Brake disc safety performance detection method and system

Abstract

The invention relates to the technical field of image processing, in particular to a brake disc safety performance detection method and system. When the safety performance of the brake disc is detected, appearance detection, size detection and material performance detection are carried out on the brake disc, and detection is comprehensive; meanwhile, an improved adaptive filtering algorithm is adopted to carry out de-noising processing on the to-be-detected brake disc image; performing multi-scale decomposition on the to-be-detected brake disc image, and decomposing the to-be-detected brake disc image into sub-images of multiple scales; performing local feature extraction on each sub-image, and dynamically allocating weights according to the local features; performing adaptive filtering on the sub-image of each scale according to the weight so as to improve the filtering effect; the filtering intensity is dynamically adjusted according to the local variance, the gradient intensity and the texture information, so that the edges and details of the image can be better reserved, and excessive smoothness is avoided; in combination with global and local information, a self-adaptive weight is distributed for each pixel, the filtering effect is optimized, and the adaptability and robustness of the algorithm are improved.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a method and system for detecting the safety performance of a brake disc. Background Art

[0002] Brake discs are a core component of a vehicle's braking system. Their primary function is to slow the rotation of the wheels through friction with the brake pads, thereby decelerating or stopping the vehicle. Brake disc performance is directly related to the vehicle's braking effectiveness and driving safety. After production, brake discs are prone to problems such as scratches, pinholes, and shrinkage. If these problems are not promptly detected and addressed, they can lead to brake failure and, in turn, serious traffic accidents. Therefore, there is an urgent need for a method and system that can efficiently, accurately, and comprehensively test the safety performance of brake discs.

[0003] Regarding brake disc testing solutions, Chinese invention patent application CN113819878A provides a brake disc performance testing device and method, in which the brake disc is mounted on a rotating structure; a synchronous drive structure drives a flatness measuring structure and a braking structure to move and contact the side wall of the brake disc; the rotating structure drives the brake disc to rotate, and after the brake disc rotates, the flatness measuring structure measures the flatness of the brake disc; however, the above solution has the problem of incomplete testing because it only tests the flatness of the brake disc.

[0004] At the same time, in the existing technology, when using brake disc images to detect brake discs, the preprocessing or image filtering of brake disc images is a difficult point. Since the defects of brake discs are relatively rare in images, existing adaptive filtering algorithms (such as adaptive Gaussian filtering) can achieve the detection goal of brake discs to a certain extent; however, there are still deficiencies in some cases, such as insufficient detail preservation. While removing noise, important details in the image may be blurred, especially tiny sand holes and scratches. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention provides a brake disc safety performance detection method and system for solving the problems existing in the prior art.

[0006] The present invention provides a brake disc safety performance detection method, comprising the following steps: S1: Perform visual inspection on the brake disc to be tested; The step S1 comprises: S1.1: Use a camera to obtain an image of the brake disc to be inspected; S1.2: Performing image preprocessing on the brake disc image to be tested; performing denoising on the brake disc image to be tested using an improved adaptive filtering algorithm; specifically comprising: Sa: Decomposing the brake disc image to be inspected into sub-images at multiple scales through multi-scale decomposition; Sb: Extracting local features from each sub-image, including local variance, gradient intensity, and texture information; Sc: Dynamically assigning weights based on the local features; Sd: Adaptively filtering the sub-images at each scale based on the weights; Se: Multi-scale reconstructing the adaptively filtered sub-images to obtain the final filtered image; S1.3: Extracting scratch features, pore features, and shrinkage features of the brake disc to be inspected from the preprocessed image of the brake disc to be inspected; S1.4: Inputting the scratch characteristics, pore characteristics, and shrinkage characteristics of the brake disc to be tested into an image analysis model to obtain the degree of scratches, pore conditions, and shrinkage conditions of the brake disc to be tested; S1.5: Conduct a comprehensive appearance and performance evaluation of the brake disc to be tested based on the degree of scratches, pinholes, and shrinkage of the brake disc to be tested.

[0007] S2: Performing dimensional inspection on the brake disc to be inspected.

