A method for detecting defects in carbon-based composite coatings of metal bipolar plates of PEM fuel cells

Abstract

The present application relates to the technical field of defect detection, and discloses a PEM fuel cell metal bipolar plate carbon-based composite coating defect detection method, which comprises the following steps: applying a stepwise thermal excitation to the bipolar plate carbon-based composite coating to obtain a plurality of temperature step points corresponding to the bipolar plate carbon-based composite coating; after each temperature step point is stabilized, generating an optical response data sequence according to the optical response data at each temperature step point; analyzing a thermal distortion coefficient sequence corresponding to the temperature step points based on reference optical characteristic data and the optical response data sequence; performing differential processing on the thermal distortion coefficient sequence to obtain a gradient change curve, and analyzing the inflection point characteristics in the gradient change curve; analyzing the defect evolution behavior of the bipolar plate carbon-based composite coating according to the inflection point characteristics, and detecting the defect type and defect grade of the bipolar plate carbon-based composite coating through the defect evolution behavior. The present application can improve the accuracy of PEM fuel cell metal bipolar plate carbon-based composite coating defect detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of defect detection, and particularly relates to a defect detection method for a carbon-based composite coating of a PEM fuel cell metal bipolar plate. BACKGROUND

[0002] The carbon-based composite coating of the PEM fuel cell metal bipolar plate is prone to defects such as microcracks and interface peeling during preparation and use, which can significantly reduce the efficiency and service life of the fuel cell.

[0003] In the prior art, the defect detection method mainly relies on single optical detection or electrochemical testing, such as visible light imaging or electrochemical impedance spectroscopy. These methods have obvious technical defects: single optical detection cannot effectively identify interface bonding state defects, and electrochemical testing cannot accurately locate the defect position, and both are greatly affected by environmental interference, resulting in low defect detection rate and high misjudgment rate. SUMMARY

[0004] The present application provides a defect detection method for a carbon-based composite coating of a PEM fuel cell metal bipolar plate, which mainly aims to solve the problem of low accuracy in defect detection of the carbon-based composite coating of the PEM fuel cell metal bipolar plate.

[0005] To achieve the above purpose, the present application provides a defect detection method for a carbon-based composite coating of a PEM fuel cell metal bipolar plate, which comprises:

[0006] Optically scanning the surface area of the preset bipolar plate carbon-based composite coating at a preset reference temperature to obtain reference optical characteristic data;

[0007] Applying a stepwise thermal excitation to the bipolar plate carbon-based composite coating to obtain a plurality of temperature step points corresponding to the bipolar plate carbon-based composite coating;

[0008] After each temperature step point is stabilized, generating an optical response data sequence according to the optical response data at each temperature step point;

[0009] Based on the reference optical characteristic data and the optical response data sequence, analyzing a thermal distortion coefficient sequence corresponding to the temperature step points;

[0010] Differential processing the thermal distortion coefficient sequence to obtain a gradient change curve, and analyzing the inflection point characteristics in the gradient change curve;

[0011] Analyzing the defect evolution behavior of the bipolar plate carbon-based composite coating according to the inflection point characteristics, and detecting the defect type and defect grade of the bipolar plate carbon-based composite coating through the defect evolution behavior.

[0012] Optionally, the surface area of the preset bipolar plate carbon-based composite coating is optically scanned at a preset reference temperature to obtain reference optical characteristic data, including:

[0013] The bipolar plate carbon-based composite coating is placed on a temperature control platform, and the temperature control platform is adjusted to the preset reference temperature;

[0014] Based on the reference temperature, the optical scanning unit is controlled to perform full-coverage scanning on the surface area according to a preset serpentine scanning path, while recording the spatial coordinates of each scanning point;

[0015] After the full-coverage scanning is completed, the reflected light intensity data of the surface area at multiple target wavebands is collected;

[0016] The spatial coordinates of each scanning point are associated and integrated with the reflected light intensity data to generate reference optical characteristic data.

[0017] Optionally, the bipolar plate carbon-based composite coating is subjected to a stepwise thermal excitation to obtain multiple temperature step points corresponding to the bipolar plate carbon-based composite coating, including:

[0018] A nonlinear temperature increment sequence is determined according to the material heat capacity and thermal conductivity of the bipolar plate carbon-based composite coating, and the nonlinear temperature increment sequence is taken as a target temperature sequence;

[0019] According to the target temperature sequence, an infrared heating source is controlled to heat the bipolar plate carbon-based composite coating according to a power loading strategy of fast first and slow later;

[0020] During the heating process, the actual temperature of the surface area of the bipolar plate carbon-based composite coating is monitored in real time, and when the actual temperature reaches and stabilizes at any step point in the target temperature sequence, the step point is recorded as a stable temperature step point;

[0021] All step parameters in the target temperature sequence are traversed to obtain multiple temperature step points.

[0022] Optionally, after each temperature step point stabilizes, optical response data at each temperature step point is generated to generate an optical response data sequence, including:

[0023] After each temperature step point stabilizes, optical response data corresponding to each temperature step point is collected according to the serpentine scanning path and a preset scanning waveband;

[0024] Based on the spatial coordinates, the optical response data is point-by-point registered with the reference optical characteristic data;

[0025] calculating, according to the registered data, a reflectivity change amount of each spatial point at each wave band with respect to a reference temperature, and generating a temperature step point corresponding optical response change data set according to the reflectivity change amount;

[0026] sequentially arranging, in order of temperature step from low to high, the optical response change data sets at all temperature step points to generate an optical response data sequence.

[0027] Optionally, the analysis of the thermal distortion coefficient sequence corresponding to the temperature step points based on the reference optical characteristic data and the optical response data sequence comprises:

[0028] determining a statistical distribution feature of the reflectivity change amount corresponding to each temperature step point based on the reference optical characteristic data and the optical response data sequence;

[0029] analyzing a stress coupling factor of the bipolar plate carbon-based composite coating, and mapping the statistical distribution feature to a distortion physical quantity of a coating thermal mechanical stress response corresponding to each temperature step point according to the stress coupling factor;

[0030] sequentially arranging the distortion physical quantity according to the temperature order of the temperature step points to obtain a thermal distortion coefficient sequence.

[0031] Optionally, the analysis of the stress coupling factor of the bipolar plate carbon-based composite coating comprises:

[0032] establishing a theoretical constitutive equation for correlating macroscopic optical response and microscopic interface stress based on a microstructure model of the bipolar plate carbon-based composite coating material;

[0033] analyzing optical response data and stress response data of a preset standard sample data under thermal excitation;

[0034] performing stress coupling analysis on the optical response data and the stress response data by using the theoretical constitutive equation to obtain a target numerical range of the stress coupling factor;

[0035] selecting the stress coupling factor of the bipolar plate carbon-based composite coating from the target numerical range according to a composition parameter of the bipolar plate carbon-based composite coating.

[0036] Optionally, the differential processing of the thermal distortion coefficient sequence to obtain a gradient change curve comprises:

[0037] identifying a local fluctuation feature in the thermal distortion coefficient sequence, and adaptively determining an order and a step length of a numerical differential algorithm based on an amplitude-frequency characteristic of the local fluctuation feature;

[0038] perform order processing on the thermal distortion coefficient sequence based on the order and step length convolution smoothing differential algorithm to obtain a first derivative sequence;

[0039] take the first derivative sequence as a preliminary gradient sequence and perform normalization processing on the preliminary gradient sequence based on a physical interval of a temperature step point;

[0040] fit the preliminary gradient sequence after normalization processing in a preset temperature-gradient coordinate system to generate a gradient change curve.

