Nodular iron casting simulation monitoring method and system, electronic equipment and medium

Abstract

The invention relates to the technical field of casting monitoring, in particular to a nodular iron casting simulation monitoring method and system, electronic equipment and a medium, and the method comprises the steps: obtaining casting image information, carrying out the image feature scanning of the casting image information, and obtaining a casting feature set, respectively inputting the casting features in each casting feature set into the anomaly identification model for training to obtain a primary identification result, determining whether the casting feature set has casting anomaly of the nodular iron casting or not based on the primary identification result, if so, simulating and constructing an initial casting dynamic model based on the casting feature set, and if not, constructing an initial casting dynamic model; and determining an abnormal casting feature and an abnormal casting reason according to a primary identification result, determining an abnormal casting position in the initial casting dynamic model, binding the abnormal casting reason to the initial casting dynamic model according to the abnormal casting position to obtain a monitoring casting dynamic model, and controlling and displaying the monitoring casting dynamic model. The casting efficiency of the nodular iron casting is improved.

Description

Technical Field

[0001] This application relates to the technical field of casting monitoring, and in particular, to a simulation monitoring method, system, electronic device and medium for ductile iron castings. Background Art

[0002] Due to their high strength, good toughness and corrosion resistance, ductile iron castings are widely used in fields such as machinery manufacturing, automobile manufacturing, and aerospace. However, the casting process of ductile iron castings is complex, involving multiple physical and chemical processes such as molten iron flow, solidification, and graphite spheroidization. These processes have a crucial impact on the performance and quality of the final castings. Traditional casting process design and optimization mainly rely on the experience and tests of engineers. This method not only takes a long time and is costly, but also is difficult to comprehensively and accurately predict and control various variables in the casting process, thereby reducing the casting efficiency of ductile iron castings. Summary of the Invention

[0003] To solve at least one of the above technical problems, this application provides a simulation monitoring method, system, electronic device and medium for ductile iron castings.

[0004] In a first aspect, this application provides a simulation monitoring method for ductile iron castings, adopting the following technical solutions: Obtain casting image information, where the casting image information is the image information corresponding to different casting links of ductile iron castings at different casting time periods during the casting process; Perform image feature scanning on the casting image information to obtain a set of casting features corresponding to each casting node; Input the casting features in each set of casting features into an anomaly recognition model for training in the order of casting time to obtain a primary recognition result; Based on the primary recognition result, determine whether there are casting anomalies in the set of casting features. If so, based on the set of casting features, simulate and construct an initial casting dynamic model, and determine the abnormal casting features and abnormal casting reasons according to the primary recognition result; Determine the abnormal casting position corresponding to the abnormal casting features in the initial casting dynamic model, and bind the abnormal casting reasons to the initial casting dynamic model according to the abnormal casting position to obtain a monitored casting dynamic model; Control the display of the monitored casting dynamic model.

[0005] By adopting the above technical solution, the casting image information is obtained, providing a comprehensive and accurate data basis for subsequent anomaly recognition, enabling technicians to accurately track every detail in the casting process, and thus more effectively identify potential problems. The casting image information is scanned for image features to obtain a set of casting features. The complex image information is converted into quantifiable casting features, facilitating subsequent data processing and model training. At the same time, the features are input into the anomaly recognition model in the order of casting time, ensuring that the model can learn the temporal sequence of the casting process and improving the accuracy of anomaly recognition. The anomaly recognition model is used for training to obtain a primary recognition result, which can quickly and accurately determine whether there are anomalies in the set of casting features. Once an anomaly is detected, an initial casting dynamic model is immediately constructed, and the abnormal casting features and reasons are determined based on the primary recognition result. This process greatly shortens the time for anomaly recognition, improves the controllability and safety of the casting process, determines the abnormal casting location, binds the reasons for abnormal casting to the initial casting dynamic model, and obtains a monitored casting dynamic model. It not only achieves precise positioning of casting anomalies but also provides an intuitive monitoring tool for technicians, enabling them to clearly understand the abnormal conditions in the casting process and thus take targeted measures for improvement and optimization. Controlling and displaying the monitored casting dynamic model enables technicians to grasp the status of the casting process in real time, promptly discover and handle potential problems. It improves the transparency and traceability of the casting process, and thereby also improves the casting efficiency of ductile iron castings.

[0006] In a possible implementation manner, the scanning the casting image information for image features to obtain a set of casting features corresponding to each of the casting nodes includes: Collecting the casting element equipment used in the casting process of the ductile iron casting; Calibrating and extracting each casting element contour in the casting image information according to the casting element equipment to obtain a key casting area corresponding to each casting image in the casting image information; Extracting image feature points of the key casting area in the casting image to obtain a set of area feature points corresponding to the key casting area; Recombining the set of area feature points according to the casting nodes to obtain a set of casting features corresponding to each of the casting nodes.

