Method for detecting thermal information on surface of brake disc under dynamic operating conditions by means of computerized processing

Through computerized processing and image analysis technology, the brake disc heat information under dynamic conditions is automatically detected and analyzed, and the problem of time-consuming and unobjective detection in the existing technology is solved, and fast and accurate hot spot positioning and temperature distribution analysis is achieved. .

CN119032029APending Publication Date: 2024-11-26FRENI BREMBO SPA
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202280085455.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2021-12-23
Filing Date
2022-12-19
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

When the prior art detects and analyzes the brake disc heat hot spot phenomenon under dynamic operating conditions, it lacks automation and accuracy, and relies on manual operations to cause time-consuming and unobjective results.

Method used

Using computerized processing methods, digital images and videos are obtained through thermal imaging cameras, masks are generated using image analysis algorithms, hot spots are identified and positioned, thermal analysis is performed, and information on the surface temperature evolution and hot spot distribution of brake discs are automatically extracted.

Benefits of technology

Automatic detection of brake disc heat information under dynamic conditions is achieved, the accuracy and efficiency of the analysis is improved, manual intervention is reduced, and the objectivity and repeatability of the results are ensured.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119032029A_ABST
    Figure CN119032029A_ABST
Patent Text Reader

Abstract

A method is described for automatically detecting, by computerized processing, information about the temperature evolution on the surface of a brake disc under dynamic operating conditions and / or information about the location / distribution of hot spots and / or tropical zones and / or hot zones on the surface of a brake disc under dynamic operating conditions. The method comprises the following steps: acquiring a plurality of digital images and / or digital videos; a representation of each of the digital images and / or digital video frames is obtained in the form of matrix data, which representation is processed by an algorithm including an image analysis or a "computer vision" algorithm, the method may include providing information about temperature evolution and / or location / distribution of hot spots and / or tropical zones and / or hot zones on a region of interest of the surface of the brake disc to obtain and provide information about temperature evolution and / or location / distribution of the hot spots and / or tropical zones and / or hot zones on the region of interest of the surface of the brake disc. The aforementioned obtaining step comprises obtaining, by means of at least one thermal imaging camera, a plurality of digital images and / or digital videos (including a plurality of digital frames) of at least one region of interest of the brake disc to be thermally characterized during evolution of the aforementioned dynamic operating conditions. Each of the digital images and / or each of the digital video frames depicts the temperature detected at each point by a color map. The processing steps comprise the steps of: identifying the region of interest by generating a mask based on an analysis of the acquired plurality of digital images and / or digital video frames; then, applying the generated mask to each of the acquired digital images and / or digital video frames, and obtaining processed matrix data related to the region of interest; then defining an analysis region and thermally analyzing the data relating to the defined analysis region to obtain information about the temperature evolution at each point of interest; finally, a hot spot is identified based on the information on the temperature evolution at each point of interest. The providing step comprises providing the obtained information in the form of digital images or graphics and / or digital tables and / or digital videos.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a method for automatically detecting thermal information on the surface of a brake disc under dynamic operating conditions by computerized processing.

[0002] In particular, the invention relates to a method for automatically detecting information about the temperature evolution and / or the location / distribution of hot spots and / or hot zones and / or regions on the surface of a brake disc of a vehicle brake system during a dynamic bench test. Background Art

[0003] The dissipation of heat generated during a braking event is one of the most critical issues in evaluating the performance of a braking system.

[0004] For brake discs, heat generated in the friction members (pads and braking surfaces) causes thermal deformation in the disc, which can lead to localized contact areas between mechanical elements and result in the formation of thermal hot spots. A hot spot is an area in the brake band with a high thermal gradient.

[0005] The formation of thermal hot spots during braking events can lead to a variety of negative consequences.

[0006] From a materials perspective, it has been demonstrated that thermomechanical stresses due to the presence of thermal hot spots can induce traction and compression stress cycles accompanied by changes in plastic deformation.

[0007] The presence of thermal hot spots may also affect the initiation and growth of cracks on the surface of the disk.

[0008] Finally, from a driving perspective, it is well known that high temperatures in the brake system can degrade brake performance, causing a phenomenon known as “fading” or “thermal chatter”, which are undesirable low-frequency vibrations.

[0009] Therefore, it is extremely important to analyze the thermal hot spot phenomena in brake discs under dynamic conditions, not only to properly characterize the discs, but also to obtain indications on how to improve the design of the discs themselves.

[0010] Currently, the standard procedure for studying hot spot phenomena is to test the brake system on a dynamometer test bench. An experimental setup is provided on the bench to allow acquisition of images representing temperature information, for example by means of a test instrument provided with a thermal imaging camera.

