Method and system for identifying a cell of a backup battery of a communication base station using thermal imaging

Abstract

The present application belongs to the field of battery pole piece detection, and relates to a method and system for identifying cracks in communication base station standby battery pole pieces using thermal imaging, comprising: heating the battery pole piece to a target temperature range and collecting thermal distribution image data of the surface of the battery pole piece; continuously applying a pulsed thermal excitation signal to the surface of the battery pole piece and collecting dynamic thermal distribution image data of the surface of the battery pole piece; processing the reference thermal image and the dynamic thermal image sequence to extract the characteristic intensity distribution of the suspected crack area; constructing a three-dimensional thermal gradient model according to the characteristic intensity distribution of the suspected crack area, screening the suspected crack area, and obtaining the real crack area; comparing the three-dimensional thermal gradient model of the real crack area with a standard crack library to determine the crack type and crack size; solving the deficiencies of the prior art in micro crack detection and large-scale production line rapid detection, improving the overall performance of the battery, and ensuring the safety of the base station standby battery.

Description

Technical Field

[0001] This invention relates to the field of battery electrode inspection, and specifically discloses a method and system for identifying cracks in the electrodes of backup batteries for communication base stations using thermal imaging. Background Technology

[0002] In the manufacturing process of backup batteries for communication base stations, rapid and efficient quality inspection technology is required. High-quality control of battery electrodes is a crucial link in ensuring the overall performance and safety of the battery. With the continuous advancement of backup battery technology for communication base stations, the quality control and crack detection of battery electrodes have gradually become key factors affecting battery performance and safety. Currently, the industry's demand for inspection solutions that combine efficiency and intelligence is increasingly prominent in battery production processes. However, existing crack detection methods mostly employ electrical signal analysis or mechanical vibration monitoring. These methods often face challenges in actual production environments, such as insufficient accuracy and difficulty in achieving non-destructive testing. Furthermore, their ability to distinguish the specific location and morphology of cracks is weak, making it difficult to fully adapt to the high standards required by production lines. Existing technology discloses a technical method and supporting device for crack monitoring and repair of wing components. This device mainly consists of electrode sheets, a microcontroller, a thermal imaging detector, a filter, and a battery. Its working principle is to detect cracks through surface current and automatically perform repair operations during flight. Specifically, this technology first uses microcurrent detection to identify the location of the crack, then applies a strong current to the crack to bring the metal material close to its melting point, while simultaneously using a thermal imaging detector to monitor temperature changes in real time, thereby achieving precise control over the repair process. However, this existing technology relies on a strong current to bring the metal at the crack close to its melting point for repair, which is not suitable for the material characteristics of battery electrodes and may lead to material damage or performance degradation. Furthermore, thermal imaging technology is only used to monitor temperature changes during the repair process, rather than directly for crack identification and location, and lacks the ability to accurately analyze the crack morphology.

[0003] In view of this, the present invention discloses a method and system for identifying cracks in the electrode sheets of backup batteries for communication base stations using thermal imaging. This method enables high-precision, non-destructive detection of surface and internal cracks in battery electrode sheets and accurate identification of crack morphology, effectively improving the efficiency and accuracy of crack detection in backup batteries for communication base stations. It is also applicable to battery electrode sheets made of complex materials, overcoming the shortcomings of existing technologies in detecting micro-cracks and rapid detection on large-scale production lines, thus improving the overall performance of the battery and ensuring the safety of backup batteries for base stations. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for identifying electrode cracks in backup batteries for communication base stations using thermal imaging. The problem addressed is that it overcomes the shortcomings of existing technologies in detecting micro-cracks and rapid detection on large-scale production lines, improving the overall performance of the battery and ensuring the safety of backup batteries for base stations. The specific solution is as follows:

[0005] A method for identifying cracks in the electrode plates of backup batteries for communication base stations using thermal imaging includes: Step 1, heating the battery electrode plate to a target temperature range and acquiring thermal distribution image data of the battery electrode plate surface to obtain a reference thermal image; Step 2, continuously applying a pulsed thermal excitation signal to the surface of the battery electrode plate and acquiring dynamic thermal distribution image data of the battery electrode plate surface to obtain a dynamic thermal image sequence; Step 3, processing the reference thermal image and the dynamic thermal image sequence using a multiphysics coupling analysis algorithm to extract the characteristic intensity distribution of suspected crack areas; Step 4, constructing a three-dimensional thermal gradient model based on the characteristic intensity distribution of suspected crack areas, and filtering suspected crack areas based on the three-dimensional thermal gradient model to obtain real crack areas; Step 5, comparing the three-dimensional thermal gradient model of the real crack areas with a standard crack library to determine the crack type and crack size.

