Quality Prediction Method and System during the Shot Peening Process of Brake Drums

Abstract

The present invention discloses a quality prediction method and system during the shot peening process of a brake drum, which relates to the technical field of data processing. The method includes: obtaining the area to be processed and the qualified coverage rate threshold, obtaining the number of projectile launches, obtaining the shot peening time period, obtaining the start time and end time of shot peening; obtaining the real-time surface image of the surface of the brake drum to be shot peened during the shot peening process, and obtaining the real-time coverage rate according to the real-time surface image; judging whether the real-time coverage rate is less than the qualified coverage rate threshold. If it is greater, obtaining the first quality prediction result according to the real-time coverage rate. If it is less, obtaining the coverage rate difference between the qualified coverage rate threshold and the real-time coverage rate; obtaining the change weight based on the coverage rate degree change model and the coverage rate difference, and obtaining the second quality prediction result according to the change weight, the time of shot peening that has been performed, the real-time coverage rate, and the end time of shot peening. The present invention has the advantages of high prediction efficiency, dynamic prediction, and accuracy and reliability.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to a method and system for predicting the quality during the shot peening process of brake drums. Background Art

[0002] During the manufacturing and maintenance processes of braking systems, the performance and quality of brake drums are of crucial importance. As a key component, the surface state of the brake drum directly affects the braking effect and durability. To improve the surface hardness and wear resistance of the brake drum, shot peening technology is usually adopted. Shot peening is to impact the surface of the workpiece by high-speed spraying of shot peening media to achieve the purposes of cleaning, strengthening, and changing the surface state.

[0003] However, most of the traditional shot peening processes for brake drums rely on manual experience and fixed parameters, which leads to instability and unpredictability of the processing quality. Specifically, the effect of shot peening is affected by various factors, such as the material, size, launching speed, and shot peening time of the shot peening media. In addition, the initial state of the surface of the brake drum to be shot peened (such as roughness, pollution degree, etc.) will also have a significant impact on the processing results.

[0004] In the prior art, although there are some methods attempting to monitor and adjust the shot peening process, they usually can only achieve simple on-off control or adjustment based on fixed time intervals. These methods cannot reflect the actual processing situation of the brake drum surface in real time, nor can they dynamically adjust the prediction results according to the changing state during the processing. For example, as the shot peening time increases, the efficiency of shot peening is completely different in the early, middle, and late stages of shot peening, and it is impossible to accurately predict the shot peening process and ensure the consistency of shot peening and achieve the expected quality target. Summary of the Invention

[0005] Aiming at the defects in the prior art, the present invention provides a method and system for predicting the quality during the shot peening process of brake drums.

[0006] A quality prediction method during the shot peening process of a brake drum, the method comprising: obtaining the area to be processed and the qualified coverage rate threshold of the surface of the brake drum to be shot peened, and obtaining the number of shot peening projectiles based on the crater coverage model, the area to be processed, and the qualified coverage rate threshold, and obtaining the shot peening time period according to the shot peening channel flow rate and the number of shot peening projectiles, and obtaining the start time and end time of shot peening according to the shot peening time period; obtaining a real-time surface image of the surface of the brake drum to be shot peened during the shot peening process, and obtaining the real-time coverage rate according to the real-time surface image; determining whether the real-time coverage rate is less than the qualified coverage rate threshold, if it is greater, obtaining a first quality prediction result according to the real-time coverage rate, if it is less, obtaining the coverage rate difference between the qualified coverage rate threshold and the real-time coverage rate; obtaining a change weight based on the coverage rate degree change model and the coverage rate difference, and obtaining a second quality prediction result according to the change weight, the time of shot peening that has been performed, the real-time coverage rate, and the end time of shot peening.

[0007] Optionally, the crater coverage model in obtaining the number of shot peening projectiles based on the crater coverage model, the area to be processed, and the qualified coverage rate threshold is expressed as: ; where is the number of shot peening projectiles, is the area to be processed, is the qualified coverage rate threshold, is the average processing range of a single projectile, is the degree of fuzziness.

[0008] Optionally, obtaining the shot peening time period according to the shot peening channel flow rate and the number of shot peening projectiles is expressed as: ; where is the shot peening time period, is the shot peening channel flow rate.

[0009] Optionally, obtaining the real-time coverage rate according to the real-time surface image includes: converting the real-time surface image into a grayscale image; performing binary processing on the grayscale image and forming a comparison image with only the crater area and the non-crater area; obtaining the real-time coverage rate according to the crater area and the non-crater area in the comparison image.

[0010] Optionally, the coverage rate degree change model in obtaining the change weight based on the coverage rate degree change model and the coverage rate difference is expressed as: , ; where is the change weight, is the qualified coverage rate threshold, is the real-time coverage rate, is the correlation coefficient.

