Method and system for optimizing 42CrMo steel heat treatment process based on digital twinning

Abstract

The invention discloses an optimization method and system for a 42CrMo steel heat treatment process based on digital twinning, and the method comprises the steps: obtaining historical data of 42CrMo steel in each stage of the heat treatment process, and constructing a corresponding digital twinning model based on each cooling rate, deploying all the digital twin models at specified positions in a preset virtual space; acquiring a real-time data packet of the 42CrMo steel in the heat treatment process, and dividing the real-time data packet into a plurality of sub-data packets according to different cooling rates; determining a target time sequence identifier corresponding to each sub-data packet according to the cooling rate, and transmitting the target time sequence identifier to a corresponding target digital twin model; the target digital twin model runs the sub-data packets and generates corresponding optimization information; and detecting the current visual field range of the user, and guiding the user to adjust the visual field until the target digital twinborn model can be seen. By means of the digital twinborn model, accurate control over the cooling rate can be achieved, and therefore the abrasion resistance and hardness of the 42CrMo steel are optimized.

Description

Technical Field

[0001] The present invention relates to the field of digital twin technology, and in particular to a method and system for optimizing a 42CrMo steel heat treatment process based on digital twin. Background Art

[0002] 42CrMo steel is a high-strength alloy steel widely used in machinery manufacturing, such as automotive, aerospace, and heavy machinery. Its wear resistance and hardness are key performance indicators, directly affecting the service life and reliability of parts. The heat treatment process of 42CrMo steel, especially the control of cooling rate, has a decisive influence on the ultimate performance of 42CrMo steel.

[0003] Traditional heat treatment process optimization methods have numerous limitations. First, they rely on experience or trial-and-error methods, requiring extensive physical testing. Each test consumes significant amounts of raw materials and energy, leading to high costs. Second, trial-and-error methods require multiple iterations and waiting for results after each test, making the entire process time-consuming and inefficient. Furthermore, because the material properties of 42CrMo steel are influenced by multiple factors, traditional methods struggle to fully account for all variables and achieve the optimal performance balance. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, the present invention provides a method and system for optimizing the heat treatment process of 42CrMo steel based on digital twin. By establishing a digital twin model of the heat treatment process, the cooling rate is optimized and controlled, thereby improving the performance of 42CrMo steel.

[0005] The technical solution adopted by the present invention to solve its technical problem is:

[0006] In a first aspect, the present invention provides a method for optimizing a 42CrMo steel heat treatment process based on digital twinning, comprising the following steps:

[0007] S1. Obtain historical data of 42CrMo steel at various stages of a heat treatment process, wherein the historical data includes state changes of the 42CrMo steel at different cooling rates;

[0008] S2. Construct a corresponding digital twin model based on each cooling rate, and deploy all the digital twin models at a specified location in a preset virtual space, where each digital twin model has a unique location identifier and timing identifier in the preset virtual space;

[0009] S3. Acquire a real-time data packet of 42CrMo steel during heat treatment, and divide the real-time data packet into a plurality of sub-data packets according to different cooling rates;

[0010] S4. Determine a target timing identifier corresponding to each sub-data packet according to the cooling rate, and transmit the sub-data packet to the corresponding target digital twin model according to the target timing identifier; the target digital twin model runs the sub-data packet and generates corresponding optimization information;

[0011] S5. Detect the user's current field of view and determine whether the target digital twin model is within the user's field of view. If not, generate prompt information containing the location identifier of the target digital twin model to guide the user to adjust the field of view so that the target digital twin model can be seen.

[0012] In one embodiment, step S2 includes:

[0013] S21. Deploy M virtual display platforms in a preset virtual space according to the number M of cooling rates;

[0014] S22. Assign a timing identifier to each of the virtual display platforms according to the timing relationship of the cooling rates, and determine one of the M virtual display platforms as a reference virtual display platform according to the timing identifier;

[0015] S23. Rendering an offline scene of heat treatment of 42CrMo steel in the reference virtual display platform to obtain a corresponding digital twin model, and projecting the digital twin model in the reference virtual display platform;

[0016] S24: Apply the offline scene rendered by the reference virtual display platform to the remaining virtual display platforms to obtain corresponding M-1 digital twin models, and project the M-1 digital twin models into the corresponding virtual display platforms.

