Defect detection method and device for heat exchanger plate and storage medium

Abstract

The invention discloses a heat exchanger plate defect detection method and device and a storage medium, and the method comprises the following steps: S1, obtaining the actual temperature distribution characteristics of a heated plate after the plate of a heat exchanger is heated to a target temperature according to a preset heating condition; s2, acquiring preset temperature distribution characteristics of the sheet under a preset heating condition; and S3, comparing the actual temperature distribution characteristics of the sheet with the preset temperature distribution characteristics, obtaining a comparison result, and determining a temperature abnormal area of the sheet according to the comparison result. Through the method, the abnormal change in the plate can be judged according to the temperature distribution of the heat exchanger plate, the temperature abnormal area in the plate is obtained, and the defect on the heat exchanger plate is accurately recognized.

Description

Technical Field

[0001] This invention relates to the field of heat exchanger technology, and in particular to a method, apparatus and storage medium for detecting defects in heat exchanger plates. Background Technology

[0002] Plates are one of the most critical components of a plate heat exchanger. These thin sheets, made of metal or other corrosion-resistant materials and featuring specific geometries, are assembled together using a clamping device to form flow channels, allowing heat exchange between hot and cold fluids. The condition of the heat exchanger plates directly affects its overall performance, including heat transfer efficiency, pressure loss, equipment reliability, and economy. Because the plates come into contact with fluids of different temperatures and properties on both sides, high requirements are placed on their materials, structural design, and manufacturing processes. The quality of the plates directly affects the long-term stable operation of the heat exchanger.

[0003] Potential defects in plate heat exchanger plates mainly include cracks, corrosion, perforation, deformation, and scaling. Current detection methods for these defects primarily involve visual inspection and ultrasonic testing. Visual inspection involves disassembling the heat exchanger to directly observe the plate surface for obvious defects such as cracks, corrosion, and perforation. Ultrasonic testing utilizes the propagation characteristics of ultrasound waves within materials, detecting internal cracks and corrosion by measuring the reflection and attenuation of the waves. However, visual inspection of plate heat exchanger plates is largely manual, resulting in low efficiency and a high risk of missed defects. Ultrasonic testing is ill-suited to the diverse sizes, shapes, and thicknesses of the plates. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method for detecting defects in heat exchanger plates.

[0005] The technical solution adopted by this invention to solve its technical problem is: to construct a method for detecting defects in heat exchanger plates, the method comprising the following steps:

[0006] S1. After the heat exchanger plates are heated to the target temperature according to the preset heating conditions, the actual temperature distribution characteristics of the heated plates are obtained.

[0007] S2. Obtain the preset temperature distribution characteristics of the plate under the preset heating conditions;

[0008] S3. Compare the actual temperature distribution characteristics of the plate with the preset temperature distribution characteristics, and obtain the comparison result. Determine the temperature anomaly area of ​​the plate based on the comparison result.

[0009] Preferably, in the heat exchanger plate defect detection method constructed by the present invention, step S1 specifically includes:

[0010] Acquire a thermal image of the plate, and obtain the actual temperature distribution characteristics from the thermal image.

[0011] Preferably, in the heat exchanger plate defect detection method constructed by the present invention, step S2, obtaining the preset temperature distribution characteristics of the plate under the preset heating conditions, includes:

[0012] A heat conduction model of the plate is constructed based on the preset heating conditions to obtain the preset temperature distribution characteristics of the plate under the preset heating conditions.

[0013] Preferably, in the heat exchanger plate defect detection method constructed by the present invention, the method further includes the following steps before performing step S1:

[0014] S0. Control the emission of continuous wave laser to heat the plate according to the preset heating conditions;

[0015] In step S1, the preset heating conditions include: initial temperature, target temperature, heating time, and ambient pressure.

[0016] Preferably, in the heat exchanger plate defect detection method constructed by the present invention, step S2, which involves constructing a heat conduction model of the plate based on the preset heating conditions to obtain the preset temperature distribution characteristics of the plate under the preset heating conditions, includes:

[0017] Based on the principle of active heating, combined with boundary conditions and heat conduction equations, the influence of different characteristics on temperature distribution during the heating process is simulated to obtain the preset temperature distribution characteristics of the plate under the preset heating conditions.

[0018] Preferably, in the heat exchanger plate defect detection method constructed by the present invention, step S3 includes:

[0019] S31. Using the Canny edge detection algorithm, the thermal image is divided into several partitions;

[0020] S32. The thermal image is clustered using a fuzzy C-means clustering algorithm to identify and classify several of the partitions and determine the temperature anomaly areas of the plate.

