Automobile parts-based machining burr detection system and related methods
The burr detection system for automotive parts processing, which integrates control, vision, and sensor modules, solves the problems of inflexibility and low accuracy in existing burr detection technologies, and achieves in-depth monitoring and precise detection of the processing process.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- 广州信邦智能装备股份有限公司
- Filing Date
- 2026-05-09
- Publication Date
- 2026-06-09
AI Technical Summary
Existing technologies for burr detection in automotive parts manufacturing are not flexible enough and have low accuracy, failing to take into account the manufacturing process in depth.
A burr detection system based on automotive parts is adopted, including a control module, a vision module, and a sensor module. By acquiring images, parameter information, and processing data of automotive parts, the system determines the burr detection strategy, enabling in-depth monitoring and accurate detection of the processing process.
It improves the accuracy, completeness, and scientific nature of burr detection, and can deeply consider the processing and component characteristics, adapting to the corresponding burr detection methods.
Smart Images
Figure CN122171554A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of intelligent manufacturing technology, specifically to a burr detection system and related methods for automotive parts. Background Technology
[0002] In the manufacturing process of automotive parts, burrs are mainly generated during metal cutting, stamping, casting, forging, welding, and PCB manufacturing. Among these, burrs are particularly common in stamping and machining. Since burrs are generated during the manufacturing process, they can also be called machining burrs. Although machining burrs are small, they have a significant impact on product quality, product safety, assembly efficiency of automotive parts, and the service life of automotive parts.
[0003] Currently, the detection of burrs in automotive parts is usually based on images of the parts being processed. However, this method does not take into account the actual processing of the parts, making the burr detection relatively mechanical, inflexible, and with low accuracy.
[0004] Therefore, the problem of how to provide a burr detection method that deeply considers the processing of automotive parts in order to improve the accuracy of burr detection urgently needs to be solved. Summary of the Invention
[0005] This application provides a burr detection system and related methods for automotive parts, which can deeply consider the burr detection methods in the processing of automotive parts to improve the accuracy of burr detection.
[0006] In a first aspect, embodiments of this application provide a burr detection system based on automotive parts. The system includes: a control module, a processing module, a vision module, and a sensor module. The vision module is used to acquire a first image of the automotive parts; the automotive parts are automotive parts that have completed a preset processing procedure. The control module is used to acquire first parameter information of the automotive parts; acquire first processing data corresponding to the preset processing process; and determine a first processing burr detection strategy based on the first parameter information, the first processing data, and the first image. The first processing data includes first video data, first state data, and first sensor data. The first video data is acquired by the vision module, the first state data is acquired by the processing module, and the first sensor data is acquired by the sensor module. The control module is further configured to perform burr detection on the automotive parts according to the first burr detection strategy and the first image, and obtain the target burr detection result.
[0007] Secondly, embodiments of this application provide a method for detecting machining burrs on automotive parts, applied to a machining burr detection system for automotive parts. This system includes a control module, a machining module, a vision module, and a sensor module. The method for detecting machining burrs on automotive parts includes: The first image of the automotive component is obtained through the vision module; the automotive component is an automotive component that has completed a preset processing procedure. The control module acquires first parameter information of the automotive parts; acquires first processing data corresponding to the preset processing process; and determines a first processing burr detection strategy based on the first parameter information, the first processing data, and the first image. The first processing data includes first video data, first state data, and first sensor data. The first video data is acquired by the vision module, the first state data is acquired by the processing module, and the first sensor data is acquired by the sensor module. The control module performs burr detection on the automotive parts according to the first burr detection strategy and the first image to obtain the target burr detection result.
[0008] Implementing the embodiments of this application has the following beneficial effects: As can be seen, the burr detection system based on automotive parts described in this application includes a control module, a processing module, a vision module, and a sensor module. It can synchronously monitor the processing process during a preset processing step for automotive parts, collecting corresponding first processing process data. The first video data reflects the video monitoring process at the processing location, the first status data reflects the working status of the equipment during the processing, the first sensor data reflects the environmental impact of the processing, and the first parameter information reflects the inherent characteristics and / or related uses of the automotive parts. After the automotive parts complete the preset processing step, the system deeply considers the actual video monitoring, equipment status, and environmental conditions of the automotive parts' processing process. Therefore, it can deeply consider the processing process of the automotive parts and the inherent characteristics and / or related uses of the automotive parts to adapt to the corresponding burr detection method, helping to improve the accuracy, completeness, scientific nature, and intelligence of burr detection. Attached Figure Description
[0009] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0010] Figure 1 This is a schematic diagram of a burr detection system for automotive parts provided in an embodiment of this application; Figure 2 This is a schematic diagram illustrating a reference image provided in an embodiment of this application; Figure 3 This is a schematic flowchart of a method for detecting burrs in the machining of automotive parts provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application; Figure 5 This is a functional unit block diagram of a burr detection device for automotive parts provided in an embodiment of this application. Detailed Implementation
[0011] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.