[0041] Optionally, the inflection point characteristics in the gradient change curve are analyzed, including:

[0042] calculate a multi-scale curvature of the gradient change curve, determine curvature extreme points under different scale parameters through the multi-scale curvature, and screen preliminary candidate inflection points according to the curvature extreme points;

[0043] identify a neighboring area of the preliminary candidate inflection points and analyze gradient statistical characteristics of the neighboring area;

[0044] test pseudo inflection points in the preliminary candidate inflection points according to the gradient statistical characteristics, and screen true inflection points based on the preliminary candidate inflection points after testing;

[0045] extract temperature data and inflection point intensity corresponding to the true inflection points, and combine the temperature data and the inflection point intensity into inflection point characteristics.

[0046] Optionally, the defect evolution behavior of the bipolar plate carbon-based composite coating is analyzed according to the inflection point characteristics, including:

[0047] construct a defect evolution phase diagram according to preset inflection point temperature attributes and inflection point intensity attributes;

[0048] project the inflection point characteristics into the defect evolution phase diagram, and judge a stable state, a slow evolution state or an accelerated evolution state of the bipolar plate carbon-based composite coating according to a belonging area of the inflection point characteristics in the defect evolution phase diagram;

[0049] for the inflection points in the slow evolution state or the accelerated evolution state, calculate a Euclidean distance between the inflection points and a defect evolution path template in the defect evolution phase diagram, and analyze an evolution trend and an evolution level of the bipolar plate carbon-based composite coating according to the Euclidean distance;

[0050] determine the defect evolution behavior of the bipolar plate carbon-based composite coating based on the evolution trend and the evolution level.

[0051] Optionally, the defect type and the defect level of the bipolar plate carbon-based composite coating are detected through the defect evolution behavior, including:

[0052] mapping the stable state to material inherent heterogeneity, mapping the slow evolution state to micro-crack initiation defect, and mapping the accelerated evolution state to interface bonding failure defect;

[0053] identifying the defect type corresponding to the defect evolution behavior based on the mapping relationship library;

[0054] calculating the inflection point characteristic coordinates of the defect type in the defect evolution phase diagram, analyzing the minimum Euclidean distance between the defect type and a preset standard evolution path, and calculating the deviation amplitude of the inflection point characteristics in the direction perpendicular to the standard evolution path;

[0055] grading the bipolar plate carbon-based composite coating according to the minimum Euclidean distance and the deviation amplitude under the defect type, to obtain a defect grade.

[0056] The embodiment of the present application establishes a coating initial state benchmark through benchmark optical scanning, provides a basis for subsequent change detection; simulates the thermal stress environment of the coating during work through a stepped thermal excitation, induces defect response; generates an optical response sequence through data processing of space-time alignment, ensures data consistency; converts optical signals into physical defect features through the quantification of thermal distortion coefficient; identifies the critical state of the defect through inflection point analysis of the gradient change curve; and realizes accurate determination of the defect type and grade through defect evolution behavior mapping. Therefore, the PEM fuel cell metal bipolar plate carbon-based composite coating defect detection method proposed in the present application can solve the problem of low accuracy in PEM fuel cell metal bipolar plate carbon-based composite coating defect detection. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 A flowchart of the PEM fuel cell metal bipolar plate carbon-based composite coating defect detection method provided by an embodiment of the present application is shown.

[0058] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0059] It should be understood that the specific embodiments described herein are merely intended to explain the present application, and are not intended to limit the present application.

[0060] The embodiment of the present application provides a PEM fuel cell metal bipolar plate carbon-based composite coating defect detection method. The execution subject of the PEM fuel cell metal bipolar plate carbon-based composite coating defect detection method includes but is not limited to at least one of electronic devices such as a server, a terminal and the like which can be configured to execute the method provided by the embodiment of the present application. In other words, the PEM fuel cell metal bipolar plate carbon-based composite coating defect detection method can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to a single server, a server cluster, a cloud server or a cloud server cluster and the like. The server can be a stand-alone server, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks (CDN), and big data and artificial intelligence platforms and the like basic cloud computing services.

[0061] Referring to Figure 1 Fig. 1 is a flowchart of a PEM fuel cell metal bipolar plate carbon-based composite coating defect detection method provided by an embodiment of the present application. In the embodiment, the PEM fuel cell metal bipolar plate carbon-based composite coating defect detection method includes the following steps.

[0062] S1, performing optical scanning on a surface area of a preset bipolar plate carbon-based composite coating at a preset reference temperature to obtain reference optical characteristic data.

[0063] In the embodiment of the present application, the reference temperature refers to a stable temperature environment of the coating without thermal stress interference, which is usually set to room temperature 25 degrees Celsius; the bipolar plate carbon-based composite coating refers to a composite structure with metal as a matrix and carbon-based material as a coating; and the reference optical characteristic data refers to a set of multi-band reflected light intensity and spatial coordinates of the coating at the reference temperature.

[0064] In the embodiment of the present application, the optical scanning on the surface area of the preset bipolar plate carbon-based composite coating at the preset reference temperature to obtain the reference optical characteristic data includes the following steps.

[0065] Placing the bipolar plate carbon-based composite coating on a temperature control platform, and adjusting the temperature control platform to the preset reference temperature;

[0066] Based on the reference temperature, controlling an optical scanning unit to perform full-coverage scanning on the surface area according to a preset serpentine scanning path, and recording spatial coordinates of each scanning point;

[0067] After the full-coverage scanning is completed, collecting reflected light intensity data of the surface area at a plurality of target wave bands;

[0068] The spatial coordinates of each scanning point are associated and integrated with the reflected light intensity data to generate reference optical feature data.

[0069] In detail, the bipolar plate carbon-based composite coating to be detected is fixed flat on the ceramic stage of the temperature control platform, ensuring that the coating surface is parallel to the platform surface (parallelism error ≤ 0.02 mm), and avoiding the subsequent spatial coordinate offset of the scanning point due to the inclination of the coating. Then, the PID temperature control module of the temperature control platform is started, and the preset reference temperature 25℃ is input. The temperature control platform adjusts the temperature through the cooperation of the heating sheet (power 50W) and the cooling fan: in the initial stage, the heating sheet operates at full power, and when the platform temperature reaches 23℃, the PID algorithm automatically reduces the heating power to 10W, entering the constant temperature fine tuning stage; at the same time, the temperature data is collected in real time by the platinum resistance temperature sensor (accuracy ± 0.05℃) built-in the platform, and fed back to the control module to correct the heating power, until the platform temperature stabilizes at 25℃±0.1℃, and the continuous stable time is ≥5 minutes (to ensure that the internal temperature of the coating is consistent with the surface temperature, and avoid the distortion of the reference data due to temperature gradient), then the PID high-precision temperature control makes the reference data have repeatability. After the temperature control platform stabilizes at 25℃, the displacement driving module (such as a stepper motor with a step angle of 1.8° and a reduction ratio of 1:100) of the optical scanning unit is started, and the scanning is performed according to the snake-shaped scanning path: the scanning starting point is set as the upper left corner of the coating surface (spatial coordinates X=0mm, Y=0mm), and moves along the positive direction of X axis, and collects 1 scanning point (corresponding to 1 pixel column of the linear array CCD camera) every 0.1mm of movement. When moving to X=100mm (the upper right corner of the coating), move 0.1mm in the Y axis direction (along the positive direction of Y axis), then move along the negative direction of X axis, and repeat the trajectory of X axis back and forth + Y axis progressive, until the entire coating surface is covered. In the scanning process, the encoder of the displacement driving module records the X, Y axis spatial coordinates of each scanning point, and the coordinate data is stored synchronously with the acquisition trigger signal of the scanning unit (trigger interval 0.005 seconds, to ensure that the coordinates correspond to the subsequent light signals one by one), and the coordinate data is bound with the light signal acquisition time stamp of the point, solving the defects of missing or redundant data in some areas due to the existence of blind area or overlap in the scanning path, covering the entire surface and avoiding data redundancy.

