gradient change, identifies the pixel mutation point and records the image coordinates of the mutation point, and obtains the pixel mutation point distribution data; The ring density calculation submodule calls the pixel mutation point distribution data, constructs multiple groups of multi-radius concentric ring areas with each mutation point as the center, counts the number of mutation points in each ring area, calculates the number and density of mutation points in each ring area, constructs a density value sequence in increasing radius order, and obtains the pixel mutation point ring density sequence; The anomaly detection and evaluation submodule analyzes the distribution density trend of the mutation points based on the pixel mutation point ring density sequence, calculates the abnormality score value of each area, detects the color difference abnormal area, and generates the density aggregation trend.

[0008] As a further solution of the present invention, the frequency identification module includes: The data acquisition submodule calls the density aggregation trend, collects stress response data and temperature response data in the color difference abnormal area, extracts the cycle peak point sequence recorded by the stress sensor and the cycle peak point sequence recorded by the temperature sensor in each cycle, and obtains a sensor response sequence group; The frequency extraction submodule counts the peak values ​​of stress and temperature responses in each cycle according to the sensor response sequence group and uses the peak values ​​as the response frequency values ​​to obtain a cycle-frequency matching pair sequence; The consistency analysis submodule calls the periodic frequency matching pair sequence, analyzes the numerical variation difference of stress frequency and temperature frequency in each period, calculates the frequency synchronization convergence value, evaluates the regional resonance response state, and establishes the response frequency information.

[0009] As a further solution of the present invention, the rhythm extraction module includes: The amplitude sequence extraction submodule calls the response frequency information, analyzes the image sequence of the color difference abnormal area, identifies the color difference value of the corresponding pixel between consecutive image frames, calculates the color difference change amplitude between adjacent frames, and obtains the change amplitude sequence; The change direction analysis submodule analyzes the change direction of the color difference values ​​between adjacent frames based on the change amplitude sequence, analyzes the direction change of each pixel in multiple frame sequences, identifies the direction state of color change in continuous cycles, and generates a change trend sequence; The trend consistency evaluation submodule compares the trend directions of multiple pixels in each cycle according to the change trend sequence, evaluates the trend consistency of regional color evolution in the time series, and obtains evolution rhythm information.

[0010] As a further solution of the present invention, the path comparison module includes: The center of gravity extraction submodule uses the evolution rhythm information to locate the color difference abnormal area of ​​the pressure-sensitive coating area in consecutive cycles, extracts the set of mutation points in the abnormal area in each cycle, calculates the average value of the pixel coordinates in the set and uses it as the center of gravity coordinate to generate a sequence of the center of gravity of the mutation points; The path construction submodule connects the center of gravity coordinates of each period in chronological order based on the mutation point center of gravity sequence to form a continuous center of gravity trajectory, constructs the center of gravity evolution path, analyzes the actual stress path in the target structure, and establishes a path fitting sequence; The direction offset calculation submodule calls the established path fitting sequence, calculates the path consistency by comparing it with the stress path in the target structure design model, analyzes the consistency of the direction change trend and the offset angle, and generates offset direction information.

[0011] As a further solution of the present invention, the system further includes: The early warning judgment module calls the offset direction information, analyzes the color difference change frequency of the abnormal color difference area of ​​the pressure-sensitive coating area within multiple consecutive cycles, records and analyzes the frequency change trend, identifies the mutation time point of the color difference gradient within each cycle, and identifies the accelerated evolution state of the color difference response of the area by analyzing the synchronization and consistency of the frequency change trend and the gradient mutation time point, thereby generating crack trend synchronization information; The crack trend synchronization information specifically refers to the frequency increasing trend, the gradient mutation time point sequence, and the response synchronization level.

[0012] As a further solution of the present invention, the early warning determination module includes: The frequency analysis submodule calls the offset direction information to analyze the color difference change frequency of the color difference abnormal area in the pressure-sensitive coating area within multiple continuous cycles, extracts the frequency value according to the continuous cycle sequence, and obtains the color difference frequency change sequence; The mutation extraction submodule identifies the color difference gradient of the corresponding area in each cycle according to the color difference frequency change sequence, detects the inflection point of the change and locates the occurrence cycle based on the curve shape of the gradient value changing with the cycle, and obtains the gradient mutation time point sequence; The synchronous evaluation submodule calls the gradient mutation time point sequence, extracts the frequency increase rate and mutation density in each time period, analyzes the synchronization and consistency of the frequency change trend and the gradient mutation time point, identifies the accelerated evolution state of the color difference response of the region, and generates crack trend synchronization information.

[0013] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by combining image color difference gradient density analysis with physical response frequency information, dynamic tracking and response feature extraction of color difference abnormal areas in a time series are realized. The continuous extraction and comparison of color evolution trends and center of gravity trajectory directions are utilized to improve the recognition accuracy of path changes in abnormal areas and the ability to determine structural offset trends. The synchronous analysis of frequency changes and mutation time points is adopted to enhance the recognition sensitivity of regional accelerated evolution states, optimize the matching relationship between color difference responses and stress evolution, and use trend sequence and direction consistency analysis to enable crack warning to have temporal continuity and spatial positioning capabilities. The original static judgment method is expanded to a multi-period dynamic monitoring mechanism, thereby improving the abnormal behavior recognition effect under multi-source information fusion in complex stress environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a system flow chart of the present invention; Figure 2 This is a flow chart of the image analysis module of the present invention; Figure 3 This is a flow chart of the frequency identification module of the present invention; Figure 4 This is a flow chart of the rhythm extraction module of the present invention; Figure 5 This is a flow chart of the path comparison module of the present invention; Figure 6 This is a flow chart of the early warning judgment module of the present invention. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0016] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined.

