Aluminum ingot production process quality monitoring method and system

Abstract

The invention provides an aluminum ingot production process quality monitoring method and system, and belongs to the technical field of quality detection.The method comprises the steps that image acquisition is conducted on an aluminum ingot based on an image acquisition trigger signal, and aluminum ingot image data are obtained; performing defect identification on the aluminum ingot based on the aluminum ingot image data to obtain first defect information of the aluminum ingot; the first defect information comprises a defect proportion and a defect position of the aluminum ingot; in response to the condition that the aluminum ingot defect ratio is smaller than a first preset ratio, determining an ultrasonic scanning path based on the defect position; performing ultrasonic scanning on the aluminum ingot based on the ultrasonic scanning path to obtain aluminum ingot ultrasonic data; second defect information of the aluminum ingot is obtained based on the aluminum ingot ultrasonic data, and the quality grade of the aluminum ingot is determined based on the second defect information; the second defect information is the internal defect of the aluminum ingot. According to the aluminum ingot production process quality monitoring method and system provided by the invention, the aluminum ingot quality control and production efficiency can be improved.

Description

Technical Field

[0001] This application belongs to the field of quality inspection technology, and more specifically, relates to a method and system for quality monitoring in the aluminum ingot production process. Background Technology

[0002] In the aluminum ingot production process, quality monitoring is a key link to ensure product qualification. Traditional testing methods have obvious limitations. For example, existing technology directly uses full-area ultrasonic testing to cover the surface and interior of the aluminum ingot. Although it can detect internal defects, ultrasonic testing has low accuracy in identifying surface defects and it is difficult to distinguish between surface depressions and normal textures. Moreover, full-area scanning requires covering the aluminum ingot point by point, which is time-consuming and cannot meet the high-efficiency testing requirements of industrial production lines. As a result, traditional methods cannot balance aluminum ingot quality control and production efficiency. Summary of the Invention

[0003] The purpose of this application is to provide a method and system for quality monitoring in the aluminum ingot production process, so as to improve the quality control and production efficiency of aluminum ingots.

[0004] A first aspect of this application provides a method for quality monitoring in the aluminum ingot production process, comprising: Image acquisition is performed on aluminum ingots based on image acquisition trigger signals to obtain aluminum ingot image data; the image acquisition trigger signal is the signal detected by the infrared sensor when the aluminum ingot is transported to the image acquisition area; the aluminum ingot image data includes the image data of the upper surface of the aluminum ingot and the image data of the four sides. Defect identification is performed on aluminum ingots based on image data to obtain the first defect information of the aluminum ingots; the first defect information includes the defect percentage and defect location of the aluminum ingots. In response to the fact that the proportion of defects in the aluminum ingot is less than the first preset proportion value, the ultrasonic scanning path is determined based on the defect location; the aluminum ingot is ultrasonically scanned based on the ultrasonic scanning path to obtain the ultrasonic data of the aluminum ingot. The second defect information of the aluminum ingot is obtained based on the ultrasonic data of the aluminum ingot, and the quality grade of the aluminum ingot is determined based on the second defect information; the second defect information is the internal defect of the aluminum ingot.

[0005] A second aspect of this application provides a quality monitoring system for aluminum ingot production, comprising: The image acquisition module is used to acquire images of aluminum ingots based on an image acquisition trigger signal to obtain aluminum ingot image data. The image acquisition trigger signal is the signal detected by the infrared sensor when the aluminum ingot is transported to the image acquisition area. The aluminum ingot image data includes the image data of the upper surface of the aluminum ingot and the image data of the four sides. The first defect identification module is used to identify defects in aluminum ingots based on aluminum ingot image data to obtain the first defect information of the aluminum ingots; the first defect information includes the defect ratio and defect location of the aluminum ingots. The ultrasonic acquisition module is used to determine the ultrasonic scanning path based on the defect location in response to the fact that the proportion of defects in the aluminum ingot is less than a first preset proportion value; and to perform ultrasonic scanning on the aluminum ingot based on the ultrasonic scanning path to obtain ultrasonic data of the aluminum ingot. The second defect identification module is used to obtain the second defect information of the aluminum ingot based on the ultrasonic data of the aluminum ingot, and to determine the quality grade of the aluminum ingot based on the second defect information; the second defect information is the internal defect of the aluminum ingot.

[0006] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above-described method for quality monitoring in aluminum ingot production.

[0007] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method for quality monitoring in an aluminum ingot production process.

[0008] The beneficial effects of the quality monitoring method and system for aluminum ingot production provided in this application are as follows: This application uses an infrared sensor to trigger image acquisition, simultaneously acquiring images of the upper surface and four sides of the aluminum ingot. This avoids the defect omission problem of traditional single-view acquisition, and the automated triggering eliminates the need for manual intervention, reducing human error and improving the completeness and efficiency of surface inspection. Secondly, the defect ratio and location are obtained through image recognition, and aluminum ingots with severe surface defects are screened based on a first preset ratio, preventing such ingots from entering the subsequent ultrasonic testing stage, reducing ineffective testing costs. Simultaneously, the ultrasonic path is planned based on the defect location, focusing the detection on the internal area corresponding to the surface defect, solving the problem of low efficiency in full-area scanning, and balancing detection accuracy and speed. Compared to a single method that only detects the surface or interior, this application can achieve a comprehensive assessment of aluminum ingot quality, reducing product quality risks caused by hidden internal defects, and meeting the dual needs of quality control and efficiency improvement in industrial production. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application, 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 A flowchart illustrating a quality monitoring method for aluminum ingot production process according to an embodiment of this application; Figure 2A structural block diagram of a quality monitoring system for aluminum ingot production process provided in one embodiment of this application; Figure 3 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0011] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0012] To make the objectives, technical solutions, and advantages of this application clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0013] Please refer to Figure 1 , Figure 1 A flowchart illustrating a quality monitoring method for aluminum ingot production, provided in one embodiment of this application, can be executed by an electronic device. The method may include: S101: Image acquisition is performed on the aluminum ingot based on the image acquisition trigger signal to obtain aluminum ingot image data; the image acquisition trigger signal is the signal detected by the infrared sensor when the aluminum ingot is transported to the image acquisition area, and the aluminum ingot image data includes the image data of the upper surface of the aluminum ingot and the image data of the four sides.