[0017] In one embodiment, the process of setting the location identifier includes:

[0018] Determine the center line Lc of the digital twin model and the direction vector of the preset virtual space baseline Lb; calculate the angle θ between the center line Lc and the baseline Lb;

[0019] Determine the coverage angle range of the digital twin model according to the angle θ between the center line Lc and the baseline Lb and the steering angle φ covered by the digital twin model;

[0020] The relative position of the digital twin model in the preset virtual space is determined according to the coverage angle range of the digital twin model and a corresponding position identifier is set.

[0021] In one embodiment, the coverage angle range of the digital twin model is θ start ~θ end ,

[0022] θstart Identify the starting angle,

[0023] θ end Indicates the end angle,

[0024]

[0025] In one embodiment, in step S5, detecting the user's current field of view includes:

[0026] Obtaining the user's current turning angle α, and determining the user's current line of sight centerline based on the turning angle α;

[0027] Obtain the user's field of view angle β, and generate the user's current field of view range based on the field of view angle β and the line of sight center line

[0028] In one embodiment, in step S4, the target digital twin model runs the sub-data package and generates corresponding optimization information, including:

[0029] An optimization information generation module is provided inside the digital twin model. After receiving the sub-data package, the optimization information generation module inputs the sub-data package into the trained machine learning model. The machine learning model outputs the predicted performance parameters of 42CrMo steel. The optimization information generation module calculates the comprehensive performance score of 42CrMo steel, which is w1×performance parameter score 1+w2×performance parameter score 2+w n × performance parameter n score, w1, w2, w n represents the weight coefficient;

[0030] The optimization information generated by the optimization information generation module includes:

[0031] The optimal cooling rate that maximizes the comprehensive performance score, the predicted values ​​of the performance parameters of 42CrMo steel at the optimal cooling rate, and the adjustment strategy given according to the difference between the current cooling rate and the optimal cooling rate.

[0032] In one embodiment, each of the sub-data packets corresponds to state data of 42CrMo steel at a cooling rate.

[0033] In a second aspect, a digital twin-based optimization system for a 42CrMo steel heat treatment process is provided, which utilizes the digital twin-based optimization method for a 42CrMo steel heat treatment process. The optimization system includes:

[0034] A historical data acquisition module is used to obtain historical data of 42CrMo steel at various stages of the heat treatment process, wherein the historical data includes the state changes of 42CrMo steel at different cooling rates;

[0035] A digital twin model construction module is used to construct a corresponding digital twin model based on each cooling rate, and deploy all digital twin models at a specified location in a preset virtual space, each digital twin model having a unique location identifier and timing identifier in the preset virtual space;

[0036] A real-time data acquisition module acquires real-time data packets of 42CrMo steel during heat treatment and divides the real-time data packets into several sub-data packets according to different cooling rates;

[0037] An optimization module, configured to determine a target timing identifier corresponding to each sub-data packet according to a cooling rate, and transmit the sub-data packet to a corresponding target digital twin model according to the target timing identifier; the target digital twin model runs the sub-data packet and generates corresponding optimization information;

[0038] The visual guidance module is used to detect the user's current field of view and determine whether the target digital twin model is within the user's field of view. If not, it generates a prompt message containing the location identifier of the target digital twin model to guide the user to adjust the field of view so that the target digital twin model can be seen.