[0006] Furthermore, the target temperature range is 40℃~80℃; the heating power density range is 10W / cm²~50W / cm².

[0007] Furthermore, the waveform of the pulsed thermal excitation signal is a square wave or a sine wave, with a frequency of 1Hz to 50Hz, an amplitude of 10W to 50W, and a duration of 1s to 10s.

[0008] Furthermore, the multiphysics coupling analysis algorithm is as follows:

[0009]

[0010] Where F(x,y) represents the characteristic intensity distribution function; Indicates the start time of the pulsed thermal excitation signal; The pulsed thermal excitation signal ends at the application time; T(x,y,t) represents the temperature value of pixel (x,y) at time t; x and y represent the horizontal and vertical coordinates of the thermal image, respectively. This represents the reference temperature value of pixel (x,y) in the reference thermal image. This indicates the highest temperature in the dynamic thermal image sequence; This indicates the lowest temperature in a dynamic thermal image sequence. This represents the integral over time during the application period of the pulsed thermal excitation signal.

[0011] Further, step 4 includes: establishing a correlation mapping relationship between two-dimensional image coordinates and temperature values ​​based on feature intensity distribution; setting the crack detection area of ​​the battery electrode as the XY plane, with the Z-axis vertical direction representing the temperature gradient, to obtain the spatial structure of the three-dimensional thermal gradient model; constructing the three-dimensional thermal gradient model based on the correlation mapping relationship and the spatial structure of the three-dimensional thermal gradient model; the expression of the three-dimensional thermal gradient model is:

[0012] ;

[0013] Where G(x,y,z) represents the three-dimensional thermal gradient value of the pixel with coordinates (x,y) in the two-dimensional image in the three-dimensional thermal gradient model (x,y,z); F(x,y) represents the spatial gradient of the feature intensity distribution F(x,y) at the two-dimensional plane coordinates (x,y); The expression represents the derivative with respect to time t; T(x,y,t) represents the temperature value of pixel (x,y) at time t; t represents the time-series variable; the three-dimensional thermal gradient model of the suspected crack region is screened based on the feature intensity threshold to obtain the real crack region.

[0014] Further, the crack type is determined by: calculating the similarity between the three-dimensional gradient vector of the real crack region and the three-dimensional gradient vector of the crack sample to obtain the global thermal gradient similarity; the three-dimensional gradient vector refers to the vector obtained by gradient calculation of the three-dimensional thermal gradient model of the crack; evaluating the fit between the three-dimensional spatial structure of the real crack region and the three-dimensional spatial structure of the crack sample using Hausdorff distance to obtain the three-dimensional morphological similarity; the three-dimensional spatial structure refers to the spatial structure of the three-dimensional thermal gradient model of the crack; calculating the divergence of temperature in the vector field of the three-dimensional thermal gradient model to obtain the divergence characteristics of the thermal gradient vector field; quantifying the degree of heat accumulation in the crack region using the energy calculation formula to obtain the heat accumulation effect at the crack; verifying the thermal response data and material property data of the real crack and the crack sample based on the coupled equation set to obtain the data verification results; the crack sample refers to the crack sample stored in the crack standard database; the coupled equation set includes the unsteady heat conduction equation and the elasticity equation; and outputting the crack type by integrating the global thermal gradient similarity, three-dimensional morphological similarity, thermal gradient vector field divergence characteristics, heat accumulation effect at the crack, and data verification results.

[0015] Furthermore, the similarity between the three-dimensional gradient vector of the actual crack region and the three-dimensional gradient vector of the crack sample is calculated as follows:

[0016]

[0017] Where Sim represents the global thermal gradient similarity; A three-dimensional gradient vector representing the actual crack region; Represents the three-dimensional gradient vector of the crack sample; Represents the weight vector;

[0018] The divergence of temperature in the vector field of the three-dimensional thermal gradient model is calculated as follows:

[0019]

[0020] Wherein, divG represents the divergence characteristic of the thermal gradient vector field; , and These represent the components of the vector field of the three-dimensional thermal gradient model in the x, y, and z directions, respectively. , and Let x, y, and z represent the partial derivatives with respect to the x, y, and z directions, respectively.

[0021] The energy calculation formula is:

[0022] ;

[0023] Where E represents the heat accumulation effect at the crack; ρ represents the material density; c represents the specific heat capacity of the material; ΔT represents the temperature change; and dV represents the volume element.