[0008] S3: Performing material property testing on the brake disc to be tested.

[0009] Preferably, in step Sa, the brake disc image to be inspected is decomposed into sub-images of multiple scales, each sub-image corresponding to image information of a different frequency; The step Sa is expressed by the formula: ; Wherein, I is the brake disc image to be detected, I s represents the sub-image of the sth scale, and S is the total number of scales.

[0010] Preferably, in step Sb, the specific formula is: ; ; ; Where (x, y) represents the pixel coordinates in the image; Window represents the local window area centered on the pixel (x, y), which is used to calculate the local statistics; N represents the number of pixels in the local window; μ s Represents the sub-image I in the local window Window s The average value of Var(I s ) represents the sub-image I in the local window Window s The local variance of x Is Represents sub-image I s Gradient in the horizontal direction; y I s Represents sub-image I s Gradient in the vertical direction; Grad(I s ) represents sub-image I s Gradient intensity of Texture(I s ) represents the sub-image I in the local window Window s Texture information of I s (x, y) represents the sub-image I s Pixels in .

[0011] Preferably, in step Sc, the formula for dynamically allocating weight ω(x, y) is: ; Among them, α(x, y), β(x, y), and γ(x, y) are weight coefficients used to balance the influence of different features; ε is a constant.

[0012] Preferably, the method for determining the weight coefficients α(x, y), β(x, y) and γ(x, y) specifically includes: Calculating the global noise level Global Var of the brake disc image to be detected; Calculating the global texture complexity Global Texture of the brake disc image to be detected; Calculate the local noise level Local Var(x,y) of each pixel (x,y) and the local texture complexity Local Texture(x,y) of each pixel (x,y); The weight coefficients α(x, y), β(x, y) and γ(x, y) are determined according to the global noise level, the global texture complexity, the local noise level of each pixel, and the local texture complexity of each pixel.

[0013] Preferably, the specific formula for determining the weight coefficients α(x, y), β(x, y) and γ(x, y) according to the global noise level, the global texture complexity, the local noise level of each pixel, and the local texture complexity of each pixel is: ; ; ; Where, is a constant.

[0014] Preferably, the step S1.1 includes: S1.1.1: Install the camera at the monitoring station, ensuring that the camera can capture images of the brake disc to be inspected from multiple angles; S1.1.2: Install an adjustable light source around the camera; S1.1.3: Obtain an image of the brake disc to be inspected.

[0015] Preferably, in step S1.1.3, obtaining the image of the brake disc to be inspected includes: Taking a surface image of the brake disc to be inspected from the front side, Taking a side image of the brake disc to be inspected from its side, The brake disc to be inspected is photographed from the top, bottom, and oblique angles of different directions.

[0016] Preferably, in step S1.2, the image preprocessing further includes grayscale processing.

[0017] According to another aspect of the present invention, a brake disc safety performance detection system is provided. The brake disc safety performance detection system adopts the above-mentioned brake disc safety performance detection method. The brake disc safety performance detection system includes: Appearance inspection module, used to perform appearance inspection on the brake disc to be inspected; A size detection module, used for performing size detection on the brake disc to be detected; The material performance testing module is used to perform material performance testing on the brake disc to be tested.

[0018] Compared with the prior art, the present invention has the following technical effects: When testing the safety performance of brake discs, the brake discs are subjected to appearance inspection, size inspection and material performance inspection, and the inspection is comprehensive; at the same time, the present invention adopts an improved adaptive filtering algorithm to denoise the brake disc image to be tested; the brake disc image to be tested is decomposed into sub-images of multiple scales by multi-scale decomposition; local features are extracted from each sub-image, and the local features include local variance, gradient intensity and texture information; weights are dynamically assigned according to local features; the sub-images of each scale are adaptively filtered according to the weights; by analyzing and processing images at multiple scales, high-frequency noise (such as random noise) and low-frequency noise (such as uneven lighting) can be removed simultaneously, thereby improving the filtering effect; the filtering intensity is dynamically adjusted according to the local variance, gradient intensity and texture information, thereby better retaining the edges and details of the image and avoiding over-smoothing; combining global and local information, an adaptive weight is assigned to each pixel, the filtering effect is optimized, and the adaptability and robustness of the algorithm are improved.