[0012] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.
[0013] It should be understood that the term "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document indicates that the preceding and following related objects are in an "or" relationship. In the embodiments of this application, "multiple" refers to two or more.
[0014] In the embodiments of this application, "at least one item" or its similar expression refers to any combination of these items, including any combination of a single item or a plurality of items. "One or more" means one or more, while "multiple" means two or more. For example, "at least one item" of a, b, or c can represent the following seven cases: a, b, c; a and b; a and c; b and c; a, b, and c. Each of a, b, and c can be an element or a set containing one or more elements.
[0015] In this application, the term "connection" refers to various connection methods, such as direct connection or indirect connection, to achieve communication between devices. This application does not impose any limitations on this.
[0016] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.
[0017] Please see Figure 1 , Figure 1 This is a schematic diagram of a burr detection system for automotive parts, provided in an embodiment of this application. The system includes a control module, a processing module, a vision module, and a sensor module. The control module, processing module, vision module, and sensor module are communicatively connected.
[0018] The control module can be understood as the "brain" of the burr detection system for automotive parts. The control module may include a control platform, server, robot, or other devices with communication and computing functions.
[0019] The processing modules can vary depending on the specific processing of automotive parts. For example, the processing methods can include any of the following: metal cutting, stamping, casting, forging, welding, PCB manufacturing, etc. Different processing methods can correspond to different processing modules, which can include robots (e.g., welding robots, stamping robots, robotic arms), intelligent machine tools, etc.
[0020] The vision module may include at least one of the following: a camera (e.g., a high-resolution industrial camera, or a high-resolution industrial camera in conjunction with a directional light source), an ultrasonic sensor, a radar sensor, a laser sensor (e.g., a laser displacement sensor), etc., without limitation.
[0021] The sensor module may include at least one of the following: a temperature sensor, a humidity sensor, a magnetic field detection sensor, a sound detection sensor, etc. The sensor module can be used to acquire sensor data at preset time intervals. During the manufacturing process of automotive parts, the sensor module can acquire sensor data at the processing location. The sensor data may include at least one of the following: temperature, humidity, magnetic field interference intensity, environmental noise, etc., without limitation.
[0022] based on Figure 1 The burr detection system shown, based on automotive parts, can achieve the following functions: The vision module is used to acquire a first image of the automotive parts; the automotive parts are automotive parts that have completed a preset processing procedure. The control module is used to acquire first parameter information of the automotive parts; acquire first processing data corresponding to the preset processing process; and determine a first processing burr detection strategy based on the first parameter information, the first processing data, and the first image. The first processing data includes first video data, first state data, and first sensor data. The first video data is acquired by the vision module, the first state data is acquired by the processing module, and the first sensor data is acquired by the sensor module. The control module is further configured to perform burr detection on the automotive parts according to the first burr detection strategy and the first image, and obtain the target burr detection result.
[0023] Automotive parts can include any automotive part that may produce machining burrs during the automotive parts manufacturing process. For example, automotive parts can include: battery electrodes, automotive stampings, automotive die castings, precision components of automotive engines (such as turbocharger blades, internal oil / water passages in cylinder blocks, pistons, crankshafts, etc.), core components of transmissions, wheel hubs, shaft parts, complex irregular-shaped parts, etc.
[0024] Among them, automotive parts can be automotive parts that have undergone preset processing procedures, which can be pre-set or system defaults. For example, preset processing procedures may include: metal cutting, stamping, casting, forging, welding, PCB manufacturing, etc.
[0025] After the automotive parts have completed the preset processing steps, the first image of the automotive parts can be obtained through the vision module.
[0026] The first parameter information of an automotive component can be used to characterize the component's properties and / or processing purpose (i.e., related use). This first parameter information may include: a first characteristic parameter and / or a first use parameter. The first characteristic parameter may include at least one of the following: the component's model number, material, dimensions, specifications, etc., without limitation. The first use parameter can be understood as the component's function or purpose, i.e., its subsequent function or purpose after completing the pre-defined processing steps, such as assembly location, assembly procedure, and assembly precautions.