[0039] The beneficial effects of the present invention are:

[0040] The present invention utilizes digital twin technology to create a virtual model of the physical entity of 42CrMo steel during the heat treatment process and update it in real time. The digital twin model can achieve accurate simulation and optimization of 42CrMo steel during the heat treatment process. The present invention can effectively improve the limitations of traditional methods and achieve efficient and accurate optimization of the cooling rate of 42CrMo steel during the heat treatment process, which can not only improve efficiency and reduce costs, but also improve accuracy and enhance safety. The digital twin model can quickly simulate material properties under different cooling rates, reduce the number of physical tests, speed up the optimization process, and comprehensively consider multiple variables at the same time, accurately predict material properties, and achieve the best performance balance. Optimization in a virtual environment avoids the potential threat to operators in dangerous environments such as high temperature and high pressure, significantly improves the wear resistance and hardness of 42CrMo steel, and optimizes production efficiency and cost-effectiveness. In addition, the present invention can also provide visual guidance to users so that key simulation scenes after optimization and adjustment can be quickly seen by users. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The present invention will be further described below with reference to the accompanying drawings and examples.

[0042] Figure 1 It is a flow chart of the optimization method of the 42CrMo steel heat treatment process based on digital twin of the present invention.

[0043] Figure 2 It is a schematic diagram of the location identifier calculation process of the present invention.

[0044] Figure 3 Schematic diagram of the user visual field calculation process of the present invention. DETAILED DESCRIPTION

[0045] The present invention will now be described in further detail with reference to the accompanying drawings, which are simplified schematic diagrams that illustrate the basic structure of the present invention in a schematic manner.

[0046] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, features defined as "first" or "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0047] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0048] like Figure 1 As shown, the optimization method of the 42CrMo steel heat treatment process based on digital twin of this embodiment includes the following steps:

[0049] S1. Obtain historical data of 42CrMo steel at various stages of a heat treatment process, where the historical data includes state changes of the 42CrMo steel at different cooling rates.

[0050] It should be noted that the heat treatment process for 42CrMo steel includes stages such as austenitization, quenching, and tempering. The historical data collected during these stages can characterize the performance and structural changes of 42CrMo steel during the heat treatment process, such as hardness, wear resistance, and microstructure. This historical data covers the state changes of 42CrMo steel at different cooling rates. By analyzing this historical data, it is possible to truly reflect the performance changes of 42CrMo steel during the actual heat treatment process.

[0051] S2. Build a corresponding digital twin model based on each cooling rate, and deploy all digital twin models at a specified location in a preset virtual space. Each digital twin model has a unique location identifier and timing identifier in the preset virtual space.

[0052] It should be noted that each cooling rate corresponds to a digital twin model, which can simulate the performance changes of 42CrMo steel under that cooling rate. Within the preset virtual space, all digital twin models have a unique location identifier and a timing identifier. The location identifier is used to determine the location of the digital twin model. The timing identifier is assigned to the corresponding digital twin model based on the temporal relationship of the cooling rate.

[0053] For example, the specific process of deploying a digital twin model in a preset virtual space is as follows:

[0054] S21. Deploy M virtual display platforms in a preset virtual space according to the number M of cooling rates.

[0055] In other words, the number of virtual display platforms matches the number of digital twin models. A virtual display platform is a platform created within a virtual environment for displaying images, videos, 3D models, or other media content. Virtual display platforms can be resized as needed, unconstrained by physical space. Users can interact with the virtual display platform by positioning the canvas within a pre-defined virtual space and mapping the digital twin model onto it.

[0056] S22 . Allocate a timing identifier to each virtual display platform according to the timing relationship of the cooling rates, and determine one of the M virtual display platforms as a reference virtual display platform according to the timing identifier.

[0057] According to the timing relationship of the cooling rate, a timing identifier is assigned to each virtual display platform, and one of the M virtual display platforms is determined as the reference virtual display platform based on the timing identifier. The timing identifier can be a number, a letter, or a symbol that can reflect the order. For example, assuming that there are three cooling rates in the heat treatment process, namely rapid cooling, medium cooling, and slow cooling, the timing identifiers can be set to 1, 2, and 3 respectively, and three virtual display platforms are established respectively, and timing identifiers are assigned. When selecting a reference virtual display platform, the virtual display platform with the earliest timing relationship can be set as the reference virtual display platform, such as setting the virtual display platform with a timing identifier of 1 as the reference virtual display platform.