[0019] At the same time, the present invention proposes a method for determining weight coefficients in the adaptive filtering process, which is dynamically adjusted according to the local and global features of the image, and can better adapt to different types of images and noise distributions; at the same time, by combining global and local features, it can better balance noise removal, detail preservation and texture processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 This is a flow chart of a brake disc safety performance testing method provided by an embodiment of the present invention; Figure 2 This is a flow chart of performing appearance inspection on a brake disc to be inspected provided by an embodiment of the present invention; Figure 3 This is a flowchart of performing denoising on the brake disc image to be detected using an improved adaptive filtering algorithm provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention are described clearly and completely below. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are also within the scope of protection of the present invention.

[0023] Example 1 like Figure 1 As shown, a brake disc safety performance testing method includes the following steps: S1: Perform visual inspection on the brake disc to be tested; Among them, such as Figure 2 As shown, step S1 specifically includes: S1.1: Use a camera to obtain an image of the brake disc to be inspected; Image acquisition is the first step in brake disc safety performance testing. Its goal is to obtain high-quality brake disc images, providing a reliable data foundation for subsequent image preprocessing, feature extraction, and safety performance evaluation. High-quality brake disc images can more clearly reveal surface features such as scratches, pinholes, and shrinkage, thereby improving the accuracy and reliability of testing.

[0024] To ensure that the collected images meet the detection requirements, a high-resolution industrial camera is used as the image acquisition device in this step. The high-resolution industrial camera is preferably an SVS-Vistek SHR series camera with a resolution of 25 million pixels (5120×5120). It uses a CMOS sensor, which has the advantages of high sensitivity, low power consumption, and fast reading speed. The frame rate of this high-resolution industrial camera is 23fps (12 million pixels), which is suitable for dynamic scenes and fast continuous shooting.

[0025] Furthermore, step S1.1 specifically includes: S1.1.1: Install the camera at the monitoring station, ensuring that the camera can capture the brake disc to be inspected from multiple angles; The position and angle of the camera should be adjusted according to the size and shape of the brake disc to ensure that the captured image can cover the entire surface and sides of the brake disc.

[0026] S1.1.2: Install adjustable light sources around the camera. The adjustable light source can ensure that light is evenly irradiated on the surface of the brake disc. The intensity and angle of the adjustable light source should be adjusted according to the material and surface reflection characteristics of the brake disc to avoid reflected light interfering with image acquisition.

[0027] Before formally capturing images, debug the camera and adjustable light source to ensure that the camera's autofocus and lighting adjustment functions are working properly. By taking a small number of test images, check the image clarity, contrast, and brightness, and adjust the camera parameters and light source settings until a satisfactory image is obtained.

[0028] S1.1.3: Obtain an image of the brake disc to be inspected; Among them, step S1.1.3 specifically includes: Capture the surface image of the brake disc to be inspected from the front. Adjust the camera to the optimal focal length to ensure that the image clearly reflects scratches, pinholes, and other defects on the disc surface. To improve the comprehensiveness of the inspection, capture surface images from multiple angles, such as shooting from the center outward and capturing the edge area from different directions. Take a side image from the side of the brake disc to be inspected. This side image is mainly used to detect shrinkage conditions of the brake disc to be inspected, such as uneven thickness and bending. The camera should be adjusted to a suitable height and angle to ensure that the side profile of the brake disc to be inspected can be clearly captured; To more comprehensively assess the brake disc's safety performance, step S1.1.3 also includes photographing the brake disc from multiple angles. For example, the top, bottom, side, and oblique angles of the disc under inspection can be captured to obtain image information from a wider range of angles. Multi-angle photography effectively avoids missing features that might be missed from a single angle, improving inspection accuracy.

[0029] S1.2: Perform image preprocessing on the brake disc image to be inspected; The purpose of image preprocessing is to perform preliminary processing on the collected images to improve image quality, enhance key features, and provide a better data foundation for subsequent feature extraction and analysis. In this step, image preprocessing mainly includes grayscale processing and denoising.