[0014] In this embodiment, the infrared sensor is a system that uses the principle of infrared sensing to detect the presence of objects, specifically to sense whether an aluminum ingot has entered the image acquisition area. The image acquisition trigger signal is an electrical signal generated by the infrared sensor when it detects an aluminum ingot entering the image acquisition area. This signal is used to automatically start the image acquisition device, achieving automated triggering of aluminum ingot detection and avoiding missed or duplicate detections. The aluminum ingot image data can be a collection of surface images of the aluminum ingot acquired by an industrial camera, including images of the top surface and four sides, completely covering the outer surface of the aluminum ingot and ensuring that surface defects are detected without blind spots.

[0015] In this embodiment, when the aluminum ingot enters the preset image acquisition area through the conveying system, the infrared sensor can automatically detect the aluminum ingot and generate an image acquisition trigger signal, triggering the image acquisition device (such as an industrial camera) to work. The device can acquire images of the top surface and four sides of the aluminum ingot, ensuring coverage of all outer surfaces of the aluminum ingot, avoiding omission of surface defect detection dimensions, and ultimately obtaining complete aluminum ingot image data.

[0016] For example, a roller conveyor is used to transport the finished aluminum ingots to the inspection area at a fixed speed. Infrared beam sensors are installed on both sides of the image acquisition area entrance; as the aluminum ingot passes through, it blocks the infrared light, generating a trigger signal. Industrial cameras acquire surface images of the aluminum ingots, including one top industrial camera perpendicular to the upper surface of the ingot, and one side industrial camera (8-megapixel resolution, 16mm lens focal length). The side cameras can be slidably mounted on a slide rail, and are arranged at 45° angles to the four sides of the aluminum ingot to ensure no blind spots. The ultrasonic probe scanning range can cover the full size of the aluminum ingot.

[0017] When the aluminum ingot is conveyed to the image acquisition area, the infrared sensor is blocked, outputting a high-level trigger signal to the control system. Upon receiving the trigger signal, the control system synchronously activates two industrial cameras, completing the image capture within 0.3 seconds to obtain raw images (BMP format, 1200×800 resolution) of the upper surface and four sides of the aluminum ingot. The image data is transmitted to an industrial computer for storage via gigabit Ethernet.

[0018] S102: Based on the image data of aluminum ingots, perform defect identification on the aluminum ingots to obtain the first defect information of the aluminum ingots; the first defect information includes the defect ratio and defect location of the aluminum ingots.

[0019] In this embodiment, the first defect information is aluminum ingot surface defect data obtained through image recognition, including defect percentage (the percentage of the total surface defect area to the aluminum ingot surface area) and defect location (the three-dimensional coordinates of the defect on the aluminum ingot surface).

[0020] In this embodiment, the acquired aluminum ingot image data is analyzed using algorithms (such as machine vision defect recognition algorithms) to identify defects on the aluminum ingot surface (such as cracks, dents, inclusions, etc.), and the defect percentage and defect location are calculated. The defect percentage is the proportion of the area of ​​the defect region on the aluminum ingot surface to the total surface area; the defect location is the specific coordinates or area of ​​each surface defect on the aluminum ingot.

[0021] For example, the original image is converted to grayscale, Gaussian filtered, and edge enhanced. A trained YOLOv5 object detection model is then used to analyze the preprocessed image and identify surface defects (such as cracks, dents, and flash). The total area of ​​all defects is calculated using a pixel-counting method and divided by the total surface area of ​​the aluminum ingot (calculated based on the nominal dimensions of the ingot, e.g., the surface area of ​​a 1m × 0.5m × 0.2m aluminum ingot is approximately 1.6). The percentage value is obtained. Based on the mapping relationship between the image coordinate system and the physical size of the aluminum ingot (pre-calibrated by a calibration plate), the position of the defect in the image is converted into the three-dimensional physical coordinates of the aluminum ingot surface (e.g., X=0.3m, Y=0.2m, Z=0.05m, with the Z-axis being the height direction).

[0022] Output the first defect information, in which the defect rate is 2.1%, and the defect locations are: (0.3, 0.2, 0.05) and (0.4, 0.3, 0.05).

[0023] S103: In response to the fact that the proportion of defects in the aluminum ingot is less than the first preset proportion value, the ultrasonic scanning path is determined based on the defect location; the aluminum ingot is ultrasonically scanned based on the ultrasonic scanning path to obtain the ultrasonic data of the aluminum ingot.

[0024] In this embodiment, the first preset percentage can be a manually set threshold for the percentage of surface defects, used to determine whether the aluminum ingot needs internal inspection. When the percentage of surface defects exceeds this value, the aluminum ingot is directly judged as scrap and no further inspection is required. The ultrasonic scanning path is the trajectory of the ultrasonic probe planned according to the location of the surface defects, so that the ultrasonic inspection focuses on covering the internal area corresponding to the surface defects, balancing inspection accuracy and efficiency. The ultrasonic data of the aluminum ingot is the echo signal data formed by the reflection of ultrasonic waves emitted by the ultrasonic probe when they propagate inside the aluminum ingot and encounter defects.