[0021] Preferably, in the heat exchanger plate defect detection method constructed by the present invention, step S3 further includes the following steps performed before step S31:

[0022] S30. Perform image enhancement processing on the thermal image, and perform peak signal-to-noise ratio analysis on the thermal image:

[0023] Wherein, PSNR is the peak signal-to-noise ratio, MSE is the mean square error between the output image and the thermal image, and MAX is the maximum pixel value of the thermal image.

[0024] Preferably, in the heat exchanger plate defect detection method constructed by the present invention, the method further includes the following steps:

[0025] S4. Determine the defect type of each temperature abnormality area on the plate according to preset rules to obtain the defect status of the plate;

[0026] The defect types include at least one of crack defects, corrosion defects, scratch defects, pit defects, and impurity defects.

[0027] The present invention also constructs a storage medium storing a computer program, which, when executed by a processor, implements the steps of the heat exchanger plate defect detection method described in any of the above claims.

[0028] The present invention also constructs a heat exchanger plate defect detection device for heating the heat exchanger plates, obtaining the actual temperature distribution characteristics of the heat exchanger plates, and detecting defects in the plates. The device includes a support platform for stabilizing the entire heat exchanger plate defect detection device, and further includes a clamping device, a laser emitting device, an infrared image sensing device, and a controller mounted on the support platform.

[0029] The clamping device is used to fix the plate;

[0030] The laser emitting device is used to emit a beam of a specific wavelength onto the plate fixed by the clamping device, so as to heat the plate to the target temperature;

[0031] The infrared image sensing device is arranged perpendicularly to the clamping device that holds the plate, and is used to acquire infrared thermal images of the plate.

[0032] The controller is connected to the laser emitting device and the infrared image sensing device, and is used to control the laser emitting device to emit the light beam, and also to acquire the infrared thermal image and apply the heat exchanger plate defect detection method described above to detect defects in the plate.

[0033] By implementing this invention, the following beneficial effects are achieved:

[0034] This invention discloses a method, apparatus, and storage medium for detecting defects in heat exchanger plates. The method includes the following steps: S1, after the heat exchanger plates are heated to a target temperature according to preset heating conditions, the actual temperature distribution characteristics of the heated plates are obtained; S2, the preset temperature distribution characteristics of the plates under preset heating conditions are obtained; S3, the actual temperature distribution characteristics and the preset temperature distribution characteristics of the plates are compared, and the comparison result is obtained. Based on the comparison result, the temperature anomaly areas of the plates are determined. This method can determine abnormal changes in the heat exchanger plates based on their temperature distribution and identify temperature anomaly areas, thereby accurately identifying defects on the heat exchanger plates. Attached Figure Description

[0035] The present invention will be further described below with reference to the accompanying drawings and embodiments. In the accompanying drawings:

[0036] Figure 1 This is a flowchart illustrating the heat exchanger plate defect detection method in the first embodiment of the present invention;

[0037] Figure 2 This is a flowchart of the iterative steps of FCM in the first embodiment of the present invention;

[0038] Figure 3 This is a schematic diagram of the first structure of the heat exchanger plate defect detection device in the second embodiment of the present invention;

[0039] Figure 4 This is a schematic diagram of the working path of the infrared image sensing device of the heat exchanger plate defect detection device in the second embodiment of the present invention. Detailed Implementation

[0040] To provide a clearer understanding of the technical features, objectives, and effects of the present invention, specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0041] It should be noted that the flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0042] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0043] See Figure 1The first embodiment of the present invention discloses a method for detecting defects in heat exchanger plates, the method comprising the following steps:

[0044] S1. After the heat exchanger plates are heated to the target temperature according to the preset heating conditions, the actual temperature distribution characteristics of the heated plates are obtained.

[0045] S2. Obtain the preset temperature distribution characteristics of the plate under preset heating conditions.

[0046] S3. Compare the actual temperature distribution characteristics of the plate with the preset temperature distribution characteristics, obtain the comparison results, and determine the temperature anomaly area of ​​the plate based on the comparison results.

[0047] Furthermore, in the heat exchanger plate defect detection method disclosed in this embodiment, step S1 specifically involves: acquiring a thermal image of the plate and obtaining the actual temperature distribution characteristics from the thermal image. When detecting defects in multiple plates, thermal images of the plates can be acquired in batches for batch defect detection.