[0024] The unsteady-state heat conduction equation is:

[0025] ;

[0026] The equation of elasticity is:

[0027] ;

[0028] in, This represents the partial derivative of the temperature T on the surface of the battery electrode with respect to time t; The term represents heat conduction; k represents the thermal conductivity of the material; Q represents the internal heat source term. T represents the temperature gradient vector; Represents the divergence operator; Represents the fourth-order elastic tensor; Represents the strain tensor; Represents the displacement vector; Indicates the transpose operation; The strain represents the thermal expansion; α represents the coefficient of thermal expansion of the material; T represents the temperature value at the current time t. Indicates the reference temperature value; This represents the volumetric force density.

[0029] Further, the crack size is determined by: using a linear regression model based on the thermal gradient propagation characteristics to solve for the length parameter; using a curve fitting model based on the edge gradient change to solve for the width parameter; and using an exponential model based on the thermal decay characteristics to solve for the depth parameter.

[0030] Furthermore, the linear regression model for the thermal gradient extension characteristics is as follows:

[0031] ;

[0032] Where L represents the length parameter; β represents the first constant coefficient; β represents the second constant coefficient; | T| represents the magnitude of the temperature gradient vector; Represents a length infinitesimal element;

[0033] The curve fitting model for the edge gradient change is as follows:

[0034] ;

[0035] Where W represents the width parameter; σ represents the standard deviation; and ln represents the logarithmic function.

[0036] The exponential model for thermal decay characteristics is as follows:

[0037] ;

[0038] Where D represents the depth parameter; λ represents the maximum depth; exp represents the exponential function; λ represents the material attenuation coefficient; and ΔT represents the surface temperature difference.

[0039] This invention also provides a system for identifying cracks in the electrode plates of backup batteries for communication base stations using thermal imaging, as described above. The system includes: a constant-temperature heating platform, a pulsed thermal excitation signal source, an infrared thermal imager, and a data processing unit. The constant-temperature heating platform heats the battery electrode plates to a target temperature range. The infrared thermal imager acquires thermal distribution image data of the battery electrode plate surface to obtain a reference thermal image. It also acquires dynamic thermal distribution image data of the battery electrode plate surface to obtain a dynamic thermal image sequence. The pulsed thermal excitation signal source continuously applies a pulsed thermal excitation signal to the battery electrode plate surface. The data processing unit processes the reference thermal image and the dynamic thermal image sequence using a multiphysics coupling analysis algorithm to extract the characteristic intensity distribution of suspected crack areas. Based on the characteristic intensity distribution of the suspected crack areas, a three-dimensional thermal gradient model is constructed, and the suspected crack areas are screened based on the three-dimensional thermal gradient model to obtain the actual crack areas. The three-dimensional thermal gradient model of the actual crack areas is compared with a standard crack library to determine the crack type and crack size.

[0040] The present invention has the following advantages and beneficial effects:

[0041] This invention utilizes thermal conductivity to locate crack regions, enabling the identification of micro-cracks and complex-shaped cracks in battery electrodes. It is also applicable to battery electrodes with various material properties, overcoming the limitations of traditional detection technologies under complex operating conditions and providing an efficient and intelligent solution for the manufacturing process of backup batteries for communication base stations.

[0042] This invention uses thermal imaging technology combined with multiphysics coupling analysis algorithms to achieve high-precision, non-destructive detection of surface and internal cracks in the electrode sheets of base station backup batteries, and to accurately identify the crack morphology.

[0043] This invention introduces deep learning algorithms to achieve intelligent classification and size quantification of crack types, providing an efficient and intelligent detection solution for modern battery manufacturing processes. Attached Figure Description

[0044] Figure 1 This is an exemplary flowchart of the method for identifying cracks in the electrode plates of a backup battery in a communication base station using thermal imaging, according to the present invention.