[0025] In this embodiment, the decision to proceed to the next step of inspection is made based on the comparison between the surface defect ratio and the first preset ratio. If the defect ratio is greater than or equal to the first preset ratio, the product is directly deemed unqualified and no further inspection is required; if the defect ratio is less than the first preset ratio, the product proceeds to the internal defect inspection stage.

[0026] For example, if the control system determines that the defect percentage (2.1%) is less than the first preset percentage (3%), it activates the ultrasonic scanning path planning module. Centered on the surface defect location, a 5cm outward expansion is made to form a key scanning area, such as expanding (0.3, 0.2, 0.05) into a rectangular area of ​​0.25-0.35m × 0.15-0.25m. A serpentine scanning trajectory with a grid density of 0.2cm × 0.2cm is used; a parallel scanning trajectory with a grid density of 0.5cm × 0.5cm is also used; and a circular arc transition connects the key and non-key areas to ensure smooth probe movement.

[0027] The control system translates the scanning path into robot motion commands, controlling the ultrasonic probe to move along the planned path while simultaneously emitting ultrasonic waves (frequency 2MHz, pulse width 50ns). The probe receives the echo signals reflected from the defects, which are then converted into digital signals by a preamplifier (gain 40dB) and an A / D converter (sampling rate 100MHz), and stored as an ultrasonic data file. During the scanning process, the position of the aluminum ingot is monitored in real time (the conveyor speed can be fed back via an encoder) to ensure that the scanning position is synchronized with the aluminum ingot.

[0028] S104: Obtain the second defect information of the aluminum ingot based on the ultrasonic data of the aluminum ingot, and determine the quality grade of the aluminum ingot based on the second defect information; the second defect information is the internal defect of the aluminum ingot.

[0029] In this embodiment, the second defect information is the internal defect information of the aluminum ingot obtained based on ultrasonic data analysis, including the types of defects such as internal cracks, porosity, and inclusions.

[0030] In this embodiment, the ultrasonic data of the aluminum ingot is processed (e.g., through analysis of the reflection and attenuation characteristics of the ultrasonic signal) to identify the second defect information of the aluminum ingot (i.e., internal defects, such as internal cracks, pores, and porosity). Finally, based on the internal defect situation, the quality grade of the aluminum ingot is determined (e.g., superior, qualified, or unqualified), completing the entire quality monitoring process.

[0031] For example, characteristic parameters of the echo signal (such as amplitude, frequency, and propagation time) are extracted, the three-dimensional coordinates of the internal defect are located using wavelet transform, and the defect size (such as length 5mm, width 2mm, depth 10mm) is calculated. Second defect information is generated: {Defect type: internal crack, size: 5mm × 2mm × 10mm, location: (0.3, 0.2, 0.08)}.

[0032] Based on the preset quality judgment criteria (such as internal crack length <3mm is qualified product, 3-10mm is defective product, and >10mm is scrap product), the aluminum ingot is determined to be defective and is sent to the defective product area by a conveyor.

[0033] As can be seen from the above, this embodiment uses an infrared sensor to trigger image acquisition, simultaneously acquiring images of the upper surface and four sides of the aluminum ingot. This avoids the defect omission problem of traditional single-view acquisition, and the automated triggering eliminates the need for manual intervention, reducing human error and improving the completeness and efficiency of surface inspection. Secondly, the defect ratio and location are obtained through image recognition, and aluminum ingots with severe surface defects are screened based on a first preset ratio, preventing such ingots from entering the subsequent ultrasonic inspection stage and reducing ineffective inspection costs. At the same time, the ultrasonic path is planned based on the defect location, so that the inspection focus is on the internal area corresponding to the surface defect, solving the problem of low efficiency of full-area scanning and balancing inspection accuracy and speed. Compared with a single method that only inspects the surface or interior, this embodiment can achieve a comprehensive assessment of the aluminum ingot quality, reduce the product quality risk caused by hidden internal defects, and meet the dual needs of quality control and efficiency improvement in industrial production.

[0034] In one embodiment of this application, the quality grades of aluminum ingots include qualified products, substandard products, and scrap products; Before determining the ultrasonic scanning path based on the defect location in response to the aluminum ingot defect ratio being less than a first preset ratio value, the process also includes: If the proportion of defects in an aluminum ingot is greater than or equal to a first preset proportion value, the quality grade of the aluminum ingot is determined to be scrap.

[0035] In this embodiment, a pre-set threshold for the proportion of surface defects is used to quickly screen severely defective products. When the defect proportion is greater than or equal to this value, the product is directly judged as scrap.

[0036] First, clearly define the quality grade classification (qualified, substandard, and scrap). Compare the percentage of defects in the aluminum ingot with the first preset percentage. If the percentage of surface defects is greater than or equal to the first preset percentage, it means that the surface damage of the aluminum ingot has seriously affected its use (such as dense surface cracks and large-area oxidation). No further ultrasonic testing is needed, and it is directly judged as scrap, reducing the cost of ineffective testing. If the percentage of defects is less than the first preset percentage, it enters the ultrasonic scanning stage. Through internal defect detection, qualified and substandard products are finally distinguished. This achieves an efficient process of directly rejecting products with serious surface defects and accurately re-inspecting products with minor surface defects, which ensures both quality and improves testing efficiency.

