Hose surface defect detection method and system, storage medium and program product

Abstract

A hose surface defect detection method, system, storage medium and program product relate to the field of testing or analyzing materials by means of measuring chemical or physical properties of materials, in which method, internal pressure is sequentially applied to a hose according to a preset pressure level, and a hose surface image is acquired at each pressure level, obtaining a pressure response image sequence, extracting the position information of a defect area in the pressure response image sequence, and calculating the displacement variation of the defect area under each pressure grade relative to the surface reference image under the hose pressure-free state; calculating a defect flexibility coefficient, a plastic deformation rate and dynamic stability according to the relationship between the displacement variation and the corresponding pressure grade; and judging the defect type of the hose according to the defect flexibility coefficient, the plastic deformation rate and the dynamic stability. The accuracy of hose surface defect category detection and judgment is improved.

Description

Technical Field

[0001] The present application relates to the field of testing or analyzing materials by measuring the chemical or physical properties of the materials, and more particularly to a method, system, storage medium, and program product for detecting surface defects of a hose. Background Art

[0002] With the development of industrial production, hose products have become an important component in industry, agriculture, and daily life. Their product quality directly affects their safety. During the hose production process, due to factors such as materials, processes, and the environment, defects such as cracks, bubbles, and pits often appear on the hose surface. These defects not only affect the product appearance, but also reduce the hose's service life and even lead to safety accidents. Therefore, accurate detection of hose surface defects is of great significance.

[0003] In the chemical industry, regular inspections of hoses are necessary to ensure the safe transportation of hazardous chemicals. Machine vision technology is commonly used to detect surface defects in hoses. This technology uses industrial cameras to capture images of the hose surface and, combined with image enhancement and defect analysis algorithms, identifies the type of defects and assesses their severity, thereby determining whether the hose needs replacement. Compared to manual inspection, this method offers the advantages of increased efficiency and objectivity, and the ability to save test results for subsequent analysis.

[0004] However, due to long-term exposure to corrosive chemicals, conveyor hoses develop an uneven oxide layer on their surfaces. When classifying defects in hoses with this oxide layer, the presence of the oxide layer alters the morphological characteristics of the defect. For example, a previously sharp crack edge can become blurred by the oxide layer, resembling a process scratch, making it more difficult to determine the defect type. Summary of the Invention

[0005] The present application provides a hose surface defect detection method, system, storage medium and program product for improving the accuracy of hose surface defect classification detection.

[0006] In a first aspect, the present application provides a method for detecting surface defects in a hose, wherein internal pressure is applied to the hose in sequence according to preset pressure levels, and an image of the hose surface is captured at each pressure level to obtain a pressure response image sequence; Extract the position information of the defective area from the pressure response image sequence, and calculate the displacement change of the defective area relative to the surface reference image of the hose in the no-pressure state at each pressure level; The defect compliance coefficient, plastic deformation rate, and dynamic stability are calculated based on the relationship between the displacement change and the corresponding pressure level. The defect compliance coefficient is the ratio of the displacement change to the pressure value of the corresponding pressure level. The plastic deformation rate is the ratio of the residual displacement change after pressure relief to the maximum displacement change. The dynamic stability is the fluctuation amplitude during the displacement change process. If the defect compliance coefficient is greater than the first preset value, the dynamic stability is less than the second preset value, and the plastic deformation rate continues to increase during the cyclic pressurization process, the hose is determined to have a crack defect; If the defect compliance coefficient is less than the third preset value, the dynamic stability is greater than the fourth preset value, and the plastic deformation rate is less than the fifth preset value, then the hose is determined to have a process scratch defect; If the defect compliance coefficient is between the sixth preset value and the seventh preset value, and the dynamic stability shows a step change during the pressure change process, and the plastic deformation rate changes suddenly at the preset specific pressure, the hose is determined to have a corrosion pit defect.

[0007] By adopting the above technical solution, a series of pressure response images of the hose surface were collected at different pressure levels. Combined with the displacement change of the defect area, the three key parameters of the defect compliance coefficient, plastic deformation rate, and dynamic stability were calculated, and a corresponding relationship between the defect type and these parameters was established. Crack defects are characterized by a large compliance coefficient, small dynamic stability, and a continuously increasing plastic deformation rate. Process scratch defects are characterized by a small compliance coefficient, large dynamic stability, and a small plastic deformation rate. Corrosion pit defects are characterized by a medium-range compliance coefficient, a step-like change in dynamic stability, and a sudden change in plastic deformation rate under a specific pressure. This judgment method based on a combination of multiple parameters improves the accuracy of defect type identification.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, extracting position information of a defect area in a pressure response image sequence specifically includes: Obtaining the grayscale value distribution of each frame in the pressure response image sequence; Determine the grayscale difference threshold according to the grayscale value distribution; Determine the area where the grayscale value difference is greater than the grayscale difference threshold as a candidate defect area; Perform region growing on the candidate defect region to obtain the complete defect region; The endpoint coordinates and center coordinates of the boundary contour of the defect area are determined as the position information of the defect area.

[0009] By adopting the above technical solution, the location information of the defect area is extracted by analyzing the grayscale value distribution characteristics in the pressure response image sequence. The candidate defect areas are initially screened using a grayscale difference threshold. The complete defect area is then obtained through a region growing algorithm. Finally, the coordinates of the boundary contour endpoints and the center coordinates are extracted as the location information. This defect area extraction method based on image grayscale features can accurately capture the geometric characteristics and spatial distribution information of the defect. The use of an adaptive grayscale difference threshold makes the method highly adaptable to various environments. The application of the region growing algorithm can also solve problems such as blurred defect boundaries and unclear local features, ensuring the acquisition of complete and accurate defect area information, providing reliable data support for subsequent defect feature analysis.

[0010] In conjunction with some embodiments of the first aspect, in some embodiments, calculating the displacement change of the defective area relative to the surface reference image of the hose in a pressure-free state at each pressure level specifically includes: Obtaining initial position information of the defect area in the surface reference image of the hose in a pressure-free state; Calibrate the coordinates of the defect area position information at each pressure level in the pressure response image sequence; Calculate the coordinate offset of the position information of the defect area relative to the initial position information at each pressure level; The modulus of the coordinate offset is determined as the displacement change.