[0011] Optionally, obtaining the second quality prediction result based on the change weight, the peening time, the real-time coverage rate, and the peening end time includes: obtaining the real-time coverage speed according to the peening time and the real-time coverage rate; obtaining the predicted coverage rate of the brake drum at the peening end time according to the real-time coverage speed and the change weight; and obtaining the second quality prediction result according to the predicted coverage rate.

[0012] Optionally, obtaining the predicted coverage rate of the brake drum at the peening end time according to the real-time coverage speed and the change weight is expressed as: ; where is the predicted coverage rate, is the real-time coverage speed, is the remaining time.

[0013] There is also provided a quality prediction system during the peening process of a brake drum. The system includes: a first acquisition and calculation module, configured to acquire the area to be processed and the qualified coverage rate threshold of the surface of the brake drum to be peened, and based on the crater coverage model, the area to be processed, and the qualified coverage rate threshold, acquire the number of projectile launches, and according to the flow rate of the peening channel and the number of projectile launches, acquire the peening time period, and according to the peening time period, acquire the peening start time and the peening end time; a second acquisition and calculation module, configured to acquire the real-time surface image of the surface of the brake drum to be peened during the peening process, and acquire the real-time coverage rate according to the real-time surface image; a judgment and prediction module, configured to judge whether the real-time coverage rate is less than the qualified coverage rate threshold. If it is greater, acquire the first quality prediction result according to the real-time coverage rate. If it is less, acquire the coverage rate difference between the qualified coverage rate threshold and the real-time coverage rate; a calculation and prediction module, configured to acquire the change weight based on the coverage rate degree change model and the coverage rate difference, and obtain the second quality prediction result according to the change weight, the peening time, the real-time coverage rate, and the peening end time.

[0014] Optionally, the second acquisition and calculation module is further configured to: convert the real-time surface image into a grayscale image; perform binarization processing on the grayscale image and form a comparison image with only the crater area and the non-crater area; and acquire the real-time coverage rate according to the crater area and the non-crater area in the comparison image.

[0015] Optionally, the calculation and prediction module is further configured to: obtain the real-time coverage speed according to the peening time and the real-time coverage rate; obtain the predicted coverage rate of the brake drum at the peening end time according to the real-time coverage speed and the change weight; and obtain the second quality prediction result according to the predicted coverage rate.

[0016] The beneficial effects of the present invention are embodied in:

[0017] In the quality prediction method for the entire brake drum shot peening process, by accurately measuring the area of the surface of the brake drum to be processed and setting a reasonable qualified coverage rate threshold, combined with an advanced crater coverage model, the required number of shot emissions and the shot peening time period can be accurately calculated, thus realizing the precise planning and time management of the shot peening process; further, during the shot peening process, by using high-precision image acquisition equipment and advanced image processing technology, the change in the coverage rate of the brake drum surface is monitored in real time and compared with the preset qualified coverage rate threshold, and the deficiencies in the processing process can be discovered and adjusted in a timely manner to ensure the processing quality and consistency; further, by introducing concepts such as the coverage rate change model and change weight, the prediction ability of the coverage rate change during the shot peening process is further improved, and the final shot peening quality and effect can be comprehensively predicted based on multiple parameters such as the real-time coverage rate, the shot peening time, and the shot peening end time. This dynamic adjustment and prediction strategy not only improves the accuracy and stability of the shot peening process, but also greatly enhances the flexibility and adaptability of the processing process, making the brake drum shot peening process more intelligent and automated, effectively solving the problems of unstable and unpredictable processing quality caused by relying on manual experience and fixed parameters in the traditional shot peening process, and providing a more reliable and efficient shot peening solution for the manufacturing of brake drums and other components. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0019] Figure 1 It is a schematic diagram of the steps of the quality prediction method for the brake drum shot peening process of the present invention;

[0020] Figure 2 It is a partial schematic diagram of the steps of S2 in the quality prediction method for the brake drum shot peening process of the present invention;

[0021] Figure 3 It is a partial schematic diagram of the steps of S4 in the quality prediction method for the brake drum shot peening process of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Usually, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0023] Accordingly, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0024] It should be noted that like reference numerals and letters denote like items in the following figures, and thus, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", etc. are only used for descriptive distinction and cannot be understood as indicating or implying relative importance.