[0017] See also Figure 1 , a structural stress monitoring system based on color difference recognition of pressure-sensitive coatings includes: The image analysis module collects images of the paint area, analyzes the color gradient changes of each pixel and its neighboring pixels in the image, identifies pixel mutation points and uses them as the center to establish multi-radius concentric ring areas, analyzes the distribution density trend of mutation points, detects color abnormality areas, and generates density aggregation trends; The frequency identification module uses density aggregation trends and stress and temperature sensors to obtain response data from areas with abnormal color differences. It records the number of peak occurrences as the response frequency value, analyzes the consistency between stress and temperature response frequencies, evaluates the regional resonance response state, and establishes response frequency information. The rhythm extraction module uses the response frequency information to identify the paint color difference in adjacent frames in the image sequence of the abnormal color difference area, identifies the trend of color change, evaluates the trend consistency of regional color evolution in the time series, and generates evolution rhythm information; The path comparison module uses the evolution rhythm information to construct the center of gravity evolution path based on the coordinates of the center of gravity of the mutation point in the abnormal area in each cycle. It then compares this path with the stress path in the target structural design model, analyzes the consistency of the direction change trend and the offset angle, and generates offset direction information. The early warning judgment module calls the offset direction information, analyzes the color difference change frequency of the abnormal color difference area of ​​the pressure-sensitive coating area in multiple consecutive cycles, records and analyzes the frequency change trend, identifies the mutation time point of the color difference gradient in each cycle, and identifies the accelerated evolution state of the color difference response of the area by analyzing the synchronization and consistency of the frequency change trend and the gradient mutation time point, and generates crack trend synchronization information.

[0018] The density aggregation trend includes the distribution density of pixel mutation points, the scale level of concentric ring areas, and the density change ratio sequence. The response frequency information includes the stress response frequency, the temperature response frequency, and the frequency consistency state. The evolution rhythm information includes the color difference change time series, the color change trend between image frames, and the time rhythm consistency level. The offset direction information specifically includes the color difference center of gravity evolution path, the theoretical stress path direction, and the center of gravity path offset angle. The crack trend synchronization information specifically refers to the frequency increase trend, the gradient mutation time point sequence, and the response synchronization level.

[0019] See also Figure 2 , the image analysis module includes: The pixel gradient extraction submodule collects images of the pressure-sensitive coating area, obtains the RGB channel value of each pixel in the image, calculates the RGB difference between the pixel point and the neighboring pixels, analyzes the color gradient change, identifies the pixel mutation point and records the image coordinates of the mutation point, and obtains the pixel mutation point distribution data; The pressure-sensitive coating area image is collected by continuously shooting the pressure-sensitive coating area on the surface of the structure to be tested with a high-resolution digital camera to obtain RGB channel images with an image resolution of 1920×1080 pixels. The images are stored frame by frame as PNG format files and marked with a timestamp. A specific example is that the coating area is about 100 cm² in a steel beam bridge structure. A high-definition camera is installed at a distance of 0.5 meters from the surface of the structure, and one frame of image is captured every 1 second. 1800 frames of image are obtained by continuous shooting for 30 minutes. The image is then traversed pixel by pixel, and the R , G, B three-channel values ​​(value range 0-255), the center pixel channel value and the neighboring 3×3 pixels (a total of 8 neighboring pixels) centered on the pixel are subtracted. For example, for a pixel point (600,450), the RGB channel values ​​of the center pixel point are recorded as (125,120,130), and the RGB channel values ​​of the neighboring pixels are (128,118,133), (127,119,132), (126,117,129), (123,121,131), (1 24,122,130), (122,123,128), (125,119,127), (124,120,129), then the RGB value of each neighborhood pixel is subtracted from the RGB value of the center pixel, and the difference is (3,-2,3), (2,-1,2), (1,-3,-1), (-2,1,1), (-1,2,0), (-3,3,-2), (0,-1,-3), (-1,0,-1); further take the absolute value of each difference and sum it up, for example, the absolute value of the difference of the first neighborhood pixel is The sum of the values ​​is |3|+|-2|+|3|=8. Similarly, the sum of the absolute values ​​of the eight neighborhood pixel differences is 8, 5, 5, 4, 3, 8, 4, and 2. If the sum of the absolute values ​​of any neighborhood pixel is greater than the set threshold (for example, the threshold is set to 6, and the threshold setting method is obtained by statistics on 200 images, see Table 1), the central pixel is determined to be the mutation point and the coordinates are recorded. For example, in the above example, the sum of the absolute values ​​of the first neighborhood pixel is 8, which is greater than the threshold 6, so the central pixel point (600, 450) is recorded as the mutation point. Finally, after the traversal is completed, the coordinate data of all mutation points are obtained.