[0030] Grayscaling is the process of converting a color image into a grayscale image. Color images typically contain three color channels (red, green, and blue), each with its own pixel value. Grayscaling combines the three color channel information into a single grayscale channel, where the grayscale value of each pixel represents its brightness.

[0031] In this step, the weighted average method is used to grayscale the brake disc image to be inspected; Specifically, the weighted average method assigns different weights to the three color channels (red, green, and blue) based on the human eye's sensitivity to different colors and calculates the grayscale value Gray; the calculation formula is: ; Where R, G, and B are the pixel values ​​of the red, green, and blue channels, respectively.

[0032] Among them, this step uses an improved adaptive filtering algorithm to perform denoising on the brake disc image to be inspected; in brake disc detection, the purpose of image preprocessing is to remove noise while retaining key features (such as sand holes, scratches, etc.). Although existing adaptive filtering algorithms (such as adaptive Gaussian filtering) can achieve this goal to a certain extent, they still have shortcomings in some cases; for example, details are not sufficiently retained, and while removing noise, important details in the image (especially tiny sand holes and scratches) may be blurred. Based on this, this embodiment proposes an improved adaptive filtering algorithm that combines multiple filtering strategies and optimization mechanisms to improve the filtering effect; specifically, such as Figure 3 As shown in the figure, the specific steps of using the improved adaptive filtering algorithm to denoise the brake disc image to be detected include: Sa: Perform multi-scale decomposition on the brake disc image to be inspected, decomposing it into sub-images of multiple scales; The brake disc image I to be inspected is decomposed into sub-images of multiple scales, each sub-image corresponding to image information of different frequencies; In this step, Gaussian pyramid decomposition is used to decompose the brake disc image to be inspected into sub-images of multiple scales; Specifically, step Sa is expressed by the formula: ; Among them, I is the brake disc image to be detected, I s represents the sub-image of the sth scale, and S is the total number of scales.

[0033] Sb: Extract local features of each sub-image, including local variance, gradient intensity and texture information; Among them, local variance is used to measure the noise level, gradient strength is used to detect edges, and texture information is used to identify complex areas; The specific formula is:

[0034]

[0035] ; Where (x, y) represents the pixel coordinates in the image; Window represents the local window area centered on the pixel (x, y), which is used to calculate the local statistics; N represents the number of pixels in the local window; μ s Represents the sub-image I in the local window Window s The average value of Var(I s ) represents the sub-image I in the local window Window s The local variance of x I s Represents sub-image I s Gradient in the horizontal direction; y I s Represents sub-image I s Gradient in the vertical direction; Grad(I s ) represents sub-image I s Gradient intensity of Texture(I s ) represents the sub-image I in the local window Window s Texture information of I s (x, y) represents the sub-image I s Pixels in .

[0036] Sc: Dynamically assign weights based on the local features; Dynamically assign weights based on local features to optimize filtering effects; Specifically, the weight distribution strategy is as follows: 1. Noise suppression weight: Assign larger weights to high variance areas (more noise) to enhance noise suppression; 2. Detail-preserving weight: Assign smaller weights to high-gradient areas (edges and details) to avoid over-smoothing; 3. Texture weight: Assign moderate weight to areas with complex textures to balance noise removal and detail preservation.

[0037] Specifically, the formula for dynamically assigning weight ω(x, y) is: ; Among them, α(x, y), β(x, y), and γ(x, y) are weight coefficients used to balance the influence of different features; ε is a constant.

[0038] Furthermore, this embodiment proposes a method for determining weight coefficients α(x, y), β(x, y), and γ(x, y), which specifically includes: Calculate the global noise level Global Var of the brake disc image to be inspected; The calculation formula of the global noise level is: ; Where M and N are the width and height of the brake disc image to be tested, μ is the global average value of the brake disc image to be tested, and I(x, y) is the brake disc image to be tested; Calculate the global texture complexity of the brake disc image to be detected; The calculation formula for global texture complexity is: ; Calculate the local noise level Local Var(x,y) and the local texture complexity Local Texture(x,y) of each pixel (x,y); the specific formula is as follows: ; ; Where I(x+u,y+v) is the pixel value in the local window centered at (x,y) with an offset of (u,v); μlocal is the average value in the local window; The weight coefficients α(x, y), β(x, y), and γ(x, y) are determined according to the global noise level, global texture complexity, the local noise level of each pixel, and the local texture complexity of each pixel. The specific formula is: ; ; .