[0058] S23. Render an offline scene of heat treatment of 42CrMo steel in a reference virtual display platform to obtain a corresponding digital twin model, and project the digital twin model in the reference virtual display platform.

[0059] For example, a 3D rendering engine can be used to render an offline scene of the 42CrMo steel heat treatment process on a reference virtual display platform. Actual environmental data for the 42CrMo steel heat treatment process (such as site layout, equipment location, and environmental conditions) can be collected in advance to enhance the realism of the simulation. The corresponding digital twin model is then placed on the reference virtual display platform and matched to the rendered offline scene. The position, scale, and orientation of the digital twin model are then adjusted to ensure that the digital twin model is well displayed on the reference virtual display platform.

[0060] S24. Apply the offline scene rendered by the reference virtual display platform to the remaining virtual display platforms to obtain corresponding M-1 digital twin models, and project the M-1 digital twin models into the corresponding virtual display platforms.

[0061] For other virtual display platforms, the offline scene of the reference virtual display platform can be applied to them, saving rendering time. For example, the offline scene can be reused using a spatial transformation matrix. The spatial transformation matrix between the other virtual display platform and the reference virtual display platform is determined, and the offline scene rendered in the reference virtual display platform is transformed to the other virtual display platform based on the spatial transformation matrix. Specifically, first, a translation vector representing the translation from the reference virtual display platform to the other virtual display platform is determined. Then, a rotation matrix is ​​determined. The rotation matrix can be the product of three basic rotation matrices for rotations about three coordinate axes. The translation vector and the rotation matrix are combined to form a spatial transformation matrix. Furthermore, the coordinates of each point on the reference virtual display platform are obtained, and each point is multiplied by the spatial transformation matrix to obtain the transformed point. The transformed point is then rendered on the other virtual display platform. In this way, the offline scene in the reference virtual display platform can be accurately transformed and rendered on the other virtual display platform, achieving spatial transformation of the scene. In other words, the rendering results of the reference virtual display platform can be directly copied to the other virtual display platform using the spatial transformation matrix, reducing the number of offline scene renderings. Then, the remaining digital twin models are projected in the corresponding virtual display platform, and a location identifier is assigned to each digital twin model.

[0062] In addition, if Figure 2 As shown in the figure, the process of setting the location identifier includes: determining the direction vector of the center line Lc of the digital twin model and the preset virtual space baseline Lb; calculating the angle θ between the center line Lc and the baseline Lb; determining the coverage angle range of the digital twin model based on the angle θ between the center line Lc and the baseline Lb and the steering angle φ covered by the digital twin model; determining the relative position of the digital twin model in the preset virtual space based on the coverage angle range of the digital twin model and setting the corresponding location identifier. The coverage angle range of the digital twin model is θ start ~θ end ,θ start Identify the starting angle, θ end Indicates the end angle,

[0063] In the virtual space, the corresponding digital twin model can be quickly found using the location identifier. The location identifier can be a value between 0 and 1, indicating the relative position of the digital twin model in the virtual space. The digital twin model will occupy a certain space in the virtual space, which can be represented by the coverage angle range. The location identifier can be calculated according to the formula. For example, if the angle between the center line Lc and the baseline Lb is θ = 60° and the steering angle φ = 60°, then the starting angle θ is calculated. start =30°, ending angle θ end=90°, position identifier =0.333.

[0064] S3. Acquire a real-time data packet of 42CrMo steel during heat treatment, and divide the real-time data packet into several sub-data packets according to different cooling rates.

[0065] It should be noted that the real-time data package contains the process conditions, cooling rates, and performance parameters (such as hardness, wear resistance, and microstructure) of 42CrMo steel at different heat treatment stages. A sub-data package is created for each cooling rate, and the corresponding relationship between the other data in the real-time data package and the cooling rate is decomposed into the corresponding sub-data package.

[0066] S4. Determine the target timing identifier corresponding to each sub-data packet according to the cooling rate, and transmit the sub-data packet to the corresponding target digital twin model according to the target timing identifier; the target digital twin model runs the sub-data packet and generates corresponding optimization information.