[0020] Table 1 Pixel mutation threshold setting table: ; As shown in Table 1, actual tests show that setting the threshold to 6 can effectively distinguish mutation points from non-mutation points and generate mutation point distribution data.

[0021] The ring density calculation submodule calls the pixel mutation point distribution data, constructs multiple groups of multi-radius concentric ring areas with each mutation point as the center, counts the number of mutation points in each ring area, calculates the number and density of mutation points in each ring area, constructs a density value sequence in increasing radius order, and obtains the pixel mutation point ring density sequence; Call the pixel mutation point coordinate data, and establish multi-radius concentric ring areas with each mutation point as the center. For example, set the radius of the concentric ring to 2, 4, 6, and 8 pixels respectively. Count the number of mutation points in each concentric ring area. For example, with the coordinate (600, 450) as the center point, the number of mutation points in the inner ring with a radius of 2 pixels is 5. The area calculation formula is: , which is an area of ​​about 12.57 pixels² and a density of / pixel². Similarly, the number of rings within a radius of 4 pixels is 10, with an area of ​​approximately 50.27 pixels² and a density of 0.199 / pixel². Similarly, the number of mutation points within a radius of 6 pixels is 15, with an area of ​​approximately 113.10 pixels² and a density of 0.133 / pixel². The number of mutation points within a radius of 8 pixels is 20, with an area of ​​approximately 201.06 pixels² and a density of 0.099 / pixel². The density value of each ring is calculated in turn and a density value sequence is constructed. For example, the density value sequence obtained is 0.398, 0.199, 0.133, and 0.099. All density values ​​are obtained by actual calculation by dividing the number of mutation points by the corresponding ring area, thereby obtaining the density sequence of the pixel mutation point ring domain.

[0022] The anomaly detection evaluation submodule analyzes the distribution density trend of mutation points based on the density sequence of the pixel mutation point ring domain, using the formula: ; Calculate the abnormality score of each area, detect color abnormality areas, and generate density aggregation trends; in, is the abnormality score, dimensionless, For the The normalized value of the mutation point density in the concentric ring area is obtained by dividing the number of mutation points in each ring area by the corresponding ring area and performing normalization. For the Normalized mutation point density value of concentric ring area, is the standard deviation of the normalized mutation point density value, which indicates the degree of dispersion of the mutation point distribution between different ring regions. is the total number of concentric ring areas, Indicates the current The number of the concentric ring areas, Indicates the The last ring in the ring area; According to the ring domain density sequence, for example, the density value sequence is 0.398, 0.199, 0.133, 0.099, and the sequence is normalized by dividing each value by the maximum value of the sequence (0.398) to obtain the normalized density value sequence. are 1.000, 0.500, 0.334, and 0.249 respectively; calculate the standard deviation of the normalized density values , for example, taking this sequence as an example to calculate: ; Then substitute the formula to calculate the abnormality score. The specific formula is: ; Substituting the above parameters into the formula, we can get: ; The anomaly score represents the intensity of abnormal clustering of color aberration mutations in a concentric ring structure region within the image, expressed as a dimensionless number. Larger values ​​indicate greater instability in the region's color aberration mutation frequency, rate of change, and density consistency. This score reflects the evolutionary trend of the local structural response and is used to identify potential microcrack initiations or stress concentration points within the image. It serves as a core determinant in the structural stress anomaly screening mechanism and is subsequently used for regional prioritization and tracking. The formula objectively quantifies the density trend and distribution dispersion of mutation points using the normalized density difference and standard deviation, effectively determining the degree of regional anomaly. The results indicate a regional anomaly score of 0.555. Previous experiments have verified that regions with anomaly scores between 0.5 and 0.7 are considered mildly abnormal and can be further processed into density cluster trend data.

[0023] Table 2 Abnormal scoring results corresponding status table: ; As shown in Table 2, the regional anomaly score is 0.555, indicating that the area is in a mild anomaly state. This numerical result can be directly organized into density aggregation trend information for subsequent frequency recognition module calls.

[0024] See also Figure 3 , the frequency identification module includes: The data acquisition submodule uses the density aggregation trend to collect stress response data and temperature response data in the color difference abnormal area, extracts the cycle peak point sequence recorded by the stress sensor and the cycle peak point sequence recorded by the temperature sensor in each cycle, and obtains the sensor response sequence group; The density aggregation trend is called, that is, the abnormality score obtained by the previous identification (such as 0.555 mild abnormal area) is used to collect data for the color abnormal area. In actual operation, by setting high-sensitivity strain gauges and high-precision thermocouple sensors on the surface of the area, the stress response data and temperature response data of the structure are recorded in real time. For example, a BX120-3AA strain gauge and a K-type thermocouple are arranged in the designated abnormal area of ​​the bridge structure. In each cycle (for example, each cycle is 5 minutes, and continuous collection is carried out for 30 minutes for a total of 6 cycles), the voltage signal output by the sensor is sampled and calibrated, and the sampled data is converted into a stress and temperature data sequence, and then filtered based on the numerical peak value judgment: for the stress data sequence of the strain gauge, the data point is set from the beginning of the sequence. Compare the values ​​of two adjacent points one by one, and record when a data point is greater than the previous and next data points, mark it as a peak point. For example, the stress response data sequence of the first cycle contains the data points [8.2MPa, 8.5MPa, 8.9MPa, 8.4MPa, 8.1MPa, 8.3MPa, 8.7MPa, 8.2MPa], then the peak points filtered out are 8.9MPa and 8.7MPa. The temperature data sequence is filtered out in the same way. For example, the temperature response data sequence in the first cycle is [25.1℃, 25.3℃, 25.5℃, 25.2℃, 25.0℃, 25.4℃, 25.7℃, 25.1℃], then the recorded peaks are 25.5℃ and 25.7℃. The data are stored by cycle and a sensor response sequence group is generated.