[0027] In the preset processing procedure, the vision module can monitor the processing areas of the automotive parts. For example, it can acquire video data at a preset frame rate to obtain first video data, which may include multiple video frames, each corresponding to a processing position and a processing time. During the preset processing procedure, the processing module can acquire status data of the processing module at a first time interval to obtain first status data. The first status data can be used to characterize the processing status of the processing module. Different processing modules may focus on different status data; for example, status data may include at least one of the following: processing voltage, processing current, processing power, processing timing, etc., without limitation. The first status data may include at least one status data, each corresponding to a processing position and a processing time. During the preset processing procedure, the sensor module can acquire sensor data at the processing position at a second time interval to obtain first sensor data. The preset frame rate, first time interval, and second time interval can all be preset or defaulted to by the system.
[0028] The control module can acquire first parameter information of automotive parts and first processing data corresponding to a preset processing process. Since the first parameter information of automotive parts can be used to characterize the characteristics of the automotive parts and / or the processing purpose, while the first processing data can be used to characterize the processing process of the automotive parts, the control module determines a first burr detection strategy based on the first parameter information, the first processing data, and the first image. Then, based on the first burr detection strategy and the first image, the control module performs burr detection on the automotive parts to obtain the target burr detection result. This allows for a deep consideration of the processing process of automotive parts, as well as their characteristics and / or processing purpose, enabling the reasonable customization of corresponding burr detection strategies. Consequently, it provides a burr detection method that deeply considers the processing process of automotive parts, improving the accuracy of burr detection.
[0029] As can be seen, the burr detection system based on automotive parts described in this application includes a control module, a processing module, a vision module, and a sensor module. The vision module acquires a first image of the automotive part, which is an automotive part that has completed a preset processing procedure. The control module acquires first parameter information of the automotive part and first processing process data corresponding to the preset processing procedure. Based on the first parameter information, the first processing process data, and the first image, a first burr detection strategy is determined. The first processing process data includes first video data, first state data, and first sensor data. The first video data is acquired by the vision module, the first state data is acquired by the processing module, and the sensor data is acquired by the sensor module. The control module detects burrs on the automotive part based on the first burr detection strategy and the first image. The component undergoes burr detection to obtain the target burr detection result. This allows for simultaneous monitoring of the processing process during the pre-defined processing of automotive parts, collecting corresponding first processing process data. First video data reflects the video monitoring process at the processing location, first status data reflects the working status of the equipment during processing, first sensor data reflects the environmental impact of the processing process, and first parameter information reflects the inherent characteristics and / or related uses of the automotive parts. After the automotive parts complete the pre-defined processing, the actual video monitoring, equipment status, and environmental conditions of the processing process are thoroughly considered. This allows for the adaptation of appropriate burr detection methods based on the processing process and the inherent characteristics and / or related uses of the automotive parts, helping to improve the accuracy, completeness, scientific rigor, and intelligence of burr detection.
[0030] Optionally, in determining the first burr detection strategy based on the first parameter information, the first processing data, and the first image, the control module is specifically used for: A first region of interest image is determined based on the first parameter information, the first processing data, and the first image. The first region of interest image is divided into regions based on the first processing data to obtain n sub-region images and n region location identifiers; n is a positive integer; Based on the first processing process data and the n region location identifiers, a processing burr detection algorithm is determined for each of the n sub-region images, resulting in n processing burr detection algorithms; The first burr detection strategy is determined based on the n region location identifiers and the n burr detection algorithms.
[0031] The first parameter information includes a first characteristic parameter and / or a first application parameter. The first region of interest image is determined based on the first parameter information, the first processing data, and the first image. That is, the region of interest can be marked in the first image by combining the characteristics of the automotive parts and / or the application of the automotive parts and the processing process to obtain the first region of interest image.
[0032] Next, the first processing data reflects the condition of the equipment and the processing environment during processing. Different equipment conditions and processing environments will result in different burr locations and areas requiring attention. Therefore, the first region of interest (ROI) image can be divided into n sub-region images and n region location markers based on the first processing data; n is a positive integer, and there is a one-to-one correspondence between the n sub-region images and the n region location markers, meaning each sub-region image corresponds to one region location marker. This allows for region division of the ROI image based on the processing process, enabling early analysis of burr locations or regions in conjunction with the equipment condition and processing environment. Furthermore, different locations may produce different burr types and probabilities, which, based on location and corresponding region characteristics, helps in configuring appropriate processing burr detection algorithms.
[0033] Furthermore, based on the first processing data and n region location identifiers, a processing burr detection algorithm can be determined for each of the n sub-region images, resulting in n processing burr detection algorithms. This allows for the matching of the corresponding processing burr detection algorithm by combining the regional characteristics of each region, the status of the corresponding equipment, and the processing environment, which helps to ensure the accuracy and efficiency of processing burr detection.
