Intelligent control method for ascending rate of ejector rod of vacuum isothermal forging blank heating furnace

Abstract

The invention provides an intelligent control method and device for the rising rate of an ejector rod of a vacuum isothermal forging blank heating furnace, and relates to the field of high-end intelligent device manufacturing. The method comprises the following steps: acquiring attribute information of a to-be-heated blank; based on the attribute information and a preset ejector rod rising rate intelligent control model, the target rising rate corresponding to the to-be-heated blank is determined; wherein the ejector rod ascending rate intelligent control model is used for predicting the ascending rate when the ejector rod ascends and descends to drive the blank according to the attribute information of the blank; and the ejector rod is controlled to drive the to-be-heated blank to enter the blank heating chamber according to the target rising speed. The method is suitable for the blank heating process of vacuum isothermal forging and is used for improving the intelligent level of a heating furnace.

Description

Technical Field

[0001] The present application relates to the field of high-end intelligent device manufacturing, and in particular to a method and device for intelligently controlling the rise rate of a mandrel of a vacuum isothermal forging billet heating furnace. Background Art

[0002] Vacuum forging is a metal forging process performed in a vacuum environment. Since there is almost no air or other impurities in a vacuum environment, the metal is prevented from reacting with gases such as oxygen and nitrogen during heating and forging, reducing the generation of defects such as oxidation and decarburization. It is also beneficial to remove gas impurities in the metal and improve the quality of forgings.

[0003] In the vacuum forging solution provided by the related art, the blank needs to be taken out of the heating furnace after being heated in the heating furnace, and then reloaded into the vacuum forging chamber for forging.

[0004] After being taken out of the heating furnace, the temperature of the blank drops rapidly, and coarse grains are easily formed in the surface area of ​​the blank, which makes it easy for the blank to fail to achieve superplastic forming. Summary of the invention

[0005] The present application provides a method and device for intelligently controlling the rising rate of the push rod of a vacuum isothermal forging billet heating furnace. A method for intelligently controlling the rising rate of the push rod of a vacuum isothermal forging billet heating furnace can be provided. The vacuum isothermal forging billet heating furnace can heat the billet in a vacuum environment, is convenient for docking with a vacuum forging chamber without breaking the vacuum, and improves the intelligence level of the vacuum isothermal forging billet heating furnace.

[0006] In the first aspect, the present application provides a method for intelligently controlling the rising rate of a push rod of a vacuum isothermal forging billet heating furnace, and the method is applied to an intelligent control device of a vacuum isothermal forging billet heating furnace; the vacuum isothermal forging billet heating furnace also includes a billet placing chamber and a billet heating chamber arranged above the billet placing chamber; the billet heating chamber is connected to the billet placing chamber through a lower end opening; a tray for placing billets is arranged in the billet placing chamber, and a liftable push rod is installed at the bottom of the tray; the push rod is used to lift and drive the billet placed in the tray to enter or leave the billet heating chamber through the lower end opening of the billet heating chamber; the billet heating chamber is used to heat the billet in a vacuum environment; the method includes: obtaining attribute information of the billet to be heated; determining a target rising rate corresponding to the billet to be heated based on the attribute information and a preset push rod rising rate intelligent control model; wherein the push rod rising rate intelligent control model is used to predict the rising rate of the push rod when lifting and driving the billet according to the attribute information of the billet; and controlling the push rod to drive the billet to be heated into the billet heating chamber according to the target rising rate.

[0007] In the method for intelligently controlling the rising rate of the push rod of the vacuum isothermal forging billet heating furnace provided in the present application, the vacuum isothermal forging billet heating furnace includes a billet placement chamber and a billet heating chamber arranged above the billet placement chamber, and the push rod in the billet placement chamber can be lifted and lowered to drive the billet placed in the tray to enter the billet heating chamber through the lower port of the billet heating chamber, and the billet heating chamber can be used to heat the billet in a vacuum environment. In this way, it is convenient for the billet heating furnace to directly dock with the vacuum forging chamber without breaking the vacuum, thereby improving the transfer efficiency, avoiding the rapid drop in billet temperature leading to the formation of coarse grains in the surface area of ​​the billet, and making it easy for the billet to achieve superplastic forming.