[0011] By adopting the above technical solution and establishing a method for calculating the displacement change of the defect area relative to a reference image in a pressure-free state, accurate quantification of the dynamic response characteristics of the defect area is achieved. This method establishes a spatial correspondence between images at different pressure levels through coordinate calibration and uses the modulus of the coordinate offset as the displacement change, reducing measurement errors caused by factors such as shooting angle and image distortion. This relative displacement-based measurement method not only accurately reflects the deformation behavior of the defect area under pressure, but also, by using a reference image in a pressure-free state, eliminates interference from the structural characteristics of the hose itself, improving the accuracy and reliability of displacement measurement and making the quantification of defect response characteristics more objective and precise.

[0012] In conjunction with some embodiments of the first aspect, in some embodiments, after determining that the hose has a crack defect, the method further includes: Obtain the strain value distribution along the circumference of the crack defect; Calculate the position of the strain mutation point based on the strain value distribution; The plastic zone radius of the crack defect tip is calculated with the position of the strain mutation point as the center of the circle; Collecting data on changes in the radius of the plastic zone within a preset time period; When the change rate of the plastic zone radius is greater than the preset expansion threshold, it is determined that the crack defect is in the rapid expansion stage.

[0013] By adopting the above technical solution, the strain distribution characteristics around the crack defect are analyzed, the radius of the plastic zone at the crack tip is determined based on the strain mutation point, and the rate of change of the plastic zone radius is monitored to determine whether the crack is in the rapid expansion stage. This crack growth warning method based on the evolution characteristics of the plastic zone can capture the development trend of plastic deformation in the local area of ​​the crack tip before the macro crack propagates. Because the formation and expansion of the plastic zone are precursors to crack growth, real-time monitoring of the rate of change of the plastic zone radius can early detect the critical state of crack growth, thereby providing sufficient response time to prevent sudden hose failure and improving the timeliness and reliability of crack growth warning.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, after determining that the hose has a process scratch defect, the method further includes: Continuously collect dynamic stability of process scratch defects within a preset time period; Calculate the attenuation coefficient of dynamic stability, which is the change in dynamic stability per unit time; When the attenuation coefficient is less than the preset stability threshold, it is determined that the process scratch defect has a tendency to transform into a crack defect.

[0015] By adopting the above technical solution, the dynamic stability of process scratch defects is continuously collected within a preset time period, the attenuation coefficient of dynamic stability is calculated, and the trend of process scratch defects transforming into crack defects is determined based on the comparison of the attenuation coefficient with the preset stability threshold, so that the system can quantitatively monitor the evolution process of process scratch defects. Dynamic stability reflects the degree of fluctuation of the defect response, and its attenuation characterizes the gradual change of the defect state. When the attenuation coefficient is less than the preset stability threshold, it means that the deformation response of the defect area gradually develops in an unstable direction. This instability increases the risk of the defect expanding into a crack. By establishing a corresponding relationship between the attenuation of dynamic stability and the defect transformation trend, the system realizes early warning of the potential hazards of process scratch defects, avoids sudden failure of the hose due to defect transformation, and improves the safety and reliability of the hose during use.

[0016] In conjunction with some embodiments of the first aspect, in some embodiments, after determining that the hose has a corrosion pit defect, the method further includes: Obtain the strain field distribution diagram of corrosion pit defects at different pressure levels; The strain concentration factor is calculated based on the strain field distribution diagram. The strain concentration factor is the ratio of the maximum strain value in the defect area to the strain value at the defect edge. Repeat the acquisition of the strain concentration factor within a preset number of pressure cycles; Calculate the rate of change of the strain concentration factor and the increment of displacement change after each pressure cycle; When the rate of change of the strain concentration factor is greater than a first preset threshold and the increment of the displacement change is greater than a second preset threshold, it is determined that the corrosion pit defect has a trend of continuous expansion.

[0017] By employing this technical solution, the strain concentration factor (SCF) is calculated by obtaining strain field distribution maps of the corrosion pit defect at different pressure levels. The rate of change of the SCF and the incremental displacement change are monitored over a preset number of pressure cycles. The SCF characterizes the degree of strain unevenness in the defect region, while its rate of change reflects the rate of damage accumulation, and the incremental displacement change reflects the severity of defect deformation. When both the rate of change of the SCF and the incremental displacement change exceed their respective preset thresholds, it indicates that both the strain concentration effect and the deformation response in the defect region are deteriorating, improving the accuracy of the assessment of corrosion pit defect expansion trends.

[0018] In conjunction with some embodiments of the first aspect, in some embodiments, after determining that the corrosion pit defect has a trend of continuous expansion, the method further includes: Extract the strain gradient features in the strain field distribution diagram; Calculate the anisotropy coefficient of the strain gradient feature. The anisotropy coefficient is the ratio of the maximum strain gradient direction to the minimum strain gradient direction. Obtain anisotropy coefficients over multiple pressure cycles; Determine the main direction variation trend of the anisotropy coefficient; When the deflection angle of the main direction change trend is greater than a preset angle threshold, it is determined that the expansion direction of the corrosion pit defect has changed.

[0019] By adopting the above technical solution, by extracting the strain gradient characteristics from the strain field distribution diagram, calculating the anisotropy coefficient of the strain gradient characteristics, and tracking the main direction change trend of the anisotropy coefficient over multiple pressure cycles, dynamic monitoring of the expansion direction of the corrosion pit defect is achieved. The strain gradient characteristics reflect the spatial variation law of the strain distribution around the defect, the anisotropy coefficient quantifies the directional characteristics of the strain distribution, and the main direction change trend characterizes the spatial orientation of the defect expansion. When the deflection angle of the main direction change trend exceeds the preset angle threshold, it means that the defect expansion has undergone a directional change, and this change may cause the defect to develop in a more unfavorable direction. By capturing the dynamic change characteristics of the defect expansion direction, the system has enhanced the depth of understanding of the evolution law of the corrosion pit defect, which helps to more accurately predict the expansion path of the defect.

[0020] In a second aspect, an embodiment of the present application provides a hose surface defect detection system, which comprises: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code comprises computer instructions, and the one or more processors call the computer instructions to cause the system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer-readable storage medium comprising instructions, which, when executed on a system, enables the system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer program product, which, when executed on a system, enables the system to execute the method described in any possible implementation manner in the first aspect.