[0011] Each test provides the application of a series of braking maneuvers that are predefined according to operating parameters, and the frames acquired for each braking maneuver can be combined in sequence to form a video.

[0012] However, for analyzing the relationship between the temperature distribution on the disk and complex physical phenomena, such as the onset of deformations and vibrations, the standard analysis tools provided by currently known test tools are at least partially lacking or unsuitable.

[0013] In fact, although the standard software available for currently known thermal imaging cameras allows some information to be extracted automatically, this information is not sufficient to perform the above-mentioned analysis in a satisfactory manner.

[0014] Therefore, the prior art in this field provides for a separate visual inspection of the video provided by the thermal imaging camera by a dedicated operator to record information about uneven temperature distribution, such as hot spots, cold zones and hot zones, i.e. circular crowns with higher temperatures compared to the surrounding areas. Based on these features, their number, size and index in relation to the temperature values ​​are recorded.

[0015] This known information extraction procedure is very time-consuming as it requires a qualified operator to individually screen the acquired videos.

[0016] Furthermore, such procedures are typically subject to operator bias, resulting in less objective and non-reproducible results.

[0017] As mentioned above, there are still many unmet needs in the field of detecting and analyzing information related to thermal hot spots in brake discs under dynamic operating conditions, and the solutions known to date have not provided a completely effective solution to these needs. Summary of the invention

[0018] Therefore, the present invention relates to a method for detecting and analyzing thermal information associated with a brake disc under dynamic operating conditions.

[0019] In particular, the object of the present invention is to provide a method for automatic detection by computerized processing of information about the evolution of the temperature on the surface of a brake disc under dynamic operating conditions and / or about the location / distribution of hot spots and / or hot zones and / or hot areas on the surface of a brake disc under dynamic operating conditions, which method allows at least partially to eliminate the above-mentioned disadvantages complained of in the prior art and responds to the above-mentioned needs, particularly felt in the considered technical field. This object is achieved by a method according to claim 1.

[0020] Further embodiments of the method are defined in claims 2-18. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Further characteristics and advantages of the method according to the invention will become apparent from the following description of a preferred embodiment given by way of non-limiting example with reference to the accompanying drawings, in which:

[0022] - Figure 1An example of a framing that can be obtained in the digital image / video acquisition step provided in an embodiment of the method of the present invention is shown;

[0023] - Figure 2 A simplified flow chart showing the steps involved in an embodiment of the method according to the present invention;

[0024] - Figure 3 shows a hierarchy of analyses performed in an embodiment of the method according to the invention;

[0025] - Figure 4 shows different image processing steps provided in a mask definition procedure included in an embodiment of the method according to the invention;

[0026] - Figure 5 shows the implementation options according to Figure 2 A simplified flowchart of the steps included in the "Data Preparation" block in the

[0027] - Figure 6 An example of setting input parameters for searching and verifying hotspots according to an embodiment of the method according to the present invention is shown;

[0028] - Figure 7 shows the implementation options according to Figure 2 A simplified flow chart of the steps included in the "Temperature Analysis" block;

[0029] - Figure 8 and Fig. 9 A restated video and a line graph with connected frames, respectively, are shown, which are provided as output in respective embodiments of the method according to the invention. DETAILED DESCRIPTION

[0030] refer to Figures 1 to 9 , a method is described for automatically detecting by computerized processing information about the temperature evolution on the surface of a brake disc under dynamic operating conditions and / or about the location / distribution of hot spots and / or hot zones and / or hot areas on the surface of a brake disc under dynamic operating conditions.

[0031] The method comprises the steps of acquiring a plurality of digital images and / or digital videos; obtaining a representation of each of the digital images and / or digital video frames in the form of matrix data, processing the representation by means of algorithms including image analysis or "computer vision" algorithms, to obtain and then provide information on the temperature evolution over a region of interest of the brake disc surface and / or information on the location / distribution of hot spots and / or hot zones and / or thermal zones over a region of interest of the brake disc surface.

[0032] The aforementioned acquisition step comprises acquiring, by at least one thermal imaging camera, a plurality of digital images and / or digital videos (comprising a plurality of digital frames) of at least one region of interest of the brake disc to be thermally characterized during the evolution of the above-mentioned dynamic operating conditions. Each of the digital images and / or each of the digital video frames depicts the temperature detected at each point by means of a color map.

[0033] The above-mentioned processing step includes the following steps: identifying the area of ​​interest by generating a mask based on the analysis of multiple acquired digital images and / or digital video frames; then, applying the generated mask to each of the acquired digital images and / or digital video frames, and obtaining processed matrix data related to the area of ​​interest; then, defining the analysis area and performing thermal analysis on the data related to the defined analysis area to obtain information about the temperature evolution at each point of interest; finally, identifying hot spots based on the above-mentioned information about the temperature evolution at each point of interest.