[0007] In a possible implementation manner, before respectively inputting the casting features in each set of casting features into the anomaly recognition model for training to obtain a primary recognition result, it further includes: Collecting the abnormal casting images of the ductile iron casting in the casting process and the abnormal handling information when processing the abnormal casting images; Perform three-dimensional simulation processing on the abnormal casting image to obtain a three-dimensional casting image; Collect the corresponding abnormal image features and abnormal feature positions in the three-dimensional casting image according to a preset observation angle, and bind the abnormal image features, the abnormal feature positions, and the abnormal processing information to obtain an abnormal information group; Create an abnormal recognition model, and use the abnormal information group as a training sample to input into the abnormal recognition model for training to obtain the trained abnormal recognition model.

[0008] In a possible implementation manner, before the step of performing image feature scanning on the casting image information to obtain a casting feature set corresponding to each casting node, it further includes: Judge whether there is at least one casting image with abnormal pixel brightness in the casting image information. If so, perform stripe detection processing on the at least one casting image to obtain a pixel brightness image; Process the pixel brightness image to obtain a target correction coefficient corresponding to each pixel point; According to the target correction coefficient corresponding to each pixel point, perform correction processing on the at least one casting image to obtain a corrected casting image; Based on the corrected casting image, update and replace the corresponding casting image in the casting image information to obtain updated and replaced casting image information.

[0009] In a possible implementation manner, when determining whether there is a casting abnormality of ductile iron castings in the casting feature set based on the primary recognition result, it further includes: If there is no casting abnormality of ductile iron castings in the casting feature set, reorganize the features in the casting feature set according to different feature positions in the casting image information to obtain a position feature set for different feature positions; Arrange each position feature set in a matrix according to the casting time sequence to obtain a position feature matrix corresponding to each feature position; Deduce the casting features according to the position feature matrix in a time period to obtain a predicted feature matrix corresponding to different feature positions within a preset future time period; Input the casting features in each predicted feature matrix into the abnormal recognition model for training to obtain a secondary recognition result; Judge whether there is a casting abnormality of ductile iron castings in the secondary recognition result. If so, determine the abnormal time and abnormal inducing factors in the secondary recognition result, and bind the abnormal time, the abnormal inducing factors, and the feature positions to obtain casting predicted abnormal information.

[0010] In a possible implementation, the initial casting dynamic model constructed by simulating based on the set of casting features includes: Determine the two-dimensional coordinates of the casting key points based on the set of casting features; Determine the coordinate system of the casting model according to the casting model in the casting equipment library; Input the two-dimensional coordinates of the casting key points into a deep learning model for perspective transformation to obtain the three-dimensional coordinates of the casting key points corresponding to the two-dimensional coordinates of the casting key points; Map the three-dimensional coordinates of the casting key points to the coordinate system of the casting model to obtain the initial casting dynamic model.

[0011] In a possible implementation, after controlling the display of the monitored casting dynamic model, it further includes: Collect management personnel information and determine the target terminal device based on the management personnel information; Determine the maintenance time range corresponding to the abnormal casting cause according to the abnormal casting cause and the preset monitoring standard; When it is detected that the monitored casting dynamic model is sent to the target terminal device, record the arrival time of the management personnel at the abnormal casting position, and match the arrival time with the maintenance time range to determine whether there is an abnormality in the maintenance timeliness; If there is an abnormality in the maintenance timeliness, mark the management personnel information and send the marked management personnel information to the terminal device of the management personnel's superior management personnel.

[0012] In a second aspect, the present application provides a ductile iron casting simulation monitoring system, adopting the following technical solution: A ductile iron casting simulation monitoring system includes: An information acquisition module, configured to acquire casting image information, where the casting image information is the image information corresponding to different casting links of the ductile iron casting at different casting time periods; A feature scanning module, configured to perform image feature scanning on the casting image information to obtain the set of casting features corresponding to each casting node; An abnormal recognition module, configured to input the casting features in each set of casting features into an abnormal recognition model for training in the order of casting time to obtain a primary recognition result; A model construction module, configured to determine whether there is a casting abnormality of the ductile iron casting based on the primary recognition result. If so, construct an initial casting dynamic model by simulating based on the set of casting features, and determine the abnormal casting features and the abnormal casting cause according to the primary recognition result; A data binding module, configured to determine an abnormal casting position corresponding to the abnormal casting feature in the initial casting dynamic model, and bind the abnormal casting cause to the initial casting dynamic model according to the abnormal casting position, so as to obtain a monitored casting dynamic model; A control display module, configured to control the display of the monitored casting dynamic model.