[0023] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. This application provides a method for detecting hose surface defects. By collecting a sequence of pressure response images of the hose surface at different pressure levels, combined with the displacement change of the defect area, the three key parameters of the defect compliance coefficient, plastic deformation rate, and dynamic stability are calculated, and a corresponding relationship between the defect type and these parameters is established. Crack defects are manifested as a larger compliance coefficient, smaller dynamic stability, and a continuously increasing plastic deformation rate. Process scratch defects are manifested as a smaller compliance coefficient, larger dynamic stability, and a smaller plastic deformation rate. Corrosion pit defects are manifested as a medium-range compliance coefficient, a step-like change in dynamic stability, and a sudden change in plastic deformation rate under a specific pressure. This determination method based on a multi-parameter combination improves the accuracy of defect type identification.

[0024] 2. This application provides a method for detecting surface defects in hoses. The method obtains the strain field distribution diagram of the corrosion pit defect at different pressure levels, calculates the strain concentration factor, and monitors the rate of change of the strain concentration factor and the incremental displacement change within a preset number of pressure cycles. The strain concentration factor characterizes the unevenness of the strain distribution in the defect area, its rate of change reflects the cumulative rate of defect damage, and the incremental displacement change reflects the degree of aggravation of the defect deformation. When the rate of change of the strain concentration factor and the incremental displacement change simultaneously exceed their respective preset thresholds, it indicates that the strain concentration effect and deformation response in the defect area are showing a trend of continuous deterioration, thereby improving the accuracy of judging the expansion trend of the corrosion pit defect.

[0025] 3. The present application provides a method for detecting surface defects of hoses. By extracting the strain gradient characteristics in the strain field distribution diagram, calculating the anisotropy coefficient of the strain gradient characteristics, and tracking the main direction change trend of the anisotropy coefficient during multiple pressure cycle periods, dynamic monitoring of the expansion direction of corrosion pit defects is achieved. The strain gradient characteristics reflect the spatial variation law of the strain distribution around the defect, the anisotropy coefficient quantifies the directional characteristics of the strain distribution, and the main direction change trend characterizes the spatial orientation of the defect expansion. When the deflection angle of the main direction change trend exceeds the preset angle threshold, it means that the defect expansion has undergone a directional change, and this change may cause the defect to develop in a more unfavorable direction. By capturing the dynamic change characteristics of the defect expansion direction, the system improves the depth of understanding of the evolution law of corrosion pit defects, which helps to more accurately predict the expansion path of the defect. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flow chart of a hose surface defect detection method in an embodiment of the present application.

[0027] Figure 2 This is another flow chart of a hose surface defect detection method in an embodiment of the present application.

[0028] Figure 3 This is a schematic diagram of the physical device structure of a hose surface defect detection system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The terms used in the following examples of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and appended claims of this application, the singular expressions "a," "an," "said," "above," "the," and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in this application refers to any or all possible combinations comprising one or more of the listed items.

[0030] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0031] The following uses an embodiment and combines Figure 1 , a method for detecting surface defects of a hose in an embodiment of the present application is described: See also Figure 1, is a flow chart of a hose surface defect detection method in an embodiment of the present application.

[0032] S101, applying internal pressure to the hose in sequence according to preset pressure levels, and collecting a surface image of the hose at each pressure level to obtain a pressure response image sequence; This step applies different levels of internal pressure to the hose. The pressure levels can be set based on actual conditions, such as 0.1 MPa, 0.2 MPa, and 0.3 MPa. The intervals between pressure levels can also be adjusted based on actual conditions. At each pressure level, the system captures an image of the hose surface, generating an image of the hose surface at that pressure level. These images at multiple pressure levels form a pressure response image sequence, which reflects how the hose surface changes under different pressure levels.

[0033] The system applies internal pressure to the hose using a pressure pump connected to the hose. The system controls the pump's output pressure to maintain pressure within the hose. At each pressure level, the system captures images of the hose surface using an image acquisition device, such as an industrial camera or CCD camera. The image acquisition device is kept at a distance from the hose surface to ensure clear images. The captured images can undergo pre-processing, such as grayscale conversion and noise reduction, to improve image quality.

[0034] S102, extracting the position information of the defective area in the pressure response image sequence, and calculating the displacement change of the defective area relative to the surface reference image of the hose in a pressure-free state at each pressure level; The system extracts the position information of defective areas from the pressure response image sequence, specifically by obtaining the grayscale value distribution of each frame in the pressure response image sequence; determining a grayscale difference threshold based on the grayscale value distribution; identifying areas with grayscale value differences greater than the grayscale difference threshold as candidate defective areas; performing region growing on the candidate defective areas to obtain a complete defective area; and determining the position information of the defective area using the endpoint coordinates and center coordinates of the boundary contour of the defective area. The system also calculates the displacement change of the defective area relative to a surface reference image of the hose in the unpressurized state at each pressure level, specifically by obtaining the initial position information of the defective area in the surface reference image of the hose in the unpressurized state; performing coordinate calibration on the position information of the defective area at each pressure level in the pressure response image sequence; calculating the coordinate offset of the position information of the defective area at each pressure level relative to the initial position information; and determining the modulus of the coordinate offset as the displacement change.

[0035] This step first extracts the position information of the defective area from the pressure response image sequence. This step specifically involves obtaining the grayscale value distribution of each frame, determining a grayscale difference threshold based on the grayscale value distribution, identifying areas with grayscale value differences greater than the threshold as candidate defective areas, performing region growing on the candidate defective areas to obtain a complete defective area, and determining the position information of the defective area using the endpoint coordinates and center coordinates of the boundary contour of the defective area. The displacement change of the defective area relative to the surface reference image of the hose in the unpressurized state is then calculated at each pressure level. This step specifically involves obtaining the initial position information of the defective area in the surface reference image, performing coordinate calibration on the position information of the defective area at each pressure level in the pressure response image sequence, calculating the coordinate offset of the position information of the defective area at each pressure level relative to the initial position information, and determining the modulus of the coordinate offset as the displacement change.