[0025] As Figure 1 shown, a method for predicting the quality during the shot peening process of a brake drum is provided, and the method includes:

[0026] S1. Obtain the area to be processed and the qualified coverage rate threshold of the surface of the brake drum to be shot peened, and based on the crater coverage model, the area to be processed and the qualified coverage rate threshold, obtain the number of shot peening projectiles, and according to the flow rate of the shot peening channel and the number of shot peening projectiles, obtain the shot peening time period, and according to the shot peening time period, obtain the start time and end time of shot peening;

[0027] S2. Obtain the real-time surface image of the surface of the brake drum to be shot peened during the shot peening process, and obtain the real-time coverage rate according to the real-time surface image;

[0028] S3. Judge whether the real-time coverage rate is less than the qualified coverage rate threshold. If it is greater, obtain the first quality prediction result according to the real-time coverage rate. If it is less, obtain the coverage rate difference between the qualified coverage rate threshold and the real-time coverage rate;

[0029] S4. Based on the coverage rate degree change model and the coverage rate difference, obtain the change weight, and according to the change weight, the time of shot peening that has been performed, the real-time coverage rate and the end time of shot peening, obtain the second quality prediction result.

[0030] In this embodiment, it should be noted that in S1, first, the total area of the surface of the brake drum to be shot-peened is determined, which is the basis for calculating the number of projectile launches and the shot-peening time period; usually, a laser rangefinder, a 3D scanner, or image processing technology is used to accurately measure the area of the surface of the brake drum to be processed. These devices or technologies can capture the detailed dimensions of the surface, thereby calculating the accurate area. Then, a coverage standard is set to ensure that the surface after shot-peening meets the expected coverage requirements, thus meeting the quality and performance standards; the qualified coverage threshold is usually determined according to industry standards, customer requirements, or internal quality control standards. For example, in some applications, a coverage rate of 99% or higher may be required to ensure the durability and performance of the brake drum. Finally, the number of projectile launches is obtained based on the crater coverage model, the area to be processed, and the qualified coverage threshold; the crater coverage model is a mathematical model or algorithm used to describe the crater distribution and coverage rate formed by projectiles on the surface of the brake drum. It takes into account factors such as the size of the shot-peening flow channel and the projectile, the processing area, and the qualified coverage threshold; the crater coverage model calculates the number of projectile launches required to achieve the required coverage rate based on these parameters. Then, the shot-peening time period is obtained based on the shot-peening flow channel flow rate and the number of projectile launches. Dividing the number of projectile launches by the shot-peening flow channel flow rate gives the required shot-peening time period, which represents the minimum time required to complete the entire shot-peening process. Finally, the shot-peening start time and the shot-peening end time are obtained based on the shot-peening time period for time management and scheduling; specifically, according to the production plan and the shot-peening time period, the start time and the end time of the shot-peening process are determined, which helps to ensure that the shot-peening process is carried out within a predetermined time window to meet the production requirements.

[0031] Suppose there is a brake drum with a surface area of 100 square centimeters to be shot-peened, and the qualified coverage threshold is set at 99%. According to the crater coverage model, the crater coverage area formed by each projectile on the surface of the brake drum is 1 square centimeter. The shot-peening flow channel flow rate is 1000 projectiles per minute. The number of projectile launches calculated by the crater coverage model is 1900. Calculate the shot-peening time period: 1900 projectiles / 1000 projectiles per minute = 1.9 minutes. Determine the shot-peening start time and the shot-peening end time: Suppose the production plan arranges for the shot-peening process to start at 10:00 am, then the start time is 10:00:00, and the end time is 10:01:54.

[0032] In S2, it involves the real-time monitoring and analysis of the surface of the brake drum to be shot-peened during the shot-peening process. The purpose of this step is to obtain the real-time coverage rate of the brake drum surface, so as to compare it with the preset qualified coverage rate threshold and adjust the shot-peening process accordingly to ensure the processing quality and consistency. First, in order to achieve real-time monitoring, it is necessary to rely on high-precision and high-speed image acquisition devices, such as industrial cameras, high-speed cameras or specific machine vision systems. These devices should have sufficient resolution and frame rate to capture the subtle changes and dynamic processes on the brake drum surface. Then, using existing image processing methods, such as edge detection, morphological processing, threshold segmentation, etc., the contour and position information of the craters (or traces left by shot-peening) are extracted from the preprocessed images. Finally, based on the extracted crater information, the coverage rate of the current processed surface is calculated, which involves calculating the proportion of the crater area to the total area.

[0033] Suppose there is a surface of a brake drum to be shot-peened, with an area of 100 square centimeters, and the qualified coverage rate threshold is set at 99%. In step S2, a high-precision industrial camera is used for real-time monitoring. Initial state: Before the start of shot-peening, the camera takes an initial image of the brake drum surface. Since shot-peening has not been carried out at this time, the coverage rate is 0%. As the shot-peening process progresses, the camera continuously acquires new images. In the initial stage of shot-peening, due to the small number of shot peens, the coverage rate is low; as the number of shot peens increases, the coverage rate gradually rises; for example, when the processing reaches 1 minute, the coverage rate may reach 80%; when the processing reaches 1.5 minutes, the coverage rate may rise to 90%; finally, before the end of the processing, the coverage rate should reach or exceed the qualified threshold of 99%.