[0070] Specifically, when the serpentine scanning path covers the entire coating surface, the optical scanning unit switches to a multi-waveband light signal acquisition mode: through an electrically driven filter wheel (switching speed ≤ 0.1 s / filter), the visible light filter of 400-760 nm and the near-infrared filter of 800-1100 nm are switched in turn, and for each target waveband, the linear array CCD camera is controlled to perform secondary scanning on the coating surface (the scanning path is consistent with the step of controlling the optical scanning unit to perform full coverage scanning on the surface area according to the preset serpentine scanning path, so as to ensure that each scanning point has data under two wavebands). During the acquisition process, the spectrometer synchronously records the reflection intensity of each scanning point at the corresponding waveband: for example, the reflection intensity of the 500th scanning point is 2500 counts in the visible light waveband, and the reflection intensity of the scanning point is 1800 counts in the near-infrared waveband. At the same time, the ambient light interference is eliminated through a dark current correction algorithm (the actual acquisition value is reduced by the dark current value of 50 counts when there is no light source), so as to ensure the accuracy of the reflection intensity data, and the visible light waveband can capture macro defects such as scratches and depressions on the coating surface, and the near-infrared waveband can detect the interface separation between the carbon matrix and the composite particles in the coating. The X-Y coordinates of each scanning point and the visible light reflection intensity-near-infrared reflection intensity are bound to form the characteristic data of a single scanning point (for example, X=50mm, Y=0.49mm, visible light intensity 2450 counts, near-infrared intensity 1750 counts), and then the characteristic data of all scanning points are imported into a matrix database to obtain the reference optical characteristic data.

[0071] Further, by thermal excitation, the temperature fluctuation of the fuel cell during operation is simulated, and the optical characteristic change of the coating at different temperatures must be compared with the characteristic at the same reference temperature, so as to eliminate the interference of the initial state difference on the thermal change.

[0072] S2, a stepwise thermal excitation is applied to the carbon-based composite coating of the bipolar plate to obtain a plurality of temperature step points corresponding to the carbon-based composite coating of the bipolar plate.

[0073] In the embodiment of the present application, the stepwise thermal excitation is a method of gradually increasing the temperature of the coating according to a preset temperature step sequence and stably inputting heat at each step, so that thermal shock damage to the coating caused by sudden temperature rise can be avoided, and the response data of the coating at different temperatures can be obtained. The temperature step point is a specific temperature value at which the temperature of the coating reaches and stabilizes in the stepwise thermal excitation, and each step point corresponds to a stable thermal environment for collecting the optical response data of the coating at the temperature.

[0074] In the embodiment of the present application, the step of applying stepwise thermal excitation to the carbon-based composite coating of the bipolar plate to obtain a plurality of temperature step points corresponding to the carbon-based composite coating of the bipolar plate comprises:

[0075] determine a nonlinear temperature increasing sequence according to the material heat capacity and heat conductivity of the bipolar plate carbon-based composite coating, and take the nonlinear temperature increasing sequence as a target temperature sequence;

[0076] According to the target temperature sequence, control the infrared heating source to heat the bipolar plate carbon-based composite coating in a power loading strategy of fast first and slow later;

[0077] During the heating process, the actual temperature of the surface area of the bipolar plate carbon-based composite coating is monitored in real time, and when the actual temperature reaches and stabilizes at any step point in the target temperature sequence, the step point is recorded as a stable temperature step point;

[0078] Traverse all step parameters in the target temperature sequence to obtain multiple temperature step points.

[0079] In detail, the material heat capacity of the coating is measured by a differential scanning calorimeter, and the heat conductivity is measured by a laser flash method. According to the two parameters, it is known that the heat capacity and heat conductivity of the coating change gently in the low temperature interval (25-80℃), and the temperature response speed is fast; in the high temperature interval (80-200℃), the heat capacity increases and the heat conductivity decreases, and the temperature response speed becomes slow (it takes a longer time to reach stability). Based on the above characteristics, a nonlinear temperature increasing sequence is formulated using the principle of low temperature density and high temperature sparsity: taking 25℃ as the starting point, the temperature interval of the low temperature interval (25-80℃) is 25℃ (25℃→50℃→80℃), and the temperature interval of the high temperature interval (80-160℃) is 40℃ (80℃→120℃→160℃), and the target temperature sequence is finally determined as [25℃ (reference), 50℃, 80℃, 120℃, 160℃], which not only ensures the detection accuracy of the low temperature interval, but also avoids the damage of the coating caused by frequent temperature rise in the high temperature interval. An infrared heating source (power range 0-1000W, radiation wavelength 3-5μm) is fixed 10cm above the coating to ensure that the heating spot completely covers the surface of the coating. For each step point (50℃, 80℃, 120℃, 160℃) in the target temperature sequence, the infrared heating source is controlled to heat the bipolar plate carbon-based composite coating using a PWM power regulation strategy of fast first and slow later.

[0080] Exemplarily, taking the first step point 50℃ as an example: in the initial stage (current temperature 25℃→45℃), the infrared heating source is heated at a power of 600W (duty cycle 60%) to quickly raise the temperature, and the heating rate of the coating under this power is about 5℃ / min (based on the heat capacity 1.2J / (g·℃)), wherein the power is calculated as , then is the power, is the mass of the coating, is the heat capacity, is the temperature difference between the initial temperature and the target temperature, The time interval experienced by the temperature of the carbon-based composite coating of the electrode plate changing from the initial temperature to the target temperature is amplified by 10 times because the heating source needs to heat the temperature control platform at the same time; when the coating temperature reaches 45℃ (close to 50℃, difference of 5℃), switch to 100W power (duty cycle of 10%) for slow heating, and the heating rate is reduced to 0.8℃ / min to avoid overheating. For the high temperature step point 160℃: use 800W power (duty cycle of 80%) for rapid heating (heating rate of 3℃ / min) in the initial stage (120℃→155℃); switch to 150W power (duty cycle of 15%) when close to 160℃ (difference of 5℃), and the heating rate is reduced to 0.5℃ / min to ensure that the temperature reaches the target value smoothly.

[0081] Specifically, the actual temperature of the coating surface is collected in real time by using an infrared temperature measuring instrument (resolution 0.01℃, measurement distance 10cm), the collection frequency is 1 time / second, and the temperature data is transmitted to the control module. When heating to the target step point (such as 50℃), the control module judges whether the actual temperature reaches 50℃±0.2℃, if it does, it enters the stable monitoring stage: continuously collects temperature data for 3 minutes (180 times), calculates the standard deviation of temperature in 3 minutes, if the standard deviation ≤0.1℃, it is determined that the coating temperature has stabilized, and records 50℃ as the temperature step point that has reached stability; if the standard deviation >0.1℃, the power of the infrared heating source is adjusted (such as from 100W to 105W) until the temperature standard deviation in 3 minutes ≤0.1℃, and then the heating, monitoring and stability judgment are performed in turn for the four step points 50℃, 80℃, 120℃ and 160℃ in the target temperature sequence: such as 50℃: heating for 5 minutes to reach the target value, and recording after 3 minutes of stability; 80℃: heating for 6 minutes to reach the target value, and recording after 3 minutes of stability; finally, all step parameters are traversed to obtain the temperature step points that have reached stability. By traversing all step points of the nonlinear sequence, the full range from room temperature to high temperature is covered, providing complete temperature dimension data for subsequent analysis of defect evolution of the coating at different working temperatures.