[0048] Furthermore, in the heat exchanger plate defect detection method disclosed in this embodiment, step S2, obtaining the preset temperature distribution characteristics of the plate under preset heating conditions, includes: constructing a heat conduction model of the plate according to the preset heating conditions to obtain the preset temperature distribution characteristics of the plate under the preset heating conditions.

[0049] Furthermore, in the heat exchanger plate defect detection method disclosed in this embodiment, step S2 involves constructing a heat conduction model of the plate based on preset heating conditions to obtain preset temperature distribution characteristics of the plate under preset heating conditions. This includes: based on the active heating principle, combined with boundary conditions and the heat conduction equation, simulating the influence of different characteristics on the temperature distribution during the heating process to obtain preset temperature distribution characteristics of the plate under preset heating conditions. The preset temperature distribution characteristics are the temperature distribution characteristics that the plate possesses when there are no defects. By comparing the actual temperature distribution characteristics with the preset temperature distribution characteristics, abnormal areas on the plate can be identified.

[0050] Furthermore, in the heat exchanger plate defect detection method disclosed in this embodiment, the method further includes the following steps before performing step S1: S0, controlling the emission of a continuous wave laser to heat the plate according to preset heating conditions; in step S1, the preset heating conditions include: initial temperature, target temperature, heating time and ambient pressure.

[0051] Furthermore, the preset heating conditions include heating time. The specific steps for calculating the preset heating time are as follows:

[0052] 1) Calculate the laser spot area: Where A is the laser spot area and d is the laser spot diameter.

[0053] 2) Calculate the power density of the laser: Among them, P d P is the power density of the laser, A is the laser power, and P is the laser spot area.

[0054] 3) Calculate the mass per unit area of ​​the plate: M = ρ × T; where M is the mass per unit area of ​​the plate, ρ is the density of the plate, and T is the thickness of the plate.

[0055] 4) Calculate the amount of heat required to heat a unit area of ​​the plate to the target temperature: Q = MCΔt; where Q is the amount of heat required to heat a unit area of ​​the plate to the target temperature, M is the mass of a unit area of ​​the plate, C is the specific heat capacity of the plate, and Δt is the difference between the target temperature and the initial temperature.

[0056] 5) Calculate the heating time per unit area of ​​the plate to reach the target temperature: Where t1 is the heating time for a unit area of ​​the plate to reach the target temperature, Q is the amount of heat required to heat a unit area of ​​the plate to the target temperature, and P... d It is the power density of the laser.

[0057] 6) Calculate the heating time of a single spot heating plate to the target temperature: t = Q × A; where t is the heating time of a single spot heating plate to the target temperature, Q is the amount of heat required to heat a unit area of ​​the plate to the target temperature, and A is the laser spot area.

[0058] 7) The heating time t from the entire heating plate of a single spot to the target temperature is recorded as the preset heating time.

[0059] In one specific embodiment, the plate to be tested is a stainless steel plate with a density ρ of 8000 kg / m³. 3 The thickness T is 0.8 mm. The laser power P used to heat the plate is 400 W, the laser spot diameter d is 55 mm, and the vertical distance between the laser center and the plate is 10 mm. The initial temperature is 25℃, the target temperature is 75℃, and the difference between the target temperature and the initial temperature Δt is 50℃.

[0060] In this embodiment, the area A of the laser spot is calculated:

[0061] Calculate laser power density P d :

[0062] Calculate the mass M per unit area of ​​the stainless steel sheet:

[0063] M = ρ × d = 8000 kg / m 3 ×0.8mm=6.4kg / m 2 ;

[0064] Calculate the amount of heat required to heat a unit area of ​​stainless steel sheet to the target temperature (take the specific heat capacity of the stainless steel sheet, C, as C = 500 J / kg℃): Q = MCΔt = 6.4 kg / m 2 ×500J / kg℃×50℃=160000J / m 2 ;

[0065] The heating time per unit area of ​​stainless steel sheet is:

[0066] Therefore, the heating time for a single light spot is: t = 947 s / m 2 ×2376mm 2 =2.26s;

[0067] To determine the optimal preset heating time, the heating time can be initially set to 2 to 5 seconds, and then adjusted accordingly based on the actual test results during actual operation.