[0036] The system can extract the location of defective areas through image processing algorithms, such as using threshold segmentation and edge detection to extract the outline of the defective area and then calculate the endpoint and center coordinates of the outline. To calculate the displacement change, the system can align the images in the pressure response image sequence with the surface reference image through image registration, and then calculate the coordinate offset of the defective area. The coordinate offset can be calculated using metrics such as Euclidean distance or Manhattan distance.

[0037] S103. Calculate the defect compliance coefficient, plastic deformation rate, and dynamic stability based on the relationship between the displacement change and the corresponding pressure level; The system calculates the defect compliance coefficient, plastic deformation rate and dynamic stability based on the relationship between the displacement change and the corresponding pressure level. The defect compliance coefficient is the ratio of the displacement change to the pressure value of the corresponding pressure level, the plastic deformation rate is the ratio of the residual displacement change after pressure relief to the maximum displacement change, and the dynamic stability is the fluctuation amplitude during the displacement change process.

[0038] The system calculates the defect compliance coefficient, plastic deformation rate, and dynamic stability based on the relationship between displacement change and the corresponding pressure level. The defect compliance coefficient is the ratio of displacement change to the pressure value of the corresponding pressure level, reflecting the deformation capacity of the defect area under pressure. The plastic deformation rate is the ratio of the residual displacement change after pressure relief to the maximum displacement change, reflecting the degree of plastic deformation in the defect area. Dynamic stability is the fluctuation amplitude during displacement change, reflecting the stability of the defect area during pressure changes.

[0039] The system can use data fitting to establish a functional relationship between displacement change and pressure, then calculate the slope of the function to obtain the defect compliance coefficient. To calculate the plastic deformation rate, the system records the location of the defect area after pressure unloading, calculates the residual displacement change, and then divides it by the maximum displacement change to obtain the plastic deformation rate. To calculate dynamic stability, the system can differentiate the displacement change to obtain the displacement change rate, and then calculate the standard deviation of the displacement change rate to obtain dynamic stability.

[0040] S104: If the defect compliance coefficient is greater than a first preset value, the dynamic stability is less than a second preset value, and the plastic deformation rate continues to increase during the cyclic pressurization process, then the hose is determined to have a crack defect; The system determines whether the defect compliance coefficient is greater than a first preset value, whether the dynamic stability is less than a second preset value, and whether the plastic deformation rate continues to increase during the cyclic pressurization process. If these three conditions are met, the hose is determined to have a crack defect. This step determines whether the hose has a crack defect by evaluating the defect compliance coefficient, dynamic stability, and plastic deformation rate.

[0041] The system can set three preset thresholds: the defect flexibility coefficient threshold, the dynamic stability threshold, and the plastic deformation rate threshold. The calculated parameter values ​​are compared with the thresholds to determine whether the conditions are met. If the defect flexibility coefficient is greater than the defect flexibility coefficient threshold, it indicates that the defect area has a strong deformation capacity and may contain a crack. If the dynamic stability is less than the dynamic stability threshold, it indicates that the defect area has poor stability during pressure changes and may contain a crack. If the plastic deformation rate continues to increase during the cyclic pressurization process, it indicates that the plastic deformation in the defect area is accumulating and may contain a crack. Only when all three conditions are met can the hose be determined to have a crack defect.

[0042] S1041. Obtain strain value distribution along the circumferential direction of the crack defect; The system acquires the strain distribution along the circumference of the crack defect. This step provides data support for the subsequent calculation of the plastic zone radius at the crack tip by obtaining the strain distribution in the area surrounding the crack defect.

[0043] The system uses digital image correlation (DIC) to obtain strain distribution. Specifically, the system places several markers around the crack defect. Then, using an image acquisition device, it captures images of the crack defect at different pressure levels. By comparing the positional changes of the markers in the different images, the system calculates the strain value. The strain value can be represented by a strain tensor, which includes normal strain and tangential strain.

[0044] S1042. Calculate the position of the strain mutation point based on the strain value distribution; The system calculates the location of the strain mutation point based on the strain value distribution. This step analyzes the strain value distribution and finds the location where the strain value mutation occurs, which is used as the center point of the plastic zone at the crack tip.

[0045] The system can identify strain mutation points through threshold segmentation. Specifically, the system can set a strain mutation threshold and mark points with strain values ​​greater than the threshold as strain mutation points. The threshold can be set adaptively based on factors such as material properties and loading conditions. After identifying the strain mutation points, the system can use clustering algorithms, such as the k-means algorithm, to cluster the strain mutation points and identify the cluster center, which serves as the center of the plastic zone.

[0046] S1043. Calculate the radius of the plastic zone at the crack tip with the position of the strain mutation point as the center of the circle; The system calculates the radius of the plastic zone at the crack tip, using the strain mutation point as the center. This step uses the strain mutation point as the center to calculate the radius of the plastic zone, which is used to assess the damage level at the crack tip.

[0047] The system can calculate the plastic zone radius using an integral method. Specifically, the system uses a series of concentric circles centered around the strain mutation point and calculates the average strain value for each concentric circle. When the average value is less than the critical strain value, the corresponding concentric circle radius is the plastic zone radius. The critical strain value can be pre-set based on material properties, such as the yield strain.

[0048] S1044, collecting data on changes in the radius of the plastic zone within a preset time period; The system collects data on changes in the plastic zone radius over a preset time period. This step continuously collects data on changes in the plastic zone radius over a period of time to analyze crack growth.

[0049] The system can be configured with a sampling frequency and sampling time, collecting plastic zone radius data at a fixed frequency within a preset time period and storing the data in a database. The sampling frequency can be set based on an estimated crack growth rate, and the sampling time can be set based on the timescale of crack growth, such as 1 / 10 of the crack growth lifespan.

[0050] S1045: When the rate of change of the plastic zone radius is greater than a preset expansion threshold, it is determined that the crack defect is in a rapid expansion stage; The system determines whether the rate of change of the plastic zone radius is greater than a preset expansion threshold. If so, the crack defect is determined to be in the rapid expansion stage. This step determines whether the crack is in the rapid expansion stage by determining the rate of change of the plastic zone radius.