[0082] Further, the temperature step point is the temperature carrier for generating the optical response data sequence, and if the temperature of each step point is not ensured to be stable, the collected optical data will have false changes due to temperature fluctuations (such as the reflectivity of the same scanning point fluctuating continuously when the temperature is not stable, which cannot be determined whether it is caused by temperature or interference). Therefore, temperature stability is a prerequisite for accurate collection of optical response data, and the two together constitute the temperature-optical correspondence.

[0083] S3、In each temperature step point, the optical response data sequence is generated according to the optical response data at each temperature step point.

[0084] In the embodiment of the present application, the optical response data sequence is an ordered set formed by arranging the optical response change data sets corresponding to all temperature step points in order from low to high temperature, which can intuitively reflect the continuous trend of the change of the optical properties of the coating with temperature.

[0085] In the embodiment of the present application, the optical response data sequence is generated according to the optical response data at each temperature step point after stabilization, comprising:

[0086] After stabilization at each temperature step point, the optical response data corresponding to each temperature step point is collected according to the serpentine scanning path and the preset scanning waveband;

[0087] The optical response data and the reference optical characteristic data are point-by-point registered based on the spatial coordinates;

[0088] The reflectivity change amount of each spatial point at each waveband with respect to the reference temperature is calculated according to the registered data, and the optical response change data set corresponding to the temperature step point is generated according to the reflectivity change amount;

[0089] The optical response change data sets at all temperature step points are sequentially arranged in time according to the temperature step from low to high, and the optical response data sequence is generated.

[0090] In detail, after a certain temperature step point reaches stability, the optical scanning unit is started to follow the serpentine scanning path (starting point X=0mm, Y=0mm, X-axis reciprocating + Y-axis progressive, scanning interval 0.1mm) in S1, and at the same time, the optical response data is collected by switching to the preset two target wavebands (400-760nm visible light waveband, 800-1100nm near-infrared waveband). During the collection process, the line array CCD camera collects the reflected light intensity at two wavebands for each scanning point, for example, the scanning point with spatial coordinates X=50mm, Y=0.49mm has a visible light reflection intensity of 2600 counts at 80℃. All scanning points of the temperature step point are collected one by one to obtain the visible light and near-infrared optical response original data corresponding to 80℃, and the same scanning point is ensured to have the same optical data collection position at different temperatures by multiplexing the serpentine path. The optical response data of the current temperature step point is bound to the reference optical characteristic data by taking the X-Y spatial coordinates of each scanning point as the unique identifier.

[0091] For example, taking a scanning point with X=50mm and Y=0.49mm as an example, the reference data for this point is 2450 counts of visible light intensity and 1750 counts of near-infrared intensity. At 80℃, the optical response data for this point is 2600 counts of visible light intensity and 1900 counts of near-infrared intensity. Through coordinate matching, the two sets of data are associated as a correspondence between coordinates (50, 0.49) - reference (2450, 1750) - 80℃ (2600, 1900). This operation is performed on all scanning points one by one. If an abnormal coordinate matching occurs (such as missing coordinates of individual scanning points), the average of the reference data of the four adjacent scanning points is used as a substitute to ensure that the registration coverage reaches 100%.

[0092] Specifically, the formula for calculating the change in reflectance is as follows: ,in The change in reflectivity Current temperature The intensity of reflection, Using the baseline temperature reflectance intensity, the reflectance change is calculated for each scan point in both wavelength bands. The coordinates of the scan point and the reflectance change in both wavelength bands are recorded as a single data record. After calculating the reflectance for all scan points at a specific temperature step, the results are imported into a MySQL database to form an optical response change dataset for that temperature step. The dataset fields include X-coordinate, Y-coordinate, visible light reflectance change, and near-infrared reflectance change. The optical response change datasets corresponding to the temperature step points are extracted and arranged sequentially from low to high temperature to obtain different data blocks. For example, the first data block is the 50℃ optical response change dataset (containing the reflectance change in both wavelength bands for all scan points at that temperature), the second is the 80℃ optical response change dataset, and so on. These different data blocks are then sequentially integrated into a three-dimensional data sequence (dimension: number of scan points × number of wavelength bands × number of temperature steps). This sequence is the optical response data sequence.

[0093] Furthermore, without arranging the reflectance changes at multiple temperature steps in sequence, it is impossible to obtain the variation of reflectance with temperature, and thus impossible to deduce the evolution of thermal distortion with temperature. Therefore, multiple temperature steps are a prerequisite for realizing quantitative analysis of thermal distortion.

[0094] S4. Analyze the thermal distortion coefficient sequence corresponding to the temperature step point based on the reference optical feature data and the optical response data sequence.

[0095] In this embodiment of the invention, the thermal distortion coefficient sequence is an ordered set formed by arranging the thermal distortion coefficients calculated at each temperature step point in order from low to high temperature. This sequence can directly reflect the degree of change of the thermal mechanical stress of the coating with temperature.

[0096] In the embodiment of the present application, the sequence of thermal distortion coefficients corresponding to the temperature step points is analyzed based on the reference optical feature data and the optical response data, comprising:

[0097] The statistical distribution characteristics of the reflectivity variation corresponding to each temperature step point are determined based on the reference optical feature data and the optical response data sequence;

[0098] The stress coupling factor of the bipolar plate carbon-based composite coating is analyzed, and the statistical distribution characteristics are mapped to the distortion physical quantity of the coating thermal mechanical stress response corresponding to each temperature step point according to the stress coupling factor;

[0099] The distortion physical quantity is sorted in the temperature order of the temperature step points to obtain the sequence of thermal distortion coefficients.

[0100] In detail, for each temperature step point in the optical response data sequence, the reflectivity variation of all scanning points in the near-infrared band (the near-infrared band is more sensitive to the stress inside the coating) is extracted, and the mean (μ) and standard deviation (σ) of the reflectivity variation corresponding to each temperature step point are calculated using a statistical analysis algorithm, and then μ+σ of each temperature step point is taken as the statistical distribution characteristics of the temperature.

[0101] For example, 50℃: the near-infrared reflectivity variation of all scanning points is traversed, and the mean μ1=0.045 and the standard deviation σ1=0.007 are calculated (indicating that the overall reflectivity variation of the coating is small at this temperature, and the variation of each point is uniform); 80℃: the mean μ2=0.086 and the standard deviation σ2=0.009 are calculated (the overall reflectivity variation increases with the increase of temperature, and the dispersion degree slightly rises); 120℃: the mean μ3=0.120 and the standard deviation σ3=0.015 are calculated (the reflectivity variation further increases, and the dispersion degree significantly rises, indicating that stress differences begin to appear in some areas); 160℃: the mean μ4=0.180 and the standard deviation σ4=0.022 are calculated (the overall variation is significant at high temperature, and the dispersion degree is the largest, indicating that the unevenness of the stress distribution of the coating is intensified).

[0102] In the embodiment of the present application, the stress coupling factor is a coefficient representing the correlation degree between the optical response of the bipolar plate carbon-based composite coating and the micro-interface stress, and the value of the stress coupling factor is determined by the composition of the coating material (such as the proportion of carbon matrix and composite particles) and the microstructure.