[0013] In a possible implementation manner, when the feature scanning module performs image feature scanning on the casting image information to obtain a casting feature set corresponding to each casting node, it is specifically configured to: Collect casting element devices applied during the casting process of the ductile iron casting; Calibrate and extract each casting element contour in the casting image information according to the casting element device to obtain a key casting area corresponding to each casting image in the casting image information; Extract image feature points of the key casting area in the casting image to obtain a region feature point set corresponding to the key casting area; Recombine the region feature point set according to the casting nodes to obtain a casting feature set corresponding to each casting node In another possible implementation manner, the system further includes: an information collection module, a three-dimensional processing module, an information binding module, and a model training module, where The information collection module is configured to collect abnormal casting images during the casting process of the ductile iron casting and abnormal processing information when processing the abnormal casting images; The three-dimensional processing module is configured to perform three-dimensional simulation processing on the abnormal casting images to obtain three-dimensional casting images; The information binding module is configured to collect corresponding abnormal image features and abnormal feature positions in the three-dimensional casting images according to a preset observation angle, and bind the abnormal image features, the abnormal feature positions, and the abnormal processing information to obtain an abnormal information group; The model training module is configured to create an abnormal recognition model, and input the abnormal information group as a training sample into the abnormal recognition model for training to obtain the trained abnormal recognition model.

[0014] In another possible implementation manner, the system further includes: a stripe processing module, an image processing module, a calibration processing module, and an image replacement module, where The stripe processing module is configured to determine whether there is at least one casting image in the casting image information with abnormal pixel brightness and darkness. If so, perform stripe detection processing on the at least one casting image to obtain a pixel brightness and darkness image; The image processing module is used to process the pixel brightness image to obtain a target correction coefficient corresponding to each pixel point; The correction processing module is used to perform correction processing on the at least one casting image according to the target correction coefficient corresponding to each pixel point to obtain a corrected casting image; The image replacement module is used to update and replace the corresponding casting image in the casting image information based on the corrected casting image to obtain updated and replaced casting image information.

[0015] In another possible implementation manner, the system further includes: a feature recombination module, a matrix arrangement module, a feature deduction module, an anomaly training module, and an anomaly prediction module, where The feature recombination module is used to, when there is no casting anomaly of the ductile iron casting in the casting feature set, recombine the features in the casting feature set according to different feature positions in the casting image information to obtain a position feature set of different feature positions; The matrix arrangement module is used to arrange each position feature set in a matrix according to the casting time sequence to obtain a position feature matrix corresponding to each feature position; The feature deduction module is used to deduce the casting features according to the position feature matrix in a time period to obtain a predicted feature matrix corresponding to different feature positions within a preset future time period; The anomaly training module is used to input the casting features in each predicted feature matrix into the anomaly recognition model for training to obtain a secondary recognition result; The anomaly prediction module is used to determine whether there is a casting anomaly of the ductile iron casting in the secondary recognition result. If so, determine the anomaly time and anomaly inducing factors in the secondary recognition result, and bind the anomaly time, the anomaly inducing factors, and the feature position to obtain casting predicted anomaly information.

[0016] In another possible implementation manner, when the model construction module simulates and constructs an initial casting dynamic model based on the casting feature set, it specifically is used for: Determine the two-dimensional coordinates of the casting key points based on the casting feature set; Determine the coordinate system of the casting model according to the casting model in the casting equipment library; Input the two-dimensional coordinates of the casting key points into a deep learning model for perspective transformation to obtain the three-dimensional coordinates of the casting key points corresponding to the two-dimensional coordinates of the casting key points; Map the three-dimensional coordinates of the casting key points to the coordinate system of the casting model to obtain an initial casting dynamic model.

[0017] In another possible implementation, the system further includes: a personnel collection module, a time determination module, a time matching module, and a personnel management module, where the personnel collection module is configured to collect management personnel information and determine a target terminal device based on the management personnel information; the time determination module is configured to determine a maintenance time range corresponding to the abnormal casting cause according to the abnormal casting cause and a preset monitoring standard; the time matching module is configured to record the arrival time of the management personnel at the abnormal casting position after detecting that the monitored casting dynamic model is sent to the target terminal device, and match the arrival time with the maintenance time range to determine whether there is an abnormality in the maintenance timeliness; the personnel management module is configured to, when there is an abnormality in the maintenance timeliness, mark the management personnel information and send the marked management personnel information to the terminal device of the superior management personnel of the management personnel.

[0018] In a third aspect, the present application provides an electronic device, adopting the following technical solution: at least one processor; a memory; at least one application program, where at least one application program is stored in the memory and is configured to be executed by at least one processor, and at least one application program is configured to: execute a ductile iron casting simulation monitoring method according to any one of the first aspect.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium, adopting the following technical solution: A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed in a computer, the computer is made to execute a ductile iron casting simulation monitoring method according to any one of the first aspect.