[0067] Each sub-data package corresponds to the state data of 42CrMo steel at a cooling rate. Since each sub-data package corresponds to a cooling rate, a timing identifier can be assigned according to the temporal relationship of the cooling rate, and this timing identifier can be matched with the timing identifier of the digital twin model to find the target digital twin model. Then, this sub-data package is transmitted to the target digital twin model. The target digital twin model runs the sub-data package to simulate the processing process of 42CrMo steel at this cooling rate. For example, an optimization information generation module is provided inside the digital twin model. After receiving the sub-data package, the optimization information generation module inputs the sub-data package into a trained machine learning model (for example, a regression model trained based on historical data, a neural network model, etc.). The machine learning model outputs the predicted performance parameters of 42CrMo steel (for example, hardness and wear resistance). The optimization information generation module calculates the comprehensive performance score of 42CrMo steel. The comprehensive performance score = w1×performance parameter score 1 + w2×performance parameter score 2 + w n × performance parameter n score, w1, w2, w n The optimization information generated by the optimization information generation module includes the optimal cooling rate that maximizes the comprehensive performance score, the predicted values ​​of the 42CrMo steel performance parameters at the optimal cooling rate, and the adjustment strategy based on the difference between the current cooling rate and the optimal cooling rate.

[0068] For example, after receiving the sub-data package, the optimization information generation module first pre-processes the data in the sub-data package (including temperature, hardness, wear resistance and other data at the current cooling rate) (including denoising, deleting outliers and other operations). Then, features such as cooling rate, temperature change rate, hardness change rate, and wear resistance change rate are extracted from the sub-data package. These features are input into the trained machine learning model for prediction, and the machine learning model outputs the hardness and wear resistance at the current cooling rate. Assuming that the weight of hardness w1 = 0.6, the weight of wear resistance w2 = 0.4, and the comprehensive performance score = 0.6*hardness score + 0.4*wear resistance score, the hardness score and wear resistance score can be scored according to the production standard. Assuming that the comprehensive performance scores obtained under three different cooling rates (fast cooling, medium cooling, and slow cooling) are 0.85, 0.9, and 0.8 respectively, the comprehensive performance score under medium cooling is the highest, and medium cooling is the optimal cooling rate. The generated optimization information includes the optimal cooling rate, performance parameter prediction values ​​(hardness prediction value and wear resistance prediction value), and adjustment strategy (maintaining the current cooling rate or adjusting the current cooling rate according to the optimal cooling rate).

[0069] S5. Detect the user's current field of view and determine whether the target digital twin model is within the user's field of view. If not, generate a prompt message containing the location identifier of the target digital twin model to guide the user to adjust the field of view so that the target digital twin model can be seen.

[0070] When a user observes a digital twin model displayed in a virtual space, the user's line of sight may not fall on the target digital twin model, or the user's field of view may not cover the target digital twin model. In this case, the user's line of sight can be guided to the target digital twin model through visual guidance. Figure 3 As shown, the user's current field of view must first be detected, specifically including: obtaining the user's current turning angle α, and determining the user's current line of sight centerline based on the turning angle α; obtaining the user's field of view angle β, and generating the user's current field of view based on the field of view angle β and the line of sight centerline In a virtual environment, a head tracking device can be used to obtain the user's current turning angle α. The center line of sight is the imaginary line of the user's current turning direction. For example, when a user uses VR glasses, the turning angle of the head is the current turning angle α. By generally extending the field of view angle β to the left and right of the turning angle α, the user's current field of view can be obtained.

[0071] Assuming the turning angle is α = 0° and the field of view angle is β = 90°, the user's current field of view is (-45°, 45°). Assuming the digital twin model covers a steering angle of φ = 30°, the digital twin model's coverage angle range is (30°, 90°), which only overlaps with the user's field of view by 15°. In this case, the user can be visually guided by generating prompt information within the user's field of view, guiding the user to adjust their field of view so that they can see the entire target digital twin model. For example, the prompt information can be text carrying the target digital twin model's location identifier, such as "Please turn right, 0.333". If the target digital twin model is outside the right side of the user's field of view, a flashing mark can be displayed on the right side of the user's field of view to guide the user to turn right.