[0037] For example, suppose that through image acquisition and defect identification of aluminum ingots, the total area of ​​surface defects is calculated, such as the surface area of ​​an aluminum ingot being 1.2. The total defect area is 0.042. The defect percentage is calculated as 0.042 / 1.2 × 100% = 3.5%. The control system compares this to the first preset percentage (3%). If 3.5% ≥ 3%, the scrap judgment logic is triggered, and the ultrasonic testing equipment does not need to be activated. The control system sends a signal to the conveyor, triggering the sorting mechanism to push the aluminum ingot from the main conveyor roller to the scrap collection area. At the same time, the batch number and defect percentage of the aluminum ingot are recorded in the production system for subsequent quality traceability. If the defect percentage of another aluminum ingot is 2.2% (< 3%), the scrap judgment is skipped, and the ultrasonic scanning path is planned according to the process to enter the internal defect detection stage. Finally, it is judged as a qualified product or a defective product based on the internal defect situation.

[0038] As can be seen from the above, this embodiment first defines three levels of standards: qualified products, substandard products, and scrap products, avoiding the confusion caused by the ambiguity of traditional testing levels and providing a clear basis for quality control. The comparison between the proportion of surface defects and the first preset proportion is used as a preliminary screening node. Aluminum ingots with severe surface defects are directly judged as scrap products and do not need to enter the subsequent ultrasonic testing. This avoids the equipment wear and time costs caused by ineffective ultrasonic testing and enables the rapid diversion of unqualified products, reducing their dwell time on the production line. At the same time, only aluminum ingots with minor surface defects are allowed to enter the ultrasonic testing process, focusing on the detection of internal defects to distinguish between qualified and substandard products, thus balancing the accuracy of quality judgment and testing efficiency.

[0039] In one embodiment of this application, obtaining second defect information of an aluminum ingot based on ultrasonic data includes: The spatial coordinates of the aluminum ingot are determined based on the ultrasonic scanning path, and a detection network is established based on the spatial coordinates. The detection network includes multiple grid cells. The characteristic parameters of the ultrasonic echo signal of each grid cell are obtained, and the cell defect information corresponding to each grid cell is determined based on the characteristic parameters of each grid cell. The cell defect information corresponding to each grid cell is integrated to obtain the second defect information of the aluminum ingot.

[0040] In this embodiment, the spatial coordinates are a three-dimensional coordinate system established based on the ultrasonic scanning path, used to identify the physical location of each position inside the aluminum ingot, thus achieving spatial localization of defects. The detection network is a set of grid cells that divide the aluminum ingot space into fixed-size units. Each grid cell corresponds to a tiny region inside the aluminum ingot and is the smallest spatial unit for defect detection, ensuring precise detection. The grid cell is the basic building block of the detection network, with fixed spatial dimensions and coordinate ranges, used to carry the ultrasonic signal characteristics and defect information of that region. The characteristic parameters of the ultrasonic echo signal are quantitative indicators extracted from the ultrasonic echo that reflect the internal structure of the material, such as echo amplitude, propagation time, and frequency variation.

[0041] In this embodiment, the ultrasonic scanning path is bound to the physical spatial coordinates of the aluminum ingot, establishing a mapping relationship between the scanning trajectory and the actual position of the aluminum ingot, ensuring spatial consistency in subsequent defect localization. The aluminum ingot is divided into multiple independent grid units (e.g., a 1mm×1mm×1mm cube), each unit corresponding to an independent ultrasonic echo signal. By analyzing the signal characteristics within the unit, refined defect identification is achieved, avoiding the problem of fuzzy defect information in traditional whole-scan scanning. The defect information of all grid units is summarized, and based on the spatial relationship between adjacent units, continuous or related defect units are merged into complete defects (e.g., multiple adjacent defect units are identified as the same crack), ultimately forming second defect information containing parameters such as the type, location, size, and distribution density of internal defects.

[0042] For example, a three-dimensional Cartesian coordinate system is established with the lower left corner vertex of the aluminum ingot as the origin (0, 0, 0) (X-axis along the length direction, Y-axis along the width direction, and Z-axis along the thickness direction). The coordinates of each sampling point along the ultrasonic scanning path (feedback from the robot encoder) are converted into physical coordinates in this coordinate system, such as (350.2, 120.5, 50.0) mm.

[0043] Each sampling point corresponds to a unique grid cell. For example, the coordinates (350.2, 120.5, 50.0) mm belong to the cell (350, 120, 50). The characteristic parameters of the ultrasonic echo signal of this cell are extracted: amplitude 92 mV, propagation time 12.3. The main frequency is 1.8MHz (10% offset from the transmission frequency of 2MHz).

[0044] Because the amplitude 92mV > 80mV, the element is determined to have a defect; combined with the frequency offset 10% > 5%, it is initially determined to be a crack-type defect. Based on the propagation time difference, the crack depth is calculated to be 3mm; combined with the signal attenuation rate, the crack length is calculated to be 5mm and the width to be 0.2mm, forming the element defect information: {Type: Crack, Size: 5mm × 0.2mm × 3mm, Coordinates: (350, 120, 50)}. Traversing all mesh elements, the information of 23 elements with defects is summarized. Through spatial location correlation, it is found that the defects of 18 elements belong to the same continuous crack (continuous distribution of spatial coordinates). Duplicate or associated defects are merged to generate second defect information: Internal defect type: continuous crack; total size: 30mm×0.2mm×5mm; distribution range: 340-370, 120-122, 48-53.

[0045] As can be seen from the above, this embodiment ensures accurate defect localization by associating the ultrasonic path with the spatial coordinates of the aluminum ingot; it then divides the aluminum ingot into grid cells and analyzes the echo characteristic parameters of each cell individually, avoiding the ambiguity of defect information in traditional whole-scan scanning and achieving refined identification of internal defects; finally, it integrates the cell defect information to form a complete internal defect map. The entire process not only improves the accuracy and completeness of defect localization but also provides structured data support for subsequent quality level determination.