[0039] The weight coefficients α, β, and γ are dynamically adjusted according to the local and global features of the image, which can better adapt to different types of images and noise distributions. At the same time, by combining global and local features, it can better balance noise removal, detail preservation, and texture processing.

[0040] Sd: Adaptive filtering of sub-images at each scale according to the weights; Use Gaussian filtering to smooth the sub-images at each scale, and adjust the filter strength according to the weight: ; Among them, I' s (x, y) represents the smoothed sub-image; G(u, v; σ(x, y)·w(x, y)) represents the Gaussian kernel calculated based on the standard deviation adjusted by adaptive weights. The core of Gaussian filtering is the Gaussian kernel, which is a discretized version of a two-dimensional Gaussian function. The shape of the Gaussian kernel is determined by the standard deviation. The larger the standard deviation, the more dispersed the distribution of the Gaussian kernel, and vice versa. Gaussian kernels are mainly used in image processing for smoothing, blurring, and edge detection. By applying the Gaussian kernel to an image, image filtering can be achieved, thereby reducing noise and improving image quality. At the same time, the Gaussian kernel can also be used for edge detection. By performing Gaussian filtering on the second-order difference of the image, edge information in the image can be extracted.

[0041] Se: Multi-scale reconstruction of each scale sub-image of the adaptive filter is performed to obtain the final filtered image I filtered ; ; In this embodiment, by analyzing and processing images at multiple scales, high-frequency noise (such as random noise) and low-frequency noise (such as uneven lighting) can be removed simultaneously, thereby improving the filtering effect; the filtering intensity is dynamically adjusted according to the local variance, gradient strength, and texture information, which can better preserve the edges and details of the image and avoid over-smoothing; by combining global and local information, an adaptive weight is assigned to each pixel, optimizing the filtering effect and improving the adaptability and robustness of the algorithm.

[0042] S1.3: Extracting scratch features, pinhole features, and shrinkage features of the brake disc to be inspected from the preprocessed image of the brake disc to be inspected; The scratch feature characterizes the size of scratches on the brake disc surface. Scratches typically appear as areas with low grayscale values, as scratches reduce surface reflectivity. Scratch features include the mean grayscale value of the scratched area and the percentage of the scratched area. The pore feature characterizes the presence of pores on the brake disc surface. These pores typically appear as areas with low grayscale values, including pore area, pore length, and pore count. The shrinkage feature characterizes the profile changes of the brake disc side image, reflecting the presence of shrinkage. These shrinkage features include pore area, pore length, and pore count.

[0043] S1.4: Input the scratch characteristics, pore characteristics, and shrinkage characteristics of the brake disc to be tested into the image analysis model to obtain the scratch degree, pore condition, and shrinkage condition of the brake disc to be tested.

[0044] Among them, the degree of scratches includes: mild, moderate, and severe; the trachoma situation includes none, mild, moderate, and severe; the shrinkage situation includes none, mild, and severe.

[0045] In this step, the image analysis model is a convolutional neural network. A convolutional neural network (CNN) is a deep learning model particularly suited for processing image data. This CNN automatically learns feature representations in an image through a combination of convolutional, pooling, and fully connected layers. Convolutional layers extract local features, pooling layers reduce the spatial dimensionality of features, and fully connected layers perform classification or regression.

[0046] During brake disc inspection, a convolutional neural network model, trained on a large amount of labeled image data, can automatically identify the extent of scratches, pinholes, and shrinkage on brake discs. The model outputs the classification result and confidence level for each feature, providing a basis for subsequent safety performance assessments.