[0051] The system calculates the rate of change of the plastic zone radius using a differential method: the difference between the plastic zone radius at two adjacent sampling moments divided by the sampling interval. This rate of change is then compared with a preset expansion threshold. If the rate of change exceeds the threshold, the crack is considered to be in a rapid expansion phase. The expansion threshold can be pre-set based on factors such as material properties and load characteristics.

[0052] S105: If the defect compliance coefficient is less than the third preset value, the dynamic stability is greater than the fourth preset value, and the plastic deformation rate is less than the fifth preset value, then the hose is determined to have a process scratch defect; The system determines whether the defect compliance coefficient is less than a third preset value, whether the dynamic stability is greater than a fourth preset value, and whether the plastic deformation rate is less than a fifth preset value. If these three conditions are met, the hose is determined to have a process scratch defect. This step determines whether the hose has a process scratch defect by evaluating these three parameters.

[0053] The determination principle in this step is similar to that in step S104, except that the conditions are reversed. The system can set three preset thresholds: the defect compliance coefficient threshold, the dynamic stability threshold, and the plastic deformation rate threshold. By comparing the parameter values ​​with the thresholds, it determines whether the conditions are met. If the defect compliance coefficient is less than the threshold, it indicates that the defect area has weak deformation capacity; if the dynamic stability is greater than the threshold, it indicates that the defect area is relatively stable; and if the plastic deformation rate is less than the threshold, it indicates that the defect area has undergone minimal plastic deformation. Only when all three conditions are met can the hose be determined to have a process scratch defect.

[0054] S1051. Continuously collect dynamic stability data of process scratch defects within a preset time period; The system continuously collects dynamic stability data of process scratch defects over a preset time period. This step provides a basis for subsequent analysis of the process scratch-to-crack transformation trend by continuously collecting dynamic stability data.

[0055] The data collection method in this step is similar to that in step S1044. The system can set a sampling frequency and sampling time to collect dynamic stability data at a fixed frequency within a preset time period. The sampling frequency and sampling time can be set based on an estimated time scale for process scratch expansion.

[0056] S1052. Calculate the attenuation coefficient of dynamic stability; The system calculates the attenuation coefficient of dynamic stability, which is the change in dynamic stability per unit time. This step quantitatively evaluates the stability change of process scratch defects by calculating the attenuation coefficient.

[0057] The system calculates the change in dynamic stability using the differential method and then divides it by the time interval to obtain the attenuation coefficient. The attenuation coefficient reflects the rate at which dynamic stability decays over time. A larger attenuation coefficient indicates a faster decay in dynamic stability and a worse stability against process scratch defects.

[0058] S1053. When the attenuation coefficient is less than a preset stability threshold, it is determined that the process scratch defect has a tendency to transform into a crack defect; The system determines whether the attenuation coefficient is less than a preset stability threshold. If so, it determines that the process scratch defect has a tendency to transform into a crack defect. This step uses the attenuation coefficient to determine whether the process scratch defect has a risk of transforming into a crack defect.

[0059] The system can preset a stability threshold and compare the attenuation coefficient with the threshold. If the attenuation coefficient is less than the threshold, it indicates that the dynamic stability decays slowly and the process scratch defect is relatively stable. If the attenuation coefficient is greater than or equal to the threshold, it indicates that the dynamic stability decays rapidly and the process scratch defect is at risk of transforming into a crack defect. The stability threshold can be preset based on factors such as material properties and load characteristics.

[0060] S106. If the defect compliance coefficient is between the sixth preset value and the seventh preset value, and the dynamic stability shows a step change during the pressure change process, and the plastic deformation rate changes suddenly at the preset specific pressure, then the hose is determined to have a corrosion pit defect; The system determines whether the defect compliance coefficient is between the sixth and seventh preset values, whether the dynamic stability shows a step change during pressure changes, and whether the plastic deformation rate undergoes a sudden change at a preset specific pressure. If these three conditions are met, the hose is determined to have a corrosion pit defect. This step determines whether the hose has a corrosion pit defect by evaluating the changing characteristics of these three parameters.

[0061] The system can set two defect compliance coefficient thresholds, the sixth and seventh preset values, to determine whether the defect compliance coefficient falls between the two thresholds. The system also analyzes the dynamic stability and plastic deformation rate curves to determine whether there are step changes or sudden changes. A step change in the dynamic stability curve indicates that the stability of the defect area has suddenly changed during the pressure change. A sudden change in the plastic deformation rate curve at a specific pressure indicates that this pressure triggered the rapid expansion of the defect. Only when all three conditions are met can the hose be determined to have a corrosion pit defect.

[0062] S1061. Obtaining a strain field distribution diagram of the corrosion pit defect at different pressure levels; The system obtains the strain field distribution diagram of the corrosion pit defect at different pressure levels. This step provides data support for the subsequent calculation of the strain concentration factor by obtaining the strain field distribution diagram.

[0063] The system can use digital image correlation (DIC) to obtain a strain field distribution map, similar to step S1041. The system collects images of the corrosion pit defect area at different pressure levels and then calculates the strain field distribution map using the DIC algorithm. The strain field distribution map presents the strain distribution in the form of a cloud map, with areas with greater strain having darker colors.

[0064] During this step, the strain field distribution map may have insufficient resolution, resulting in unclear display of areas of strain concentration. To address this issue, the system can use high-resolution image acquisition equipment to improve image acquisition accuracy. Furthermore, the system can optimize the DIC algorithm, such as using higher-order shape functions to describe the displacement field, to improve strain field calculation accuracy.

[0065] S1062. Calculate the strain concentration factor based on the strain field distribution diagram; The system calculates the strain concentration factor based on the strain field distribution diagram. The strain concentration factor is the ratio of the maximum strain value in the defect area to the strain value at the defect edge.

[0066] The system calculates the strain concentration factor based on the strain field distribution. The strain concentration factor is the ratio of the maximum strain value in the defect area to the strain value at the defect edge. This step quantitatively assesses the degree of strain concentration in the corrosion pit defect by calculating the strain concentration factor.

[0067] The system uses image processing algorithms to extract defect areas and defect edges from the strain field distribution map. It then calculates the maximum strain value in the defect area and the average strain value at the defect edge, dividing the two to obtain the strain concentration factor. A larger strain concentration factor indicates a more concentrated strain in the defect area and a weaker load-bearing capacity.