[0068] By utilizing laser thermal excitation technology, the precise location of potential defects can be effectively determined through accurate measurement and analysis of the surface temperature distribution of the specimen. The light source technology, based on the principle of laser thermal excitation, can be divided into two main categories: continuous wave laser thermal excitation and pulsed laser thermal excitation. The former exhibits a continuous thermal excitation mode over time, while the latter presents an intermittent, discontinuous thermal excitation mode. In this embodiment, continuous wave laser thermal excitation is used to heat the plate. In particular, continuous wave laser thermal excitation provides a stable and continuous thermal excitation effect, making it easier and more intuitive to observe and analyze the temperature changes of the specimen during the thermal excitation process.

[0069] In most cases, the cross-section of a continuous-wave laser exhibits a regular circular shape, and its thermal power density distribution on a plane typically follows a mathematical model known as the Gaussian distribution. The Gaussian distribution is a widely existing distribution form in nature and engineering, describing the probability distribution of a certain characteristic in space or time. Specifically, in a circular laser spot, the thermal power density gradually decreases from the center point towards the edges, exhibiting a symmetrical bell-shaped curve. The expression for the planar distribution of thermal power density is:

[0070]

[0071] Where τ(r) is the thermal power density, P is the laser power, and r f is the distance between the plate and the center of the laser, and r is the radius of the laser spot;

[0072]

[0073] In the formula: q(r) is the heat power density, r is the laser spot radius, and P is the laser power. This formula represents the total output power P of the laser by integrating the heat power density q(r) within the laser spot region over the entire circular plane. In the integral, r·dr·dθ is the area of ​​a small element in polar coordinates, and q(r) is the power density at that point. The integral expresses the cumulative process of "local power × local area = total power," thus obtaining the heat power distribution generated by the laser source on the plate surface. Furthermore, combining Fourier's law of heat conduction, the heat transfer process is considered, and the temperature change rate is calculated by integrating the temperature gradient. Simultaneously, boundary conditions, i.e., the influence of the physical boundaries of the plate on heat conduction, also need to be considered. In addition, the heat exchange process between the plate and the surrounding environment through convection and radiation heat transfer also needs to be considered. By combining all these factors, the temperature distribution on the plate surface can be solved.

[0074] In other embodiments, normal regions exhibit a relatively uniform temperature distribution, while defective regions show abnormal temperature distributions due to differences in material properties, thickness, or internal structure. These anomalies are clearly visible in thermal images as variations in color or grayscale; for example, at crack defects, the greater the crack depth, the more significant the nearby temperature gradient, resulting in a localized temperature increase due to reduced heat conduction efficiency. This non-uniform temperature distribution reveals the location and characteristics of the defective region.

[0075] To further improve the accuracy of identification, this invention can establish a standard heat conduction model based on Fourier's law of heat conduction to theoretically predict the temperature distribution of heat exchanger plates under normal structure. Under the assumption of one-dimensional steady-state heat transfer, the surface temperature of the heat exchanger plates satisfies the following relationship:

[0076]

[0077] Where q is the heat flux density and k is the thermal conductivity of the material. The temperature gradient is represented by the laser power density and the thermophysical properties of the plate. Under ideal conditions, the temperature distribution curve along the detection path can be calculated.

[0078] The actual temperature distribution data acquired during the detection process will be compared with the theoretical temperature model. If there are areas that deviate from the threshold, they will be considered as temperature anomaly areas. This method can effectively identify heat conduction anomalies caused by microcracks, thinning, or cavitation, thereby improving the interpretability of thermal images and forming a recognition strategy that combines physical basis and image analysis.

[0079] Furthermore, in the heat exchanger plate defect detection method disclosed in this embodiment, step S3 includes: S31, using the Canny edge detection algorithm to segment the thermal image into several partitions; S32, using the fuzzy C-means clustering algorithm to perform cluster analysis on the thermal image, identifying and classifying the several partitions to determine the temperature anomaly areas of the plate. The Canny operator, which has high edge extraction accuracy, is used to perform edge detection and segmentation of the image based on the grayscale value changes at the edges between different regions. To reduce uncertainty in the data, the idea of ​​cluster analysis is further adopted, grouping parts with the same characteristics in the sample data together according to clustering rules to achieve the purpose of classification. This embodiment uses a combination of fuzzy clustering algorithm and dynamic threshold binarization to segment the defect areas in the infrared thermal image, and calculates the size of each defect area based on this.