[0034] In specific implementation, n region location markers and n burr detection algorithms can be integrated into a first burr detection strategy. The n burr detection algorithms can be bound to the n region location markers, meaning that different regions can correspond to different burr detection algorithms. The corresponding burr detection algorithm can be called based on the region location marker, which helps to ensure the accuracy and efficiency of burr detection.
[0035] Optionally, in determining the first region of interest image based on the first parameter information, the first processing data, and the first image, the control module is specifically configured to: Determine the first processing area in the first image based on the first processing data; The first target region is determined based on the first image and the first parameter information; The first region of interest image is determined in the first image based on the first processing area and the first target area.
[0036] Since the first processing data includes the first video data, which can be obtained by monitoring the processing location, the processing location can be recorded during the processing. Thus, all processing locations, i.e. processing areas, can be recorded in the first video data. Then, the corresponding processing area can be locked in the first image based on the first video data to obtain the first processing area.
[0037] Since the first parameter information includes a first characteristic parameter and / or a first application parameter, the corresponding historical burr area identification result can be obtained based on the first characteristic parameter. This historical burr area identification result can include a single burr area identification result, which can be the superposition of k burr area identification results. Each of these k burr area identification results corresponds to an automotive part, where k is a positive integer. For example, the corresponding historical burr area identification result can be obtained based on the first characteristic parameter, or based on the first application data. The historical burr area identification result can be manually verified, or it can be a combination of manual verification and visual recognition technology. In practice, processing a certain location may affect other locations. For example, during soldering, solder may splatter to other locations, potentially creating burrs.
[0038] The results of historical burr area identification can be obtained by compiling the corresponding burr detection data of similar automotive parts corresponding to the automotive parts, or the results of historical burr area identification can also be obtained by manual marking based on experience.
[0039] The historical burr area identification results can be preset or set by system default. For example, based on processing experience, the distribution pattern of burrs can be statistically analyzed during a preset processing process. This pattern can then be used to determine the corresponding burr distribution area, which is then identified as the historical burr area identification result. Different first parameter information will correspond to different historical burr area identification results.
[0040] Specifically, such as Figure 2As shown, the historical burr region identification result can include a reference image for the automotive parts. The reference image can include burr regions. Using this reference image as a mask, a first target region can be determined in a first image. In specific implementation, the first image can be aligned with the reference image. Corresponding first reference points can be set from the reference image (e.g., some specific points, which can be manually marked or obtained through feature extraction). Then, based on the first reference points, corresponding second reference points are determined in the first image. The first image and the reference image are aligned based on the first and second reference points. The region in the first image corresponding to the burr region of the reference image is the first target region.
[0041] Next, the union between the first processing area and the first target area can be determined, and the area corresponding to this union in the first image can be determined as the first region of interest.
[0042] In specific implementation, since the first processing area corresponds to the processing area monitored by the vision module, however, the vision module monitoring may also have certain blind spots, and there may be other areas that may produce burrs due to processing influences (e.g., processing vibration, solder splash, etc.). Therefore, the relevant historical burr area identification results can be obtained based on the first parameter information. This is equivalent to using big data technology to mark which areas may produce burrs or which areas need to be monitored for burrs. The areas determined by the two dimensions are fused to obtain the first region of interest image. This not only overcomes the monitoring "blind spots" but also uses big data to summarize experience and further make up for the deficiencies in processing monitoring, making the final first region of interest image more complete and helping to ensure the accuracy and completeness of burr detection.
[0043] Optionally, in the step of dividing the first region of interest image into n sub-region images and n region location markers based on the first processing data, the control module is specifically used for: Position identification is performed in the first region of interest image to obtain m reference points; m is a positive integer less than or equal to n; Based on the first processing data, the datasets corresponding to the m reference points are determined, resulting in m datasets. Each dataset includes the state data and sensor data corresponding to the reference point. Determine m influence radius values based on the m datasets; Based on the m influence radius values and the first region of interest image, m sub-region images are determined, and each sub-region image corresponds to a region location identifier; The remaining region image is determined based on the first region of interest image and the m sub-region images; Based on the remaining region image, nm sub-region images are determined, and each sub-region image corresponds to a region location identifier.
[0044] The characteristics of the reference point can be preset or set by system default. These characteristics may include at least one of the following: location coordinates, radians, name, angle, orientation, etc., without limitation. The location of the reference point can also be preset or set by system default. The location can be determined based on statistical results; for example, reference points can be set at locations with a high probability of burrs, or at locations that are critical.