[0034] The providing step includes providing the obtained information in the form of digital images or graphs and / or digital tables and / or digital videos.

[0035] According to an embodiment of the method, the aforementioned region of interest comprises at least one braking band of the disc.

[0036] According to another embodiment of the method, the region of interest comprises two mutually corresponding brake bands on two respective side surfaces of the brake disc.

[0037] In this case, the aforementioned acquisition step comprises acquiring a plurality of digital images and / or digital videos by means of at least two thermal imaging cameras, one thermal imaging camera corresponding to each brake band of interest.

[0038] According to another embodiment of the method, the aforementioned region of interest comprises two mutually corresponding brake bands on two respective side surfaces of the brake disc.

[0039] In this case, the aforementioned acquisition step includes acquiring multiple digital images and / or digital videos through a thermal imaging camera and at least one reflector, so that the thermal imaging camera directly acquires a digital image and / or digital video of a portion of interest of one brake band, and the thermal imaging camera further acquires a mirror image of a digital image and / or digital video of a portion of interest of another brake band provided by at least one reflector and located on the opposite side surface of the brake disc relative to the side surface where the thermal imaging camera is located.

[0040] According to an embodiment of the method, the aforementioned region of interest comprises a portion of one or more braking bands of the brake disc.

[0041] According to an embodiment of the method, the aforementioned operating conditions comprise at least one braking event or a braking test.

[0042] According to an implementation option, the aforementioned operating conditions comprise at least one brake disc bench test, wherein each test comprises a plurality of brake test events.

[0043] According to an implementation option of the method, the aforementioned operating conditions comprise a plurality of tests performed on a brake disc test bench, wherein an operator performing the tests is able to select a test of such a plurality of tests to be performed in a test sequence.

[0044] According to an embodiment of the method, each test includes multiple test braking events; each test braking event includes analysis of each of the sides of the brake disc in turn; each analysis of the side of the brake disc includes analysis of each frame of the digital video captured on the side; each frame analysis includes analysis of a portion of the frame depicting the corresponding portion of the area of ​​interest.

[0045] According to an embodiment, some steps of the method are common to all tests of the aforementioned plurality of tests, while other steps are performed separately for each frame or each of a set of predefined frame portions. Such steps performed separately are then extended to the entire test according to a nested structure: for each test, for each braking action, for each side of the braking side, for each frame and for each predefined frame portion.

[0046] According to an embodiment of the method, the aforementioned step of identifying the region of interest by generating a mask and applying the generated mask to each of the acquired digital images and / or digital video frames comprises: processing by computer a set of digital images or digital video frames considered important for analysis.

[0047] For each digital image or digital image frame considered important, this processing step includes the following steps in sequence:

[0048] - Force negative temperatures or temperatures below a lower temperature threshold (e.g. 10°C) to a low or zero value (typically 0);

[0049] - Apply filters to digital images or video frames to reduce noise;

[0050] - Apply Otsu segmentation to digital images or video frames;

[0051] -averaging each pixel on the time axis to obtain a corresponding average digital image or average digital video frame;

[0052] - applying Otsu segmentation to the averaged digital image or averaged digital video frame to obtain a corresponding segmented digital image or segmented digital video frame;

[0053] - identifying the edge of the brake disc by an edge recognition algorithm and removing the edge from the segmented digital image or the segmented digital video;

[0054] -The mask is refined by an image cleaning algorithm to finally obtain a processed digital image or a processed digital video.

[0055] According to an implementation option, the obtained digital data corresponding to the aforementioned processed digital image or processed digital video is organized in a matrix form, thereby obtaining the aforementioned processed matrix data related to the region of interest.

[0056] According to an implementation option, the step of obtaining processed matrix data further comprises converting the Cartesian coordinates associated with the indices of the matrix forming the frame into a polar coordinate system.

[0057] According to an implementation option, if each test includes multiple braking events, the set of digital images or digital video frames considered important for analysis includes digital images or digital video frames acquired from the last N (e.g., 3) braking events of the test, i.e., those braking events during which the brake disc reached the highest temperature and was therefore more clearly visible against the cold background of the image.

[0058] According to the implementation mode, the aforementioned edge recognition algorithm in the recognition step includes a Sobel edge detection algorithm.

[0059] According to an implementation option, the image cleaning algorithm in the aforementioned thinning step comprises a binary image morphology algorithm configured to perform the function of removing dirt and / or small gaps and / or small objects on the image.

[0060] According to an embodiment of the method, the aforementioned step of defining the analysis area comprises dividing the braking band of the brake disc to be analyzed into three equal sub-areas, namely an inner sub-area, a central sub-area and an outer sub-area, wherein each sub-area is used for a separate analysis.