[0080] Furthermore, fuzzy C-means clustering and K-means clustering are two commonly used algorithms in cluster analysis. K-means clustering uses a hard partitioning method to classify sample data; if outliers are present, the mean will deviate significantly. Fuzzy clustering analysis uses fuzzy logic theory for cluster analysis, possessing excellent descriptive ability for the uncertainty of image information and significantly improving the accuracy of defect segmentation in infrared thermograms. Therefore, this embodiment uses the fuzzy C-means clustering algorithm (FCM) to perform cluster analysis on the infrared thermogram. See also... Figure 2 In step S32, the specific iterative steps of FCM are as follows:

[0081] 1) Initialize the membership matrix F. FCM is a clustering algorithm based on fuzzy partitioning. Its principle is to assign a membership function to each sample, classifying the samples according to the membership values. Use FCM on the dataset X = {x1, x2, ..., x...} n Perform clustering to divide the samples into c classes, thus obtaining the samples x in X. k For the membership degree u of the i-th cluster k The clustering results can be represented by a c*n fuzzy matrix F, which has the following properties:

[0082]

[0083] The membership matrix F is initialized according to this formula.

[0084] 2) Initialize the cluster centers to obtain c cluster centers. The clustering process is to minimize the objective function. Iterative steps are used to reduce the error value of the objective function. When the objective function converges, the clustering process ends, and the final clustering result is obtained. Objective function:

[0085]

[0086] 3) Solve for the objective function. If the change in the objective function between two consecutive iterations does not exceed the error threshold ε, then the termination condition is met, and iteration stops. The necessary condition for FCM to minimize the objective function through iteration is:

[0087]

[0088] 4) Update the membership matrix according to the following formula, and return to step (2) to continue the loop until the maximum number of loops is reached:

[0089]

[0090] In the formula C i Let i be the i-th cluster center; F is the fuzzy classification matrix, F = [u ik ], i = 1, 2, ..., c; k = 1, 2, ..., n; M is the weighting exponent, m ∈ [1, ∞); d ik Let d be the Euclidean distance between the i-th cluster center and the k-th data point. ik =‖c i -x k ‖.

[0091] By applying a dynamic threshold segmentation algorithm based on fuzzy C-means clustering, defect features extracted from thermal images can be accurately identified and classified. This step involves in-depth analysis and processing of the thermal images to extract key feature information. Through comprehensive analysis and comparison of this feature information, various defect types can be effectively identified and classified, achieving automatic identification of surface defects on the plate and significantly improving the efficiency and accuracy of detection. This active heating detection technology can quickly identify and accurately classify defects such as micro-cracks, scratches, pits, and impurities on the plate surface, providing strong data support for subsequent repair and processing.

[0092] Furthermore, in the heat exchanger plate defect detection method disclosed in this embodiment, the collected temperature distribution data is processed to generate a thermal image of the plate surface. Infrared image enhancement is then used to adjust and sharpen edges, contours, and contrast in the thermal image, making it more suitable for human observation or machine processing. Histogram equalization, contrast-limited adaptive equalization, median filtering, mean filtering, and Gaussian filtering are commonly used to enhance the thermal image. In these thermal images, the temperature difference between normal and defective areas is clearly represented by different colors or grayscale values. Normal areas show a relatively uniform temperature distribution, while defective areas exhibit abnormal temperature distributions due to differences in material properties, thickness, or internal structure. These abnormalities are clearly visible in the thermal image as changes in color or grayscale. For example, at crack defects, due to reduced heat conduction efficiency, the greater the crack depth, the more significant the nearby temperature gradient, resulting in a localized temperature increase. This uneven temperature distribution reveals the location and characteristics of the defective area.

[0093] Furthermore, Peak Signal-to-Noise Ratio (PSNR) is commonly used for peak signal-to-noise ratio analysis of enhanced infrared images of metal material surfaces. In the heat exchanger plate defect detection method disclosed in this embodiment, step S3 further includes the following steps performed before step S31: S30, performing image enhancement processing on the thermal image and peak signal-to-noise ratio analysis on the thermal image: Wherein, PSNR is the peak signal-to-noise ratio, MSE is the mean square error between the output image and the thermal image, and MAX is the maximum pixel value of the thermal image.

[0094] Furthermore, in the heat exchanger plate defect detection method disclosed in this embodiment, the method further includes the following steps: S4, determining the defect type included in each temperature abnormality area on the plate according to preset rules, so as to obtain the defect status of the plate.