[0008] Furthermore, in the method for intelligent control of the push rod rising rate of the vacuum isothermal forging billet heating furnace provided by the present application, the intelligent control device can determine the target rising rate corresponding to the billet to be heated based on the attribute information and the preset push rod rising rate intelligent control model, and control the push rod to drive the billet to be heated into the billet heating chamber at the target rising rate. Compared with the fixed rising rate in the related art, the present application can control the rise of the push rod at different rising rates for billets with different attribute information. When the attribute information of the billet changes, the control strategy can be adaptively adjusted to adapt to different billet changes, thereby improving the heating and forging efficiency.

[0009] Optionally, the attribute information includes: material, mass, size, a first ratio, and a second ratio; wherein the first ratio is the ratio of the height of the blank to be heated to the bottom area; the second ratio is the ratio of the size of the bottom surface of the blank to be heated in the first direction to the size in the second direction; the first direction and the second direction are perpendicular to each other, and the intersection of the first direction and the second direction is the center of the bottom surface of the blank to be heated.

[0010] Optionally, based on the attribute information and a preset push rod rising rate intelligent control model, the target rising rate corresponding to the billet to be heated is determined, including: constructing a new feature according to the attribute information of the billet to be heated and adding the attribute information to obtain the attribute information of the newly added feature; inputting the attribute information of the newly added feature into the push rod rising rate intelligent control model to obtain the target rising rate output by the push rod rising rate intelligent control model.

[0011] In the intelligent control method for the push rod rising rate of the vacuum isothermal forging billet heating furnace provided in the present application, the intelligent control device can perform feature engineering on the original features in the attribute information of the heated billet, extract meaningful new features that can help evaluate and predict the push rod rising rate for prediction, and further improve the accuracy of the push rod rising rate prediction.

[0012] Optionally, the newly created feature includes at least one of the following: the product of the mass and the first ratio, the product of the mass and the second ratio, the first irregularity coefficient, the second irregularity coefficient, and the size difference rate; wherein the first ratio is the ratio of the height of the billet to be heated to the bottom area; the second ratio is the ratio of the size of the bottom surface of the billet to be heated in the first direction to the size in the second direction; the first direction and the second direction are perpendicular to each other, and the intersection of the first direction and the second direction is the center of the bottom surface of the billet to be heated; when the first ratio is greater than the first ratio threshold, the first irregularity coefficient is 1; when the first ratio threshold is less than the first ratio threshold, the first irregularity coefficient is 0; when the second ratio is greater than the second ratio threshold, the second irregularity coefficient is 1; when the second ratio threshold is less than the second ratio threshold, the second irregularity coefficient is 0; the size difference rate is determined based on the ratio of the first value to the second value; the first value is the absolute value of the difference between the size of the bottom surface of the billet to be heated in the first direction and the size in the second direction; the second value is the sum of the size of the bottom surface of the billet to be heated in the first direction and the size in the second direction.

[0013] Optionally, the intelligent control model of the push rod rising rate is trained in the following manner: obtaining a training sample set; the training sample set includes multiple training samples; each training sample includes attribute information and a rising rate label of the training blank; and training the initial model based on the training sample set to obtain the intelligent control model of the push rod rising rate.

[0014] Optionally, the initial model is trained based on the training sample set to obtain an intelligent control model for the rise rate of the push rod, including: constructing new features based on the attribute information of the training samples and adding them to the training samples to obtain a training sample set with the new features added; inputting the training samples in the training sample set with the new features into the initial model for training to obtain an intelligent control model for the rise rate of the push rod.

[0015] In the second aspect, the present application provides an intelligent control device for a vacuum isothermal forging billet heating furnace, which also includes a billet placement chamber and a billet heating chamber arranged above the billet placement chamber; the billet heating chamber is connected to the billet placement chamber through a lower end opening; a tray for placing billets is provided in the billet placement chamber, and a liftable push rod is installed at the bottom of the tray; the push rod is used to lift and drive the billet placed in the tray to enter or leave the billet heating chamber through the lower end opening of the billet heating chamber; the billet heating chamber is used to heat the billet in a vacuum environment; the intelligent control device includes: an acquisition module and a processing module; the acquisition module is used to acquire the attribute information of the billet to be heated; the processing module is used to determine the target rising rate corresponding to the billet to be heated based on the attribute information and a preset push rod rising rate intelligent control model; wherein the push rod rising rate intelligent control model is used to predict the rising rate of the push rod when lifting and driving the billet according to the attribute information of the billet; and the push rod is controlled to drive the billet to be heated into the billet heating chamber according to the target rising rate.