[0061] According to another embodiment of the method, the aforementioned step of defining the analysis area comprises: setting, by an operator through a command interface needle and for each of the two viewfinder brake band portions, at least one setting parameter suitable for defining the analysis area.

[0062] Depending on the implementation option, operator-definable setup parameters include:

[0063] (i) the angular width of the band of interest to be analyzed;

[0064] (ii) The values ​​of the inner and outer radii on a band suitable for defining the three sub-regions (inner region, central region and outer sub-region) for analysis.

[0065] According to an implementation option, each pixel of the digital image or video frame is marked to indicate whether the pixel belongs to the analysis area and, if so, to which analysis sub-area the pixel belongs.

[0066] For example, each pixel of each frame included in the analysis area is assigned an integer between 1 and 3 to identify the zone it belongs to (inner zone, central zone and outer zone). If the pixel has been excluded from the analysis area, it is assigned zero.

[0067] According to an embodiment of the method, the aforementioned step of thermally analyzing the data related to the defined analysis area to obtain information about the temperature evolution at each point of interest, and the aforementioned step of identifying thermal hot spots comprise the following steps:

[0068] - identifying as a potential thermal hotspot any area in the analysis zone where the temperature is a given percentile higher than the average temperature of the analysis zone itself;

[0069] -For each potential hotspot, calculate the coordinates of the centroid;

[0070] - verifying one or more validity requirements on potential thermal hot spots and identifying only potential thermal hot spots that satisfy the one or more validity requirements as thermal hot spots.

[0071] Depending on the implementation options, the aforementioned validity requirements may include one, more, or all of the following:

[0072] a. The area of ​​the potential hot spot is greater than the minimum hot spot area threshold;

[0073] b. the centroid of the potential hot spot is located in a non-cold zone, wherein a zone is defined as a cold zone if its average temperature is below a given percentile of the temperature distribution of the analyzed brake band side, for example below the median temperature of such distribution;

[0074] c. The area of ​​the potential hot spot is smaller than the maximum hot spot area threshold;

[0075] d. The distance between the radial coordinates of the centroids of two hot spots is greater than the distance threshold, otherwise the two hot spots are regarded as one hot spot and the information about the hot spot with a larger area is saved.

[0076] According to an implementation option, the method comprises the further step of calculating the temperature variation within each zone and identifying the presence of a band on the zone under consideration if the aforementioned temperature variation is within predetermined temperature variation limit values.

[0077] According to a possible embodiment of the method, the aforementioned information on the temperature evolution on the area of ​​interest of the brake disc surface and / or the information on the positioning / distribution of hot spots and / or hot zones and / or thermal zones on the area of ​​interest of the brake disc surface includes: for each of the identified thermal hot spots, information about the location (e.g. geometric coordinates of the center of mass or center of gravity) and / or the area and / or zone and frame in which the hot spot was found and / or metadata identifying the braking event and / or test to which such information relates.

[0078] According to an embodiment of the method, the aforementioned step of providing information about the temperature evolution on the area of ​​interest of the brake disc surface and / or about the location / distribution of hot spots and / or hot zones and / or thermal zones on the area of ​​interest of the brake disc surface comprises displaying the data via a computer interface.

[0079] Depending on different possible implementation options, such a display step includes displaying the output of the algorithm, and / or displaying the time trend of the number of hot spots in total or by zone (for example, by a line graph), and / or displaying data related to the presence or absence of hot spots in each frame in a global or by zone manner and for each of the two sides of the disk.

[0080] According to an implementation option, the displaying step further comprises displaying a reprocessed version of the original digital video frame.

[0081] For example, the digital video frame is recolored to highlight pixels above the 95th temperature percentile and below the 5th temperature percentile within the same frame and considered to belong to the same brake band; or, pixels corresponding to the center of gravity of detected thermal hotspots are marked on the digital video frame.

[0082] According to an implementation option, the displaying step further comprises aggregating the reprocessed digital video frames based on the output of the algorithm to recreate the video.

[0083] Reference again Figures 1 to 9 , further details of the method will be given below by way of non-limiting example only according to a specific embodiment of the invention.

[0084] In this example, a “computer vision” algorithm is considered, which is able to automatically extract information about the temperature evolution and hot spot distribution on the brake disc surface from videos acquired with a thermal imaging camera during dynamic bench testing.

[0085] It should be noted that the term "thermal imaging camera" refers to any electronic device that is capable of detecting thermal information from a viewed object (e.g., such as by receiving infrared light for temperature detection) and providing as output a digital image or video that depicts the thermal information in some manner (e.g., in the form of a color image).