[0103] In the embodiment of the present application, the stress coupling factor of the bipolar plate carbon-based composite coating is analyzed, comprising:

[0104] Based on the microstructure model of the bipolar plate carbon-based composite coating material, a theoretical constitutive equation for correlating the macroscopic optical response and the micro-interface stress is established;

[0105] analyzing optical response data and stress response data of preset standard sample data under thermal excitation;

[0106] performing stress coupling analysis on the optical response data and the stress response data by using the theoretical constitutive equation to obtain a target numerical range of a stress coupling factor;

[0107] selecting the stress coupling factor of the bipolar plate carbon-based composite coating from the target numerical range according to the component parameters of the bipolar plate carbon-based composite coating.

[0108] In detail, based on a coating microstructure model (a mixed packing model with carbon particles of 200 nm in diameter and Al2O3 particles of 50 nm in diameter), a linear coupling relationship between the change in optical reflectivity and the interfacial stress tensor is derived by applying the principles of continuum mechanics, a basic framework is established by Fourier heat conduction equation and optical scattering theory, and a stress-optical coefficient is introduced as a bridge parameter to establish a theoretical constitutive equation: wherein is a thermal stress generated at the micro interface, is the change in reflectivity, is the initial reflectivity at the reference temperature, is the stress coupling factor.

[0109] Specifically, the standard sample refers to a coating sample with known defect type and interfacial bonding state, the standard sample is placed on a temperature control platform, the same stepwise thermal excitation as the sample to be tested is applied, the optical data are collected by using an optical scanning system, and the stress data are collected by using a stress sensor. The data collection frequency is synchronized with the thermal excitation to ensure the time alignment of the optical and stress data at each temperature step point. The change in reflectivity in the optical response data is taken as the dependent variable, and the stress value in the stress response data is taken as the independent variable to construct the equation Then, the stress coupling factor k in the theoretical constitutive equation is solved by using the least square method or the Bayesian inversion algorithm. For each standard sample, the fitting value of k is calculated, and the distribution of k values of all samples is counted, for example, the mean and standard deviation are calculated to determine the target numerical range of k (for example, k is between 0.1 and 0.5).

[0110] Furthermore, the compositional parameters include the coating's carbon content, thickness, and dopant element ratio. The actual compositional parameters of the coating under test are obtained through energy dispersive spectroscopy (EDS) analysis or thickness measurement. These parameters are then compared with a standard sample library for similarity, using methods such as Euclidean distance or machine learning classification algorithms to find the best-matching standard sample. Finally, based on the k-value of the matching sample within a target range, interpolation or weighted averaging is performed to select the stress coupling factor of the coating under test. For example, if the coating under test has a high carbon content and a large thickness, a k-value close to the upper limit of the range is selected. This personalized parameter selection adapts to the characteristics of different coatings, improving the universality and accuracy of the detection method.

[0111] In this embodiment of the invention, the stress coupling factor and statistical distribution characteristics are substituted into the calculation formula of the distortion physical quantity characterizing the thermomechanical stress response of the coating, i.e. ,in For the first Temperature step points The thermal distortion coefficient is below. For the first Temperature step points The mean of the change in reflectivity, For the first Temperature step points The standard deviation of the change in reflectivity is used, and k is the stress coupling factor. This yields the distortion physical quantity corresponding to each temperature step point, which is then arranged in ascending order of temperature to form a thermal distortion coefficient sequence. After the sequence is arranged, its validity is verified: if the difference in distortion coefficients between two adjacent temperature step points exceeds 30% of the previous temperature, the sequence is considered valid; if an abnormal difference occurs (such as a decrease), the optical response data for that temperature is re-acquired to ensure the physical rationality of the sequence. Through the ordered distortion coefficient sequence, the increasing trend of thermal stress in the coating with increasing temperature is visually presented, providing continuous mechanical data for subsequent gradient analysis.

[0112] Furthermore, the thermal distortion coefficient sequence is the only data source for obtaining the gradient change curve through differential processing. If the thermal distortion coefficient sequence is not generated, only discrete distortion coefficients can be obtained, and the rate of change cannot be calculated.

[0113] S5. Differentiate the thermal distortion coefficient sequence to obtain the gradient change curve, and analyze the inflection point characteristics in the gradient change curve.

[0114] In this embodiment of the invention, the gradient change curve is a curve formed by fitting the rate of change (gradient value) of the distortion coefficient obtained by differential processing with the midpoint temperature of the corresponding temperature range in the temperature-gradient value coordinate system, which can reflect the speed at which the distortion coefficient changes with temperature.

[0115] In this embodiment of the invention, the step of differentiating the thermally induced distortion coefficient sequence to obtain the gradient change curve includes:

[0116] Identify local fluctuation characteristics in the thermally induced distortion coefficient sequence, and adaptively determine the order and step size of the numerical differentiation algorithm based on the amplitude-frequency characteristics of the local fluctuation characteristics;

[0117] The thermal distortion coefficient sequence is processed by the convolution smoothing differential algorithm based on the order and step size to obtain the first derivative sequence.

[0118] The first derivative sequence is used as the initial gradient sequence, and the initial gradient sequence is normalized based on the physical interval of the temperature step points.

[0119] The normalized preliminary gradient sequence is fitted in the preset temperature-gradient coordinate system to generate a gradient change curve.

[0120] In detail, the adjacent differences of the thermally induced distortion coefficient sequence are calculated. For example, the difference between adjacent temperatures from 50℃ to 80℃ is The temperature difference between adjacent values ​​from 80℃ to 120℃ is The temperature difference between adjacent values ​​from 120℃ to 160℃ is And analyze the fluctuation characteristics, if and A smaller difference indicates less fluctuation. Comparison An increase in amplitude indicates increased volatility, with the amplitude-frequency characteristics showing stability in the low and mid frequencies and fluctuations in the high frequencies. Based on this characteristic, a third-order convolutional smoothing differential algorithm is adaptively selected (higher order results in stronger smoothing, suitable for sequences with local fluctuations), with a step size of 2 (the step size matches the temperature step interval; here, the temperature interval is 40℃ / 20℃, and a step size of 2 covers two adjacent intervals). By adaptively selecting the order and step size, it is ensured that the differential result preserves the trend while eliminating abnormal fluctuation interference. The third-order convolutional kernel is used to perform differential calculations on the distortion coefficient sequence to obtain the first derivative for each temperature interval.

[0121] For example, the temperature range of 50℃→80℃ (midpoint temperature 65℃): gradient value Even after smoothing by 3rd-order convolution, it is still... (Small fluctuations, small differences before and after smoothing); 80℃→120℃ range (midpoint temperature 100℃): gradient value After smoothing, it becomes ; 120℃→160℃ range (midpoint temperature 140℃): gradient value After smoothing, it becomes (removing part of the fluctuation); the midpoint temperature is associated with the gradient value to form a first derivative sequence, and the discrete distortion coefficient is converted into a continuous gradient value through differential calculation, so as to provide data points for gradient curve fitting.

[0122] Specifically, the physical interval of the temperature step point is 50-80℃ (30℃), 80-120℃ (40℃), and 120-160℃ (40℃), the normalization processing adopts the gradient value / temperature interval mode, the influence of interval difference on the gradient value is eliminated, so as to combine the normalized gradient values into a preliminary gradient sequence, the gradient values in different temperature intervals have a unified comparison standard through normalization, and the accuracy of subsequent curve fitting is ensured. A coordinate system of temperature (abscissa, range 50-170℃) and normalized gradient value (ordinate, range 0-6×10³ Pa / ℃²) is constructed, the least square method is used for polynomial fitting (fitting order 2 order, because the number of data points is 3, 2 order fitting can pass all points) of 3 data points of the preliminary gradient sequence, and a fitting curve equation is obtained, such as ( for temperature, for normalized gradient value), and the gradient change curve is drawn according to the equation, after the fitting is completed, the goodness of fit is calculated, the goodness of fit is close to 1, indicating that the fitting curve has high consistency with the actual data points, and the curve is determined to be effective.