[0045] Figure 2 This is an exemplary module diagram of the system of the present invention that uses thermal imaging to identify cracks in the electrode plates of backup batteries for communication base stations. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0047] This invention discloses a method and system for identifying cracks in the electrode sheets of backup batteries for communication base stations using thermal imaging. The aim is to achieve high-precision, non-destructive detection of surface and internal cracks in battery electrode sheets by integrating thermal imaging technology with multiphysics coupling analysis algorithms. This allows for accurate identification of crack morphology and quantification of size, making it suitable for complex material electrode sheets and rapid inspection scenarios in large-scale production lines. The technical solution of this invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0048] Figure 1 This is an exemplary flowchart of the method for identifying cracks in the electrode plates of a backup battery in a communication base station using thermal imaging, according to the present invention. Figure 1 As shown, the method for identifying cracks in the electrode plates of backup batteries in communication base stations using thermal imaging includes the following:

[0049] Step 1: Heat the battery electrode to the target temperature range and acquire thermal distribution image data of the battery electrode surface to obtain a reference thermal image. For example, place the battery electrode to be tested on a constant-temperature heating platform and heat it with a constant power density of 10W / cm² to 50W / cm² to raise the electrode temperature to the target temperature range of 40℃ to 80℃. The selection of the target temperature needs to be optimized based on the thermal conductivity and coefficient of thermal expansion characteristics of the battery electrode material to ensure the thermal stability of the electrode and to avoid damaging the material performance. After the battery electrode temperature stabilizes, start the infrared thermal imager to acquire thermal distribution image data of the battery electrode surface to obtain a reference thermal image. The single-frame acquisition time is set to <10ms. Each pixel (x,y) in this image corresponds to a reference temperature value T0(x,y), where x and y represent the horizontal and vertical coordinates of the thermal image, respectively, providing a reference for subsequent dynamic thermal data comparison.

[0050] Step 2 involves continuously applying a pulsed thermal excitation signal to the surface of the battery electrode and acquiring dynamic thermal distribution image data of the electrode surface to obtain a dynamic thermal image sequence. For example, a pulsed thermal excitation signal is continuously applied to the surface of the battery electrode using a pulsed thermal excitation signal source. The signal waveform is a square wave or sine wave, with a frequency range of 1Hz to 50Hz, a power amplitude range of 10W to 50W, and a duration controlled between 1s and 10s. The determination of signal parameters needs to comprehensively consider the thermal diffusivity and crack depth characteristics of the electrode material to ensure that the thermal excitation effectively highlights the thermal response differences in the crack region. Throughout the application of the thermal excitation signal, an infrared thermal imager records the changes in thermal distribution on the electrode surface in real time, generating a dynamic thermal image sequence. This sequence contains thermal images at different time points t, where each pixel (x,y) corresponds to a temperature value T(x,y,t) at time point t, fully reflecting the dynamic thermal response process of the electrode under thermal excitation.

[0051] Step 3: Process the reference thermal image and the dynamic thermal image sequence using a multiphysics coupling analysis algorithm to extract the feature intensity distribution of the suspected crack region. For example, the data processing unit calls the multiphysics coupling analysis algorithm to jointly process the reference thermal image and the dynamic thermal image sequence to extract the feature intensity distribution of the suspected crack region. The multiphysics coupling analysis algorithm is as follows:

[0052] ;

[0053] Where F(x,y) represents the feature intensity distribution function, which is used to quantify the degree of thermal response anomaly at pixel (x,y); Indicates the start time of the pulsed thermal excitation signal; The pulsed thermal excitation signal ends at the application time; T(x,y,t) represents the temperature value of pixel (x,y) at time t; x and y represent the horizontal and vertical coordinates of the thermal image, respectively. This represents the reference temperature value of pixel (x,y) in the reference thermal image. This indicates the highest temperature in the dynamic thermal image sequence; This indicates the lowest temperature in a dynamic thermal image sequence. This represents the integral over time during the application period of the pulsed thermal excitation signal. This represents the cumulative effect of the temperature difference between pixel (x,y) and the reference temperature during the thermal excitation application period.

[0054] Step 4: Based on the characteristic intensity distribution of suspected crack areas, construct a three-dimensional thermal gradient model, and use this model to filter suspected crack areas to obtain the actual crack areas. For example, based on the characteristic intensity distribution F(x,y) obtained in Step 3, establish a mapping relationship between two-dimensional image coordinates (x,y) and temperature values ​​T(x,y,t), clarifying the correspondence between pixel coordinates and thermal response data. Set the crack detection area of ​​the battery electrode as the XY plane (maintaining the same resolution as the image captured by the infrared thermal imager), and characterize the temperature gradient in the vertical direction of the Z-axis (each gradient is 0.1℃), forming the spatial structure of the three-dimensional thermal gradient model. Based on the mapping relationship and the spatial structure of the three-dimensional thermal gradient model, construct the three-dimensional thermal gradient model; the expression of the three-dimensional thermal gradient model is:

[0055] ;

[0056] Where G(x,y,z) represents the three-dimensional thermal gradient value of the pixel with coordinates (x,y) in the two-dimensional image in the three-dimensional thermal gradient model (x,y,z); F(x,y) represents the spatial gradient of the feature intensity distribution F(x,y) at the two-dimensional plane coordinates (x,y); This indicates the derivative with respect to time t; T(x,y,t) represents the temperature value of pixel (x,y) at time t; t represents the time series variable.