[0086] This implementation example relates to a process of detecting thermal information on a brake disc that has been tested on a test bench.

[0087] The process is disclosed below in two steps of acquiring data on the test bench and processing such data.

[0088] As for the data acquisition step, in this implementation example, the brake system is tested on a test bench on which an experimental acquisition device is provided.

[0089] In this example, the evolution of the temperature over time on two brake bands of a disc was recorded using a thermal imaging camera and a mirror. The thermal imaging camera is positioned so that it can directly frame a portion of the brake band and indirectly frame a portion of the band on the opposite side of the disc through mirror reflection.

[0090] The acquisition is performed while the disk is rotating, and the acquisition rate of the thermal imaging camera is such that the portion of the rotating disk in view remains constant during the entire braking action. Figure 1 An example of a framing that can be obtained through this acquisition step is shown.

[0091] Each test provides for applying a series of braking actions that are predefined based on operating parameters (e.g. initial and final speeds, pressure in the braking system or deceleration of the vehicle, system temperature at the start of braking). The relevant data is stored in different frame variables "Frame_00N", one per video frame and numbered accordingly. Each frame variable contains a floating point array with specific dimensions (video height) x (video width).

[0092] As previously mentioned, in this description, the term "frame" or "digital frame" is used to refer to a data set corresponding to the view of a thermal imaging camera.

[0093] In the examples disclosed herein, the frames acquired for each braking action are combined in sequence to form a video. The video in matrix format (an example of such a format is MATLAB MAT) is the output of the thermal imaging camera.

[0094] In this example, the data is stored as files on the file system and organized into folders. Each folder represents a different test and contains different video files. The files are numbered by the position of the corresponding braking event in the sequence of all braking events for a given test.

[0095] The acquisition step is followed by the data processing step, whose logical stages are as follows: Figure 2 shown.

[0096] The analysis units can vary in each step. Some operations occur only once per test, others are performed separately on each frame or part thereof and extended to the entire test according to the following type of nested structure: for each test, for each braking action, for each side of the disc, for each frame, for each part (as described above).

[0097] Figure 3 The hierarchy is shown where, consistent with the examples described herein, the brake band of each frame is isolated into three sections: an inner section, a central section, and an outer section.

[0098] The interaction with the user is through a software application having a graphical user interface (GUI), such as a specially developed GUI.

[0099] The first step consists in the user selecting the test to be analyzed. The software application allows the user to select a folder containing videos related to all braking actions related to the selected test.

[0100] The next step consists in generating a mask corresponding to the analysis area of ​​interest for this application, namely the braking band of the disc.

[0101] To obtain the mask, the algorithm used in this implementation option of the method performs the following operations (eg Figure 4 shown):

[0102] - it takes as input for each test the video of the last three braking maneuvers, i.e. the video in which the disc reaches the highest temperature and is therefore more clearly visible against the cold background of the image;

[0103] - Negative temperatures or temperatures below a certain threshold (e.g. 10°C) in each frame are forced to be zero;

[0104] -Apply a filter to each frame to reduce noise ( Figure 4 Box 1 in the figure);

[0105] - Apply Otsu segmentation to each frame ( Figure 4 Otsu segmentation (or Otsu method) is a method known per se for automatically thresholding a histogram in a digital image;

[0106] +The average value of each pixel on the time axis ( Figure 4 Box 3 in the figure);

[0107] - Perform Otsu segmentation again ( Figure 4 Box 4 in the figure);

[0108] - Identify the edges of the disk by Sobel edge detection (an algorithm known per se) and remove them ( Figure 4 Box 5 in the figure);

[0109] - Refine the mask by binary image morphology (algorithms known per se, e.g. removing dirt, small gaps, small objects) Figure 4 6 in the figure).

[0110] Downstream of this processing, the operator can accept the mask suggestion suggested by the algorithm or further modify it according to his / her needs.

[0111] By overlaying the mask and a test video frame in the GUI (where the brake band is clearly visible in the background), a comparison can be made.

[0112] In the implementation options, the operator can use the GUI to:

[0113] 1. Enlarge or reduce the mask;

[0114] 2. Redefine the contours of the two images in the mask based on the intersection of the ellipses in the image identified by the RANSAC algorithm;

[0115] 3. Completely reshape the mask by manipulating the control points of the interpolated Bezier curve.

[0116] Typically this is done only once for the entire test.

[0117] Once the desired mask is defined, in this implementation option, some data processing operations are performed to prepare for the actual temperature analysis. Such operations are Figure 5 as shown and was performed on every frame for every braking maneuver in the test.