[0072] The present invention also provides an optimization system for the heat treatment process of 42CrMo steel based on digital twin, and adopts an optimization method for the heat treatment process of 42CrMo steel based on digital twin. The optimization system includes: a historical data acquisition module for acquiring historical data of 42CrMo steel at various stages of the heat treatment process, wherein the historical data includes the state changes of 42CrMo steel at different cooling rates; a digital twin model construction module for constructing a corresponding digital twin model based on each cooling rate, and deploying all digital twin models at a specified location in a preset virtual space. Each digital twin model has a unique location identifier and timing identifier within the preset virtual space; a real-time data acquisition module for acquiring real-time data packets of 42CrMo steel during the heat treatment process and dividing the real-time data packets into several sub-data packets according to different cooling rates; an optimization module for determining the target timing identifier corresponding to each sub-data packet based on the cooling rate, and transmitting the sub-data packet to the corresponding target digital twin model based on the target timing identifier; the target digital twin model runs the sub-data packet and generates corresponding optimization information; and a visual guidance module for detecting the user's current field of view and determining whether the target digital twin model is within the user's field of view. If not, a prompt message containing the location identifier of the target digital twin model is generated to guide the user to adjust the field of view so that the target digital twin model can be seen.

[0073] Please refer to the description of the method section for the correspondence between this system and the method, which will not be repeated here.

[0074] In summary, the optimization method and system of the 42CrMo steel heat treatment process based on digital twin of the present invention can realize virtual optimization and status monitoring of the heat treatment process of 42CrMo steel. By collecting the material property data of 42CrMo steel, its heat treatment mode is determined, a digital twin panoramic model is established for each cooling rate, and these models are deployed at a specified location in the virtual space. By collecting the real-time data of 42CrMo steel, the real-time data is decomposed into several sub-data packets, which are respectively input into the corresponding digital twin panoramic models to generate corresponding optimization information, which can be used for heat treatment process parameter adjustment and performance improvement. At the same time, by detecting the field of view of the target user and providing visual guidance, the user's visual navigation efficiency in the virtual environment is improved, ensuring that the user can accurately find the target digital twin panoramic model.

[0075] With the above-described preferred embodiments of the present invention as a guide, and with reference to the above description, relevant personnel are fully capable of making various changes and modifications without departing from the technical spirit of this invention. The technical scope of this invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A method for optimizing the heat treatment process of 42CrMo steel based on digital twin, characterized in that: The following steps are involved: S1. Obtain historical data of 42CrMo steel at various stages of a heat treatment process, wherein the historical data includes state changes of the 42CrMo steel at different cooling rates; S2. Construct a corresponding digital twin model based on each cooling rate, and deploy all the digital twin models at a specified location in a preset virtual space, where each digital twin model has a unique location identifier and timing identifier in the preset virtual space; S3. Acquire a real-time data packet of 42CrMo steel during heat treatment, and divide the real-time data packet into a plurality of sub-data packets according to different cooling rates; S4. Determine a target timing identifier corresponding to each sub-data packet according to the cooling rate, and transmit the sub-data packet to the corresponding target digital twin model according to the target timing identifier; the target digital twin model runs the sub-data packet and generates corresponding optimization information; S5. Detect the user's current field of view and determine whether the target digital twin model is within the user's field of view. If not, generate prompt information containing the location identifier of the target digital twin model to guide the user to adjust the field of view so that the target digital twin model can be seen.