[0057] The three-dimensional thermal gradient model of suspected crack regions is screened based on the characteristic intensity threshold ΔF to obtain the true crack regions. The value of ΔF ranges from 0.1 to 0.5, and the specific value needs to be determined through experimental calibration. Moreover, its setting is adaptively adjusted according to the difference in thermal gradient between cracked and non-cracked regions to ensure the accuracy of the detection results and the robustness of the system.

[0058] Step 5: Compare the 3D thermal gradient model of the actual crack region with a standard crack database to determine the crack type and size. For example, the data processing unit compares and analyzes the 3D thermal gradient model of the actual crack region with samples in the standard crack database, and uses a deep learning algorithm (employing a convolutional neural network (CNN) structure, with the 3D thermal gradient model as input and crack type labels and size parameters as output) to complete crack type classification and size quantification. The specific process is as follows:

[0059] Accurate crack type identification is achieved through five-dimensional feature integration. Global thermal gradient similarity is calculated by comparing the three-dimensional gradient vector G1 of the actual crack region with the three-dimensional gradient vector G2 of the crack sample. The three-dimensional gradient vector is the vector obtained by calculating the gradient of the crack's three-dimensional thermal gradient model. The similarity between the three-dimensional gradient vector of the actual crack region and the three-dimensional gradient vector of the crack sample is calculated as follows:

[0060] ;

[0061] Where Sim represents the global thermal gradient similarity; The three-dimensional gradient vector representing the actual crack region is obtained by performing gradient calculations on the three-dimensional thermal gradient model of the actual crack. The three-dimensional gradient vector of the crack sample is obtained by performing gradient calculation on the three-dimensional thermal gradient model of the sample in the standard database. This represents the weight vector, used to assign different importance to different components of the gradient vector.

[0062] 3D morphological similarity: The Hausdorff distance is used to assess the degree of similarity between the 3D spatial structure of the actual crack region and the 3D spatial structure of the crack sample, thus obtaining 3D morphological similarity. The Hausdorff distance is a metric for quantifying the spatial similarity between two point sets; the smaller the distance, the better the spatial geometric structures (such as the length, width, and depth distribution of the crack) match. The 3D spatial structure refers to the spatial structure of the 3D thermal gradient model of the crack.

[0063] Divergence characteristics of the thermal gradient vector field: The divergence of temperature in the three-dimensional thermal gradient model vector field is calculated to obtain the divergence characteristics of the thermal gradient vector field. The divergence of temperature in the three-dimensional thermal gradient model vector field is calculated as follows:

[0064] ;

[0065] Wherein, divG represents the divergence characteristic of the thermal gradient vector field; , and These represent the components of the vector field of the three-dimensional thermal gradient model in the x, y, and z directions, respectively. , and These represent partial derivatives with respect to the x, y, and z directions, respectively, reflecting the divergence or convergence characteristics of the thermal gradient in space. Crack regions exhibit divergence anomalies due to impeded heat conduction.

[0066] Thermal accumulation effect at cracks: The degree of thermal accumulation in the crack region is quantified using an energy calculation formula to obtain the thermal accumulation effect at cracks; the energy calculation formula is:

[0067] ;

[0068] Where E represents the heat accumulation effect at the crack; ρ represents the material density; c represents the material specific heat capacity; ΔT represents the temperature change; dV represents the volume element; and the triple integral represents the cumulative calculation of the heat accumulation effect over the entire crack region.

[0069] Data Validation Results: Based on the coupled equation set, the thermal response data and material property data of real cracks and crack samples were validated to obtain the data validation results. Crack samples refer to crack samples stored in the crack standard database. The coupled equation set includes unsteady-state heat conduction equations and elasticity equations. During the validation process, thermal response data (time-varying temperature field T(t,x,y,z)) and material property data (ρ, c, k, α, C, etc.) of real cracks were collected and compared with the time-varying thermal response and material properties of corresponding samples in the standard database to confirm the consistency of characteristics.