[0020] In summary, the present application includes at least one of the following beneficial technical effects: By adopting the above technical solutions, the casting image information is obtained, providing a comprehensive and accurate data basis for subsequent anomaly recognition, enabling technicians to accurately track every detail in the casting process, and thus more effectively identify potential problems. The casting image information is scanned for image features to obtain a set of casting features. The complex image information is converted into quantifiable casting features, facilitating subsequent data processing and model training. At the same time, the features are input into the anomaly recognition model in the order of casting time, ensuring that the model can learn the temporal sequence of the casting process and improving the accuracy of anomaly recognition. The anomaly recognition model is used for training to obtain a primary recognition result, which can quickly and accurately determine whether there are anomalies in the set of casting features. Once an anomaly is detected, an initial casting dynamic model is immediately constructed, and the abnormal casting features and causes are determined based on the primary recognition result. This process greatly shortens the time for anomaly recognition, improves the controllability and safety of the casting process, determines the abnormal casting location, and binds the abnormal casting cause to the initial casting dynamic model to obtain a monitored casting dynamic model. It not only realizes the precise positioning of casting anomalies but also provides an intuitive monitoring tool for technicians, enabling them to clearly understand the abnormal conditions in the casting process, and thus take targeted measures for improvement and optimization. Controlling and displaying the monitored casting dynamic model enables technicians to real-time grasp the state of the casting process, promptly discover and handle potential problems. It improves the transparency and traceability of the casting process, and further improves the casting efficiency of ductile iron castings. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 FIG. is a schematic flowchart of a simulation monitoring method for ductile iron castings provided by an embodiment of the present application.

[0022] Figure 2 FIG. is a schematic structural diagram of a simulation monitoring system for ductile iron castings provided by an embodiment of the present application.

[0023] Figure 3 FIG. is a schematic structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] The following further elaborates on the present application Figures 1 - 3 in conjunction with the accompanying drawings.

[0025] This specific embodiment is merely an interpretation of the present application and does not limit the present application. Those skilled in the art can make modifications without creative contributions to this embodiment according to needs after reading this specification, but as long as they are within the scope of the present application, they are protected by the patent law.

[0026] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are some, but not all, of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of this application without creative efforts shall fall within the scope of protection of this application.

[0027] In addition, the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, unless otherwise specified.

[0028] The following further describes the embodiments of this application in detail with reference to the accompanying drawings of the specification.

[0029] The embodiments of this application provide a method for simulating and monitoring ductile iron castings, which is executed by an electronic device. Herein, the electronic device may be an independent physical electronic device, an electronic device cluster or a distributed system composed of multiple physical electronic devices, or a cloud electronic device providing cloud computing services. The embodiments of this application do not limit this here. As Figure 1 shown, the method includes: Step S10: Obtain casting image information.

[0030] Among them, the casting image information is the image information corresponding to different casting links at different casting time periods during the casting process of ductile iron castings.

[0031] Specifically, the casting image information represents the image data captured or obtained for a certain ductile iron casting during the casting process. A ductile iron casting refers to an iron casting product in which the graphite morphology inside the casting is spherical through special process treatment, thereby significantly improving the mechanical properties of the casting. A casting link refers to different stages divided by processes during the entire casting process from raw material preparation to finished product output, such as melting, pouring, cooling, etc. The casting time period refers to the specific time periods divided according to the time sequence during these casting links, which is used to more accurately locate the state of the casting process.

[0032] In an embodiment of the present application, after acquiring the casting image information, it is determined whether there is at least one casting image with abnormal pixel brightness in the casting image information. If so, stripe detection processing is performed on at least one casting image to obtain a pixel brightness image; the pixel brightness image is processed to obtain a target correction coefficient corresponding to each pixel point, and based on the target correction coefficient corresponding to each pixel point, at least one casting image is corrected to obtain a corrected casting image, and the corresponding casting image in the casting image information is updated and replaced based on the corrected casting image to obtain updated and replaced casting image information.

[0033] Step S11: Perform image feature scanning on the casting image information to obtain a casting feature set corresponding to each casting node.

[0034] For an embodiment of the present application, the casting element equipment used in the casting process of ductile iron castings is collected, the contour of each casting element in the casting image information is calibrated and extracted according to the casting element equipment to obtain a key casting area corresponding to each casting image in the casting image information, the image feature points of the key casting area in the casting image are extracted to obtain a regional feature point set corresponding to the key casting area, and the regional feature point set is reorganized according to the casting nodes to obtain a casting feature set corresponding to each casting node.

[0035] Step S12: Input the casting features in each casting feature set into the anomaly recognition model in the order of casting time for training to obtain a primary recognition result.