[0095] Furthermore, the main defects that may occur on the plates of a plate heat exchanger include cracks, corrosion, perforation, deformation, thinning, and scaling. In the heat exchanger plate defect detection method disclosed in this embodiment, the defect types include at least one of the following: crack defects, corrosion defects, scratch defects, pitting defects, and impurity defects. Cracks may be caused by inherent material defects, improper processing, or excessive mechanical stress during operation; corrosion is caused by the reaction of chemical components in the fluid with the plate material; perforation may be the result of further corrosion development; deformation may be caused by temperature changes or uneven clamping force; scaling is formed by the deposition of solid particles in the fluid on the plate surface and belongs to the category of impurity defects.

[0096] The defect identification described in this invention can combine abnormal region determination based on temperature differences with automatic classification by pattern recognition algorithms to form a parallel and complementary identification strategy.

[0097] First, in the thermal image obtained by active heating, since the heat exchanger plates conduct heat uniformly under normal conditions, the surface temperature distribution should be relatively continuous and smooth. If defects such as cracks, thinning, or inclusions exist, they will appear as localized areas of abnormal temperature in the thermal image. The system can preliminarily identify suspected defect areas by comparing the temperature gradient, uniformity, and local peak values ​​of normal and suspicious areas in the same image.

[0098] Furthermore, to improve the accuracy and automation of recognition, image processing algorithms can be used to extract key parameters such as geometric features, grayscale texture features, or thermal diffusion patterns of these regions, and input them into pattern recognition algorithms for classification. Preferably, classification models such as Support Vector Machines (SVM) or Convolutional Neural Networks (CNN) can be used to learn and discriminate the heat map features of the labeled regions, thereby achieving automatic classification and recognition of defect types (such as cracks, pits, thinning, impurities, etc.).

[0099] Both methods described above can operate independently or be deployed in parallel within the system architecture. The temperature difference comparison method offers advantages such as no training required and rapid response, enabling initial screening; while the pattern recognition algorithm boasts high recognition accuracy and strong classification capabilities, making it suitable for subsequent refined judgment. Combining the two can effectively improve the accuracy and robustness of the recognition system, making it suitable for complex or minor defect scenarios.

[0100] A second embodiment of the present invention discloses a storage medium storing a computer program, which, when executed by a processor, implements the steps of the heat exchanger plate defect detection method described above.

[0101] See Figure 3The third embodiment of the present invention discloses a heat exchanger plate defect detection device for heating heat exchanger plates, acquiring the actual temperature distribution characteristics of the heat exchanger plates, and detecting plate defects. It includes a support platform for stabilizing the entire heat exchanger plate defect detection device, and further includes a clamping device, a laser emitting device, an infrared image sensing device, and a controller mounted on the support platform. The clamping device is used to fix the plates; the laser emitting device is used to emit a beam of a specific wavelength onto the plates fixed by the clamping device to heat the plates to a target temperature; the infrared image sensing device is perpendicular to the clamping device and is used to acquire infrared thermal images of the plates; the controller connects the laser emitting device and the infrared image sensing device, and is used to control the laser emitting device to emit the beam, acquire the infrared thermal images, and apply any of the above-mentioned heat exchanger plate defect detection methods to detect plate defects. During active heating detection, the plates are precisely placed on a specially designed clamping frame, which is designed to firmly suspend and tension the plates, ensuring absolute stability of the plates throughout the detection process. The detection system consists of a high-precision semiconductor laser and an infrared image sensor, which work together to perform active heating detection. The semiconductor laser acts as an active heat source, emitting a beam of specific wavelength that evenly and concentratedly illuminates the surface of the plate, achieving rapid localized heating. This heat exchanger plate defect detection device has advantages such as non-contact operation, high sensitivity, and wide applicability.

[0102] Furthermore, the clamping device can be a clamping frame or an adaptive clamping frame. During active heating detection, the plate is precisely positioned on a specially designed clamping frame, which is designed to firmly suspend and tension the plate, ensuring absolute stability throughout the detection process. The detection system consists of a high-precision semiconductor laser and an infrared image sensor, which work together to complete the active heating detection task. The semiconductor laser acts as an active heat source, emitting a beam of specific wavelength that evenly and concentratedly irradiates the surface of the plate, achieving rapid localized heating.