[0034] In S3, it is necessary to compare this real-time coverage rate with a preset qualified coverage rate threshold. The qualified coverage rate threshold is determined based on industry standards, customer requirements, or internal quality control standards. It represents the coverage rate requirement that the surface should achieve after shot peening to ensure quality and performance. For example, in some applications, a coverage rate of 99% or higher may be required to ensure the durability and performance of the brake drum. By comparing the real-time coverage rate with the qualified coverage rate threshold, it can be determined whether the current shot peening process meets the quality requirements. If the real-time coverage rate is greater than or equal to the qualified coverage rate threshold, it indicates that the current shot peening process is already effective enough to achieve the expected coverage rate requirement. In this case, a first quality prediction result can be obtained based on the real-time coverage rate. This prediction result may include quality indicators such as the absolute completion of shot peening, the uniformity of shot peening, and the stability of the coverage rate distribution, which are used to evaluate the quality level of the final shot peening of the brake drum. If the real-time coverage rate is less than the qualified coverage rate threshold, it indicates that the current shot peening process has not yet achieved the expected coverage rate requirement and further pre-prediction processing is needed. In this case, the coverage rate difference between the qualified coverage rate threshold and the real-time coverage rate needs to be obtained, and this difference is related to the subsequent shot peening coverage efficiency.

[0035] Specifically, when the coverage rate difference is large, it means that there are still a large number of surface areas that have not been covered by the shot peening projectiles. Therefore, the projectiles have more opportunities to cover these untreated areas in the subsequent shot peening process. Since the projectiles are randomly distributed, but in the case of a large area not covered, the probability of the projectiles hitting the untreated areas is relatively high. Therefore, the number of repeated coverages will be relatively small and the coverage efficiency is high. When the coverage rate difference is small, it indicates that most of the surface areas have been covered by the projectiles, and the remaining uncovered areas are relatively small and scattered. In this case, the probability of the projectiles hitting the untreated areas will be significantly reduced because the projectiles are more likely to hit the already covered areas, resulting in an increase in the number of repeated coverages and a decrease in the coverage efficiency. Therefore, the prediction strategy is adjusted according to different coverage rate differences.

[0036] In S4, first, the coverage difference is analyzed using the coverage degree change model. The coverage degree change model is a mathematical model that describes the change of coverage over time. It takes into account various factors such as the projectile launch velocity, shot peening time, and the initial state of the brake drum surface. These factors together determine the change trend of the coverage. By inputting parameters such as the coverage difference and time, the coverage degree change model can output a change weight, which reflects how fast and difficult the coverage changes during the subsequent shot peening process under the current coverage difference. Finally, the second quality prediction result is obtained based on the change weight, the shot peening time, the real-time coverage, and the shot peening end time. After obtaining the change weight, it is possible to combine other parameters (such as the shot peening time, the real-time coverage, and the shot peening end time) to predict the final shot peening quality and effect. One or more quality indicators, such as the final coverage distribution, can be calculated based on the input data and parameters.

[0037] Suppose there is a surface of a brake drum to be shot peened, with an area of 100 square centimeters, and the qualified coverage threshold is set at 99%. During the shot peening process, the change of the coverage is monitored in real time, and the following data is obtained:

[0038] Within 1 minute after the start of the shot peening, the real-time coverage is 80%.

[0039] Within 1.5 minutes after the start of the shot peening, the real-time coverage is 90%.

[0040] At a certain point in time before the end of the shot peening, the real-time coverage is 98%.

[0041] At this time, the coverage difference is calculated as 1% (99% - 98% = 1%) and input into the coverage degree change model, obtaining a change weight. Suppose this weight is 0.05, indicating that the coverage efficiency is extremely low during the subsequent shot peening process under the current coverage difference.

[0042] Next, by combining parameters such as the shot peening time (assumed to be 1.8 minutes), the real-time coverage (98%), and the shot peening end time (assumed to be 10:02:00) and inputting them into the quality prediction algorithm, the final coverage value is obtained. Based on the final coverage value, the second quality prediction result is obtained. For example, it is predicted that the final coverage value exceeds the qualified threshold of 99%, meeting the quality requirements.