[0123] In the embodiment of the present application, the inflection point feature refers to the temperature data and gradient intensity data corresponding to the turning point at which the gradient value changes from increasing to decreasing (or vice versa) in the gradient change curve, and the feature is a key sign for judging the evolution stage of the coating defect.

[0124] In the embodiment of the present application, the analysis of the inflection point feature in the gradient change curve comprises:

[0125] calculating the multi-scale curvature of the gradient change curve, determining the curvature extreme points under different scale parameters through the multi-scale curvature, and screening preliminary candidate inflection points according to the curvature extreme points;

[0126] identifying the adjacent region of the preliminary candidate inflection point, and analyzing the gradient statistical features of the adjacent region;

[0127] verifying the false inflection points in the preliminary candidate inflection points according to the gradient statistical features, and screening out true inflection points based on the preliminary candidate inflection points after verification;

[0128] extracting the temperature data and inflection point intensity corresponding to the true inflection point, and combining the temperature data and the inflection point intensity into an inflection point feature.

[0129] In detail, the multi-scale curvature analysis refers to obtaining curvature information at different scales by changing the size of the curvature calculation window. Firstly, the curvature of the gradient change curve is calculated by using the second derivative method, and then three calculation windows of different scales are set, for example, a small-scale window contains 3 data points, a medium-scale window contains 5 data points, and a large-scale window contains 7 data points. Under each scale window, the curvature value is calculated by sliding, and the curvature extreme point, i.e. the local maximum or minimum point of curvature, is identified. Finally, the extreme points existing in common at the three scales are taken as the preliminary candidate inflection points. Through multi-scale analysis, both subtle changes at small scales and noise smoothing at larger scales can be captured, ensuring the comprehensiveness and reliability of the candidate inflection points, and solving the problem of single-scale analysis being easily disturbed by noise or missing real inflection points.

[0130] Specifically, the adjacent region refers to a set of data points within a certain range before and after the center of the candidate inflection point. For each preliminary candidate inflection point, the gradient values of the 5 temperature step points before and after it are taken to form the adjacent region. The gradient statistical features include the mean, standard deviation and skewness of the gradient values in the region. Then the gradient values of all points in the adjacent region are extracted, the average value of the gradient values reflects the overall trend, the standard deviation represents the fluctuation degree, and the skewness understands the distribution form.

[0131] Further, the pseudo inflection point test refers to distinguishing real inflection points from false inflection points caused by noise through statistical hypothesis testing method. If the absolute value of the curvature of the candidate inflection point is less than twice the standard deviation of the gradient in the adjacent region, it is determined as a pseudo inflection point. If the sign of the gradient value at the candidate inflection point is the same as that of the mean value of the adjacent region, it is determined as a pseudo inflection point. These rules are applied to each candidate inflection point for testing, and all points that meet the pseudo inflection point condition are removed. The remaining points are real inflection points. Through statistical significance test, pseudo signals caused by random fluctuations are effectively removed, ensuring the accuracy of inflection point detection and solving the problem of false alarm caused by data noise. The inflection point strength is an index to quantify the significance of the inflection point, defined as the ratio of the absolute value of the curvature at the inflection point to the standard deviation of the curvature in the adjacent region. For each real inflection point, record its corresponding temperature value as temperature data, and calculate the inflection point strength value of the point. Finally, the temperature data and the inflection point strength of each real inflection point are combined into a two-dimensional feature vector as the complete feature description of the inflection point.

[0132] Further, through this multi-level and multi-feature inflection point analysis method, the key critical points of coating defect evolution can be effectively captured, laying a solid foundation for the accurate judgment of defect type and grade in the subsequent process.

[0133] S6, analyzing the defect evolution behavior of the bipolar plate carbon-based composite coating according to the inflection point characteristics, and detecting the defect type and defect grade of the bipolar plate carbon-based composite coating through the defect evolution behavior.

[0134] In the embodiment of the present application, the defect evolution behavior refers to the development process of internal defects (such as micro-cracks and interface separation) of the bipolar plate carbon-based composite coating from nothing to expansion and from small to large during the temperature rising process, which is usually divided into three stages of stable state, slow evolution state and accelerated evolution state.

[0135] In the embodiment of the present application, the defect evolution behavior of the bipolar plate carbon-based composite coating is analyzed according to the inflection point characteristics, including:

[0136] A defect evolution phase diagram is constructed according to preset inflection point temperature attributes and inflection point strength attributes;

[0137] The inflection point characteristics are projected into the defect evolution phase diagram, and the stable state, slow evolution state or accelerated evolution state of the bipolar plate carbon-based composite coating is determined according to the belonging region of the inflection point characteristics in the defect evolution phase diagram;

[0138] For the inflection point of the slow evolution state or the accelerated evolution state, the Euclidean distance between the inflection point and the defect evolution path template in the defect evolution phase diagram is calculated, and the evolution trend and evolution level of the bipolar plate carbon-based composite coating are analyzed according to the Euclidean distance;

[0139] The defect evolution behavior of the bipolar plate carbon-based composite coating is determined based on the evolution trend and the evolution level.

[0140] In detail, the defect evolution phase diagram is a two-dimensional feature space with inflection point temperature data as the horizontal axis and inflection point strength as the vertical axis. When constructing, a large amount of sample data of known defect types is collected, the inflection point characteristics of the sample data are obtained, and clustering algorithms (such as K-means clustering) are used to automatically classify these inflection point characteristics to form different aggregation regions in the temperature-intensity coordinate system. Each region corresponds to a typical defect evolution state: the low-temperature low-intensity region corresponds to the stable state, the medium-temperature medium-intensity region corresponds to the slow evolution state, and the high-temperature high-intensity region corresponds to the accelerated evolution state. The region boundary is determined by statistical method, for example, the 95% confidence ellipse of each clustering center is calculated as the boundary. The shortest distance from the coordinate point to each region boundary is calculated, and the evolution state is determined by judging the region where the point is located. For example, when the inflection point falls within the stable state region, it indicates that the coating structure is stable near the temperature point; when it falls within the slow evolution state region, it indicates that the coating begins to have small damage but the expansion is slow; when it falls within the accelerated evolution state region, it indicates that the damage enters the rapid expansion stage. Through spatial position mapping, the objective determination of the defect evolution state is realized, and the inaccuracy problem of subjective experience judgment is solved.

[0141] Specifically, the defect evolution path template is a typical defect development trajectory established by analyzing a large amount of historical data. In the defect evolution phase diagram, the typical evolution path curve of different types of defects is drawn. For the inflection point of slow or accelerated evolution state, the Euclidean distance to the nearest path template is calculated, and the smaller the distance, the more consistent with the actual defect evolution mode. At the same time, according to the size of the distance value, the evolution level is divided: the distance less than threshold T1 is low risk level, between T1 and T2 is medium risk level, and greater than T2 is high risk level. Establishing a decision rule based on the evolution trend and the evolution level determines the defect evolution behavior of the bipolar plate carbon-based composite coating: stable state combined with any level is benign behavior; slow evolution state combined with medium and high risk levels needs to be warned; accelerated evolution state combined with any level needs to be treated immediately. Through multi-dimensional information fusion, a complete understanding of the development trend of the defect is formed, and decision support is provided.