[0016] Optionally, the attribute information includes: material, mass, size, a first ratio, and a second ratio; wherein the first ratio is the ratio of the height of the blank to be heated to the bottom area; the second ratio is the ratio of the size of the bottom surface of the blank to be heated in the first direction to the size in the second direction; the first direction and the second direction are perpendicular to each other, and the intersection of the first direction and the second direction is the center of the bottom surface of the blank to be heated.

[0017] Optionally, the processing module is specifically used to construct a new feature and add attribute information based on the attribute information of the blank to be heated, so as to obtain the attribute information of the newly added feature; the attribute information of the newly added feature is input into the intelligent control model of the push rod rising rate, so as to obtain the target rising rate output by the intelligent control model of the push rod rising rate.

[0018] Optionally, the newly created feature includes at least one of the following: the product of the mass and the first ratio, the product of the mass and the second ratio, the first irregularity coefficient, the second irregularity coefficient, and the size difference rate; wherein the first ratio is the ratio of the height of the billet to be heated to the bottom area; the second ratio is the ratio of the size of the bottom surface of the billet to be heated in the first direction to the size in the second direction; the first direction and the second direction are perpendicular to each other, and the intersection of the first direction and the second direction is the center of the bottom surface of the billet to be heated; when the first ratio is greater than the first ratio threshold, the first irregularity coefficient is 1; when the first ratio threshold is less than the first ratio threshold, the first irregularity coefficient is 0; when the second ratio is greater than the second ratio threshold, the second irregularity coefficient is 1; when the second ratio threshold is less than the second ratio threshold, the second irregularity coefficient is 0; the size difference rate is determined based on the ratio of the first value to the second value; the first value is the absolute value of the difference between the size of the bottom surface of the billet to be heated in the first direction and the size in the second direction; the second value is the sum of the size of the bottom surface of the billet to be heated in the first direction and the size in the second direction.

[0019] Optionally, the acquisition module is also used to acquire a training sample set; the training sample set includes multiple training samples; each training sample includes attribute information and a rising rate label of the training blank; the processing module is also used to train the initial model based on the training sample set to obtain an intelligent control model of the push rod rising rate.

[0020] Optionally, the processing module is specifically used to construct a new feature based on the attribute information of the training sample and add it to the training sample to obtain a training sample set with the new feature added; the training samples in the training sample set with the new feature added are input into the initial model for training to obtain an intelligent control model of the push rod rising rate.

[0021] In a third aspect, the present application provides a computer program product, comprising: computer instructions; when the computer instructions are executed on an intelligent control device, the intelligent control device implements the method described in the first aspect above.

[0022] In a fourth aspect, the present application provides an intelligent control device for a vacuum isothermal forging billet heating furnace, the intelligent control device comprising: a processor and a memory; the memory stores instructions executable by the processor; when the processor is configured to execute instructions, the intelligent control device implements the method described in the first aspect above.

[0023] In a fifth aspect, the present application provides a readable storage medium, which includes: software instructions; when the software instructions are executed in an intelligent control device, the intelligent control device implements the method described in the first aspect above.

[0024] The beneficial effects of the second to fifth aspects mentioned above can be referred to the first aspect and will not be elaborated on again. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 A schematic diagram of the composition of an intelligent control system for a vacuum isothermal forging blank heating furnace provided in an embodiment of the present application; Figure 2 A schematic diagram of the composition of a vacuum isothermal forging blank heating furnace 100 provided in an embodiment of the present application; Figure 3 A schematic flow chart of an intelligent control method for the lift rod rising rate of a vacuum isothermal forging billet heating furnace provided in an embodiment of the present application; Figure 4 A schematic diagram of the composition of an intelligent control device for a vacuum isothermal forging blank heating furnace provided in an embodiment of the present application; Figure 5 A schematic diagram of the composition of another intelligent control device for a vacuum isothermal forging billet heating furnace provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] It should be noted that, in the embodiments of the present application, words such as "exemplarily" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplarily" or "for example" is intended to present related concepts in a specific way.