[0047] Specifically, the model structure of the convolutional neural network model is as follows: Input layer: The input image size is 224×224×3.

[0048] Convolutional layer: Multiple convolutional layers extract local features of the image.

[0049] Pooling layer: Multiple pooling layers reduce the spatial dimension of features.

[0050] Fully connected layers: Multiple fully connected layers for classification.

[0051] Output layer: The output layer contains three classification tasks (scratch degree, pinhole condition, and shrinkage condition), and each task has multiple categories.

[0052] Loss Function and Optimizer: Select the cross entropy loss function and the Adam optimizer. During training, adjust the learning rate to 0.001 and the batch size to 32.

[0053] Training Process: A convolutional neural network model is trained using labeled image data. During training, hyperparameters such as the learning rate and batch size are adjusted to optimize model performance. The training process consists of 50 epochs (one epoch requires 50 iterations), each of which includes forward propagation, loss calculation, backpropagation, and parameter updates.

[0054] Model evaluation: Use the validation set to evaluate the model's performance. Evaluation metrics include accuracy, recall, precision, and F1 score. Optimize the model based on the evaluation results.

[0055] Model deployment: The features extracted from the image are fed into the trained CNN model. The model outputs the classification result and confidence level for each feature. Based on the model's output, a comprehensive assessment of the brake disc's safety performance is performed.

[0056] S1.5: Conduct a comprehensive appearance performance evaluation of the brake disc to be tested based on the degree of scratches, pinholes, and shrinkage.

[0057] In order to comprehensively evaluate the appearance performance of the brake disc to be tested, different characteristics (scratch degree, pinhole condition, shrinkage condition) need to be assigned different weights, and then the comprehensive safety performance score is obtained by weighted summation. The distribution of weights should be based on the degree of influence of each characteristic on the safety performance of the brake disc.

[0058] The weights are set as follows: the weight of the scratch degree ω1=0.4; the weight of the sand hole situation ω2=0.4; the weight of the shrinkage situation ω3=0.2.

[0059] The degree of scratches, pinholes, and shrinkage of the brake disc to be tested is quantified into a score; in this step, the score is determined using an expert scoring method; Specifically: mild scratches (1 point), moderate scratches (2 points), severe scratches (3 points); no trachoma (1 point), mild trachoma (2 points), moderate trachoma (3 points), severe trachoma (4 points); no shrinkage (1 point), mild shrinkage (2 points), severe shrinkage (3 points).

[0060] S2: Dimensional inspection of the brake disc to be inspected; As a core component of a vehicle's braking system, the dimensional accuracy of the brake disc directly impacts braking performance, vehicle stability, and safety. Dimensional testing aims to ensure that the disc's geometric dimensions meet design requirements, preventing issues such as reduced braking performance, brake noise, and brake judder caused by dimensional deviations.

[0061] Specifically, a laser triangulation sensor array, a turntable station, and a positioning fixture are used to realize the size detection of the brake disc to be detected.

[0062] The laser triangulation sensor array uses multiple high-precision laser triangulation sensors (such as the KEYENCEL J-V series) arranged around the brake disc to form a 360-degree detection ring. The number of laser triangulation sensors is determined by the required detection accuracy and speed, and is generally no less than six.

[0063] The turntable station is used to place the brake disc to be tested on a rotatable turntable. The turntable is driven by a high-precision servo motor to ensure rotation accuracy and speed stability. The rotation angle of the turntable is fed back by a high-precision rotary encoder, which is used to synchronize the measurement data of the laser sensor.

[0064] The positioning fixture is used to position and fix the brake disc to be tested on the turntable to ensure the stability of the brake disc during the measurement process.

[0065] The laser triangulation sensor emits a laser beam to the surface of the brake disc to be tested. The laser is reflected by the surface of the brake disc to be tested and then received by the laser triangulation sensor. By measuring the change in the laser reflection angle, the distance between the measured point of the brake disc to be tested and the sensor is calculated, thereby realizing the detection of the thickness and flatness of the brake disc to be tested.