[0046] In one embodiment of this application, determining the quality grade of an aluminum ingot based on second defect information includes: The defect type is determined based on characteristic parameters. The defect types include crack defects, porosity defects, and inclusion defects. A mapping table is constructed based on defect type and aluminum ingot quality grade; The quality grade of the aluminum ingot is determined by matching the second defect information with the mapping table.

[0047] In this embodiment, based on the characteristic parameters of the ultrasonic echo signal (such as amplitude, frequency, and waveform), internal defects are classified into cracks, looseness, and inclusions, solving the problem of judgment bias caused by the ambiguity of defect types in traditional detection. A mapping table between defect types and quality grades is pre-constructed, clearly defining the standards for qualified, substandard, and scrap products corresponding to different types and degrees of defects, avoiding the subjectivity of human judgment. The second defect information is compared with the mapping table, and the quality grade is automatically output, realizing the standardization and efficiency of the judgment process and ensuring consistent judgment results for the same type of defect.

[0048] For example, the preset judgment rule is: Crack-like defects: Echo signal amplitude abruptly increases by >50%, frequency decays rapidly (>30%), and the waveform is sawtooth-shaped; Loose-textured defects: The echo amplitude decreases gradually (10%-30%), the frequency does not change significantly, and the waveform is wavy; Mixed defects: The echo amplitude increases sharply (>80%), the frequency is stable, and the waveform has a sharp single peak.

[0049] A mapping table is constructed based on preset judgment rules, as shown in Table 1:

[0050] The ultrasonic characteristic parameters of a certain grid cell in the second defect information are extracted: echo amplitude abruptly changes by 60%, frequency attenuation is 35%, and the waveform is sawtooth-shaped. Matching the "crack-type defect" judgment rule, the defect is determined to be a crack. The specific parameters of the crack are obtained from the second defect information: length 4mm, single distribution, no continuous extension. The corresponding standard for crack-type defects is queried in the mapping table; a 4mm length conforms to the 2-5mm, single-line distribution standard for defective products. The system automatically determines the aluminum ingot's quality grade as defective and synchronizes the result to the production line control system, triggering the corresponding sorting process.

[0051] As can be seen from the above, this embodiment first accurately classifies defect types based on characteristic parameters, avoiding the problem of type confusion in traditional judgment; then, it clarifies the corresponding standards between different defects and quality levels through a mapping table, eliminating the subjectivity of human judgment; finally, it outputs the level through standardized matching, ensuring that the judgment results for defects of the same type are consistent. This process improves the accuracy and consistency of quality judgment, while speeding up the judgment process, adapting to the needs of industrial production for standardized and efficient quality control.

[0052] In one embodiment of this application, it further includes: Based on the first defect information, the second defect information, and the corresponding aluminum ingot production batch information, a defect-production parameter association database is established; the production parameters include aluminum melt melting temperature, holding time, casting speed, and cooling rate. Cluster analysis was performed on the data in the defect-production parameter association database to determine the abnormal range of production parameters corresponding to different types of defects; In response to the occurrence rate of the same type of defect in a consecutive preset number of production batches exceeding the second preset proportion, a production parameter adjustment strategy is generated based on the abnormal range, and the production parameters are adjusted based on the adjustment strategy.

[0053] In this embodiment, the defect-production parameter association database is a structured database that stores aluminum ingot defect information and corresponding production parameters and batch information, used to explore the correlation between defects and the production process. Production parameters are key controllable process parameters in the aluminum ingot production process, including aluminum melt melting temperature (affecting aluminum melt fluidity), holding time (affecting compositional uniformity), casting speed (affecting molding stability), and cooling rate (affecting crystallization quality), etc. The second preset percentage is a defect occurrence rate threshold that triggers parameter adjustment. When the occurrence rate of a certain type of defect in consecutive batches exceeds this value, it is determined that there is a systemic problem in the production process, and parameter adjustment is required.

[0054] In this embodiment, the surface defects (first defect information) and internal defects (second defect information) of aluminum ingots are linked to the key parameters of the production batch (melting temperature, casting speed, etc.) to establish a causal relationship between defects and the production process.

[0055] Clustering analysis algorithms (such as K-means) are used to group the data in the database, identifying the correlation between different defect types (such as cracks and inclusions) and production parameters (such as excessively high / low melting temperature). When the incidence of the same defect exceeds the standard in consecutive batches, parameter adjustment strategies are automatically generated based on the abnormal interval, optimizing the production process in reverse, reducing defect generation from the source, and achieving closed-loop control from quality issues to production optimization.

[0056] For example, after each batch of aluminum ingots is inspected, the data is automatically entered into the database. For instance, the record for batch B20230901 is: surface cracks 1.2%, internal porous volume 8... Production parameters: melting temperature 710℃, holding time 40min, casting speed 1.2m / min, cooling rate 12℃ / min. After accumulating 100 batches of data, cluster analysis was initiated. The clustering results for porosity defects showed that 85% of porosity defects were concentrated in the parameter combination of melting temperature > 700℃ and cooling rate > 10℃ / min. Therefore, this range was defined as the abnormal production parameter interval for porosity defects. It was detected that the porosity defect incidence rate of three consecutive batches (B20230902-B20230904) was 6.2% (> 5%), triggering the adjustment mechanism. Based on the abnormal interval generation strategy: melting temperature was reduced to 690℃±5℃, and cooling rate was reduced to 8℃±1℃. The strategy was sent to the production control system, adjusting the corresponding equipment parameters (such as furnace temperature controllers and cooling water valves), and tracking the defect rate of subsequent batches until the porosity defect incidence rate of two consecutive batches was < 3%, completing the closed-loop optimization.