[0070] The unsteady-state heat conduction equation is:

[0071] ;

[0072] The equation of elasticity is:

[0073] ;

[0074] in, This represents the partial derivative of the temperature T on the surface of the battery electrode with respect to time t; The term represents heat conduction; k represents the thermal conductivity of the material; Q represents the internal heat source term. T represents the temperature gradient vector; Represents the divergence operator; Represents the fourth-order elastic tensor; Represents the strain tensor; Represents the displacement vector; Indicates the transpose operation; The strain represents the thermal expansion; α represents the coefficient of thermal expansion of the material; T represents the temperature value at the current time t. Indicates the reference temperature value; This represents the volumetric force density.

[0075] By integrating global thermal gradient similarity, 3D morphological similarity, thermal gradient vector field divergence characteristics, thermal aggregation effect at crack locations, and data verification results, a deep learning algorithm is used to output crack types (such as linear cracks, network cracks, point cracks, etc.). The deep learning algorithm employs a convolutional neural network (CNN) architecture. Its input data is a 3D thermal gradient model of the crack region, and the output is crack type labels and their size parameters. The training data comes from a mixed dataset of experimentally collected samples and simulation-generated data.

[0076] Three types of mathematical models were used to solve for the crack length, width, and depth parameters: a linear regression model based on thermal gradient propagation characteristics to solve for the length parameter; a curve fitting model based on edge gradient changes to solve for the width parameter; and an exponential model based on thermal attenuation characteristics to solve for the depth parameter. The linear regression model based on thermal gradient propagation characteristics is as follows:

[0077] ;

[0078] Where L represents the length parameter, i.e., the actual length of the crack; α represents the first constant coefficient; β represents the second constant coefficient, and both α and β are determined experimentally; T| represents the magnitude of the temperature gradient vector, reflecting the intensity of spatial temperature changes; Denotes a length element, a differential length element along the crack propagation path, used for | T| accumulates the points;

[0079] The curve fitting model for the edge gradient change is as follows:

[0080] ;

[0081] Where W represents the width parameter, i.e., the actual width of the crack; σ represents the standard deviation, which represents the dispersion of the crack edge gradient change data distribution, calculated from the temperature gradient data of the crack edge pixels in the dynamic thermal image sequence; ln represents the logarithmic function.

[0082] The exponential model for thermal decay characteristics is as follows:

[0083] ;

[0084] Where D represents the depth parameter, i.e. the actual depth of the crack; The maximum possible depth is determined by the thickness of the electrode material and the resolution of the detection system; exp represents the exponential function; λ represents the material attenuation coefficient; and ΔT represents the surface temperature difference, the difference in surface temperature between the cracked area and the normal area.

[0085] Figure 2This is an exemplary block diagram of the system for identifying cracks in the electrode plates of a backup battery in a communication base station using thermal imaging, as described in this invention. This invention also provides a system for identifying cracks in the electrode plates of a backup battery in a communication base station using thermal imaging, such as... Figure 2 As shown, it includes: a constant temperature heating platform, a pulsed thermal excitation signal source, an infrared thermal imager and a data processing unit, as well as a standard crack database. The functions of each component are as follows:

[0086] Constant temperature heating platform: used to heat the battery electrode to be tested to the target temperature range and maintain the temperature stability. Its heating power density is adjustable from 10W / cm² to 50W / cm².

[0087] Pulsed thermal excitation signal source: used to continuously apply pulsed thermal excitation signals to the surface of battery electrodes.

[0088] Infrared thermal imager: used to acquire thermal distribution image data of the electrode surface, including reference thermal images and dynamic thermal image sequences. The single frame acquisition time is set to <10ms to ensure the timeliness of data acquisition.

[0089] Data processing unit: Used to execute multiphysics coupling analysis algorithms and deep learning algorithms to complete feature extraction, model building, crack screening and comparison analysis.

[0090] Standard Crack Database: Stores three-dimensional thermal gradient models of various crack types, along with their corresponding classification labels and dimensional parameters, providing a benchmark for crack identification.