[0025] The frequency extraction submodule counts the peak values ​​of stress and temperature responses in each cycle according to the sensor response sequence group and uses them as the response frequency value to obtain the cycle-frequency matching pair sequence; Frequency extraction is performed based on the sensor response sequence group, and the number of peaks recorded by the sensor is counted cycle by cycle. The specific process is to count the stress peak point sequence and temperature peak point sequence of each cycle one by one. For example, the number of stress peak points in the first cycle above is 2, and the number of temperature peak points is also 2. The number of peak points in each cycle of the two sensors is matched to obtain the cycle-frequency matching pair sequence, as shown in Table 3 after statistics of 6 consecutive cycle data: Table 3 Periodic peak quantity statistics: ; As shown in Table 3, the statistical calculation of each period is completed to obtain the period frequency matching pair sequence.

[0026] The consistency analysis submodule calls the periodic frequency matching pair sequence to analyze the numerical change differences of stress frequency and temperature frequency in each cycle using the formula: ; Calculate the frequency synchronization convergence value, evaluate the regional resonance response state, and establish the response frequency information; in, For the The normalized frequency value of the stress sensor in the cycle is calculated by counting the The number of response peaks of the stress sensor within a cycle is normalized by combining the maximum number of peaks in all cycles. For the The normalized frequency value of the temperature sensor in a cycle is calculated by counting the The number of temperature sensor response peaks within a cycle is normalized by combining the maximum number of peaks within all cycles. For the The difference in stress frequency within a cycle is calculated as , For the The difference in temperature frequency within a cycle is calculated as , is a sign function that outputs 1 if the input value is positive and -1 if it is negative. is the collection cycle number, is the total number of current collection cycles, is the frequency synchronization convergence value; Call the cycle frequency matching sequence data and perform normalization based on the number of peaks in each cycle. The normalization method is based on the maximum number of peaks in 6 cycles (the maximum number of stress peaks is 4, and the maximum number of temperature peaks is 4). Taking cycle 1 as an example, the stress frequency value is , temperature frequency value , other periods are calculated in sequence, such as period 2: , , process each cycle one by one; calculate the frequency difference between adjacent cycles, such as the stress frequency difference in cycle 2 , temperature-frequency difference ; Then substitute the consistency analysis formula to calculate the frequency synchronization convergence value: ; The parameters in the formula are explained in detail as follows: Indicates the Frequency-normalized value of cyclic stress, Indicates the Normalized value of cycle temperature frequency; difference and is the frequency change value of the adjacent cycle, which respectively represents the frequency change of stress and temperature between the current cycle and the previous cycle. The sign function Used to determine the positive or negative of the difference product. When the difference product is positive, it outputs 1, otherwise it outputs -1. Substitute 6 consecutive cycles of data into the formula for calculation: ; The frequency synchronization convergence value is a comprehensive scoring indicator that measures the degree of similarity in the stress and temperature response behavior over multiple cycles within the color difference anomaly region. It reflects the numerical proximity of two frequency values, indicating whether their cyclical variation directions are consistent, and possesses the ability to sensitively identify dynamic resonance trends. Values ​​closer to 1 indicate a high degree of synergy between the two responses over multiple cycles, suggesting the presence of potential resonance or a region of concentrated structural stress. Values ​​closer to -1 indicate opposing responses, weak regional coupling, and relatively separated structural states. Values ​​closer to 0 indicate a lack of significant trend correlation. As a crucial component of response frequency information, this parameter can be used in key analytical steps in subsequent structural monitoring, such as hazard trend assessment, crack induction mechanism analysis, and path deviation deduction. The results indicate a frequency synchronization convergence value of -0.388. Values ​​below 0 indicate that the stress and temperature response frequencies exhibit opposing trends during cyclical variation. This calculated result serves as the basis for determining regional resonance response states and is incorporated into the response frequency information sequence for subsequent use by the rhythm extraction module.