[0118] First, a mask is applied to each frame of the braking action. Then, each frame is automatically split into two parts, each part is related to one side of the braking band and completely contains the braking band. The cropping is such that only one of the width and length of the frame changes. Furthermore, since the framing remains static for the entire duration, only one position index is defined for the cropping. From here on, the frames related to both sides of the braking band are processed in parallel.

[0119] The next step consists in transforming the Cartesian coordinates associated with the matrix indices forming the frame into a polar coordinate system, which is more natural for the shape of the object being analyzed.

[0120] Downstream of this step, in this implementation example, the user is asked to enter the Figure 6 ) declare the following parameters for each of the two parts of the brake band of the frame.

[0121] 1. The angular width of the band of interest to be analyzed; the user is invited to select a region where the band width is approximately constant; in reality, due to the size of the test bench, or even just the size of the brake caliper, it is almost impossible to obtain a complete frame of the entire visible angular band interval.

[0122] 2. The values ​​of the inner and outer radius of the band. These two values ​​define three regions on the band (inner, central, and outer), each of which typically observes a different thermal pattern. The wave is divided into three equal regions by default, but the user can change these values ​​based on what is observed in the video.

[0123] Once these parameters are defined and saved, each pixel of each frame included in the analysis region is assigned an integer between 1 and 3 to identify the zone it belongs to (inner zone, central zone, and outer zone). If the pixel has been excluded from the analysis region, it is assigned zero.

[0124] The next step is to analyze the temperature patterns that developed during the test. For each frame, the following operations (summarized in Figure 7 middle).

[0125] 1. Hotspot (or thermal hotspot) search, where a hotspot is defined as an area where the temperature is a certain percentile higher than the temperature of the area itself.

[0126] 2. For each hotspot, calculate the centroid coordinates.

[0127] 3. Check validity requirements:

[0128] 3a. In order to eliminate small hot spots caused by holes in the disk or other factors, a minimum threshold is set for the area of ​​each hot spot;

[0129] 3b. Only hot spots whose center of gravity is located in non-cold zones are identified as hot spots; a cold zone is defined as a zone whose average temperature is a certain percentile lower than the temperature distribution of the brake band side being analyzed (e.g., lower than the middle temperature of such distribution); since hot spots can be defined a priori on any zone, without such a design, the hottest spot in each zone (even in a cold zone) will be detected as a hot spot, which should be avoided.

[0130] 4. Check that there are no mixed hot spots.

[0131] 4a. Check for hot spots in angle blends.

[0132] It may happen that the hotspot defined at point 1 above is actually formed by the intersection of several hotspots and is therefore very broad. This problem is addressed by calibrating the threshold for maximum area.

[0133] If the area of ​​the hotspot identified at point 1 above is greater than the threshold, the operations at points 1-3 above are performed again in that area and the search is performed using a higher percentile than the percentile selected at point 1. The processed data with the increased percentile is saved and replaces the previously processed data in the angular portion of the zone where too many hotspots were detected.

[0134] 4b. Check for hot spots in radial blending.

[0135] When the distance between the radial coordinates of the centroids of two hot spots is less than a certain threshold, they are considered to be one hot spot, and the information of the single hot spot with a larger initial area is saved.

[0136] 5. Calculate the temperature variation within each zone; if this variation is within certain predetermined limits, the presence of a band on that zone is identified.

[0137] For identified hotspots, the output of the above action stream contains, in addition to identification metadata in terms of braking actions and tests, information about the location (geometric coordinates of the centroid), region, zone and frame in which they were found. This data can be aggregated at different levels and exported in table form.

[0138] The output of the algorithm can be displayed within the app.

[0139] In particular, once the desired braking action is selected via the drop-down menu, the user is presented with various displays.

[0140] For example, the time trend of the number of hot spots (total or by zone) can be displayed in a line graph. In addition, due to buttons on the GUI, data related to whether there are hot spot bands for each frame can be displayed globally or by zone. The graph can be tracked separately for both sides of the disk.

[0141] In addition, a remastered version of the original frame may also be displayed. In particular, in an embodiment of the method described herein, at least the following options are available:

[0142] - frames that are recolored by highlighting pixels above the 95th temperature percentile and below the 5th temperature percentile within the same frame and considered to belong to the brake band to highlight any errors in its definition (e.g. inclusion of ventilation chambers);

[0143] - Frames marked with pixels corresponding to the centroids of hotspots detected by the algorithm.

[0144] In turn, the frames reinterpreted according to the algorithm's output can be aggregated to recreate the video (see Figure 8 ).

[0145] Finally, individual displays can be connected. For example, a line graph can be made reactive so that for a frame selected on the x-axis the corresponding restated frame is displayed (see Fig. 9 ). This strategy allows the user to get visual feedback on the analysis results proposed by the algorithm.