[0068] S1063: When the attenuation coefficient is less than a preset stability threshold, it is determined that the process scratch defect has a tendency to transform into a crack defect; When the attenuation coefficient is less than a preset stability threshold, the system determines that the process scratch defect has a tendency to transform into a crack defect. This step determines whether the process scratch defect has a risk of transforming into a crack defect by comparing the attenuation coefficient to the preset stability threshold.

[0069] The system can set a preset stability threshold and compare the attenuation coefficient with the threshold. If the attenuation coefficient is less than the threshold, the dynamic stability of the process scratch defect is relatively high, and the risk of defect expansion is low. If the attenuation coefficient is greater than or equal to the threshold, the dynamic stability of the process scratch defect is relatively poor, and the defect is at risk of transforming into a crack defect. The preset stability threshold can be set based on material properties, load characteristics, environmental factors, and other factors.

[0070] S1064, repeatedly obtaining the strain concentration factor within a preset number of pressure cycles; The system repeatedly acquires the strain concentration factor within a preset number of pressure cycles. This step, by repeatedly acquiring the strain concentration factor, provides data support for subsequent analysis of corrosion pit defect expansion trends.

[0071] The system can preset the number of pressure cycles, such as 10 or 20, based on the timescale of corrosion pit defect expansion. Then, within each pressure cycle, steps S1061 and S1062 are repeated to obtain a strain field distribution diagram and strain concentration factor. This yields a set of strain concentration factor data, reflecting the changes in strain concentration within the corrosion pit defect over multiple pressure cycles.

[0072] During this step, the number of pressure cycles may be improperly set. For example, too few cycles may not fully reflect the defect growth process, while too many cycles may result in low detection efficiency. To address this issue, the system can employ an adaptive pressure cycle strategy, dynamically adjusting the number of pressure cycles based on the rate of change of the strain concentration factor. If the strain concentration factor changes slowly, indicating a gradual defect growth, the number of pressure cycles can be reduced. However, if the strain concentration factor changes dramatically, indicating rapid defect growth, the number of pressure cycles may need to be increased to capture the critical moment of defect growth.

[0073] S1065. Calculate the rate of change of the strain concentration factor and the increment of the displacement change after each pressure cycle; The system calculates the rate of change of the strain concentration factor and the incremental displacement change after each pressure cycle. This step quantitatively evaluates the growth rate of the corrosion pit defect by calculating these two parameters.

[0074] The system uses the difference method to calculate the difference between the strain concentration factors of two adjacent pressure cycles to obtain the rate of change of the strain concentration factor. It also calculates the difference between the displacement changes of two adjacent pressure cycles to obtain the displacement increment. The strain concentration factor rate of change reflects the rate of change in the degree of strain concentration in the defect area, while the displacement increment reflects the rate of geometric expansion of the defect area. Together, these two parameters reflect the expansion rate of the corrosion pit defect.

[0075] In this step, inaccurate parameter calculations may occur. For example, if the time interval between two pressure cycles is long, resulting in small rate of change and increment values, the system can address this issue by shortening the time interval between pressure cycles to improve the temporal resolution of parameter calculations. Furthermore, the system can use curve fitting to fit the strain concentration factor and displacement change data into a continuous function. This function can then be differentiated to obtain the rate of change and increment at any moment, improving the accuracy of parameter calculations.

[0076] S1066: When the rate of change of the strain concentration factor is greater than a first preset threshold and the increment of the displacement change is greater than a second preset threshold, it is determined that the corrosion pit defect has a trend of continuous expansion.

[0077] When the rate of change of the strain concentration factor exceeds a first preset threshold and the incremental displacement change exceeds a second preset threshold, the system determines that the corrosion pit defect has a trend of continued expansion. This step determines whether the corrosion pit defect is in a state of continued expansion by evaluating the rate of change of the strain concentration factor and the incremental displacement change.

[0078] The system can set a first preset threshold and a second preset threshold to determine the strain concentration factor change rate and displacement change increment, respectively. If the strain concentration factor change rate is continuously greater than the first preset threshold, it indicates that the strain concentration effect of the corrosion pit defect is continuously worsening; if the displacement change increment is continuously greater than the second preset threshold, it indicates that the size of the corrosion pit defect is continuously expanding. When both conditions are met, it can be determined that the corrosion pit defect is in a state of continuous expansion. The two thresholds can be set based on factors such as material failure criteria and structural safety margin.

[0079] In the above embodiment, by capturing a sequence of pressure response images of the hose surface at different pressure levels and combining them with the displacement change of the defect area, three key parameters—the defect compliance coefficient, plastic deformation rate, and dynamic stability—are calculated. A corresponding relationship between defect type and these parameters is established. Crack defects manifest as a large compliance coefficient, low dynamic stability, and a continuously increasing plastic deformation rate; process scratch defects manifest as a small compliance coefficient, high dynamic stability, and a small plastic deformation rate; and corrosion pit defects manifest as a medium-range compliance coefficient, a step-like change in dynamic stability, and a sudden change in plastic deformation rate at a specific pressure. This multi-parameter combination-based determination method improves the accuracy of defect type identification.

[0080] After determining that the hose surface defect is a corrosion pit defect, the system needs to further evaluate the expansion behavior of this type of defect. The expansion process of the corrosion pit defect often shows complex directional characteristics. This directional change may cause the defect to develop along an unexpected path, increasing the risk of hose failure. Based on this, after completing the determination of the continuous expansion trend of the corrosion pit defect, the system further evaluates the dynamic evolution of the defect expansion direction by analyzing the anisotropic characteristics of the strain field distribution. Figure 2 , another hose surface defect detection method in an embodiment of the present application is described: See also Figure 2 , is another flow chart of a hose surface defect detection method in an embodiment of the present application.

[0081] S201, extracting strain gradient features in the strain field distribution diagram; The system extracts strain gradient features from the strain field distribution diagram. This step extracts gradient features from the strain field distribution diagram, reflecting the inhomogeneity of the strain distribution, providing data support for subsequent analysis of the anisotropy of the strain field. Strain gradient features characterize the rate of change of the strain field in different directions and reflect the distribution pattern of areas of strain concentration. The system can use a variety of methods to extract strain gradient features, such as gradient operators based on image processing and numerical differentiation based on finite element analysis.