[0057] As can be seen from the above, this embodiment binds defect information with production parameters, breaking down the information silo between traditional inspection and production processes. Cluster analysis locates abnormal parameter ranges corresponding to defects, providing precise basis for improvement. When the defect rate exceeds the standard in consecutive batches, an adjustment strategy is automatically generated to optimize production parameters, reducing defects from the source. This process achieves a shift from post-inspection to pre-inspection prevention, reducing the non-conforming rate, while also reducing trial-and-error costs and improving production stability and quality control efficiency.

[0058] In one embodiment of this application, it further includes: Obtain the nominal volume parameters of the aluminum ingots to be produced in the current batch, and determine the first initial preset percentage value based on the nominal volume parameters; Obtain the usage information of the current batch of aluminum ingots to be produced, and determine the correction coefficient of the first initial preset proportion value based on the usage information; The first preset percentage value is determined based on the first initial preset percentage value and the correction coefficient.

[0059] In this embodiment, the nominal volume parameter is the theoretical volume value specified during the design of the aluminum ingot, reflecting the size of the ingot and serving as the fundamental parameter for determining the initial defect threshold. The application information refers to the intended use scenario or application area of ​​the aluminum ingot (such as high-precision machining, ordinary casting, recycling and remelting), which determines the stringency of the surface quality requirements. The correction factor is an adjustment factor set based on the application information, used to adapt the initial threshold to specific application needs.

[0060] In this embodiment, a first initial preset percentage is determined based on the nominal volume of the aluminum ingot. Since a larger volume corresponds to a larger actual defect area for the same defect percentage, its impact on quality is more significant; therefore, volume and the initial threshold are negatively correlated (a larger volume results in a lower threshold). A correction coefficient is determined based on the intended use of the aluminum ingot (e.g., high-precision machined parts, ordinary structural parts). The higher the precision requirement of the application, the smaller the correction coefficient (the stricter the threshold), ensuring that the threshold is suitable for the actual usage scenario. By multiplying the initial threshold and the correction coefficient, a first preset percentage that balances volume characteristics and application requirements is obtained, avoiding overly strict or lenient thresholds and improving the rationality of surface defect screening.

[0061] For example, a volume-initial threshold correspondence table (see Table 2 below) and a usage-correction coefficient correspondence table are pre-defined.

[0062] Table 2. Volume-Initial Threshold Correspondence Table

[0063] Table 3 Applications - Correspondence Table of Correction Factors

[0064] A certain batch of aluminum ingots has a nominal volume of 0.8. The volume-initial threshold table is consulted to determine the first initial preset percentage as 2.5%. The preset application for this batch of aluminum ingots is high-precision machined parts; the application-correction coefficient table is consulted to obtain a correction coefficient of 0.8. The final first preset percentage = initial threshold × correction coefficient = 2.5% × 0.8 = 2.0%. The control system enters 2.0% into the detection parameter library. When the surface defect percentage of this batch of aluminum ingots is ≥2.0%, it is directly judged as scrap. If the subsequent application changes to ordinary structural parts, the threshold is automatically recalculated (2.5% × 1.2 = 3.0%) to ensure dynamic adaptation of the threshold to requirements.

[0065] As can be seen from the above, this embodiment determines the initial threshold based on volume, taking into account the actual differences in the proportion of defects under different volumes; then, a correction coefficient is set according to the application to adapt to the quality requirements of different scenarios. Finally, the threshold is calculated through the initial value and the coefficient, avoiding the rigidity of fixed thresholds. This prevents small-volume aluminum ingots from being misjudged due to overly strict thresholds, and also prevents large-volume aluminum ingots from being allowed defects due to overly lenient thresholds, thus improving the accuracy and flexibility of surface defect screening and adapting to diverse production needs.

[0066] In one embodiment of this application, it further includes: When the surface of the aluminum ingot is free of defects, ultrasonic scanning points are randomly determined, and the aluminum ingot is scanned based on the ultrasonic scanning points to obtain the ultrasonic data of the aluminum ingot.

[0067] In this embodiment, when no defects are found during surface inspection, it indicates that the surface quality of the aluminum ingot is acceptable. However, hidden defects (such as internal cracks or inclusions) may still exist internally, requiring verification through ultrasonic testing. Randomly determining scanning points avoids systematic omissions that might occur with fixed paths, ensuring that all areas within the aluminum ingot have a certain probability of being inspected, balancing inspection efficiency and sampling representativeness. Even if the surface is defect-free, random ultrasonic scanning still enables sampling monitoring of internal quality, preventing aluminum ingots with acceptable surfaces but inferior internal quality from flowing downstream, thus improving the quality control system.

[0068] For example, the image recognition system outputs the first defect information: 0% defect rate, no defect location, and determines that the aluminum ingot surface is defect-free.

[0069] The volume of the aluminum ingot is 0.08. The system initiates a random point generation module, generating 15 three-dimensional coordinate points based on a uniform distribution algorithm, such as (200, 100, 50), (500, 250, 80), etc., in mm. The point spacing is checked to be ≥5cm, meeting the constraints. The control system converts the coordinates of the 15 points into ultrasonic probe movement commands, plans the scanning sequence according to proximity, and drives the probe to move sequentially to each point, emitting 2MHz ultrasonic waves and collecting echo signals to form ultrasonic data for the aluminum ingot. If the ultrasonic data from all scanned points shows no abnormal signals, it is determined that there are no internal defects, and the quality level is qualified. If an abnormal signal is detected at a point (e.g., amplitude 95mV, consistent with inclusion defect characteristics), the scanning range of that area is expanded (adding 5 surrounding points), and the quality level is determined according to the corresponding rules after confirming the defect.