[0066] S3: Conduct material performance test on the brake disc to be tested; The material properties of brake discs directly determine their braking performance and service life under high-temperature and high-load conditions. Even slight changes in material properties can lead to reduced braking performance, increased thermal decay, fatigue fracture, and other issues, posing safety risks.

[0067] Among them, eddy current heaters, infrared thermal imagers, electromagnetic ultrasonic transducers and data acquisition and processing systems are used to carry out material performance testing on the brake disc to be tested.

[0068] Furthermore, the eddy current heater uses high-frequency eddy current heating technology, which can evenly heat the brake disc to a set temperature (such as 120℃±2℃) in a short time. The power and heating time of the eddy current heater can be adjusted according to the material and size of the brake disc.

[0069] Infrared thermal imagers are used to obtain the temperature field distribution on the brake disc surface. The resolution and frame rate of the infrared thermal imager must meet high-precision measurement requirements. For example, the FLIR A655sc thermal imager has a resolution of up to 640×480 pixels and a frame rate of up to 120Hz.

[0070] Electromagnetic ultrasonic transducers (EMATs) are used to excite and receive ultrasonic signals and measure the acoustic properties of materials. The EMAT probe excites transverse and longitudinal waves on the material surface through the principle of electromagnetic induction, eliminating the need for coupling agents and making it suitable for high-temperature environments.

[0071] The data acquisition and processing system includes a high-speed data acquisition card, a signal processing module and an industrial PC, which is used to collect and process the measurement data of the infrared thermal imager and the electromagnetic ultrasonic transducer in real time.

[0072] After the eddy current heater completes heating, the infrared thermal imager captures the temperature field image of the brake disc surface to calculate the thermal conductivity (λ) and specific heat capacity (c) of the brake disc material. The calculated values ​​are then compared with standard values ​​to determine whether the material properties meet the requirements. For example, for gray cast iron HT250 brake discs, the standard values ​​for thermal conductivity are 45±3W / (m·K) and specific heat capacity are 0.5±0.05kJ / (kg·K).

[0073] After the brake disc to be tested is heated to a set temperature, an electromagnetic ultrasonic transducer probe is used to excite shear and longitudinal waves on the disc surface. The probe's excitation frequency is optimized based on the material's characteristics, typically within the 1-5 MHz range. The probe receives the reflected ultrasonic signal and transmits it to a data processing system via a high-speed data acquisition card. The acquired signals include the acoustic time difference (TOF) and amplitude of the shear and longitudinal waves. The Young's modulus (E) and Poisson's ratio (ν) of the brake disc material to be tested are then calculated based on the TOF and amplitude data. The calculated values ​​are then compared with standard values ​​to verify the material properties of the disc. For example, for gray cast iron HT250 brake discs, the standard values ​​for Young's modulus are 110 ± 5 GPa, and for Poisson's ratio are 0.25 ± 0.02. If the detected material performance parameters deviate from the standard range, the brake disc material is deemed unqualified.

[0074] Example 2 The present invention further provides a brake disc safety performance detection system, which adopts a brake disc safety performance detection method of embodiment 1. The brake disc safety performance detection system includes: Appearance inspection module, used to perform appearance inspection on the brake disc to be inspected; Size detection module, used to perform size detection on the brake disc to be inspected; The material performance testing module is used to perform material performance testing on the brake disc to be tested.

[0075] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A brake disc safety performance testing method, characterized in that: The following steps are involved: S1: Perform visual inspection on the brake disc to be tested; The step S1 comprises: S1.1: Use a camera to obtain an image of the brake disc to be inspected; S1.2: Perform image preprocessing on the brake disc image to be tested; perform denoising on the brake disc image to be tested using an improved adaptive filtering algorithm, specifically: Sa: Perform multi-scale decomposition on the brake disc image to be tested into sub-images of multiple scales; Sb: Extract local features from each sub-image, where the local features include local variance, gradient intensity, and texture information; Sc: Dynamically assign weights based on the local features; Sd: Perform adaptive filtering on the sub-images of each scale based on the weights; Se: Perform multi-scale reconstruction on the adaptively filtered sub-images to obtain the final filtered image; S1.3: Extracting scratch features, pore features, and shrinkage features of the brake disc to be inspected from the preprocessed image of the brake disc to be inspected; S1.4: Inputting the scratch characteristics, pore characteristics, and shrinkage characteristics of the brake disc to be tested into an image analysis model to obtain the degree of scratches, pore conditions, and shrinkage conditions of the brake disc to be tested; S1.5: Conduct a comprehensive appearance and performance evaluation of the brake disc to be tested based on the degree of scratches, pinholes, and shrinkage. S2: Performing size inspection on the brake disc to be inspected; S3: Performing material property testing on the brake disc to be tested.