[0082] The system can calculate the strain difference between adjacent pixels in the strain field distribution map to obtain a strain gradient vector field. Specifically, the system can use gradient operators such as the Sobel operator and the Prewitt operator to perform convolution operations on the strain field distribution map to extract the horizontal and vertical strain gradient components. The system can then calculate the magnitude and direction of the strain gradient based on the gradient components to obtain a strain gradient vector field. In the strain gradient vector field, the magnitude of the vector represents the intensity of the strain gradient, and the direction of the vector represents the direction of the strain gradient.

[0083] S202, calculating the anisotropy coefficient of the strain gradient characteristic; The system calculates the anisotropy coefficient of the strain gradient feature. The anisotropy coefficient is the ratio of the maximum strain gradient direction to the minimum strain gradient direction. This step quantitatively assesses the degree of anisotropy in the strain field distribution by calculating the ratio of the strain gradient feature in different directions. A larger anisotropy coefficient indicates a more uneven variation in the strain field in different directions and a more pronounced directionality in defect propagation.

[0084] The system can perform principal component analysis (PCA) on the strain gradient vector field to obtain the primary and secondary directions of the strain gradient characteristics. The system then calculates the mean strain gradient in the primary and secondary directions and divides the mean values ​​in the two directions to obtain the anisotropy coefficient of the strain gradient characteristics. To improve computational efficiency, the system can also use matrix decomposition methods such as singular value decomposition (SVD) to directly solve for the maximum and minimum eigenvalues ​​of the strain gradient matrix and divide them to obtain the anisotropy coefficient.

[0085] S203, obtaining anisotropy coefficients within multiple pressure cycles; The system acquires anisotropy coefficients over multiple pressure cycles. This step continuously acquires anisotropy coefficient data over multiple pressure cycles, providing data support for subsequent analysis of the dynamic changes in the defect expansion direction. Because the expansion of corrosion pit defects is a gradual process, the anisotropy coefficients obtained under a single pressure cycle may be accidental and difficult to accurately reflect the overall evolution of the defect expansion direction. Therefore, the system needs to continuously acquire anisotropy coefficients over multiple pressure cycles to capture the dynamic changes in the defect expansion direction.

[0086] The system can appropriately set the number and time intervals of pressure cycles based on the expansion rate of corrosion pit defects. Within each pressure cycle, the system repeats steps S201 and S202 to obtain the strain gradient characteristics and anisotropy coefficients for the current cycle. Furthermore, the system can store the anisotropy coefficients obtained within each cycle in chronological order, forming a time series data set. To conserve storage space, the system can employ data compression algorithms, such as wavelet compression and singular value decomposition, to compress and store the time series data.

[0087] S204, determining the main direction change trend of the anisotropy coefficient; The system determines the principal direction of the anisotropy coefficient. This step analyzes the variation of the anisotropy coefficient over multiple pressure cycles to determine the primary direction of variation in the anisotropy of the strain field distribution. The principal direction of the anisotropy coefficient reflects the overall evolution of the defect propagation direction and is important for predicting defect propagation paths and assessing hose failure risks.

[0088] The system can convert anisotropy coefficient time series data obtained over multiple pressure cycles into frequency domain or time-frequency domain representations, such as Fourier transforms or wavelet transforms. Through frequency domain or time-frequency domain analysis, the system can extract characteristics such as the periodicity and trend of anisotropy coefficient changes. The system can then use trend analysis methods such as linear regression and polynomial regression to fit anisotropy coefficient trend curve. By analyzing the slope and curvature of the trend curve, the system can determine the primary direction of change in the anisotropy coefficient, that is, the main direction of change in the anisotropy of the strain field distribution.

[0089] S205 : When the deflection angle of the main direction change trend is greater than a preset angle threshold, it is determined that the expansion direction of the corrosion pit defect has changed.

[0090] The system determines whether the deflection angle of the main direction trend exceeds a preset angle threshold. If so, the system determines that the corrosion pit defect's expansion direction has changed. This step evaluates the dynamic evolution of the corrosion pit defect's expansion direction by determining the degree of deflection in the main direction trend. A large deflection angle indicates a significant change in the defect's expansion direction, potentially causing the defect to expand along an unintended path and increasing the risk of hose failure.

[0091] The system can set a preset angle threshold and compare the deflection angle of the main direction change trend with the threshold. The deflection angle can be determined by calculating the change in the tangent slope of the main direction change trend curve. When the deflection angle is less than or equal to the preset angle threshold, it indicates that the defect expansion direction remains relatively stable; when the deflection angle is greater than the preset angle threshold, it indicates that the defect expansion direction has changed significantly. The threshold setting can be reasonably selected based on factors such as material properties and loading conditions to balance the sensitivity and robustness of changes in the defect expansion direction.

[0092] In the above embodiment, dynamic monitoring of the expansion direction of corrosion pit defects is achieved by extracting the strain gradient characteristics from the strain field distribution diagram, calculating the anisotropy coefficient of the strain gradient characteristics, and tracking the main direction change trend of the anisotropy coefficient over multiple pressure cycles. The strain gradient characteristics reflect the spatial variation law of the strain distribution around the defect, the anisotropy coefficient quantifies the directional characteristics of the strain distribution, and the main direction change trend characterizes the spatial orientation of the defect expansion. When the deflection angle of the main direction change trend exceeds the preset angle threshold, it means that the defect expansion has undergone a directional change, and this change may cause the defect to develop in a more unfavorable direction. By capturing the dynamic change characteristics of the defect expansion direction, the system enhances the depth of understanding of the evolution law of corrosion pit defects and helps to more accurately predict the expansion path of the defect.

[0093] The following describes the system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of the physical device structure of a hose surface defect detection system provided in an embodiment of the present application.

[0094] It should be noted that Figure 3 The structure of the system shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0095] like Figure 3 As shown, the system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes, such as the methods described in the above embodiments, based on programs stored in a read-only memory (ROM) 302 or programs loaded from a storage unit 308 into a random access memory (RAM) 303. RAM 303 also stores various programs and data required for system operation. CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to bus 304.