[0027] See also Figure 4 , the rhythm extraction module includes: The amplitude sequence extraction submodule calls the response frequency information, analyzes the image sequence of the color difference abnormal area, identifies the color difference value of the corresponding pixels between consecutive image frames, calculates the color difference change amplitude between adjacent frames, and obtains the change amplitude sequence; Call the response frequency information, select the image sequence of the corresponding area on the surface of the structure according to the aforementioned abnormal area (such as an abnormality score of 0.555 corresponds to a mild abnormal area) (for example, one frame of image is taken per second, and continuous shooting is performed for 10 seconds, for a total of 11 frames of image), and call the RGB channel value of each pixel of the image one by one to perform a comparison operation on consecutive frames. For example, taking the specific pixel coordinates (600, 450) as an example, the RGB channel value of the pixel in the first frame is (120, 125, 130), and the RGB channel value of the pixel in the second frame is (123, 122, 128). Calculate the absolute value of the RGB difference and sum it, that is, the calculation process is: |123-120|+|122 -125|+|128-130|=3+3+2=8. Similarly, pixel difference calculations for consecutive frames are performed and recorded. For example, the third frame after the pixel point (600,450) is (126,123,131), which is calculated as |126-123|+|123-122|+|131-128|=3+1+3=7. The color difference change data of all consecutive frames are processed in sequence to construct a change amplitude sequence. For example, the color difference amplitude of the pixel (600,450) between 10 frames is [8,7,9,6,5,8,7,4,6,5]. Finally, the change amplitude sequence of all pixels of interest in the area is obtained.

[0028] The change direction analysis submodule analyzes the change direction of the color difference values ​​between adjacent frames based on the change amplitude sequence, analyzes the direction change of each pixel in multiple frame sequences, identifies the direction state of color change in continuous cycles, and generates a change trend sequence; The change amplitude sequence is called to analyze and judge the change direction of the color difference change amplitude value between consecutive frames. For example, for the pixel at coordinate (600, 450), the color difference amplitude changes from 8 to 7 from the first frame to the second frame, and the change direction is decreasing. From the second frame to the third frame, it changes from 7 to 9, and the direction is increasing. The direction change state is judged and recorded one by one. The change direction is determined by comparing the amplitude values ​​of two adjacent frames. If the amplitude of the latter frame is greater than that of the previous frame, the direction is defined as "increasing". If the amplitude of the latter frame is less than that of the previous frame, it is defined as "decreasing". If the amplitude of the latter frame is equal to that of the previous frame, it is defined as "unchanged". For example, the change direction corresponding to the specific example sequence [8→7→9→6→5→8→7→4→6→5] is [decreasing→increasing→decreasing→decreasing→increasing→decreasing→decreasing→increasing]. The direction states of all pixels of interest in multiple consecutive frames are recorded in sequence to generate a change trend sequence.

[0029] The trend consistency assessment submodule compares the trend directions of multiple pixels in each cycle based on the change trend sequence, evaluates the trend consistency of regional color evolution in the time series, and obtains evolution rhythm information; Call the change trend sequence and perform consistency assessment based on the pixel change trend within multiple cycles (for example, 6 consecutive cycles). The analysis method is to count the consistency ratio of the pixel trend direction in each cycle. The specific calculation method is to calculate the ratio of the number of times a specific number of pixels selected in the area (for example, 5 typical pixels) have the same change direction in each cycle. For example, the change trend direction of 5 typical pixels selected in cycle 1 is shown in Table 4 below: Table 4 Pixel change trend direction consistency table: ; As shown in Table 4, in period 1, with "decreasing" as the main direction, the proportion of 4 pixels in the 4 change trends is at least 3 directions of decreasing direction, accounting for 4 / 5 = 80% of the total pixels; then, the trend direction consistency is calculated for 6 consecutive periods according to the above method and the consistency ratio of each period is recorded. If the consistency ratio of a period exceeds 70%, the trend is defined as relatively consistent, if it is 50%-70%, it is defined as moderately consistent, and if it is less than 50%, it is defined as a dispersed trend, thus obtaining the evolution rhythm information of the region in the time series.

[0030] See also Figure 5 , the path comparison module includes: The center of gravity extraction submodule uses the evolution rhythm information to locate the color difference abnormal areas of continuous cycles in the pressure-sensitive coating area, extract the set of mutation points in the abnormal area in each cycle, calculate the average value of the pixel coordinates in the set and use it as the center of gravity coordinates to generate a sequence of mutation point centers of gravity; The evolution rhythm information is called to determine the color difference abnormal area in the pressure-sensitive coating area within continuous cycles. For example, taking the abnormal area on the surface of the bridge structure (the area with an abnormality score of 0.555) as an example, the pixel coordinates of the abnormal area are called and recorded in 5 consecutive cycles (each cycle lasts 5 minutes, a total of 25 minutes). For the set of mutation points in the color difference abnormal area identified in each cycle, by traversing all the pixel coordinate data in the set, the center of gravity coordinates of each cycle are determined by adding the horizontal and vertical coordinates of each pixel point and dividing by the total number of pixels; for example, in cycle 1, a total of 10 pixel mutation points are detected, and their coordinates are (600,450), (602,448), (598,452), (601,451), (603,449), (599,453), (600,449), (602,450), (597, 452), (601, 448), the sum of the horizontal coordinates is 600+602+598+601+603+599+600+602+597+601=6003, and the sum of the vertical coordinates is 450+448+452+451+449+453+449+450+452+448=4502. Divide the above coordinates by 10 to obtain the centroid coordinates (600.3, 450.2). In this way, the centroid coordinates of all abnormal areas are calculated periodically to generate the centroid sequence of mutation points.