[0045] In practice, location identification can be performed on the first region of interest image based on the relevant characteristics of the reference points to obtain m reference points, where m is a positive integer less than or equal to n.
[0046] Next, based on the data from the first processing step, a dataset corresponding to each of the m reference points can be obtained, resulting in m datasets. Each dataset includes state data and sensor data corresponding to the relevant reference point. The state data reflects the processing status of the equipment (e.g., potential stability), while the sensor data reflects the environmental impact during processing. Then, based on the m datasets, m influence radius values are determined, ensuring that the influence radius values correspond to the processing status of the equipment and the prevailing environment. Different state data and sensor data will result in different ranges of influence from the processing.
[0047] Next, we can draw circles with each of the m reference points as the center and its corresponding influence radius as the radius, thus obtaining m circles. Then, we can determine the intersection area between the m circles and the first region of interest image, thus obtaining m intersection areas. Each intersection area can correspond to a sub-region image, thus obtaining m sub-region images. Each sub-region image corresponds to a region location identifier, which can include a number or name to facilitate reference point positioning.
[0048] Next, regions other than the m sub-region images can be filtered out from the first region of interest image to obtain the remaining region image. Finally, nm sub-region images can be determined based on the remaining region image. Each sub-region image corresponds to a region location identifier. For example, an isolated region in the remaining region image can be taken as a sub-region image. Non-isolated regions in the remaining region image can be divided into at least one region according to the region division. The area of the region can be within a preset range. The preset range can be preset or system default. The preset range can be an empirical value.
[0049] In this example, for the first region of interest image, reference points are scientifically configured based on experience or requirements. Taking into account the processing status of the equipment and the environmental impact during the processing, the influence range of quantitative processing on the reference points is reasonably determined. Then, the corresponding sub-region images are reasonably divided, which facilitates targeted and purposeful burr detection and helps to ensure the accuracy, completeness and scientific nature of burr detection.
[0050] Optionally, in determining the m influence radius values based on the m datasets, the control module is specifically used for: Obtain the first state data and first sensor data corresponding to the first dataset; the first dataset is any dataset among the m datasets. Determine the reference influence radius value based on the first state data; The first adjustment parameter is determined based on the data from the first sensor. The influence radius value corresponding to the first dataset is determined based on the reference influence radius value and the first adjustment parameter.
[0051] In a specific implementation, taking the first dataset as an example, where the first dataset is any dataset from m datasets, the first state data and first sensor data corresponding to the first dataset can be obtained. Then, the first state data can be used to evaluate the working condition of the device. For example, a pre-stored mapping relationship between preset state data and evaluation values can be used, and the first evaluation value corresponding to the first state data can be determined based on this mapping relationship. Alternatively, the first state data can include at least one indicator data and at least one weight. Each indicator data corresponds to an indicator type, and each indicator type corresponds to a mapping relationship. Each mapping relationship is a mapping relationship between indicator data and evaluation value. At least one indicator data corresponds one-to-one with at least one weight, meaning one indicator data corresponds to one weight, and the sum of at least one weight is 1. Therefore, when the first state data includes one indicator data, the first evaluation value can be determined using the indicator data and the corresponding mapping relationship. Then, a reference influence radius value is determined based on the first evaluation value. When the first state data includes multiple indicator data, the evaluation value corresponding to each indicator data can be determined using the multiple indicator data and the corresponding mapping relationship, resulting in multiple evaluation values. These multiple evaluation values and their corresponding weights are then weighted to obtain the first evaluation value.
[0052] Next, a pre-stored mapping relationship between preset evaluation values and influence radius values can be used to determine the reference influence radius value corresponding to the first evaluation value.
[0053] Next, a pre-stored mapping relationship between preset sensor data and adjustment parameters can be established. Based on this mapping relationship, a first adjustment parameter can be determined. The range of the adjustment parameter can be preset or set by system default. For example, the range of the adjustment parameter can be -0.1 to 0.1. Then, the influence radius value corresponding to the first dataset is determined according to the reference influence radius value and the first adjustment parameter. For example, the influence radius value corresponding to the first dataset = (1 + first adjustment parameter) × reference influence radius value. In this way, the processing status of the equipment and the environmental influence during the processing can be comprehensively considered to reasonably determine the influence range of quantitative processing on the reference point. Furthermore, the corresponding sub-region images can be reasonably divided to facilitate targeted and purposeful burr detection, which helps to ensure the accuracy, completeness and scientific nature of burr detection.