[0096] The following components are connected to the I / O interface 305: an input section 306 including a camera, infrared sensor, and the like; an output section 307 including a liquid crystal display (LCD) and speakers; a storage section 308 including a hard disk and the like; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. Removable media 311, such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, is installed in the drive 310 as needed, so that computer programs read from the media can be installed in the storage section 308 as needed.

[0097] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for executing the methods illustrated in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 309 and / or installed from removable media 311. When executed by the central processing unit (CPU) 301, the computer program performs the various functions defined in the present invention.

[0098] It should be noted that the computer-readable medium described in the embodiments of the present invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium may include a data signal transmitted in baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal may take any of a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof.

[0099] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two boxes shown in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0100] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the system described in the above embodiments, or may exist independently and not incorporated into the system. The storage medium carries one or more computer programs, and when executed by a processor of a system, the system implements the methods provided in the above embodiments.

[0101] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0102] As used in the above embodiments, the term “when…” may be interpreted as “if…” or “after…” or “in response to determining…” or “in response to detecting…”, depending on the context. Similarly, the phrases “upon determining…” or “if (stated condition or event) is detected” may be interpreted as “if determining…” or “in response to determining…” or “upon detecting (stated condition or event)” or “in response to detecting (stated condition or event)”, depending on the context.

[0103] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, hard disk, tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive).

[0104] Those skilled in the art will appreciate that all or part of the process steps in the above-described method embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, the program can include the process steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for detecting surface defects of a hose, characterized in that: include: applying internal pressure to the hose in sequence according to preset pressure levels, and collecting a surface image of the hose at each pressure level to obtain a pressure response image sequence; Extracting position information of the defective area from the pressure response image sequence, and calculating the displacement change of the defective area relative to the surface reference image of the hose in a pressure-free state at each pressure level; The defect compliance coefficient, plastic deformation rate, and dynamic stability are calculated based on the relationship between the displacement change and the corresponding pressure level. The defect compliance coefficient is the ratio of the displacement change to the pressure value of the corresponding pressure level. The plastic deformation rate is the ratio of the residual displacement change after pressure relief to the maximum displacement change. The dynamic stability is the fluctuation amplitude during the displacement change process. If the defect compliance coefficient is greater than a first preset value, the dynamic stability is less than a second preset value, and the plastic deformation rate continues to increase during the cyclic pressurization process, then the hose is determined to have a crack defect; If the defect compliance coefficient is less than a third preset value, the dynamic stability is greater than a fourth preset value, and the plastic deformation rate is less than a fifth preset value, then the hose is determined to have a process scratch defect; If the defect compliance coefficient is between the sixth preset value and the seventh preset value, and the dynamic stability undergoes a step change during the pressure change process, and the plastic deformation rate undergoes a sudden change at a preset specific pressure, then the hose is determined to have a corrosion pit defect.

2. The method according to claim 1, characterized in that The extracting the position information of the defect area in the pressure response image sequence specifically includes: Obtaining the grayscale value distribution of each frame of the pressure response image sequence; determining a grayscale difference threshold according to the grayscale value distribution; Determine an area where the grayscale value difference is greater than the grayscale difference threshold as a candidate defect area; Performing region growing on the candidate defect region to obtain a complete defect region; The endpoint coordinates and the center coordinates of the boundary contour of the defect area are determined as the position information of the defect area.

3. The method according to claim 1, characterized in that The calculating of the displacement change of the defective area at each pressure level relative to the surface reference image of the hose in a pressure-free state specifically includes: Acquire initial position information of the defective area in the surface reference image of the hose in a pressure-free state; performing coordinate calibration on the position information of the defect area at each pressure level in the pressure response image sequence; Calculating the coordinate offset of the position information of the defective area relative to the initial position information at each pressure level; The modulus of the coordinate offset is determined as the displacement change.

4. The method according to claim 1, wherein After determining that the hose has a crack defect, the method further includes: Acquiring strain value distribution along the circumferential direction of the crack defect; Calculating the position of the strain mutation point based on the strain value distribution; Calculating the plastic zone radius of the crack defect tip with the position of the strain mutation point as the center of the circle; Collecting data on changes in the radius of the plastic zone within a preset time period; When the rate of change of the plastic zone radius is greater than a preset expansion threshold, it is determined that the crack defect is in a rapid expansion stage.

5. The method according to claim 1, wherein After determining that the hose has a process scratch defect, the method further includes: Continuously collecting the dynamic stability of the process scratch defect within a preset time period; Calculating an attenuation coefficient of the dynamic stability, where the attenuation coefficient is a change in the dynamic stability per unit time; When the attenuation coefficient is less than a preset stability threshold, it is determined that the process scratch defect has a tendency to transform into the crack defect.

6. The method according to claim 1, wherein After determining that the hose has a corrosion pit defect, the method further includes: Obtaining a strain field distribution diagram of the corrosion pit defect at different pressure levels; Calculating a strain concentration factor based on the strain field distribution diagram, where the strain concentration factor is the ratio of the maximum strain value of the defect area to the strain value of the defect edge; Repeating the acquisition of the strain concentration factor within a preset number of pressure cycles; Calculating the rate of change of the strain concentration factor and the increment of the displacement change after each pressure cycle; When the change rate of the strain concentration factor is greater than a first preset threshold and the increment of the displacement change is greater than a second preset threshold, it is determined that the corrosion pit defect has a trend of continuous expansion.

7. The method according to claim 6, characterized in that After determining that the corrosion pit defect has a trend of continuous expansion, the method further includes: extracting strain gradient features from the strain field distribution map; Calculating an anisotropy coefficient of the strain gradient characteristic, wherein the anisotropy coefficient is a ratio of a maximum strain gradient direction to a minimum strain gradient direction; Obtain anisotropy coefficients over multiple pressure cycles; Determining a main direction variation trend of the anisotropy coefficient; When the deflection angle of the main direction change trend is greater than a preset angle threshold, it is determined that the expansion direction of the corrosion pit defect has changed.

8. A hose surface defect detection system, characterized in that: The system comprises: One or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the system to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a system, the system is caused to perform the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a system, the system is caused to perform the method according to any one of claims 1 to 7.

Images