[0091] The detection method of this invention combines non-contact thermal imaging detection and pulsed thermal excitation signals as core technologies. By using a GPU-accelerated multiphysics coupling analysis algorithm, it can achieve millisecond-level data processing speed, efficiently complete the acquisition of thermal distribution images on the electrode surface and the extraction of crack region features, fully meeting the detection efficiency requirements of large-scale production lines. At the same time, the training data of its deep learning algorithm adopts a mixed dataset of experimentally collected samples and simulation-generated data, which can cover crack features of different types and sizes, effectively ensuring the accuracy of crack identification and laying the foundation for subsequent accurate classification and quantification. Furthermore, this method relies on the established three-dimensional thermal gradient model and a pre-set standard crack database for comparative analysis, which can further improve the efficiency and accuracy of crack detection. It can also acquire the thermal distribution image data of the entire electrode sheet at once, avoiding the limitations of local detection. Its non-contact detection characteristics do not damage the performance of the battery electrode sheet material throughout the process, and it is compatible with the backup battery electrode sheets of communication base stations with various material properties. It effectively solves the shortcomings of existing technologies in the detection of micro-cracks and complex working conditions. At the same time, it can be combined with the production line MES system to realize rapid identification, comparison analysis and continuous detection of electrode sheet cracks, and completely overcome the current technical difficulties in crack identification accuracy and adaptability to rapid detection on large-scale production lines.

[0092] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for identifying a crack in a plate of a standby battery for a communication base station using thermography, characterized by, The method comprises the following steps: Step 1, heating the battery pole piece to a target temperature range, and collecting thermal distribution image data of the surface of the battery pole piece to obtain a baseline reference thermal image; Step 2, continuously applying a pulsed thermal excitation signal to the surface of the battery pole piece, and collecting dynamic thermal distribution image data of the surface of the battery pole piece to obtain a dynamic thermal image sequence; Step 3, processing the baseline reference thermal image and the dynamic thermal image sequence by a multi-physical field coupling analysis algorithm to extract the characteristic intensity distribution of the suspected crack area; Step 4, constructing a three-dimensional thermal gradient model according to the characteristic intensity distribution of the suspected crack area, and screening the suspected crack area based on the three-dimensional thermal gradient model to obtain a real crack area, comprising: establishing a correlation mapping relationship between a two-dimensional image coordinate and a temperature value based on the characteristic intensity distribution; setting the crack detection area of the battery pole piece as an XY plane, and setting a Z axis vertical direction to represent a temperature gradient to obtain a spatial structure of the three-dimensional thermal gradient model; constructing the three-dimensional thermal gradient model based on the correlation mapping relationship and the spatial structure of the three-dimensional thermal gradient model; the expression of the three-dimensional thermal gradient model is: ； wherein G(x, y, z) represents a three-dimensional thermal gradient value of a pixel point with coordinates (x, y) in a two-dimensional image in a three-dimensional thermal gradient model (x, y, z); F(x, y) represents a spatial gradient of the feature intensity distribution F(x, y) at the two-dimensional plane coordinates (x, y); denotes derivation with respect to the time sequence t; T(x, y, t) represents a temperature value of the pixel point (x, y) at the time sequence t; t represents a time sequence variable; screening the three-dimensional thermal gradient model of the suspected crack area based on a characteristic intensity threshold to obtain a real crack area; Step 5, comparing the three-dimensional thermal gradient model of the real crack area with a standard crack library to determine a crack type and a crack size.

2. The method of claim 1, wherein the method further comprises: The target temperature range is 40-80℃, and the power density range of heating is 10-50W / cm².

3. The method of claim 1, wherein the method further comprises: The waveform of the pulsed thermal excitation signal is a square wave or a sine wave, the frequency is 1-50Hz, the amplitude is 10-50W, and the duration is 1-10s.

4. The method of claim 1, wherein the method further comprises: identifying the crack in the battery plate by using thermal imaging. The multi-physical field coupling analysis algorithm is: ； where F(x, y) represents a feature intensity distribution function; represents the start application time of the pulsed thermal excitation signal; represents the end application time of the pulsed thermal excitation signal; T(x, y, t) represents the temperature value of the pixel point (x, y) at the t time sequence; x and y represent the horizontal and vertical coordinates of the thermal image, respectively; represents the reference temperature value of the pixel point (x, y) in the reference thermal image; represents the highest temperature in the dynamic thermal image sequence; represents the lowest temperature in the dynamic thermal image sequence; represents the integral of time over the application time period of the pulsed thermal excitation signal.