[0031] The path construction submodule is based on the sequence of the centroids of the mutation points. It connects the centroid coordinates of each cycle in chronological order to form a continuous centroid trajectory, constructs the centroid evolution path, analyzes the actual stress path in the target structure, and establishes a path fitting sequence. Based on the centroid sequence of the mutation point, for example, the centroid coordinates obtained in period 1 to period 5 are (600.3, 450.2), (601.0, 451.1), (601.7, 452.0), (602.5, 452.7), and (603.2, 453.5), these coordinates are connected in sequence according to the time sequence of the period to form a continuous centroid point trajectory. For example, the centroid trajectory from the first period to the second period is from (600.3, 450.2) to (601.0, 451.1), and the trajectory from the second period to the third period is from ( At the same time, the actual stress path marked in the structural design drawing is called (for example, the stress path coordinates of a certain area in the design drawing are (600, 450), (600.8, 450.9), (601.5, 451.7), (602.3, 452.4), and (603.0, 453.2) in 5 cycles), and the design paths are connected in the same way to form a design path trajectory, thereby obtaining the path fitting sequence of the actual observation and the design structure.

[0032] The direction offset calculation submodule calls the established path fitting sequence and compares it with the stress path in the target structure design model using the formula: ; Calculate the degree of path consistency, analyze the consistency of direction change trends and offset angles, and generate offset direction information; in, is the degree of path consistency, is the number of path segments involved in the comparison, The cycle index number of the path segment is used to identify the The path vector within a period, For the The direction vector of the design model path within a cycle is obtained by extracting the stress direction coordinate sequence of the cycle in the target structure design model and performing vector processing. For the The direction vector of the actual path within a cycle is calculated by the coordinate difference of the center of gravity of the chromatic aberration mutation point in consecutive cycles. For the mid-cycle and The angle between the two vectors is obtained by calculating the inverse cosine function of the angle between the two vectors. is the reference threshold of the path deviation angle, which is obtained by setting the upper limit of the allowable deviation angle set in the design standard; Call the path fitting sequence and compare the continuous path segments one by one to calculate the path consistency. Vector with design model path Calculate for input, for example, the actual path vector of the first cycle is (601.0-600.3,451.1-450.2)=(0.7,0.9), the designed path vector is (600.8-600,450.9-450)=(0.8,0.9), the angle between the two vectors is The calculation process is: ; Similarly, the vector and angle of each periodic path segment are calculated to obtain the specific data in Table 5: Table 5 Path segment angle calculation results: ; As shown in Table 5, the path consistency degree is calculated by substituting it into the formula: ; Substitute the angle of the specific example path segment into the calculation (reference threshold Set to 10°): ; The path consistency degree indicates the degree of consistency between the directional trends of the structural stress evolution path and the designed target path over multiple consecutive cycles. The closer the value is to 1, the more consistent the actual path is with the target path, indicating stable and controlled expansion of cracks or abnormal areas. Lower values ​​indicate significant path deviation, potentially indicating changes in the local stress state or abnormal expansion trends. This indicator serves as an important reference parameter for subsequent structural condition assessment, deviation diagnosis, and early warning decisions, providing a quantitative basis for directional anomaly evolution within the context of color difference recognition for pressure-sensitive coatings. The calculated result of 0.797 indicates high consistency between the observed path and the designed path (according to the path consistency degree, a value of 0.7 or higher is considered high consistency, 0.5-0.7 is considered moderate consistency, and less than 0.5 is considered low consistency). This indicates that the directional trends of the actual center of gravity evolution path and the designed path are relatively consistent, while there is a certain degree of deviation. This deviation direction information is generated for further processing in the subsequent early warning and judgment module.

[0033] See also Figure 6 , the early warning judgment module includes: The frequency analysis submodule uses the offset direction information to analyze the color difference change frequency of the color difference abnormal area in the pressure-sensitive coating area within multiple consecutive cycles, extracts the frequency value based on the continuous cycle sequence, and obtains the color difference frequency change sequence; After accessing the offset direction information, the system obtains the offset angle and direction trend data for each cycle path identified in the previous stage. Based on this data, it locates the corresponding color difference abnormality region in the coating image. The image sequence is then analyzed cycle by cycle, targeting this region and calculating the frequency of the color difference response within each cycle. Specifically, the color difference frequency is extracted based on the frame-by-frame variation in the number of color difference mutation points within the image frame sequence within the cycle. For example, if the image is captured at one frame per second within a cycle, with a total of 30 frames, the system analyzes the fluctuation in the number of mutation pixels within the abnormal region within each frame to identify the color difference mutation peak point. The number of mutations within each cycle is used as the basis for frequency calculation. For example, in the frame sequence within the first cycle, a peak is recorded when the number of mutation pixels reaches a local maximum (e.g., greater than the previous or next frame). If a total of four local extreme points are detected, the frequency is 4. Repeating this process, frequency extraction is performed for the next five consecutive cycles, resulting in a frequency variation sequence, such as [4, 5, 7, 6, 9, 11]. This sequence indicates that within the color difference abnormality region, the frequency of mutations increases as the cycle progresses. All frequency values ​​belong to a continuous periodic sequence, forming a complete color difference frequency change sequence, which serves as the quantitative input basis for subsequent mutation behavior.