[0036] For an embodiment of the present application, the anomaly recognition model is a neural network model. The training process of the anomaly recognition model includes: collecting abnormal casting images during the casting process of ductile iron castings and abnormal processing information when processing the abnormal casting images, performing three-dimensional simulation processing on the abnormal casting images to obtain three-dimensional casting images, then collecting the corresponding abnormal image features and abnormal feature positions in the three-dimensional casting images according to a preset observation angle, binding the abnormal image features, abnormal feature positions, and abnormal processing information to obtain an abnormal information group, creating an anomaly recognition model, and inputting the abnormal information group as a training sample into the anomaly recognition model for training to obtain a trained anomaly recognition model.

[0037] Step S13: Based on the primary recognition result, determine whether there is a casting anomaly of the ductile iron casting in the casting feature set. If so, an initial casting dynamic model is simulated and constructed based on the casting feature set, and the abnormal casting features and abnormal casting reasons are determined according to the primary recognition result.

[0038] For the embodiments of the present application, based on the set of casting features, the two-dimensional coordinates of the casting key points are determined. According to the casting model in the casting equipment library, the coordinate system of the casting model is determined. The two-dimensional coordinates of the casting key points are input into the deep learning model for perspective transformation to obtain the three-dimensional coordinates of the casting key points corresponding to the two-dimensional coordinates of the casting key points. The three-dimensional coordinates of the casting key points are mapped into the coordinate system of the casting model to obtain the initial casting dynamic model.

[0039] In the embodiments of the present application, if there is no casting abnormality of ductile iron castings in the set of casting features, the features in the set of casting features are reorganized according to different feature positions in the casting image information to obtain the position feature sets of different feature positions. Each position feature set is arranged in a matrix according to the casting time sequence to obtain the position feature matrix corresponding to each feature position. According to the position feature matrix, the casting features are deduced according to the time period to obtain the predicted feature matrices corresponding to different feature positions within a preset future time period. The casting features in each predicted feature matrix are input into the abnormality recognition model for training to obtain the secondary recognition result. It is judged whether there is a casting abnormality of ductile iron castings in the secondary recognition result. If so, the abnormal time and the abnormal inducing factors in the secondary recognition result are determined, and the abnormal time, the abnormal inducing factors and the feature positions are bound to obtain the casting estimated abnormal information.

[0040] Step S14: Determine the abnormal casting position corresponding to the abnormal casting feature in the initial casting dynamic model, and bind the abnormal casting cause to the initial casting dynamic model according to the abnormal casting position to obtain the monitored casting dynamic model.

[0041] Specifically, machine learning and artificial intelligence technologies are used to train and learn a large amount of casting data to automatically identify and predict abnormal features and their positions; at the same time, these technologies can also be used to intelligently analyze the abnormal causes to improve the accuracy and efficiency of abnormal recognition. Finally, the results of automatic identification and prediction are integrated with the initial model to obtain the monitored casting dynamic model.

[0042] Step S115: Control to display the monitored casting dynamic model.

[0043] For the embodiments of the present application, obtaining the casting image information provides a comprehensive and accurate data basis for subsequent anomaly recognition, enabling technicians to accurately track every detail in the casting process, thereby more effectively identifying potential problems. Scanning the image features of the casting image information to obtain a set of casting features. Converting complex image information into quantifiable casting features facilitates subsequent data processing and model training. At the same time, inputting the features into the anomaly recognition model in the order of casting time ensures that the model can learn the temporality of the casting process and improves the accuracy of anomaly recognition. Training with the anomaly recognition model and obtaining a primary recognition result can quickly and accurately determine whether there are anomalies in the set of casting features. Once an anomaly is detected, an initial casting dynamic model is immediately constructed, and the abnormal casting features and reasons are determined based on the primary recognition result. This process greatly shortens the time for anomaly recognition, improves the controllability and safety of the casting process, determines the abnormal casting position, binds the reasons for abnormal casting to the initial casting dynamic model, and obtains a monitored casting dynamic model. It not only achieves precise positioning of casting anomalies but also provides an intuitive monitoring tool for technicians, enabling them to clearly understand the abnormal conditions in the casting process, thereby taking targeted measures for improvement and optimization. Controlling the display of the monitored casting dynamic model enables technicians to grasp the status of the casting process in real time, promptly discover and handle potential problems. It improves the transparency and traceability of the casting process, and further improves the casting efficiency of ductile iron castings.

[0044] Further, after controlling the display of the monitored casting dynamic model, it further includes: collecting management personnel information, determining the target terminal device based on the management personnel information, determining the maintenance time range corresponding to the reason for abnormal casting according to the reason for abnormal casting and the preset monitoring standard, when it is detected that the monitored casting dynamic model is sent to the target terminal device, recording the arrival time of the management personnel at the abnormal casting position, and matching the arrival time with the maintenance time range to determine whether there is an abnormal maintenance timeliness. If there is an abnormal maintenance timeliness, the management personnel information is marked and the marked management personnel information is sent to the terminal device of the upper-level management personnel of the management personnel.