2. A brake disc safety performance testing method according to claim 1, characterized in that: In the step Sa, the brake disc image to be inspected is decomposed into sub-images of multiple scales, each sub-image corresponding to image information of a different frequency; The step Sa is expressed by the formula: ； Wherein, I is the brake disc image to be detected, I s represents the sub-image of the sth scale, and S is the total number of scales.

3. A brake disc safety performance testing method according to claim 2, characterized in that: In the step Sb, the specific formula is: ； ； ； Where (x, y) represents the pixel coordinates in the image; Window represents the local window area centered on the pixel (x, y), which is used to calculate the local statistics; N represents the number of pixels in the local window; μ s Represents the sub-image I in the local window Window s The average value of Var(I s ) represents the sub-image I in the local window Window s The local variance of x I s Represents sub-image I s Gradient in the horizontal direction; y I s Represents sub-image I s Gradient in the vertical direction; Grad(I s ) represents sub-image I s Gradient intensity; Texture(Is) represents the texture information of the sub-image Is in the local window Window; Is(x, y) represents the sub-image I s Pixels in .

4. A brake disc safety performance testing method according to claim 3, characterized in that: In the step Sc, the formula for dynamically allocating weight ω(x, y) is: ； Among them, α(x, y), β(x, y), and γ(x, y) are weight coefficients used to balance the influence of different features; ε is a constant.

5. A brake disc safety performance testing method according to claim 4, characterized in that: The method for determining the weight coefficients α(x, y), β(x, y) and γ(x, y) includes: Calculating the global noise level Global Var of the brake disc image to be detected; Calculating the global texture complexity Global Texture of the brake disc image to be detected; Calculate the local noise level Local Var(x,y) of each pixel (x,y) and the local texture complexity Local Texture(x,y) of each pixel (x,y); The weight coefficients α(x, y), β(x, y) and γ(x, y) are determined according to the global noise level, the global texture complexity, the local noise level of each pixel, and the local texture complexity of each pixel.

6. A brake disc safety performance testing method according to claim 5, characterized in that: The specific formula for determining the weight coefficients α(x, y), β(x, y) and γ(x, y) according to the global noise level, global texture complexity, the local noise level of each pixel, and the local texture complexity of each pixel is: ； ； ； Where, is a constant.

7. A brake disc safety performance testing method according to claim 1, characterized in that: The step S1.1 includes: S1.1.1: Install the camera at the monitoring station, ensuring that the camera can capture images of the brake disc to be inspected from multiple angles; S1.1.2: Install an adjustable light source around the camera; S1.1.3: Obtain an image of the brake disc to be inspected.

8. A brake disc safety performance testing method according to claim 7, characterized in that: In step S1.1.3, obtaining the image of the brake disc to be inspected includes: Taking a surface image from the front side of the brake disc to be inspected, Taking a side image from the side of the brake disc to be inspected, The brake disc to be inspected is photographed from the top, bottom, and oblique angles of different directions.

9. A brake disc safety performance testing method according to claim 1, characterized in that: In the step S1.2, the image preprocessing further includes grayscale processing.

10. A brake disc safety performance detection system, characterized in that: The brake disc safety performance detection system adopts a brake disc safety performance detection method according to any one of claims 1 to 9, and the brake disc safety performance detection system includes: Appearance inspection module, used to perform appearance inspection on the brake disc to be inspected; A size detection module, used for performing size detection on the brake disc to be detected; The material performance testing module is used to perform material performance testing on the brake disc to be tested.

Images