[0070] As can be seen from the above, the absence of surface defects in this embodiment does not necessarily mean that the internal quality is acceptable. Random scanning can effectively capture potential internal defects and prevent aluminum ingots with acceptable surfaces but poor internal quality from flowing downstream. Random point selection takes into account the detection probability of each area and prevents systematic missed detections along fixed paths. At the same time, it significantly reduces the detection time compared to full-area scanning. While ensuring the comprehensiveness of internal quality monitoring, it balances detection efficiency, improves the quality control system, and adapts to the dual requirements of quality and efficiency in industrial production.

[0071] A quality monitoring method for aluminum ingot production process corresponding to the above embodiment, Figure 2 This is a structural block diagram of a quality monitoring system for aluminum ingot production, provided as an embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 2 The aluminum ingot production process quality monitoring system 20 includes: an image acquisition module 21, a first defect identification module 22, an ultrasonic acquisition module 23, and a second defect identification module 24.

[0072] The image acquisition module 21 is used to acquire images of aluminum ingots based on an image acquisition trigger signal to obtain aluminum ingot image data. The image acquisition trigger signal is a signal detected by an infrared sensor when the aluminum ingot is transported to the image acquisition area. The aluminum ingot image data includes image data of the upper surface of the aluminum ingot and image data of the four sides. The first defect identification module 22 is used to identify defects in aluminum ingots based on aluminum ingot image data to obtain first defect information of the aluminum ingots; the first defect information includes the defect ratio and defect location of the aluminum ingots. The ultrasonic acquisition module 23 is used to determine the ultrasonic scanning path based on the defect location in response to the fact that the proportion of defects in the aluminum ingot is less than a first preset proportion value; and to perform ultrasonic scanning on the aluminum ingot based on the ultrasonic scanning path to obtain ultrasonic data of the aluminum ingot. The second defect identification module 24 is used to obtain the second defect information of the aluminum ingot based on the ultrasonic data of the aluminum ingot, and to determine the quality grade of the aluminum ingot based on the second defect information; the second defect information is the internal defect of the aluminum ingot.

[0073] In one embodiment of this application, the quality grades of aluminum ingots include qualified products, substandard products, and scrap products; A quality monitoring system 20 for aluminum ingot production also includes: a third defect identification module, specifically used for: If the proportion of defects in an aluminum ingot is greater than or equal to a first preset proportion value, the quality grade of the aluminum ingot is determined to be scrap.

[0074] In one embodiment of this application, the second defect identification module 24 is specifically used for: The spatial coordinates of the aluminum ingot are determined based on the ultrasonic scanning path, and a detection network is established based on the spatial coordinates. The detection network includes multiple grid cells. The characteristic parameters of the ultrasonic echo signal of each grid cell are obtained, and the cell defect information corresponding to each grid cell is determined based on the characteristic parameters of each grid cell. The cell defect information corresponding to each grid cell is integrated to obtain the second defect information of the aluminum ingot.

[0075] In one embodiment of this application, the second defect identification module 24 is further configured to: The defect type is determined based on characteristic parameters. The defect types include crack defects, porosity defects, and inclusion defects. A mapping table is constructed based on defect type and aluminum ingot quality grade; The quality grade of the aluminum ingot is determined by matching the second defect information with the mapping table.

[0076] In one embodiment of this application, a quality monitoring system 20 for aluminum ingot production process further includes: a parameter adjustment module, specifically used for: Based on the first defect information, the second defect information, and the corresponding aluminum ingot production batch information, a defect-production parameter association database is established; the production parameters include aluminum melt melting temperature, holding time, casting speed, and cooling rate. Cluster analysis was performed on the data in the defect-production parameter association database to determine the abnormal range of production parameters corresponding to different types of defects; In response to the occurrence rate of the same type of defect in a consecutive preset number of production batches exceeding the second preset proportion, a production parameter adjustment strategy is generated based on the abnormal range, and the production parameters are adjusted based on the adjustment strategy.

[0077] In one embodiment of this application, a quality monitoring system 20 for aluminum ingot production further includes: a preset proportion determination module, specifically used for: Obtain the nominal volume parameters of the aluminum ingots to be produced in the current batch, and determine the first initial preset percentage value based on the nominal volume parameters; Obtain the usage information of the current batch of aluminum ingots to be produced, and determine the correction coefficient of the first initial preset proportion value based on the usage information; The first preset percentage value is determined based on the first initial preset percentage value and the correction coefficient.

[0078] In one embodiment of this application, the ultrasound acquisition module is further used for: When the surface of the aluminum ingot is free of defects, ultrasonic scanning points are randomly determined, and the aluminum ingot is scanned based on the ultrasonic scanning points to obtain the ultrasonic data of the aluminum ingot.

[0079] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 3 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of the modules in the aforementioned system embodiments, for example... Figure 2 The functions of the image acquisition module 21, the first defect identification module 22, the ultrasonic acquisition module 23, and the second defect identification module 24 are shown.

[0080] It should be understood that, in the embodiments of this application, the processor 301 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0081] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0082] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store information such as aluminum ingot image data and aluminum ingot ultrasonic data.

[0083] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this application can execute the implementation method described in the aluminum ingot production process quality monitoring method provided in the embodiments of this application, or they can execute the implementation method of the electronic device described in the embodiments of this application, which will not be repeated here.