[0045] The following introduces a ductile iron casting simulation monitoring system provided by the embodiments of the present application. The ductile iron casting simulation monitoring system described below can be mutually referred to with the ductile iron casting simulation monitoring method described above. Please refer to Figure 2 , Figure 2 FIG. 10 is a schematic structural diagram of a ductile iron casting simulation monitoring system 20 provided by the embodiments of the present application, including: An information acquisition module 21, configured to acquire casting image information, where the casting image information is the image information corresponding to different casting links of the ductile iron casting at different casting time periods during the casting process; The feature scanning module 22 is used to perform image feature scanning on the casting image information to obtain a set of casting features corresponding to each casting node; The anomaly recognition module 23 is used to input the casting features in each set of casting features into the anomaly recognition model for training in the order of casting time respectively to obtain a primary recognition result; The model construction module 24 is used to determine whether there is a casting anomaly of ductile iron castings based on the primary recognition result. If so, an initial casting dynamic model is simulated and constructed based on the set of casting features, and the abnormal casting features and the reasons for abnormal casting are determined according to the primary recognition result; The data binding module 25 is used to determine the abnormal casting position corresponding to the abnormal casting features in the initial casting dynamic model, and bind the reasons for abnormal casting to the initial casting dynamic model according to the abnormal casting position to obtain a monitored casting dynamic model; The control display module 26 is used to control the display of the monitored casting dynamic model.

[0046] In a possible implementation manner in the embodiment of the present application, when the feature scanning module 22 performs image feature scanning on the casting image information to obtain a set of casting features corresponding to each casting node, it is specifically used for: Collect the casting element equipment used in the casting process of ductile iron castings; Calibrate and extract each casting element contour in the casting image information according to the casting element equipment to obtain a key casting area corresponding to each casting image in the casting image information; Extract the image feature points of the key casting area in the casting image to obtain a set of area feature points corresponding to the key casting area; Reorganize the set of area feature points according to the casting nodes to obtain a set of casting features corresponding to each casting node In another possible implementation manner in the embodiment of the present application, the system 20 further includes: an information collection module, a three-dimensional processing module, an information binding module, and a model training module, where The information collection module is used to collect abnormal casting images during the casting process of ductile iron castings and abnormal processing information when processing the abnormal casting images; The three-dimensional processing module is used to perform three-dimensional simulation processing on the abnormal casting images to obtain three-dimensional casting images; The information binding module is used to collect the corresponding abnormal image features and abnormal feature positions in the three-dimensional casting images according to a preset observation angle, and bind the abnormal image features, abnormal feature positions, and abnormal processing information to obtain an abnormal information group; A model training module, configured to create an anomaly recognition model, and use the anomaly information group as training samples to input into the anomaly recognition model for training, so as to obtain a trained anomaly recognition model.

[0047] In another possible implementation manner in the embodiments of the present application, the system 20 further includes: a stripe processing module, an image processing module, a calibration processing module, and an image replacement module, where The stripe processing module is configured to determine whether there is at least one casting image with abnormal pixel brightness in the casting image information. If so, perform stripe detection processing on at least one casting image to obtain a pixel brightness image; The image processing module is configured to process the pixel brightness image to obtain a target calibration coefficient corresponding to each pixel point; The calibration processing module is configured to perform calibration processing on at least one casting image according to the target calibration coefficient corresponding to each pixel point to obtain a calibrated casting image; The image replacement module is configured to update and replace the corresponding casting image in the casting image information based on the calibrated casting image to obtain updated and replaced casting image information.

[0048] In another possible implementation manner in the embodiments of the present application, the system 20 further includes: a feature recombination module, a matrix arrangement module, a feature deduction module, an anomaly training module, and an anomaly estimation module, where The feature recombination module is configured to, when there is no casting anomaly of ductile iron castings in the casting feature set, recombine the features in the casting feature set according to different feature positions in the casting image information to obtain a position feature set of different feature positions; The matrix arrangement module is configured to arrange each position feature set in a matrix according to the casting time sequence to obtain a position feature matrix corresponding to each feature position; The feature deduction module is configured to deduce the casting features according to the position feature matrix in time periods to obtain a predicted feature matrix corresponding to different feature positions within a preset future time period; The anomaly training module is configured to input the casting features in each predicted feature matrix into the anomaly recognition model for training to obtain a secondary recognition result; The anomaly estimation module is configured to determine whether there is a casting anomaly of ductile iron castings in the secondary recognition result. If so, determine the anomaly time and anomaly inducing factors in the secondary recognition result, and bind the anomaly time, anomaly inducing factors, and feature positions to obtain casting estimated anomaly information.