[0043] In summary, in the entire quality prediction method for the shot peening process of a brake drum, by accurately measuring the area of the surface of the brake drum to be processed, setting a reasonable qualified coverage rate threshold, and combining with an advanced crater coverage model, the required number of shot emissions and the shot peening time period can be accurately calculated, thus realizing the precise planning and time management of the shot peening process; further, during the shot peening process, by using high-precision image acquisition equipment and advanced image processing technology, the change in the coverage rate of the brake drum surface is monitored in real time and compared with the preset qualified coverage rate threshold, and the deficiencies in the processing process can be discovered and adjusted in a timely manner to ensure the processing quality and consistency; further, by introducing concepts such as the coverage rate change model and change weight, the prediction ability of the coverage rate change during the shot peening process is further improved, and the final shot peening quality and effect can be comprehensively predicted based on multiple parameters such as the real-time coverage rate, the shot peening time, and the shot peening end time. This dynamic adjustment and prediction strategy not only improves the accuracy and stability of the shot peening process, but also greatly enhances the flexibility and adaptability of the processing process, making the shot peening process of the brake drum more intelligent and automated, effectively solving the problems of unstable and unpredictable processing quality caused by relying on manual experience and fixed parameters in the traditional shot peening process, and providing a more reliable and efficient shot peening solution for the manufacturing of brake drums and other components.

[0044] In one embodiment, the crater coverage model for obtaining the number of shot emissions based on the crater coverage model, the area to be processed, and the qualified coverage rate threshold in S1 is expressed as:

[0045] ; where

[0046] is the number of shot emissions, is the area to be processed, is the qualified coverage rate threshold, is the average processing range of a single shot, is the degree of fuzziness.

[0047] In this embodiment, it should be noted that N is the number of shot emissions, that is, the total number of shots that need to be emitted to reach the preset coverage rate threshold. S is the area to be processed, that is, the area of the surface of the brake drum that needs to be shot peened. is the qualified coverage rate threshold, that is, the coverage rate requirement that the surface should reach after shot peening to ensure quality and performance. is the average treatment range of a single shot, that is, the average radius or impact range of the crater formed by a shot on the brake drum surface, which determines the area that each shot can cover. a is the degree of blur, which is an adjustment factor used to take into account the uncertainty or randomness in the shot peening process, such as the impact of factors such as the direction of the shot, speed changes, and the unevenness of the brake drum surface on the coverage rate.

[0048] S and Directly related to the total area to be covered and the desired level of coverage, It represents the average area that a single projectile can cover, which is the basis for calculating the number of projectiles required. , reflecting the increase in coverage from 0 to The number of pellets required varies with the As the coverage increases, the number of pellets required to achieve that coverage increases nonlinearly. When the coverage approaches 100%, even a small increase requires a large number of pellets. It can reflect the trend that as the coverage rate increases, the number of required projectiles increases nonlinearly. The smaller part is more sensitive than the larger part, and can more accurately reflect the small differences in the number of shots. The fuzzy degree a is introduced to take into account various uncertainties in the shot peening process. In actual operation, even if the theoretically calculated number of shots is sufficient, the actual coverage may still be lower than expected due to various random factors. Therefore, by adjusting a, these uncertainties can be compensated to a certain extent to ensure that the final coverage meets the requirements.

[0049] In one embodiment, the shot peening time period is obtained according to the shot peening channel flow rate and the number of shot shots in S1 and is expressed as:

[0050] ;in,

[0051] is the shot peening time period, is the shot peening channel flow rate.

[0052] In this embodiment, it should be noted that the expression directly reflects the relationship between the shot peening time period (T), the number of shot launches (N), and the shot peening channel flow rate (Q). That is, the time required to complete all shot launches is equal to the total number of shots divided by the launch volume per unit time.

[0053] In one embodiment, obtaining the real-time coverage rate according to the real-time surface image in S2 includes:

[0054] S21, converting the real-time surface image into a grayscale image;

[0055] S22. Binarize the grayscale image and form a comparison image with only the crater area and the non-crater area;

[0056] S23. Obtain the real-time coverage rate based on the crater area and the non-crater area in the comparison image.

[0057] In this embodiment, it should be noted that in S21, first, read the real-time surface image from an image acquisition device (such as a camera) or a storage medium. This image may contain various colors and reflects the surface state after shot peening. Then, convert the read color image from the original color space (such as RGB) to the grayscale color space. This process can be achieved through various algorithms, and the most commonly used is the weighted average method. The weighted average method assigns different weights to the red, green, and blue channels according to the sensitivity of the human eye to different colors, and then calculates the weighted average value as the grayscale value. Finally, generate a grayscale image based on the calculated grayscale value. This image only contains brightness information and no color information, so it is simpler and more efficient to process. In summary, the purpose of converting the real-time surface image into a grayscale image is to simplify the image processing process, improve the processing speed, and reduce the interference of color information on subsequent processing steps. The grayscale image is more suitable for binarization processing because binarization only needs to distinguish bright and dark regions without considering color information.