5. The method of claim 1, wherein the method further comprises: identifying the crack in the battery plate using thermal imaging. determining the crack type, comprising: calculating the similarity of the three-dimensional gradient vector of the real crack area and the three-dimensional gradient vector of the crack sample to obtain a global thermal gradient similarity; the three-dimensional gradient vector refers to a vector obtained by gradient calculation on the three-dimensional thermal gradient model of the crack; evaluating the goodness of fit of the three-dimensional spatial structure of the real crack area and the three-dimensional spatial structure of the crack sample by Hausdorff distance to obtain a three-dimensional morphological similarity; the three-dimensional spatial structure refers to the spatial structure of the three-dimensional thermal gradient model of the crack; calculating the divergence of temperature in the three-dimensional thermal gradient model vector field to obtain a thermal gradient vector field divergence feature; quantifying the heat aggregation degree of the crack area by an energy calculation formula to obtain a crack heat aggregation effect; verifying the thermal response data and material characteristic data of the real crack and the crack sample based on a coupling equation group to obtain a data verification result; the crack sample refers to a crack sample stored in a crack standard database; the coupling equation group comprises a non-steady-state heat conduction equation and an elastic mechanics equation; outputting the crack type by integrating the global thermal gradient similarity, the three-dimensional morphological similarity, the thermal gradient vector field divergence feature, the crack heat aggregation effect and the data verification result.

6. The method of claim 5, wherein the method further comprises: The similarity of the three-dimensional gradient vector of the real crack area and the three-dimensional gradient vector of the crack sample is calculated as: ； wherein Sim denotes a global thermal gradient similarity; a three-dimensional gradient vector representing a real crack region; a three-dimensional gradient vector representing a crack sample; denotes a weight vector; the divergence of temperature in the three-dimensional thermal gradient model vector field is calculated as: ； where divG represents the divergence characteristic of the thermal gradient vector field; , and represent the components of the three-dimensional thermal gradient model vector field in the x, y, and z directions, respectively; , and represent the partial derivatives with respect to the x, y, and z directions, respectively. the energy calculation formula is: ； Wherein, E represents the thermal aggregation effect at the crack; p represents the material density; c represents the specific heat capacity of the material; ΔT represents the temperature change; dV represents the volume element; The non-steady-state heat conduction equation is: ； The equation of elasticity is: ； wherein, denotes the partial derivative of the temperature T of the surface of the battery electrode sheet with respect to the time t; denotes the heat conduction term; k denotes the thermal conductivity of the material; Q denotes the internal heat source term; T denotes the temperature gradient vector; denotes the divergence operator; denotes the fourth order elasticity tensor; denotes the strain tensor; denotes the displacement vector; denotes the transpose operation; denotes the strain caused by thermal expansion; a denotes the thermal expansion coefficient of the material; T denotes the temperature value at the current time t; denotes the reference temperature value; denotes the volume force density.

7. The method of claim 1, wherein the method further comprises: identifying the crack in the battery plate using thermal imaging. The crack size is determined, including: A linear regression model of thermal gradient extension characteristics is used to solve the length parameter; A curve fitting model of edge gradient change is used to solve the width parameter; An exponential model based on thermal attenuation characteristics is used to solve the depth parameter.

8. The method of claim 7, wherein the method further comprises: The linear regression model of thermal gradient extension characteristics is: ； wherein L represents a length parameter; represents a first constant coefficient; β represents a second constant coefficient; T| represents the magnitude of the temperature gradient vector; represents a length differential. The curve fitting model of edge gradient change is: ； Wherein, W represents the width parameter; σ represents the standard deviation; ln represents the logarithmic function; The exponential model based on thermal attenuation characteristics is: ； where D represents a depth parameter; where D represents a depth parameter; Dmax represents a maximum depth; exp represents an exponential function; λ represents a material attenuation coefficient; and ΔT represents a surface temperature difference.

9. A system for identifying a crack in a plate of a backup battery of a communication base station using thermal imaging according to any one of claims 1 to 8, wherein Including: A constant temperature heating platform, a pulse thermal excitation signal source, an infrared thermal imager and a data processing unit; The constant temperature heating platform is used to heat the battery pole piece to the target temperature range; The infrared thermal imager is used to collect the thermal distribution image data of the surface of the battery pole piece, to obtain the reference reference thermal image; collect the dynamic thermal distribution image data of the surface of the battery pole piece, to obtain the dynamic thermal image sequence; The pulse thermal excitation signal source is used to continuously apply a pulse thermal excitation signal to the surface of the battery pole piece; The data processing unit is used to process the reference reference thermal image and the dynamic thermal image sequence through a multi-physical field coupling analysis algorithm, to extract the characteristic intensity distribution of the suspected crack area; according to the characteristic intensity distribution of the suspected crack area, a three-dimensional thermal gradient model is constructed, and the suspected crack area is screened based on the three-dimensional thermal gradient model, to obtain the real crack area; the three-dimensional thermal gradient model of the real crack area is compared with a standard crack library, to determine the crack type and the crack size.

Images