[0049] In another possible implementation manner in the embodiments of the present application, when the model construction module 24 constructs the initial casting dynamic model based on the casting feature set by simulation, it is specifically configured to: Determine the two-dimensional coordinates of the casting key points based on the casting feature set; Determine the coordinate system of the casting model according to the casting model in the casting equipment library; Input the two-dimensional coordinates of the casting key points into the deep learning model for perspective transformation to obtain the three-dimensional coordinates of the casting key points corresponding to the two-dimensional coordinates of the casting key points; Map the three-dimensional coordinates of the casting key points to the coordinate system of the casting model to obtain the initial casting dynamic model.

[0050] In another possible implementation manner in the embodiments of the present application, the system 20 further includes: a personnel collection module, a time determination module, a time matching module, and a personnel management module, where The personnel collection module is used to collect management personnel information and determine the target terminal device based on the management personnel information; The time determination module is used to determine the maintenance time range corresponding to the abnormal casting cause according to the abnormal casting cause and the preset monitoring standard; The time matching module is used to record the arrival time of the management personnel at the abnormal casting position when it is detected that the monitored casting dynamic model is sent to the target terminal device, and match the arrival time with the maintenance time range to determine whether there is an abnormality in the maintenance timeliness; The personnel management module is used to mark the management personnel information when there is an abnormality in the maintenance timeliness, and send the marked management personnel information to the terminal device of the upper-level management personnel of the management personnel.

[0051] The embodiments of the present application provide an electronic device, such as Figure 3 shown Figure 3 is a schematic structural diagram of an electronic device provided by the embodiments of the present application, Figure 3 The electronic device 300 shown includes: a processor 301 and a memory 303. Among them, the processor 301 and the memory 303 are connected, such as connected through a bus 302. Optionally, the electronic device 300 may further include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation to the embodiments of the present application.

[0052] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in connection with the disclosed content of the embodiments of the present application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0053] The bus 302 may include a path for transmitting information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0054] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory), or other types of dynamic storage devices that can store information and instructions. It may also be an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0055] The memory 303 is used to store the application program code for executing the solution of the embodiments of the present application and is controlled by the processor 301 for execution. The processor 301 is used to execute the application program code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0056] Among them, the electronic devices include but are not limited to: mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic devices shown are merely examples and should not impose any limitations on the functions and scope of use of the embodiments of the present application.

[0057] Next, a computer-readable storage medium provided by the embodiments of the present application will be introduced. The computer-readable storage medium described below can be correspondingly referred to the method described above.

[0058] The embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned simulation monitoring method for ductile iron castings are implemented.

[0059] Since the embodiments of the computer-readable storage medium part correspond to the embodiments of the method part, for the embodiments of the computer-readable storage medium part, please refer to the description of the embodiments of the method part.

[0060] It should be understood that although the steps in the flowchart of the accompanying drawings are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order restriction and can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0061] The above are only some embodiments of the present application. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. A simulation monitoring method for ductile iron castings, characterized in that: include: Acquire casting image information, wherein the casting image information is image information corresponding to different casting links and different casting time periods during the casting process of the ductile iron casting; Performing image feature scanning on the casting image information to obtain a casting feature set corresponding to each casting node; Inputting the casting features in each casting feature set into the abnormality recognition model in the order of casting time for training to obtain a primary recognition result; Determine whether the casting feature set has casting anomalies of ductile iron parts based on the first-level recognition result, and if so, construct an initial casting dynamic model based on the casting feature set through simulation, and determine the abnormal casting features and the causes of the abnormal casting according to the first-level recognition result; Determine an abnormal casting position corresponding to the abnormal casting feature in the initial casting dynamic model, and bind the abnormal casting cause to the initial casting dynamic model according to the abnormal casting position to obtain a monitoring casting dynamic model; The control displays the monitoring casting dynamic model.

2. A simulation monitoring method for ductile iron castings according to claim 1, characterized in that: The image feature scanning of the casting image information to obtain a casting feature set corresponding to each casting node includes: Collecting casting element equipment used in the casting process of the ductile iron casting; Calibrate and extract each casting element contour in the casting image information according to the casting element equipment to obtain a key casting area corresponding to each casting image in the casting image information; Extracting image feature points of the key casting area in the casting image to obtain a set of regional feature points corresponding to the key casting area; The regional feature point set is reorganized according to the casting nodes to obtain a casting feature set corresponding to each casting node. The simulation monitoring method for ductile iron castings according to claim 1 is characterized in that the casting features in each casting feature set are respectively input into the abnormality recognition model in the order of casting time for training to obtain a primary recognition result, and the method also includes: Collecting abnormal casting images of the ductile iron casting during the casting process and abnormal processing information when processing the abnormal casting images; Performing three-dimensional simulation processing on the abnormal casting image to obtain a three-dimensional casting image; Collecting the abnormal image features and abnormal feature positions corresponding to the three-dimensional casting image according to a preset observation angle, and binding the abnormal image features, the abnormal feature positions and the abnormal processing information to obtain an abnormal information group; An abnormality recognition model is created, and the abnormal information group is input as a training sample into the abnormality recognition model for training to obtain the trained abnormality recognition model.