[0084] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to implement these processes. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or system capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0085] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD) card, flash card, etc., equipped on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0086] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0087] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0088] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connections shown or discussed may be indirect coupling or communication connections through some interfaces or units, or they may be electrical, mechanical, or other forms of connection.

[0089] The units described 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 the embodiments of this application, depending on actual needs.

[0090] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0091] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for quality monitoring in the aluminum ingot production process, characterized in that, include: Image data of aluminum ingot is obtained by acquiring an image of the aluminum ingot based on an image acquisition trigger signal. The image acquisition trigger signal is a signal detected by an infrared sensor when the aluminum ingot is transported to the image acquisition area. The image data of aluminum ingot includes image data of the upper surface and image data of the four sides of the aluminum ingot. Based on the image data of the aluminum ingot, defects are identified in the aluminum ingot to obtain the first defect information of the aluminum ingot; the first defect information includes the defect ratio and defect location of the aluminum ingot. In response to the fact that the proportion of defects in the aluminum ingot is less than a first preset proportion value, an ultrasonic scanning path is determined based on the location of the defects; an ultrasonic scan is performed on the aluminum ingot based on the ultrasonic scanning path to obtain ultrasonic data of the aluminum ingot. The second defect information of the aluminum ingot is obtained based on the ultrasonic data of the aluminum ingot, and the quality grade of the aluminum ingot is determined based on the second defect information; the second defect information is an internal defect of the aluminum ingot.

2. The quality monitoring method for aluminum ingot production process as described in claim 1, characterized in that, The quality grades of the aluminum ingots include qualified products, substandard products, and scrap products; Before determining the ultrasonic scanning path based on the defect location in response to the aluminum ingot defect ratio being less than a first preset ratio value, the method further includes: In response to the fact that the proportion of defects in the aluminum ingot is greater than or equal to a first preset proportion value, the quality grade of the aluminum ingot is determined to be scrap.

3. The quality monitoring method for aluminum ingot production process as described in claim 2, characterized in that, The second defect information of the aluminum ingot obtained based on the ultrasonic data of the aluminum ingot includes: The spatial coordinates of the aluminum ingot are determined based on the ultrasonic scanning path, and a detection network is established based on the spatial coordinates. The detection network includes multiple grid cells. The characteristic parameters of the ultrasonic echo signal of each grid cell are obtained, and the cell defect information corresponding to each grid cell is determined based on the characteristic parameters corresponding to each grid cell. The defect information of each grid cell is integrated to obtain the second defect information of the aluminum ingot.

4. The quality monitoring method for aluminum ingot production process as described in claim 3, characterized in that, Determining the quality grade of the aluminum ingot based on the second defect information includes: The defect type is determined based on the aforementioned characteristic parameters, and the defect type includes crack defects, porosity defects, and inclusion defects; A mapping table is constructed based on the defect type and the quality grade of the aluminum ingot; The quality grade of the aluminum ingot is determined by matching the second defect information with the mapping table.

5. The quality monitoring method for aluminum ingot production process as described in claim 4, characterized in that, Also includes: Based on the first defect information, the second defect information, and the corresponding aluminum ingot production batch information, a defect-production parameter association database is established; the production parameters include aluminum melt smelting temperature, holding time, casting speed, and cooling rate. Cluster analysis is performed on the data in the defect-production parameter association database to determine the abnormal range of production parameters corresponding to different types of defects; In response to the occurrence rate of the same type of defect exceeding a second preset proportion in a consecutive preset number of production batches, a production parameter adjustment strategy is generated based on the abnormal interval, and the production parameters are adjusted based on the adjustment strategy.

6. The quality monitoring method for aluminum ingot production process as described in claim 2, characterized in that, Also includes: Obtain the nominal volume parameters of the aluminum ingots to be produced in the current batch, and determine the first initial preset percentage value based on the nominal volume parameters; Obtain the usage information of the current batch of aluminum ingots to be produced, and determine the correction coefficient of the first initial preset proportion value based on the usage information; The first preset percentage value is determined based on the first initial preset percentage value and the correction coefficient.

7. The quality monitoring method for aluminum ingot production process as described in claim 1, characterized in that, Also includes: When the surface of the aluminum ingot is free of defects, ultrasonic scanning points are randomly determined, and the aluminum ingot is scanned based on the ultrasonic scanning points to obtain ultrasonic data of the aluminum ingot.

8. A quality monitoring system for aluminum ingot production process, characterized in that, include: The image acquisition module is used to acquire images of aluminum ingots based on the image acquisition trigger signal to obtain aluminum ingot image data; The image acquisition trigger signal is a signal detected by an infrared sensor when the aluminum ingot is transported to the image acquisition area. The aluminum ingot image data includes the image data of the upper surface of the aluminum ingot and the image data of the four sides. The first defect identification module is used to identify defects in the aluminum ingot based on the image data of the aluminum ingot, and obtain the first defect information of the aluminum ingot; the first defect information includes the defect ratio and defect location of the aluminum ingot. An ultrasonic acquisition module is used to determine an ultrasonic scanning path based on the location of the defects in the aluminum ingot in response to the fact that the proportion of defects in the aluminum ingot is less than a first preset proportion value; and to perform ultrasonic scanning on the aluminum ingot based on the ultrasonic scanning path to obtain ultrasonic data of the aluminum ingot. The second defect identification module is used to obtain the second defect information of the aluminum ingot based on the ultrasonic data of the aluminum ingot, and to determine the quality grade of the aluminum ingot based on the second defect information; the second defect information is an internal defect of the aluminum ingot.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images