[0054] Optionally, in determining the burr detection algorithm for each of the n sub-region images based on the first processing process data and the n region location identifiers, to obtain n burr detection algorithms, the control module is specifically used for: Based on the n region location identifiers, determine n burr type label sets; The n processing burr detection algorithms are determined based on the n region location identifiers, the first processing process data, and the n burr type label sets.
[0055] Since the reference points correspond to the regional location identifiers and are scientifically configured based on experience or needs, big data can be used to statistically analyze the types of punctures that occur at each reference point and their corresponding probabilities. It is also possible to statistically analyze the types of punctures that each reference point focuses on. Furthermore, n puncture type label sets can be determined based on n regional location identifiers. That is, each regional location identifier corresponds to one puncture type label set, each puncture type label set includes at least one puncture type label, and each puncture type label corresponds to one type of puncture.
[0056] Next, based on the n regional location identifiers, the processing data corresponding to each regional location identifier can be obtained from the first processing data. Based on the processing data corresponding to each regional location identifier and the corresponding burr type label set, a corresponding processing burr detection algorithm can be adapted for it. In this way, each region can have a customized processing burr detection algorithm, which helps to ensure the accuracy of processing burr detection.
[0057] Optionally, in determining the n processing burr detection algorithms based on the n region location identifiers, the first processing data, and the n burr type label sets, the control module is specifically used for: Based on the n burr type label sets, n reference processing burr detection algorithms are determined; Based on the first processing data and the n region location identifiers, determine the n control parameters corresponding to the n reference processing burr detection algorithms; The n burr detection algorithms are determined based on the n reference machining burr detection algorithms and the n control parameters.
[0058] The burr detection algorithm can include at least one of the following: neural network model, YOLO series object detection model, Transformer classifier, random forest model, etc., without limitation.
[0059] In specific implementation, a corresponding reference processing burr detection algorithm can be configured for each of the n burr type label sets. For example, the reference processing burr detection algorithm may include one processing burr detection algorithm, or it may include multiple processing burr detection algorithms. For example, taking the first burr type label set as an example, the first burr type label set is any burr type label set in the n burr type label sets. The first burr type label set may include x burr type labels, that is, x burr types, where x is a positive integer. Specifically, x burr types may correspond to one processing burr detection model, or x burr types may correspond to x processing burr detection models. When x burr types can correspond to one processing burr detection model, that processing burr detection model can identify x burr types. When x burr types can correspond to x processing burr detection models, there is a one-to-one correspondence between burr types and processing burr detection models, that is, each processing burr detection model can be used to identify one burr type.
[0060] Next, based on the n region location identifiers, the processing data corresponding to each region location identifier can be obtained from the first processing data. Based on the processing data corresponding to each region location identifier, corresponding control parameters are configured for the corresponding reference processing burr detection algorithm. These control parameters can be used to control the algorithmic effect of the reference processing burr detection algorithm, such as burr detection accuracy and burr detection speed. For example, taking the first region location identifier as an example, if the first region location identifier is any one of the n region location identifiers, its corresponding processing data can be obtained, such as target state data and / or target sensor data. For example, a preset mapping relationship between state data and control parameters can be stored in advance, meaning the control parameters corresponding to the target state data can be determined based on this mapping relationship. Similarly, a preset mapping relationship between sensor data and control parameters can be stored in advance, meaning the control parameters corresponding to the target sensor data can be determined based on this mapping relationship. For example, if the first region location identifier includes one processing burr detection model, only the control parameters of that processing burr detection model need to be configured. If the first region location identifier includes multiple processing burr detection models, corresponding model parameters can be configured for each processing burr detection model. Furthermore, n control parameters can be configured for n reference machining burr detection algorithms, making the control parameters deeply correlated with the machining process data of their corresponding positions, thereby further ensuring the intelligence of the reference machining burr detection algorithms.
[0061] Finally, n burr detection algorithms can be determined based on n reference burr detection algorithms and n control parameters. This ensures that each region has a customized burr detection algorithm, which helps to guarantee the accuracy of burr detection.
[0062] Furthermore, the sub-region images corresponding to the m reference points can be given special attention, and a customized burr detection algorithm can be provided for them. Other sub-region images besides those corresponding to the m reference points can also use the default burr detection algorithm for burr detection. The default burr detection algorithm can be preset or set by the system. The default burr detection algorithm can be related to the first parameter information of the automotive parts. For example, the default burr detection algorithm can be related to the first characteristic parameter, or the default burr detection algorithm can be related to the first application parameter.