[0058] In S22, first, select a suitable threshold. This threshold is used to distinguish the crater area (usually darker) and the non-crater area (usually lighter). The selection of the threshold can be achieved through existing trial-and-error methods, histogram analysis, or automatic threshold algorithms. Then, compare each pixel value in the grayscale image with the threshold. If the pixel value is less than or equal to the threshold, set it to 0 (black), representing the crater area; if the pixel value is greater than the threshold, set it to 255 (white), representing the non-crater area. Finally, generate a comparison image with only the crater area and the non-crater area based on the result of the binarization processing. In this image, the black area represents the crater, and the white area represents the non-crater area, forming a clear contrast.

[0059] In S23, first, calculate the areas of the black area (crater) and the white area (non-crater) in the comparison image. Through the processing in S22, it is easy to identify the boundaries of each area and calculate its area. Then, calculate the real-time coverage rate based on the calculated crater area and the total area (i.e., the actual area obtained by dividing the total number of pixels in the comparison image by the pixel size). The coverage rate is equal to the crater area divided by the total area.

[0060] In one embodiment, in S4, the coverage rate degree change model in obtaining the change weight based on the coverage rate degree change model and the coverage rate difference is expressed as:

[0061] , ; Among them,

[0062] is the variation weight, is the qualified coverage rate threshold, is the real-time coverage rate, is the correlation coefficient.

[0063] In this embodiment, it should be noted that is the variation weight, which is used to measure the degree of difference between the real-time coverage rate and the qualified coverage rate threshold, and accordingly adjust the importance of subsequent processing or decision-making. is the qualified coverage rate threshold, that is, the minimum coverage rate at which shot peening treatment is considered to meet the qualified standard. is the real-time coverage rate, that is, the actual coverage rate of the shot peened surface obtained by technical means such as image processing at the current moment. is the correlation coefficient, which is used to adjust the sensitivity of the variation weight. The larger the correlation coefficient, the more sensitive the variation weight is to the coverage rate difference.

[0064] Specifically, by introducing the correlation coefficient k, the sensitivity of the variation weight to the coverage rate difference can be adjusted. Different k values will result in different weight distributions, thus allowing for flexible adjustment according to actual needs. Generally, k = 1. The part in the expression reflects the relative difference between the real-time coverage rate and the qualified coverage rate threshold. This difference is normalized to between 0 and 1. This is because in predicting the subsequent coverage efficiency, due to the problem of repeated coverage, the coverage efficiency of the area to be covered will necessarily be lower than that of the already covered area. Therefore, finally is also between 0 and 1, and is used to complete the prediction calculation and processing of the final coverage rate by predicting the subsequent coverage efficiency.

[0065] Among them, when is larger, it means that there is still a large gap between the current coverage rate and the qualified coverage rate threshold, that is, there are still many areas not covered. Since shot peening is carried out randomly, a large coverage rate difference means more uncovered areas, and there is more room for shot peening to cover these areas. Therefore, the number of repeated coverages is relatively low, and the subsequent shot peening coverage efficiency will necessarily be higher, because each shot peening has a high probability of covering a new area. According to the weight calculation formula, the value of will tend to 1 more, reflecting that the degree of reduction of the coverage efficiency in the prediction process is relatively small.

[0066] When The smaller it is, the closer the current coverage rate is to the qualified coverage rate threshold, that is, most of the area has been covered. At this time, the uncovered area is small, and it is easier for shot peening to repeatedly cover the already covered area during the processing. Subsequently, the subsequent shot peening coverage efficiency will inevitably be low because the probability of each shot peening covering a new area is small. According to the weight calculation formula, the value of

[0067] will get closer to 0, reflecting that the degree of reduction in the coverage efficiency during the prediction process is relatively large.

[0068] In one embodiment, obtaining the second quality prediction result according to the change weight, the shot peening processing time, the real-time coverage rate, and the shot peening end time in S4 includes:

[0069] S41. Obtain the real-time coverage speed according to the shot peening processing time and the real-time coverage rate;

[0070] S42. Obtain the predicted coverage rate of the brake drum at the shot peening end time according to the real-time coverage speed and the change weight;

[0071] S43. Obtain the second quality prediction result according to the predicted coverage rate.

[0072] In this embodiment, it should be noted that in S41, two key data need to be collected: the shot peening processing time and the real-time coverage rate. Next, these two data are used to calculate the real-time coverage speed. The real-time coverage speed here can be simplified as real-time coverage speed = real-time coverage rate / shot peening processing time.

[0073] In S42, obtain the predicted coverage rate of the brake drum at the shot peening end time according to the real-time coverage speed and the change weight. First, it is necessary to determine the remaining time from the current moment to the shot peening end time; next, use the real-time coverage speed and the change weight to calculate the predicted coverage rate of the brake drum at the shot peening end. Here, the change weight (reflecting the shrinking trend of the subsequent coverage rate change) is used to directly reduce the real-time coverage speed. Generally, the change weight can be directly multiplied by the real-time coverage speed; then, multiply the real-time coverage speed processed by the change weight by the remaining time from the current moment to the shot peening end time to obtain the coverage rate increment during this remaining time; finally, add the coverage rate increment to the real-time coverage rate to obtain the predicted coverage rate of the brake drum at the shot peening end time.