3. A simulation monitoring method for ductile iron castings according to claim 1, characterized in that: The image feature scanning of the casting image information to obtain a casting feature set corresponding to each casting node also includes: Determine whether there is at least one casting image in the casting image information with abnormal pixel brightness and darkness, and if so, perform stripe detection processing on the at least one casting image to obtain a pixel brightness and darkness image; Processing the pixel light and dark image to obtain a target correction coefficient corresponding to each pixel point; According to the target correction coefficient corresponding to each pixel point, the at least one casting image is corrected to obtain a corrected casting image; Based on the corrected casting image, the corresponding casting image in the casting image information is updated and replaced to obtain the updated and replaced casting image information.

4. A simulation monitoring method for ductile iron castings according to claim 1, characterized in that: The determining whether the casting feature set has a casting anomaly of the ductile iron casting based on the primary recognition result further includes: If the casting feature set does not contain the casting anomaly of the ductile iron casting, the features in the casting feature set are reorganized according to different feature positions in the casting image information to obtain position feature sets at different feature positions; Arrange each of the position feature sets in a matrix according to the casting time order to obtain a position feature matrix corresponding to each feature position; Deducing the casting characteristics according to the position feature matrix according to the time period, to obtain a prediction feature matrix corresponding to different feature positions in a future preset time period; Inputting each casting feature in the prediction feature matrix into the abnormality recognition model for training to obtain a secondary recognition result; Determine whether there is a casting abnormality of the ductile iron part in the secondary recognition result. If so, determine the abnormal time and abnormality inducing factors in the secondary recognition result, and bind the abnormal time, the abnormality inducing factors and the characteristic position to obtain casting estimated abnormality information.

5. A simulation monitoring method for ductile iron castings according to claim 1, characterized in that: The method of constructing an initial casting dynamic model based on the casting feature set simulation includes: Determining two-dimensional coordinates of key casting points based on the casting feature set; According to the casting model in the casting equipment library, the coordinate system of the casting model is determined; Inputting the two-dimensional coordinates of the key casting points into the deep learning model for perspective transformation to obtain the three-dimensional coordinates of the key casting points corresponding to the two-dimensional coordinates of the key casting points; The three-dimensional coordinates of the key casting points are mapped into the coordinate system of the casting model to obtain an initial casting dynamic model.

6. A simulation monitoring method for ductile iron castings according to claim 1, characterized in that: The control displays the monitoring casting dynamic model, and then further comprises: Collecting management personnel information, and determining target terminal devices based on the management personnel information; According to the abnormal casting cause and the preset monitoring standard, determining the maintenance time range corresponding to the abnormal casting cause; When it is detected that the monitoring casting dynamic model is sent to the target terminal device, the arrival time of the manager at the abnormal casting position is recorded, and the arrival time is matched with the maintenance time range to determine whether there is an abnormality in maintenance timeliness; If the maintenance timeliness is abnormal, the manager information is marked, and the marked manager information is sent to the terminal device of the manager's upper-level manager.

7. A simulation monitoring system for ductile iron castings, characterized in that: include: An information acquisition module is used to acquire casting image information, wherein the casting image information is image information corresponding to different casting links and different casting time periods during the casting process of the ductile iron casting; A feature scanning module, used for performing image feature scanning on the casting image information to obtain a casting feature set corresponding to each casting node; An anomaly recognition module, used for inputting the casting features in each casting feature set into the anomaly recognition model in the order of casting time for training, and obtaining a primary recognition result; A model building module, used to determine whether the casting feature set has casting anomalies of ductile iron parts based on the first-level recognition result, and if so, to simulate and build an initial casting dynamic model based on the casting feature set, and determine abnormal casting features and abnormal casting causes according to the first-level recognition result; A data binding module, used for determining an abnormal casting position corresponding to the abnormal casting feature in the initial casting dynamic model, and binding the abnormal casting cause to the initial casting dynamic model according to the abnormal casting position to obtain a monitoring casting dynamic model; A control display module is used to control and display the monitoring casting dynamic model.

8. An electronic device, characterized in that: The electronic device includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute a simulation monitoring method for ductile iron castings according to any one of claims 1-7.

9. A computer-readable storage medium, characterized in that: include: A computer program is stored which can be loaded by a processor and execute a simulation monitoring method for ductile iron castings as described in any one of claims 1 to 7.

Images