[0142] In the embodiment of the application, the defect type refers to the classification of the incompleteness of the bipolar plate carbon-based composite coating according to its physical mechanism and form of expression, including but not limited to material inherent heterogeneity, micro-crack initiation defect, and interface bonding failure defect; the defect level refers to the quantitative grading according to the severity and development risk of the defect under a certain defect type, such as first level (slight), second level (moderate), and third level (serious).

[0143] In the embodiment of the application, the defect type and the defect level of the bipolar plate carbon-based composite coating are detected through the defect evolution behavior, including:

[0144] A mapping relationship library between the defect evolution behavior and the defect type is constructed, wherein the stable state is mapped to material inherent heterogeneity, the slow evolution state is mapped to a micro-crack initiation defect, and the accelerated evolution state is mapped to an interface bonding failure defect.

[0145] The defect type corresponding to the defect evolution behavior is identified based on the mapping relationship library;

[0146] The inflection point characteristic coordinates of the defect type are calculated in the defect evolution phase diagram, and the minimum Euclidean distance between the defect type and the preset standard evolution path is analyzed, and the deviation amplitude of the inflection point characteristics in the direction perpendicular to the standard evolution path is calculated.

[0147] The bipolar plate carbon-based composite coating is graded according to the minimum Euclidean distance and the deviation amplitude under the defect type, and the defect level is obtained.

[0148] In detail, the mapping relationship library is a classification model trained by a machine learning method. During training, the evolution behavior characteristics (including state type, evolution level, etc.) of historical samples are taken as input, and the defect types (micro-cracks, interface peeling, etc.) verified by actual dissection are taken as output. Support vector machines or neural network algorithms are used for training. The trained model can accurately map stable states to material inherent heterogeneity, map slow evolution states to micro-crack initiation defects, and map accelerated evolution states to interface bonding failure defects. Automatic identification of defect types can be achieved through intelligent classification.

[0149] Specifically, the modal process is to input the evolution behavior characteristics obtained by real-time detection into the trained classification model, and output the corresponding defect type label. The evolution state and level characteristics of the current detection sample are extracted, and the classification model in the mapping relationship library is called for prediction to obtain the most likely defect type result. The standard path corresponding to the current defect type is found in the defect evolution phase diagram, and then the two parameters are obtained by geometric calculation method. The minimum Euclidean distance is the shortest geometric distance from the current inflection point feature to the standard evolution path, reflecting the degree of coincidence with the typical defect mode. The deviation amplitude is the deviation value of the inflection point feature in the direction perpendicular to the standard path, reflecting the abnormality degree.

[0150] Further, the level division adopts a two-dimensional decision matrix method. The level judgment rules based on the minimum Euclidean distance and deviation amplitude are established: when the minimum Euclidean distance and deviation amplitude are both less than 50% of their respective thresholds, it is classified as level one (slight); when any parameter exceeds 50% but is less than 80%, it is classified as level two (moderate); when any parameter exceeds 80%, it is classified as level three (severe). Through multi-parameter comprehensive judgment, the fine differentiation of defect level is realized.

[0151] Further, by determining the grade division threshold through statistical learning of the standard sample library of known defect grades, a large number of samples of known defect grades are collected. The defect grades of the samples have been accurately calibrated by destructive methods such as metallographic dissection, scanning electron microscope observation or performance degradation test. The sample library needs to cover different defect types (microcracks, interface peeling, etc.) and various severity levels to ensure the comprehensiveness and representativeness of the statistical results. For example, a standard library containing 50 first-level samples, 50 second-level samples and 50 third-level samples is prepared; a complete detection process is performed on each sample in the standard sample library to obtain the minimum Euclidean distance and deviation amplitude data corresponding to each sample. Then the distribution characteristics of these parameters are analyzed by statistical methods: for first-level samples, the upper limit value of the 95% confidence interval of the distance and amplitude data is calculated as the normal fluctuation range of this grade; for second-level samples, the distribution offset of their parameter values relative to first-level samples is analyzed; for third-level samples, the critical point where their parameter values are significantly different from other grades is determined. Taking the distinction between first-level and second-level samples as an example, the distance parameter is taken as the classification index, the true positive rate and false positive rate corresponding to different threshold points are calculated, and the threshold point that maximizes the Youden index is selected, which can best balance the risk of missed judgment and misjudgment. Repeat this process to determine all threshold boundaries between levels, and apply the preliminarily determined threshold to an independent validation sample set (new samples not involved in training) to evaluate its grade division accuracy. If the accuracy is lower than the preset requirement (e.g. 90%), return to adjust the threshold, and after 3-5 rounds of iteration, the stable threshold system is finally determined.

[0152] Further, by defect evolution phase diagram construction, multi-parameter quantitative analysis and intelligent classification decision, the technical leap from simple defect detection to complex evolution behavior prediction is realized, and static detection is upgraded to dynamic behavior prediction; through the phase diagram analysis method, the visualization monitoring of defect evolution is realized, effectively solving the industry problems that existing methods cannot predict the development trend of defects and cannot distinguish the evolution stages of defects, providing a new technical approach for reliability evaluation of fuel cell bipolar plate coating.

[0153] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0154] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting, and the scope of the present application is not limited only by the above description, therefore all changes within the meaning and scope of equivalent elements falling within the scope of protection are intended to be included in the present application.

[0155] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. Among them, artificial intelligence (AI) is to use digital computers or computer-controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0156] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The words "first", "second" and the like are used to distinguish names, not to indicate any particular order.

[0157] Finally, it should be pointed out that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A method for defect detection of carbon-based composite coating of PEM fuel cell metal bipolar plates, characterized in that, The method comprises: optically scanning a surface area of a preset bipolar plate carbon-based composite coating at a preset reference temperature to obtain reference optical characteristic data, wherein the reference optical characteristic data refers to a set of multi-band reflected light intensity and spatial coordinates of the coating at the reference temperature; applying a stepwise thermal excitation to the bipolar plate carbon-based composite coating to obtain a plurality of temperature step points corresponding to the bipolar plate carbon-based composite coating, wherein the temperature step point is a specific temperature value at which the temperature of the coating reaches and stabilizes in the stepwise thermal excitation, and each step point corresponds to a stable thermal environment for collecting optical response data of the coating at the temperature; After the stabilization of each temperature step point, the optical response data sequence is generated according to the optical response data at each temperature step point, wherein the optical response data sequence is an ordered set formed by arranging the optical response change data sets corresponding to all temperature step points in order from low to high temperature, wherein the reflectance change amount is calculated by the formula , is the reflectance change amount, is the current temperature reflectance intensity, is the reference temperature reflectance intensity, the reflectance change amount is calculated at two wave bands for each scanning point, the coordinates of the scanning point and the double wave band reflectance change amount are taken as a data record, and after the calculation of all scanning points of a certain temperature step point is completed, the optical response change data set at the certain temperature step point is imported into the MySQL database. sequentially analyzing thermal distortion coefficients corresponding to the temperature step points based on the reference optical characteristic data and the optical response data; differentially processing the thermal distortion coefficient sequence to obtain a gradient change curve, and analyzing the inflection point characteristics in the gradient change curve, wherein the inflection point characteristics refer to the temperature data and gradient intensity data corresponding to the turning point at which the gradient value changes from increasing to decreasing or from decreasing to increasing in the gradient change curve; analyzing the defect evolution behavior of the bipolar plate carbon-based composite coating according to the inflection point characteristics, wherein the defect evolution behavior refers to the development process of internal defects of the bipolar plate carbon-based composite coating from nonexistence to existence and from small to large during temperature rise, and detecting the defect type and defect level of the bipolar plate carbon-based composite coating through the defect evolution behavior; wherein the sequentially analyzing thermal distortion coefficients corresponding to the temperature step points based on the reference optical characteristic data and the optical response data comprises: determining the statistical distribution characteristics of the reflectivity change amount corresponding to each temperature step point based on the reference optical characteristic data and the optical response data sequence; analyzing the stress coupling factor of the bipolar plate carbon-based composite coating, and mapping the statistical distribution characteristics to the distortion physical quantity of the coating thermal mechanical stress response corresponding to each temperature step point according to the stress coupling factor, wherein: ； wherein is the distortion physical quantity at the first temperature step point , is the average of the reflectivity change amount at the first temperature step point , is the standard deviation of the reflectivity change amount at the first temperature step point , and k is a stress coupling factor. sorting the distortion physical quantity according to the temperature order of the temperature step points to obtain the thermal distortion coefficient sequence; and the analyzing the stress coupling factor of the bipolar plate carbon-based composite coating comprises: establishing a theoretical constitutive equation for correlating macroscopic optical response and microscopic interfacial stress based on the microstructure model of the bipolar plate carbon-based composite coating material: ； wherein is the thermal stress generated at the microscopic interface, is the amount of change in reflectivity, is the initial reflectivity at the reference temperature, is the stress coupling factor; analyzing the optical response data and stress response data of the preset standard sample data under thermal excitation; performing stress coupling analysis on the optical response data and the stress response data using the theoretical constitutive equation to obtain a target numerical range of the stress coupling factor; selecting the stress coupling factor of the bipolar plate carbon-based composite coating from the target numerical range according to the composition parameters of the bipolar plate carbon-based composite coating.