[0074] In S43, the predicted coverage rate is compared with the qualified coverage rate threshold. If the predicted coverage rate is greater than or equal to the qualified coverage rate threshold, it is considered that the brake drum will reach or exceed the quality standard at the end of shot peening; if the predicted coverage rate is less than the qualified coverage rate threshold, it is considered that the brake drum may not reach the quality standard at the end of shot peening. Finally, based on the above comparison results, the second quality prediction result can be determined. For example, if the predicted coverage rate meets the standard, the second quality prediction result may be positive (such as "qualified", "expected to meet the standard", etc.); if the predicted coverage rate does not meet the standard, the second quality prediction result may be negative (such as "unqualified", "may not meet the standard", etc.).

[0075] In one embodiment, the predicted coverage rate of the brake drum at the end of shot peening obtained according to the real-time coverage rate and the change weight in S42 is expressed as:

[0076] ; where

[0077] is the predicted coverage rate, is the real-time coverage rate, is the remaining time.

[0078] In this embodiment, it should be noted that by introducing the change weight , the dynamic nature of the coverage rate change during the shot peening process can be considered. This weight is calculated based on the difference between the real-time coverage rate and the qualified coverage rate threshold, which can reflect the gap between the current processing state and the desired state, and adjust the prediction result accordingly. The real-time coverage rate reflects the efficiency of the shot peening process, that is, the speed at which the coverage rate increases per unit time. By monitoring this speed, the progress and efficiency of the current processing can be understood, so as to more accurately predict the level that the coverage rate may reach within the remaining time. The remaining time is an important factor in the prediction process, which can determine how much opportunity there is to increase the coverage rate within the remaining time, so as to make a more reasonable prediction.

[0079] A quality prediction system during the shot peening process of the brake drum is also provided. The system includes:

[0080] The first acquisition and calculation module is used to acquire the area to be processed on the surface of the brake drum to be shot peened and the qualified coverage rate threshold, and obtain the number of shot peening projectiles based on the crater coverage model, the area to be processed and the qualified coverage rate threshold, obtain the shot peening time period according to the shot peening channel flow rate and the number of shot peening projectiles, and obtain the start time and end time of shot peening according to the shot peening time period;

[0081] A second acquisition and calculation module, configured to acquire a real-time surface image of the surface of the brake drum to be shot-peened during the shot-peening process, and obtain a real-time coverage rate according to the real-time surface image;

[0082] A judgment and prediction module, configured to judge whether the real-time coverage rate is less than a qualified coverage rate threshold. If it is greater, obtain a first quality prediction result according to the real-time coverage rate. If it is less, obtain the coverage rate difference between the qualified coverage rate threshold and the real-time coverage rate;

[0083] A calculation and prediction module, configured to obtain a change weight based on a coverage rate degree change model and the coverage rate difference, and obtain a second quality prediction result according to the change weight, the shot-peening time, the real-time coverage rate, and the shot-peening end time.

[0084] In one embodiment, the second acquisition and calculation module is further configured to: convert the real-time surface image into a grayscale image; perform binarization processing on the grayscale image and form a comparison image with only the crater area and the non-crater area; obtain the real-time coverage rate according to the crater area and the non-crater area in the comparison image.

[0085] In one embodiment, the calculation and prediction module is further configured to: obtain a real-time coverage speed according to the shot-peening time and the real-time coverage rate; obtain a predicted coverage rate of the brake drum at the shot-peening end time according to the real-time coverage speed and the change weight; obtain a second quality prediction result according to the predicted coverage rate.

[0086] In this embodiment, it should be noted that regarding the above-mentioned quality prediction system during the shot-peening process of the brake drum, the specific manner of performing operations has been described in detail in the embodiments of the quality prediction method during the shot-peening process of the brake drum, and will not be elaborated here.

[0087] The preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings. However, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0088] In addition, it should be noted that, in the case of no contradiction, the various specific technical features described in the above specific embodiments can be combined in any suitable manner. To avoid unnecessary repetition, the present disclosure will not separately describe various possible combination manners.

[0089] In addition, any combination can be made between various different embodiments of the present disclosure, as long as it does not violate the idea of the present disclosure, and it should also be regarded as the content disclosed by the present disclosure.

[0090] 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 them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present invention, and they should all be covered by the scope of the claims and the specification of the present invention.