[0063] Please see Figure 3 , Figure 3 This is a flowchart illustrating a method for detecting burrs in the machining of automotive parts, provided in an embodiment of this application. Figure 1The illustrated burr detection system for automotive parts includes a control module, a processing module, a vision module, and a sensor module. The burr detection method for automotive parts includes: S310: Obtain a first image of an automotive component through the vision module; the automotive component is an automotive component that has completed a preset processing procedure.
[0064] S320: Obtain first parameter information of the automotive component through the control module; obtain first processing data corresponding to the preset processing process; determine a first processing burr detection strategy based on the first parameter information, the first processing data, and the first image; the first processing data includes first video data, first state data, and first sensor data; the first video data is collected by the vision module, the first state data is collected by the processing module, and the first sensor data is collected by the sensor module.
[0065] S330: The control module performs burr detection on the automotive parts according to the first burr detection strategy and the first image to obtain the target burr detection result.
[0066] The specific descriptions of steps S310-S330 above can be found in the above descriptions. Figure 1 The description of the burr detection system based on automotive parts is omitted here.
[0067] Consistent with the above embodiments, please refer to Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device includes a processor, a memory, a communication interface, and one or more programs. The one or more programs are stored in the memory and configured to be executed by the processor. In this embodiment, the electronic device is applied to a burr detection system for automotive parts. The burr detection system for automotive parts includes a control module, a processing module, a vision module, and a sensor module. The program includes instructions for performing the following steps: The first image of the automotive component is obtained through the vision module; the automotive component is an automotive component that has completed a preset processing procedure. The control module acquires first parameter information of the automotive parts; acquires first processing data corresponding to the preset processing process; and determines a first processing burr detection strategy based on the first parameter information, the first processing data, and the first image. The first processing data includes first video data, first state data, and first sensor data. The first video data is acquired by the vision module, the first state data is acquired by the processing module, and the first sensor data is acquired by the sensor module. The control module performs burr detection on the automotive parts according to the first burr detection strategy and the first image to obtain the target burr detection result.
[0068] The electronic device may include any device used to implement the above functions; for example, the electronic device may include a control module.
[0069] Figure 5 This is a functional unit block diagram of a burr detection device 500 based on automotive parts, as described in this application embodiment. The burr detection device 500 is applied to a burr detection system based on automotive parts, which includes a control module, a processing module, a vision module, and a sensor module. The burr detection device 500 includes an acquisition unit 510, a determination unit 520, and a detection unit 530. The acquisition unit 510 is used to acquire a first image of an automotive part through the vision module; the automotive part is an automotive part that has completed a preset processing procedure. The determining unit 520 is used to acquire first parameter information of the automotive parts through the control module; acquire first processing data corresponding to the preset processing process; and determine a first processing burr detection strategy based on the first parameter information, the first processing data, and the first image; the first processing data includes first video data, first state data, and first sensor data; the first video data is acquired by the vision module, the first state data is acquired by the processing module, and the first sensor data is acquired by the sensor module. The detection unit 530 is used to perform burr detection on the automotive parts according to the first burr detection strategy and the first image through the control module, and obtain the target burr detection result.
[0070] It is understood that the functions of each program module of the burr detection device 500 for automotive parts in this embodiment can be specifically implemented according to the methods in the above method embodiments. The specific implementation process can be referred to the relevant descriptions in the above system embodiments, which will not be repeated here.
[0071] This application also provides a computer storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the methods described in the above method embodiments, wherein the computer includes an electronic device.
[0072] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may include an electronic device.
[0073] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.
[0074] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.
[0075] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.
[0076] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0077] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0078] If the aforementioned integrated units are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.
[0079] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage device, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.
[0080] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A burr detection system for automotive parts, characterized in that, The burr detection system for automotive parts includes: a control module, a processing module, a vision module, and a sensor module. The vision module is used to acquire a first image of the automotive parts; the automotive parts are automotive parts that have completed a preset processing procedure. The control module is used to acquire first parameter information of the automotive parts; acquire first processing data corresponding to the preset processing process; and determine a first processing burr detection strategy based on the first parameter information, the first processing data, and the first image. The first processing data includes first video data, first state data, and first sensor data. The first video data is acquired by the vision module, the first state data is acquired by the processing module, and the first sensor data is acquired by the sensor module. The control module is further configured to perform burr detection on the automotive parts according to the first burr detection strategy and the first image, and obtain the target burr detection result.