[0103] See Figure 3 As the detection system moves precisely, the infrared image sensor synchronously captures infrared radiation signals from the plate surface in real time. These signals are caused by temperature differences on the plate surface due to active heating. The infrared image sensor converts this infrared radiation into electrical signals, completing the initial acquisition of temperature information from the plate surface. To ensure comprehensiveness and accuracy of the detection, the detection system moves downwards line by line from left to right according to a predetermined scanning sequence, ensuring that every part of the plate is scanned meticulously, thereby obtaining complete temperature distribution data.

[0104] Furthermore, to achieve faster heating of the plates while avoiding damage to the plates themselves, the laser emitting device in the heat exchanger plate defect detection device disclosed in this embodiment can be a semiconductor laser. More specifically, the semiconductor laser preferably operates in the near-infrared band, with typical operating wavelengths of 808nm, 850nm, or 980nm. Lasers in these bands have excellent material absorption characteristics, making them suitable for surface thermal excitation of heat exchanger plates, achieving rapid and uniform temperature rise, and meeting the dual requirements of laser energy transfer efficiency and temperature control accuracy in active heating detection processes.

[0105] Furthermore, in the heat exchanger plate defect detection device disclosed in this embodiment, the plate is tensioned and suspended by a clamping frame and its position is fixed by a position fixing hole 5. The size of the position fixing hole 5 is adjustable, and it has a certain height, which can adjust the distance between the plate and the detection module.

[0106] The working process of this heat exchanger plate defect detection device is as follows:

[0107] Step 1: Equipment preparation, including mounting a support platform, an adaptive clamping frame, and a detection unit consisting of a semiconductor laser and an infrared image sensor. The support platform stabilizes the entire detection system, the adaptive clamping frame ensures the plate is securely suspended and kept taut during detection, the semiconductor laser emits a specific wavelength beam to actively heat the plate surface, and the infrared image sensor monitors changes in infrared radiation on the plate surface in real time. The adaptive clamping frame ensures the plate remains stable during active heating, preventing vibration or displacement from affecting the detection results.

[0108] Step 2: Set the experimental parameters, including heating temperature, irradiation time, and ambient pressure. Specifically, set the heating temperature to 25℃, irradiation time to 5 minutes, and ambient pressure to 1 atmosphere.

[0109] Step 3: Activate the semiconductor laser to emit a beam of specific wavelength, uniformly heating the surface of the plate. Simultaneously, an infrared image sensor records the infrared radiation from the plate surface, converting it into an electrical signal to obtain the surface temperature information of the plate. See also... Figure 4 The arrows in the figure illustrate a scanning sequence for an infrared image sensor, from left to right and then from right to left, retaining 5% overlap area each time it moves down, ensuring that every area of ​​the plate is scanned meticulously to obtain comprehensive temperature distribution data, including defect and thinning information.

[0110] Step 4: Process the temperature distribution data obtained through active heating to generate a thermal image of the plate surface, and perform detailed analysis and processing to extract key feature information, including temperature differences in defects and thinned areas.

[0111] Step 5: Employ a dynamic threshold segmentation algorithm based on fuzzy C-means clustering to accurately identify and classify the defect features extracted from the thermal images of the plate surface, while also specially marking the thinned areas of the plate.

[0112] Step Six: Based on the analysis results of the dynamic threshold segmentation algorithm using fuzzy C-means clustering, classify and identify the defects and thinned areas on the plate surface, and record the data. Pay special attention to the identification of thinned areas. By analyzing abnormal changes in temperature distribution in the thermal image, identify the thinned areas of the plate and assess the degree of thinning.

[0113] Step 7: Based on the defect and thinning identification results, conduct appropriate evaluation and treatment of the plates (to ensure the reliability and performance of the heat exchanger plates).

[0114] This embodiment employs active heating technology to accurately identify defects in heat exchanger plates, paying particular attention to thinned areas to improve the comprehensiveness and accuracy of the inspection. It rapidly identifies and accurately classifies defects such as micro-cracks, scratches, pits, and impurities on the plate surface, while also effectively identifying plate thinning, providing support for subsequent repair and treatment.

[0115] By analyzing abnormal changes in temperature distribution in thermal images, the degree of plate thinning is determined and quantitatively evaluated. This detection method strictly controls the quality of heat exchanger plates, ensuring their operational efficiency and safety. Active heating technology, combined with infrared imaging analysis and a dynamic threshold segmentation algorithm based on fuzzy C-means clustering, provides an efficient and reliable solution for identifying defects and thinning in heat exchanger plates. This helps operators quickly and accurately identify maintenance areas, providing a scientific basis for the maintenance and replacement of heat exchanger plates.