Claims

1. A method for predicting the quality of a brake drum during shot peening, characterized in that: The method comprises: Obtain the area to be treated and the qualified coverage threshold of the surface to be shot peened of the brake drum, and obtain the number of shot launches based on the crater coverage model, the area to be treated and the qualified coverage threshold, and obtain the shot peening time period according to the shot peening flow channel flow rate and the number of shot launches, and obtain the shot peening start time and shot peening end time according to the shot peening time period; Acquire a real-time surface image of the surface of the brake drum to be shot peened during the shot peening process, and acquire a real-time coverage rate according to the real-time surface image; Determine whether the real-time coverage is less than a qualified coverage threshold, if so, obtain a first quality prediction result according to the real-time coverage, if so, obtain a coverage difference between the qualified coverage threshold and the real-time coverage; Obtaining a change weight based on a coverage degree change model and a coverage difference, and obtaining a second quality prediction result according to the change weight, shot peening time, real-time coverage, and shot peening end time; The coverage degree change model in obtaining the change weight based on the coverage degree change model and the coverage difference is expressed as: , ;in, is the change weight, is the qualified coverage threshold, For real-time coverage, is the correlation coefficient; Wherein, obtaining the second quality prediction result according to the change weight, the shot peening time, the real-time coverage rate and the shot peening end time includes: obtaining the real-time coverage speed according to the shot peening time and the real-time coverage rate; obtaining the predicted coverage rate of the brake drum at the shot peening end time according to the real-time coverage speed and the change weight; obtaining the second quality prediction result according to the predicted coverage rate; The predicted coverage rate of the brake drum at the end of shot peening is obtained based on the real-time coverage speed and the change weight, which is expressed as: ;in, To predict coverage, For real-time coverage speed, For the remaining time.

2. The quality prediction method of the brake drum during shot peening according to claim 1, characterized in that: The crater coverage model in obtaining the number of projectile launches based on the crater coverage model, the area to be processed and the qualified coverage rate threshold is expressed as: ;in, is the number of projectiles fired, is the area to be processed, is the qualified coverage threshold, is the average treatment range of a single projectile, The degree of blur.

3. The quality prediction method of the brake drum during shot peening according to claim 2, characterized in that: The shot peening time period obtained according to the shot peening channel flow rate and the number of shot shots is expressed as: ;in, is the shot peening time period, is the shot peening channel flow rate.

4. The quality prediction method of the brake drum during shot peening according to claim 3 is characterized in that: The obtaining of real-time coverage rate according to the real-time surface image comprises: Convert the real-time surface image to a grayscale image; Binarization is performed on the grayscale image to form a comparison image of only the crater area and the non-crater area; Get the real-time coverage rate based on the crater area and non-crater area in the comparison image.

5. A quality prediction system for brake drum shot peening process, characterized in that: The system comprises: The first acquisition and calculation module is used to obtain the area to be treated and the qualified coverage threshold of the surface to be shot peened of the brake drum, and obtain the number of shot launches based on the crater coverage model, the area to be treated and the qualified coverage threshold, and obtain the shot peening time period according to the shot peening flow channel flow rate and the number of shot launches, and obtain the shot peening start time and shot peening end time according to the shot peening time period; A second acquisition and calculation module is used to acquire a real-time surface image of the surface of the brake drum to be shot peened during the shot peening process, and to acquire a real-time coverage rate according to the real-time surface image; A judgment and prediction module, used to judge whether the real-time coverage is less than a qualified coverage threshold, if it is greater, obtain a first quality prediction result according to the real-time coverage, if it is less than, obtain a coverage difference between the qualified coverage threshold and the real-time coverage; A calculation and prediction module, for obtaining a change weight based on a coverage degree change model and a coverage difference, and obtaining a second quality prediction result according to the change weight, shot peening time, real-time coverage and shot peening end time; The coverage degree change model in obtaining the change weight based on the coverage degree change model and the coverage difference is expressed as: , ;in, is the change weight, is the qualified coverage threshold, For real-time coverage, is the correlation coefficient; The calculation and prediction module is also used to: obtain the real-time coverage speed according to the shot peening time and the real-time coverage rate; obtain the predicted coverage rate of the brake drum at the end time of shot peening according to the real-time coverage speed and the change weight; obtain the second quality prediction result according to the predicted coverage rate; Among them, the predicted coverage rate of the brake drum at the end of shot peening is obtained according to the real-time coverage speed and the change weight as follows: ;in, To predict coverage, For real-time coverage speed, For the remaining time.

6. The quality prediction system during the shot peening process of the brake drum according to claim 5, characterized in that: The second acquisition and calculation module is also used for: Convert the real-time surface image to a grayscale image; Binarization is performed on the grayscale image to form a comparison image of only the crater area and the non-crater area; Get the real-time coverage rate based on the crater area and non-crater area in the comparison image.

Images