[0034] The mutation extraction submodule identifies the color difference gradient of the corresponding area in each cycle based on the color difference frequency change sequence. Based on the curve shape of the gradient value changing with the cycle, it detects the change inflection point and locates the occurrence cycle to obtain the gradient mutation time point sequence; Based on the color difference frequency variation sequence obtained in the previous step, the system synchronously extracts the color difference gradient values ​​of the abnormal region within each cycle within the corresponding period. The gradient is calculated based on the difference between the maximum and minimum color difference values ​​in the image frame within each cycle divided by the inter-frame distance. For example, if the maximum color difference value of the abnormal region in the first cycle is 80, the minimum is 50, and the frame interval is 30 frames, then the gradient value for this cycle is (80-50) / 30≈1.0. The color difference gradient values ​​of all cycles are arranged in sequence, for example, [1.0, 1.2, 1.8, 1.6, 2.4, 3.1]. The system then analyzes the gradient sequence for variation trends, using the first-order difference method to extract the curve trend and calculate the incremental values ​​of the gradient between adjacent cycles. For example, the second cycle increases by 0.2 compared to the first cycle, the third cycle increases by 0.6 compared to the second cycle, the fourth cycle decreases by 0.2, the fifth cycle increases by 0.8, and the sixth cycle increases by 0.7. The resulting increment sequence is [+0.2, +0.6, -0.2, +0.8, +0.7]. We further determine the inflection point of the gradient change, that is, the periodic point where the increase and decrease signs switch as the mutation period. In this example, the third period shows a change from positive to negative increment, and the fourth period changes from negative to positive. Therefore, the third and fourth periods are determined to be the inflection points of the change, corresponding to the mutation points, and the final gradient mutation time point sequence is determined to be [3, 4].

[0035] The synchronous assessment submodule calls the gradient mutation time point sequence, extracts the frequency increase rate and mutation density within each time period, analyzes the synchronization and consistency of the frequency change trend and the gradient mutation time point, identifies the accelerated evolution state of the color difference response in the area, and generates crack trend synchronization information; The system calls the gradient mutation time point sequence from the previous step and analyzes it together with the color difference frequency sequence for the corresponding time period to assess their synchronization and consistency. Specifically, the frequency increase rate before and after the mutation point is calculated. For example, if the frequency in the third cycle is 7 and the second cycle is 5, the increase rate is (7-5) / 5 = 0.4. Meanwhile, if the frequency in the fourth cycle is 6, the increase rate is (6-7) / 7 ≈ -0.14. The mutation density within ±1 cycle surrounding the mutation period is then calculated to calculate the mutation density. For example, if the number of mutation points in the three cycles before and after the third cycle is [0, 1, 1], the density is 2 / 3 ≈ 0.67. The frequency increase rate and mutation density corresponding to each mutation time point are combined and analyzed. If the two change in the same direction over multiple cycles (e.g., frequency increases when mutation points increase in density, or frequency decreases when mutation points decrease in density), the system is considered "synchronous." If the mutation point density is high but the frequency increase rate is negative or does not increase, the system is considered "out of sync." In this way, the proportion of synchronous and consistent periods in the overall cycle is calculated. For example, if there are three synchronous and consistent periods in six cycles, the proportion is 50%. If the proportion exceeds 60%, it is judged as "accelerated evolution", otherwise it is considered to be stable or fluctuating. In this example, reaching 50% is slightly below the threshold, so it does not constitute accelerated evolution for the time being. It is only recorded as a "local synchronous enhancement trend" and a corresponding crack trend synchronization information sequence is generated to provide input parameters for the subsequent structural early warning model.

[0036] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A structural stress monitoring system based on color difference recognition of pressure-sensitive coatings, characterized in that: The system comprises: The image analysis module collects images of the paint area, analyzes the color gradient changes of each pixel and its neighboring pixels in the image, identifies pixel mutation points and uses them as the center to establish multi-radius concentric ring areas, analyzes the distribution density trend of mutation points, detects color abnormality areas, and generates density aggregation trends; The frequency identification module uses the density aggregation trend to obtain response data of the color difference abnormal area using stress and temperature sensors, records the number of peak occurrences as the response frequency value, analyzes the consistency between the stress and temperature response frequencies, evaluates the regional resonance response state, and establishes response frequency information; The rhythm extraction module calls the response frequency information, identifies the paint color difference in adjacent frames in the image sequence of the color difference abnormal area, identifies the trend of color change, evaluates the trend consistency of regional color evolution in the time series, and generates evolution rhythm information; The path comparison module calls the evolution rhythm information, constructs the center of gravity evolution path according to the coordinates of the center of gravity of the mutation point in the abnormal area in each cycle, and compares it with the stress path in the target structure design model, analyzes the consistency of the direction change trend and the offset angle, and generates offset direction information.

2. The structural stress monitoring system based on color difference recognition of pressure-sensitive coatings according to claim 1 is characterized in that: The density aggregation trend includes the distribution density of pixel mutation points, the scale level of concentric ring areas, and the density change ratio sequence; the response frequency information includes the stress response frequency, the temperature response frequency, and the frequency consistency state; the evolution rhythm information includes the color difference change time series, the color change trend between image frames, and the time rhythm consistency level; the offset direction information specifically includes the color difference center of gravity evolution path, the theoretical stress path direction, and the center of gravity path offset angle.