2. The burr detection system for automotive parts according to claim 1, characterized in that, In determining the first burr detection strategy based on the first parameter information, the first processing data, and the first image, the control module is specifically used for: A first region of interest image is determined based on the first parameter information, the first processing data, and the first image. The first region of interest image is divided into regions based on the first processing data to obtain n sub-region images and n region location identifiers; n is a positive integer; Based on the first processing process data and the n region location identifiers, a processing burr detection algorithm is determined for each of the n sub-region images, resulting in n processing burr detection algorithms; The first burr detection strategy is determined based on the n region location identifiers and the n burr detection algorithms.
3. The burr detection system for automotive parts according to claim 2, characterized in that, In determining the first region of interest image based on the first parameter information, the first processing data, and the first image, the control module is specifically configured to: Determine the first processing area in the first image based on the first processing data; The first target region is determined based on the first image and the first parameter information; The first region of interest image is determined in the first image based on the first processing area and the first target area.
4. The burr detection system for automotive parts according to claim 2 or 3, characterized in that, In the process of dividing the first region of interest image into n sub-region images and n region location markers based on the first processing data, the control module is specifically used for: Position identification is performed in the first region of interest image to obtain m reference points; m is a positive integer less than or equal to n; Based on the first processing data, the datasets corresponding to the m reference points are determined, resulting in m datasets. Each dataset includes the state data and sensor data corresponding to the reference point. Determine m influence radius values based on the m datasets; Based on the m influence radius values and the first region of interest image, m sub-region images are determined, and each sub-region image corresponds to a region location identifier; The remaining region image is determined based on the first region of interest image and the m sub-region images; Based on the remaining region image, nm sub-region images are determined, and each sub-region image corresponds to a region location identifier.
5. The burr detection system for automotive parts according to claim 4, characterized in that, In determining the m influence radius values based on the m datasets, the control module is specifically used for: Obtain the first state data and first sensor data corresponding to the first dataset; the first dataset is any dataset among the m datasets. Determine the reference influence radius value based on the first state data; The first adjustment parameter is determined based on the data from the first sensor. The influence radius value corresponding to the first dataset is determined based on the reference influence radius value and the first adjustment parameter.
6. The burr detection system for automotive parts according to claim 2 or 3, characterized in that, In the aspect of determining the burr detection algorithm for each sub-region image in the n sub-region images based on the first processing process data and the n region location identifiers, to obtain n burr detection algorithms, the control module is specifically used for: Based on the n region location identifiers, determine n burr type label sets; The n processing burr detection algorithms are determined based on the n region location identifiers, the first processing process data, and the n burr type label sets.
7. The burr detection system for automotive parts according to claim 6, characterized in that, Regarding the algorithm for determining the n processing burr detection algorithms based on the n region location identifiers, the first processing data, and the n burr type label sets, the control module is specifically used for: Based on the n burr type label sets, n reference processing burr detection algorithms are determined; Based on the first processing data and the n region location identifiers, determine the n control parameters corresponding to the n reference processing burr detection algorithms; The n burr detection algorithms are determined based on the n reference machining burr detection algorithms and the n control parameters.
8. A method for detecting burrs in the machining of automotive parts, characterized in that, A burr detection system for automotive parts is provided, comprising a control module, a processing module, a vision module, and a sensor module. The burr detection method for automotive parts includes: The first image of the automotive component is obtained through the vision module; the automotive component is an automotive component that has completed a preset processing procedure. The control module acquires first parameter information of the automotive parts; acquires first processing data corresponding to the preset processing process; and determines a first processing burr detection strategy based on the first parameter information, the first processing data, and the first image. The first processing data includes first video data, first state data, and first sensor data. The first video data is acquired by the vision module, the first state data is acquired by the processing module, and the first sensor data is acquired by the sensor module. The control module performs burr detection on the automotive parts according to the first burr detection strategy and the first image to obtain the target burr detection result.
9. The method for detecting burrs in the machining of automotive parts according to claim 8, characterized in that, The step of determining the first processing burr detection strategy based on the first parameter information, the first processing data, and the first image includes: A first region of interest image is determined based on the first parameter information, the first processing data, and the first image. The first region of interest image is divided into regions based on the first processing data to obtain n sub-region images and n region location identifiers; n is a positive integer; Based on the first processing process data and the n region location identifiers, a processing burr detection algorithm is determined for each of the n sub-region images, resulting in n processing burr detection algorithms; The first burr detection strategy is determined based on the n region location identifiers and the n burr detection algorithms.
10. The method for detecting burrs in the machining of automotive parts according to claim 9, characterized in that, The step of determining the first region of interest image based on the first parameter information, the first processing data, and the first image includes: Determine the first processing area in the first image based on the first processing data; The first target region is determined based on the first image and the first parameter information; The first region of interest image is determined in the first image based on the first processing area and the first target area.