[0116] It is understood that the above embodiments only illustrate preferred embodiments of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that for those skilled in the art, the above embodiments or technical features can be freely combined, and several modifications and improvements can be made without departing from the concept of the present invention. These all fall within the protection scope of the present invention. That is, the embodiments described "in some embodiments" can be freely combined with any of the embodiments above and below. Therefore, all equivalent transformations and modifications made within the scope of the claims of the present invention should fall within the scope of the claims of the present invention.

Claims

1. A method for detecting defects in heat exchanger plates, characterized in that, The method includes the following steps: S1. After the heat exchanger plates are heated to the target temperature according to the preset heating conditions, the actual temperature distribution characteristics of the heated plates are obtained. S2. Obtain the preset temperature distribution characteristics of the plate under the preset heating conditions; S3. Compare the actual temperature distribution characteristics of the plate with the preset temperature distribution characteristics, and obtain the comparison result. Determine the temperature anomaly area of ​​the plate based on the comparison result.

2. The method for detecting defects in heat exchanger plates according to claim 1, characterized in that, Step S1 is as follows: Acquire a thermal image of the plate, and obtain the actual temperature distribution characteristics from the thermal image.

3. The method for detecting defects in heat exchanger plates according to claim 1, characterized in that, In step S2, obtaining the preset temperature distribution characteristics of the plate under the preset heating conditions includes: A heat conduction model of the plate is constructed based on the preset heating conditions to obtain the preset temperature distribution characteristics of the plate under the preset heating conditions.

4. The method for detecting defects in heat exchanger plates according to claim 3, characterized in that, The method further includes the following steps before performing step S1: S0. Control the emission of continuous wave laser to heat the plate according to the preset heating conditions; In step S1, the preset heating conditions include: initial temperature, target temperature, heating time, and ambient pressure.

5. The method for detecting defects in heat exchanger plates according to claim 4, characterized in that, In step S2, constructing a heat conduction model of the plate based on the preset heating conditions to obtain the preset temperature distribution characteristics of the plate under the preset heating conditions includes: Based on the principle of active heating, combined with boundary conditions and heat conduction equations, the influence of different characteristics on temperature distribution during the heating process is simulated to obtain the preset temperature distribution characteristics of the plate under the preset heating conditions.

6. The method for detecting defects in heat exchanger plates according to claim 2, characterized in that, Step S3 includes: S31. Using the Canny edge detection algorithm, the thermal image is divided into several partitions; S32. The thermal image is clustered using a fuzzy C-means clustering algorithm to identify and classify several of the partitions and determine the temperature anomaly areas of the plate.

7. The method for detecting defects in heat exchanger plates according to claim 6, characterized in that, Step S3 also includes the following steps performed prior to step S31: S30. Perform image enhancement processing on the thermal image, and perform peak signal-to-noise ratio analysis on the thermal image: Wherein, PSNR is the peak signal-to-noise ratio, MSE is the mean square error between the output image and the thermal image, and MAX is the maximum pixel value of the thermal image.

8. The method for detecting defects in heat exchanger plates according to claim 1, characterized in that, The method also includes the following steps: S4. Determine the defect type of each temperature abnormality area on the plate according to preset rules to obtain the defect status of the plate. The defect types include at least one of crack defects, corrosion defects, scratch defects, pit defects, and impurity defects.

9. A storage medium storing a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the heat exchanger plate defect detection method according to any one of claims 1 to 8.

10. A heat exchanger plate defect detection device, used to heat the heat exchanger plates, obtain the actual temperature distribution characteristics of the heat exchanger plates, and detect defects in the plates, characterized in that, The device includes a support platform for stabilizing the entire heat exchanger plate defect detection apparatus, and also includes a clamping device, a laser emitting device, an infrared image sensing device, and a controller mounted on the support platform. The clamping device is used to fix the plate; The laser emitting device is used to emit a beam of a specific wavelength onto the plate fixed by the clamping device, so as to heat the plate to the target temperature; The infrared image sensing device is arranged perpendicularly to the clamping device that holds the plate, and is used to acquire infrared thermal images of the plate. The controller is connected to the laser emitting device and the infrared image sensing device, and is used to control the laser emitting device to emit the light beam, and also to acquire the infrared thermal image and apply the heat exchanger plate defect detection method according to any one of claims 1 to 8 to detect defects in the plate.

Images