3. The structural stress monitoring system based on color difference recognition of pressure-sensitive coatings according to claim 1 is characterized in that: The image analysis module includes: The pixel gradient extraction submodule collects images of the pressure-sensitive coating area, obtains the RGB channel value of each pixel in the image, calculates the RGB difference between the pixel point and the neighboring pixels, analyzes the color gradient change, identifies the pixel mutation point and records the image coordinates of the mutation point, and obtains the pixel mutation point distribution data; The ring density calculation submodule calls the pixel mutation point distribution data, constructs multiple groups of multi-radius concentric ring areas with each mutation point as the center, counts the number of mutation points in each ring area, calculates the number and density of mutation points in each ring area, constructs a density value sequence in increasing radius order, and obtains the pixel mutation point ring density sequence; The anomaly detection and evaluation submodule analyzes the distribution density trend of the mutation points based on the pixel mutation point ring density sequence, calculates the abnormality score value of each area, detects the color difference abnormal area, and generates the density aggregation trend.

4. The structural stress monitoring system based on color difference recognition of pressure-sensitive coatings according to claim 3 is characterized in that: The frequency identification module includes: The data acquisition submodule calls the density aggregation trend, collects stress response data and temperature response data in the color difference abnormal area, extracts the cycle peak point sequence recorded by the stress sensor and the cycle peak point sequence recorded by the temperature sensor in each cycle, and obtains a sensor response sequence group; The frequency extraction submodule counts the peak values ​​of stress and temperature responses in each cycle according to the sensor response sequence group and uses the peak values ​​as the response frequency values ​​to obtain a cycle-frequency matching pair sequence; The consistency analysis submodule calls the periodic frequency matching pair sequence, analyzes the numerical variation difference of stress frequency and temperature frequency in each period, calculates the frequency synchronization convergence value, evaluates the regional resonance response state, and establishes the response frequency information.

5. The structural stress monitoring system based on color difference recognition of pressure-sensitive coatings according to claim 4 is characterized in that: The rhythm extraction module includes: The amplitude sequence extraction submodule calls the response frequency information, analyzes the image sequence of the color difference abnormal area, identifies the color difference value of the corresponding pixel between consecutive image frames, calculates the color difference change amplitude between adjacent frames, and obtains the change amplitude sequence; The change direction analysis submodule analyzes the change direction of the color difference values ​​between adjacent frames based on the change amplitude sequence, analyzes the direction change of each pixel in multiple frame sequences, identifies the direction state of color change in continuous cycles, and generates a change trend sequence; The trend consistency evaluation submodule compares the trend directions of multiple pixels in each cycle according to the change trend sequence, evaluates the trend consistency of regional color evolution in the time series, and obtains evolution rhythm information.

6. The structural stress monitoring system based on color difference recognition of pressure-sensitive coatings according to claim 5 is characterized in that: The path comparison module includes: The center of gravity extraction submodule uses the evolution rhythm information to locate the color difference abnormal area of ​​the pressure-sensitive coating area in consecutive cycles, extracts the set of mutation points in the abnormal area in each cycle, calculates the average value of the pixel coordinates in the set and uses it as the center of gravity coordinate to generate a sequence of the center of gravity of the mutation points; The path construction submodule connects the center of gravity coordinates of each period in chronological order based on the mutation point center of gravity sequence to form a continuous center of gravity trajectory, constructs the center of gravity evolution path, analyzes the actual stress path in the target structure, and establishes a path fitting sequence; The direction offset calculation submodule calls the established path fitting sequence, calculates the path consistency by comparing it with the stress path in the target structure design model, analyzes the consistency of the direction change trend and the offset angle, and generates offset direction information.

7. The structural stress monitoring system based on color difference recognition of pressure-sensitive coatings according to claim 1 is characterized in that: The system also includes: The early warning judgment module calls the offset direction information, analyzes the color difference change frequency of the abnormal color difference area of ​​the pressure-sensitive coating area within multiple consecutive cycles, records and analyzes the frequency change trend, identifies the mutation time point of the color difference gradient within each cycle, and identifies the accelerated evolution state of the color difference response of the area by analyzing the synchronization and consistency of the frequency change trend and the gradient mutation time point, thereby generating crack trend synchronization information; The crack trend synchronization information specifically refers to the frequency increasing trend, the gradient mutation time point sequence, and the response synchronization level.

8. The structural stress monitoring system based on color difference recognition of pressure-sensitive coatings according to claim 7 is characterized in that: The early warning determination module includes: The frequency analysis submodule calls the offset direction information to analyze the color difference change frequency of the color difference abnormal area in the pressure-sensitive coating area within multiple continuous cycles, extracts the frequency value according to the continuous cycle sequence, and obtains the color difference frequency change sequence; The mutation extraction submodule identifies the color difference gradient of the corresponding area in each cycle according to the color difference frequency change sequence, detects the inflection point of the change and locates the occurrence cycle based on the curve shape of the gradient value changing with the cycle, and obtains the gradient mutation time point sequence; The synchronous evaluation submodule calls the gradient mutation time point sequence, extracts the frequency increase rate and mutation density in each time period, analyzes the synchronization and consistency of the frequency change trend and the gradient mutation time point, identifies the accelerated evolution state of the color difference response of the region, and generates crack trend synchronization information.

Images