[0146] Graphical output is in table form and can be exported and saved by the user / operator.

[0147] It can be seen that, as mentioned above, the purpose of the present invention is fully achieved by the above method with the help of the features disclosed in detail above. The advantages and technical problems solved by the method according to the present invention have been described above in combination with various features and aspects of the method.

[0148] In particular, the above solution allows an accurate, fast, objective, repeatable and inexpensive analysis of the data provided by a thermal imaging camera viewing a disc brake under dynamic conditions.

[0149] In order to meet possible needs, those skilled in the art may modify and adjust the implementation of the above method or replace the above elements with other elements with equivalent functions without departing from the scope of the following claims. Each feature described as belonging to possible implementations can be implemented without considering other implementations described.

Claims

1. A method for automatically detecting, by computerized processing, information about the temperature evolution on a brake disc surface under dynamic operating conditions and / or about the location / distribution of hot spots and / or hot zones and / or hot areas on a brake disc surface under dynamic operating conditions, the method comprising: - acquiring, by means of at least one thermal imaging camera, a plurality of digital images and / or a digital video of at least one region of interest of said brake disc to be thermally characterized, said digital video comprising a plurality of digital frames, wherein each of said digital images and / or each of said digital video frames depicts, by means of a color map, the temperature detected at each point, wherein said acquisition step is performed during the evolution of said dynamic operating conditions; - obtaining a representation of each of said digital images and / or digital video frames in the form of matrix data; - processing the plurality of digital images or the plurality of digital video frames by means of an algorithm, including an image analysis or computer vision algorithm, to obtain information about the temperature evolution over an area of ​​interest of the brake disc surface and / or information about the location / distribution of hot spots and / or hot zones and / or thermal zones over an area of ​​interest of the brake disc surface; - provide the information obtained in the form of digital images or graphics and / or digital tables and / or digital videos; The processing steps include: - identifying said region of interest by generating a mask based on analysis of a plurality of acquired digital images and / or digital video frames; - applying the generated mask to each of said acquired digital images and / or digital video frames and obtaining processed matrix data associated with said region of interest; - limit the analysis area; - Perform thermal analysis on the data related to a defined analysis area to obtain information about the temperature evolution at each point of interest; - identifying hot spots based on said information about the temperature evolution at each point of interest.

2. The method according to claim 1, wherein: The region of interest comprises at least one braking band of the disc.

3. The method according to any one of claims 1 or 2, wherein: The region of interest includes two mutually corresponding brake bands on two corresponding side surfaces of the brake disc, And wherein the acquiring step comprises acquiring a plurality of digital images and / or digital videos by means of at least two thermal imaging cameras, one thermal imaging camera corresponding to each brake band of interest.

4. The method according to any one of claims 1 or 2, wherein: The region of interest includes two mutually corresponding brake bands on two respective side surfaces of the brake disc, And wherein the acquisition step includes: acquiring multiple digital images and / or digital videos through a thermal imaging camera and at least one reflector, so that the thermal imaging camera directly acquires a digital image and / or digital video of a portion of interest of a brake band, and the thermal imaging camera further acquires a mirror image of a digital image and / or digital video of a portion of interest of another brake band provided by the at least one reflector, and the other brake band is located on the opposite side surface of the brake disc relative to the side surface where the thermal imaging camera is located.

5. The method according to claim 1 or any one of claims 3 to 4, wherein: The region of interest includes portions of one or more braking bands of the brake disc.

6. A method according to any one of the preceding claims, wherein: The operating conditions include at least one braking event or a braking test.

7. The method according to claim 6, wherein: The operating conditions include at least one brake disc bench test, each test including a plurality of brake test events.

8. The method according to claim 7, wherein: The operating conditions comprise a plurality of tests to be performed on a brake disc test bench, wherein tests of the plurality of tests to be performed in a test sequence can be selected by an operator performing the tests.

9. The method according to claim 8, wherein: Each of the plurality of tests comprises a plurality of test braking events, each test braking event comprising an analysis of each side of the brake rotor, each analysis of a side of the brake rotor comprising an analysis of each frame of a digital video captured of the side, each frame analysis comprising an analysis of a portion of a frame depicting a corresponding portion of the region of interest.

10. The method according to claim 9, wherein: Certain steps of the method are common to all tests of the plurality of tests, whereas other steps are performed separately on each frame or for each frame portion of a set of predefined frame portions and extend to the entire test according to the following nested structure: for each test, for each braking action, for each side of the brake disc, for each frame and for each predetermined frame portion.