2. The method for detecting defects in carbon-based composite coating of PEM fuel cell metal bipolar plates as claimed in claim 1, wherein, The optical scanning of the surface area of the preset bipolar plate carbon-based composite coating at the preset reference temperature to obtain the reference optical characteristic data comprises: placing the bipolar plate carbon-based composite coating on a temperature control platform, and adjusting the temperature control platform to the preset reference temperature; Based on the reference temperature, a preset serpentine scanning path is controlled to control the optical scanning unit to perform full-coverage scanning on the surface region, and spatial coordinates of each scanning point are recorded; After the full-coverage scanning is completed, reflection intensity data of the surface region under a plurality of target wavebands is collected; The spatial coordinates of each scanning point are associated and integrated with the reflection intensity data to generate reference optical characteristic data.

3. The method for detecting defects in carbon-based composite coating of PEM fuel cell metal bipolar plates as claimed in claim 1, wherein, The stepwise thermal excitation is applied to the bipolar plate carbon-based composite coating to obtain a plurality of temperature step points corresponding to the bipolar plate carbon-based composite coating, including: According to the material heat capacity and thermal conductivity of the bipolar plate carbon-based composite coating, a nonlinear temperature increment sequence is determined as a target temperature sequence; According to the target temperature sequence, a fast-slow power loading strategy is controlled to control the infrared heating source to heat the bipolar plate carbon-based composite coating; During the heating process, the actual temperature of the surface region of the bipolar plate carbon-based composite coating is monitored in real time, and when the actual temperature reaches and stabilizes at any step point in the target temperature sequence, the step point is recorded as a stable temperature step point; All step parameters in the target temperature sequence are traversed to obtain a plurality of temperature step points.

4. The method of claim 2, wherein the PEM fuel cell metal bipolar plate carbon-based composite coating defect detection method is characterized by, After each temperature step point is stabilized, optical response data at each temperature step point are generated to generate an optical response data sequence, including: After each temperature step point is stabilized, optical response data corresponding to each temperature step point are collected according to the serpentine scanning path and a preset scanning waveband; Based on the spatial coordinates, the optical response data are point-by-point registered with the reference optical characteristic data; According to the registered data, a reflectivity change amount of each spatial point under each waveband with respect to the reference temperature is calculated, and a temperature step point corresponding optical response change data set is generated according to the reflectivity change amount; In order from low to high temperature step, the optical response change data sets under all temperature step points are time-sequentially arranged to generate an optical response data sequence.

5. The method for detecting defects in carbon-based composite coating of PEM fuel cell metal bipolar plates of claim 1, wherein, The thermal distortion coefficient sequence is differentiated to obtain a gradient change curve, including: Local fluctuation characteristics in the thermal distortion coefficient sequence are identified, and the order and step length of a numerical differentiation algorithm are adaptively determined based on the amplitude-frequency characteristics of the local fluctuation characteristics; Based on the convolution smoothing differentiation algorithm of the order and step length, the thermal distortion coefficient sequence is processed by the order to obtain a first derivative sequence; The first derivative sequence is taken as a preliminary gradient sequence, and the preliminary gradient sequence is normalized based on the physical interval of the temperature step point; In a preset temperature-gradient coordinate system, the normalized preliminary gradient sequence is fitted to generate a gradient change curve.

6. The method for detecting defects in carbon-based composite coating of PEM fuel cell metal bipolar plates of claim 1, wherein, The inflection point characteristics in the gradient change curve are analyzed, including: Multi-scale curvatures of the gradient change curve are calculated, curvature extreme points under different scale parameters are determined through the multi-scale curvatures, and preliminary candidate inflection points are screened according to the curvature extreme points; Adjacent regions of the preliminary candidate inflection points are identified, and gradient statistical characteristics of the adjacent regions are analyzed; According to the gradient statistical characteristics, false inflection points in the preliminary candidate inflection points are tested, and true inflection points are screened out based on the tested preliminary candidate inflection points; Temperature data and inflection point intensity corresponding to the true inflection points are extracted, and the temperature data and the inflection point intensity are combined as inflection point characteristics.

7. The method for detecting defects in carbon-based composite coating of PEM fuel cell metal bipolar plates of claim 1, wherein, The inflection point characteristics are used to analyze the defect evolution behavior of the bipolar plate carbon-based composite coating, including: A defect evolution phase diagram is constructed according to preset inflection point temperature attributes and inflection point intensity attributes; The inflection point characteristics are projected into the defect evolution phase diagram, and the belonging area of the inflection point characteristics in the defect evolution phase diagram is used to determine the stable state, slow evolution state or accelerated evolution state of the bipolar plate carbon-based composite coating; For the inflection points in the slow evolution state or the accelerated evolution state, the Euclidean distance between the inflection points and the defect evolution path template in the defect evolution phase diagram is calculated, and the evolution trend and evolution grade of the bipolar plate carbon-based composite coating are analyzed according to the Euclidean distance; Based on the evolution trend and the evolution grade, the defect evolution behavior of the bipolar plate carbon-based composite coating is determined.

8. The method of claim 7, wherein the PEM fuel cell metal bipolar plate carbon-based composite coating defect detection method is characterized by, The defect type and defect grade of the bipolar plate carbon-based composite coating are detected by the defect evolution behavior, including: A mapping relationship library between defect evolution behavior and defect type is constructed, wherein the stable state is mapped to material inherent heterogeneity, the slow evolution state is mapped to micro-crack initiation defect, and the accelerated evolution state is mapped to interface bonding failure defect; Based on the mapping relationship library, the defect type corresponding to the defect evolution behavior is identified; In the defect evolution phase diagram, the inflection point characteristic coordinates of the defect type are calculated, the minimum Euclidean distance between the defect type and a preset standard evolution path is analyzed, and the deviation amplitude of the inflection point characteristics in the direction perpendicular to the standard evolution path is calculated; According to the minimum Euclidean distance and the deviation amplitude, the bipolar plate carbon-based composite coating is graded under the defect type, and a defect grade is obtained.

Images