2. The method for optimizing the heat treatment process of 42CrMo steel based on digital twin according to claim 1, characterized in that: Step S2 includes: S21. Deploy M virtual display platforms in a preset virtual space according to the number M of cooling rates; S22. Assign a timing identifier to each of the virtual display platforms according to the timing relationship of the cooling rates, and determine one of the M virtual display platforms as a reference virtual display platform according to the timing identifier; S23. Rendering an offline scene of heat treatment of 42CrMo steel in the reference virtual display platform to obtain a corresponding digital twin model, and projecting the digital twin model in the reference virtual display platform; S24: Apply the offline scene rendered by the reference virtual display platform to the remaining virtual display platforms to obtain corresponding M-1 digital twin models, and project the M-1 digital twin models into the corresponding virtual display platforms.

3. The method for optimizing the heat treatment process of 42CrMo steel based on digital twin according to claim 1, characterized in that: The process of setting the location identifier includes: Determine the center line Lc of the digital twin model and the direction vector of the preset virtual space baseline Lb; calculate the angle θ between the center line Lc and the baseline Lb; Determine the coverage angle range of the digital twin model according to the angle θ between the center line Lc and the baseline Lb and the steering angle φ covered by the digital twin model; The relative position of the digital twin model in the preset virtual space is determined according to the coverage angle range of the digital twin model and a corresponding position identifier is set.

4. The method for optimizing the heat treatment process of 42CrMo steel based on digital twin according to claim 3, characterized in that: The coverage angle range of the digital twin model is θ start ~θ end , θ start Identify the starting angle, θ end Indicates the end angle, 5. The method for optimizing the heat treatment process of 42CrMo steel based on digital twin according to claim 1, characterized in that: In step S5, the user's current field of view is detected, including: Obtaining the user's current turning angle α, and determining the user's current line of sight centerline based on the turning angle α; Obtain the user's field of view angle β, and generate the user's current field of view range based on the field of view angle β and the line of sight center line 6. The method for optimizing the heat treatment process of 42CrMo steel based on digital twin according to claim 1, characterized in that: In step S4, the target digital twin model runs the sub-data package and generates corresponding optimization information, including: An optimization information generation module is provided inside the digital twin model. After receiving the sub-data package, the optimization information generation module inputs the sub-data package into the trained machine learning model. The machine learning model outputs the predicted performance parameters of 42CrMo steel. The optimization information generation module calculates the comprehensive performance score of 42CrMo steel, which is w1×performance parameter score 1+w2×performance parameter score 2+w n × performance parameter n score, w1, w2, w n represents the weight coefficient; The optimization information generated by the optimization information generation module includes: The optimal cooling rate that maximizes the comprehensive performance score, the predicted values ​​of the performance parameters of 42CrMo steel at the optimal cooling rate, and the adjustment strategy given according to the difference between the current cooling rate and the optimal cooling rate.

7. The method for optimizing the heat treatment process of 42CrMo steel based on digital twin according to claim 1, characterized in that: Each of the sub-data packets corresponds to state data of the 42CrMo steel at a cooling rate.

8. An optimization system for 42CrMo steel heat treatment process based on digital twin, characterized in that: The optimization method for the 42CrMo steel heat treatment process based on digital twinning according to any one of claims 1 to 7 is adopted, and the optimization system includes: A historical data acquisition module is used to obtain historical data of 42CrMo steel at various stages of the heat treatment process, wherein the historical data includes the state changes of 42CrMo steel at different cooling rates; A digital twin model construction module is used to construct a corresponding digital twin model based on each cooling rate, and deploy all digital twin models at a specified location in a preset virtual space, each digital twin model having a unique location identifier and timing identifier in the preset virtual space; A real-time data acquisition module acquires real-time data packets of 42CrMo steel during heat treatment and divides the real-time data packets into several sub-data packets according to different cooling rates; An optimization module, configured to determine a target timing identifier corresponding to each sub-data packet according to a cooling rate, and transmit the sub-data packet to a corresponding target digital twin model according to the target timing identifier; the target digital twin model runs the sub-data packet and generates corresponding optimization information; The visual guidance module is used to detect the user's current field of view and determine whether the target digital twin model is within the user's field of view. If not, it generates a prompt message containing the location identifier of the target digital twin model to guide the user to adjust the field of view so that the target digital twin model can be seen.

Images