11. A method according to any one of the preceding claims, wherein: The step of identifying the region of interest by generating a mask and applying the generated mask to each of the acquired digital images and / or digital video frames comprises: processing by computer a set of digital images or digital video frames considered to be important for analysis, Wherein, for each digital image or digital video frame deemed to be important, the processing steps include: - Force negative temperatures or temperatures below the lower temperature threshold to a low or zero value; - Apply filters to digital images or video frames to reduce noise; - applying Otsu segmentation to the digital image or video frame; -averaging each pixel on the time axis to obtain a corresponding average digital image or average digital video frame; - applying Otsu segmentation to the averaged digital image or averaged digital video frame to obtain a corresponding segmented digital image or segmented digital video frame; - identifying the edge of the brake disc by an edge recognition algorithm and removing the edge from the segmented digital image or the segmented digital video; -The mask is refined by an image cleaning algorithm to finally obtain a processed digital image or a processed digital video.

12. The method according to claim 11, wherein: The step of obtaining processed matrix data further comprises converting Cartesian coordinates associated with the indices of the matrix forming the frame into a polar coordinate system.

13. The method according to claim 11, wherein: If each test includes multiple braking events, the set of digital images or digital video frames considered important for analysis includes digital images or digital video frames acquired from the last N braking events of the test, i.e., those braking events during which the brake disc reached the highest temperature and was therefore more clearly visible against the cool background of the image; - the edge recognition algorithm in the recognition step includes a Sobel edge detection algorithm; - the image cleaning algorithm in the thinning step comprises a binary image morphological algorithm configured to perform a function of removing dirt and / or small gaps and / or small objects on the image.

14. A method according to any one of the preceding claims, wherein: The step of defining the analysis area comprises: - dividing the braking band of the brake disc to be analysed into three equal sub-areas, namely an inner sub-area, a central sub-area and an outer sub-area, each sub-area being used for the analysis; or - the operator sets, through the command interface and for each of the two portions of the brake band of the view, at least one setting parameter suitable for defining the analysis area, wherein the at least one setting parameter comprises: (i) the angular width of the band of interest to be analyzed; (ii) values ​​of the inner radius and the outer radius on the strip, the strip being adapted to define three sub-regions, an inner sub-region, a central sub-region and an outer sub-region, each sub-region being used for analysis; And wherein each pixel of the digital image or video frame is labeled to indicate whether the pixel belongs to the analysis area, and if so, to which analysis sub-area the pixel belongs.

15. A method according to any one of the preceding claims, wherein: The step of thermally analyzing the data related to the defined analysis area to obtain information about the temperature evolution at each point of interest and the step of identifying hot spots comprise: - identifying as a potential hotspot any area in the analysis area where the temperature is a given percentile higher than the average temperature of the analysis area itself; -For each potential hotspot, calculate the coordinates of the corresponding centroid; - verifying one or more validity requirements on potential hotspots and identifying only potential hotspots that satisfy the one or more validity requirements as hotspots, wherein the one or more validity requirements include: a. The area of ​​the potential hotspot is greater than the minimum hotspot area threshold; b. the centroid of the potential hot spot is located in a non-cold zone, wherein a zone is defined as a cold zone if its average temperature is lower than a given percentile of the temperature distribution of the analyzed brake band side, or lower than the median temperature of said distribution; c. The area of ​​the potential hotspot is smaller than the maximum hotspot area threshold; d. If the distance between the radial coordinates of the centroids of the two hotspots is greater than the distance threshold, the two hotspots are considered as one hotspot and the information about the hotspot with the larger area is saved.

16. The method according to claim 15, comprising the following further steps: -Calculate the temperature variation within each zone; If the temperature variation is within predetermined temperature variation limits, the presence of a band on the zone is identified.

17. A method according to any one of the preceding claims, wherein: For each of the identified hot spots, information about the temperature evolution over the region of interest of the brake disc surface and / or information about the location / distribution of hot spots and / or heat zones and / or thermal areas over the region of interest of the brake disc surface comprises: - Information about the location and / or area and / or zone and frame in which the discovered hotspot is located and / or metadata identifying the braking event and / or test to which said information relates.

18. A method according to any one of the preceding claims, wherein: The step of providing information about the temperature evolution on the region of interest of the brake disc surface and / or information about the location / distribution of hot spots and / or hot zones and / or thermal zones on the region of interest of the brake disc surface comprises: - Display output of hotspot identification, and / or - Display the trend of the number of hotspots over time, either in total or by region, and / or - display, globally or by zone and for each of the two sides of the disc, data relating to the presence or absence of a tropical zone in each frame, and / or - display a remastered version of the original digital video frame, and / or - Aggregating the remastered digital video frames to recreate the video based on the output of the algorithm.

Citation Information

Cited By

  • Online prediction method and equipment for hot cracks of brake disc based on microstructure transfer learning and medium

    CN121258979A