[0029] In order to facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, the words "first", "second", etc. are used to distinguish the same items or similar items with basically the same functions and effects. Those skilled in the art can understand that the words "first", "second", etc. are not limiting the quantity and execution order.

[0030] Vacuum forging is a metal forging process performed in a vacuum environment. Since there is almost no air or other impurities in a vacuum environment, the metal is prevented from reacting with gases such as oxygen and nitrogen during heating and forging, reducing the generation of defects such as oxidation and decarburization. It is also beneficial to remove gas impurities in the metal and improve the quality of forgings.

[0031] In the vacuum forging solution provided by the related art, the blank needs to be taken out of the heating furnace after being heated in the heating furnace, and then reloaded into the vacuum forging chamber for forging.

[0032] After being taken out of the heating furnace, the temperature of the blank drops rapidly, and coarse grains are easily formed in the surface area of ​​the blank, which makes it easy for the blank to fail to achieve superplastic forming.

[0033] Based on this, an embodiment of the present application provides an intelligent control method for the rising rate of the push rod of a vacuum isothermal forging billet heating furnace, and can provide a vacuum isothermal forging billet heating furnace, which can heat the billet in a vacuum environment, facilitate docking with a vacuum forging chamber without breaking the vacuum, and improve the intelligence level of the vacuum isothermal forging billet heating furnace.

[0034] The following is an introduction with reference to the accompanying drawings.

[0035] Figure 1 This is a schematic diagram of the composition of the intelligent control system of the vacuum isothermal forging billet heating furnace provided in the embodiment of the present application. Figure 1 As shown, the intelligent control system may include: a vacuum isothermal forging billet heating furnace 100 and an intelligent control device 200. The intelligent control device 200 is in communication connection with the vacuum isothermal forging billet heating furnace 100 or specific components in the vacuum isothermal forging billet heating furnace 100.

[0036] Figure 2 The schematic diagram of the composition of the vacuum isothermal forging blank heating furnace 100 provided in the embodiment of the present application. Figure 2 As shown, the vacuum isothermal forging billet heating furnace 100 may include: a billet placement chamber 10 and a billet heating chamber 20, wherein the billet heating chamber 20 is disposed above the billet placement chamber 10, and the billet heating chamber 20 is connected to the billet placement chamber through a lower end opening.

[0037] The blank placement chamber 10 includes: a bottom plate 11, a furnace door 12, a vacuum gate 13 and a lower furnace shell ( Figure 2 The top of the blank placement chamber 10 is connected to the lower end opening of the blank heating chamber 20. The blank placement chamber 10 and the vacuum forging chamber 19 can be sealed and connected through a vacuum gate 13.

[0038] A tray 14 for placing the blank 30 is arranged in the middle of the blank placement chamber 10, and the tray 14 is supported on the bottom plate 11 by a bracket 15. A three-jaw chuck 16 for clamping and positioning the blank 30 is installed on the edge of the tray 14. A tray 17 for holding the bottom of the blank 30 (or for placing the blank) is installed in the central through hole of the tray 14, and a liftable ejector rod 18 is installed at the bottom of the tray 17, which passes through the bottom plate 11 and is sealed with the bottom plate 11. The ejector rod 18 is used to lift and drive the blank 30 placed in the tray 17 to enter or leave the blank heating chamber 20 through the lower end opening of the blank heating chamber 20.

[0039] The blank heating chamber 20 can be used to heat the blank 30 in a vacuum environment.

[0040] For example, the vacuum isothermal forging blank heating furnace 100 may further include a vacuum unit ( Figure 2 The vacuum pumping unit may include a roots pump and an expansion pump, and is connected to the blank placement chamber 10 and / or the blank heating chamber 20 through a vacuum pipeline. The vacuum pumping unit may be used to vacuum the blank placement chamber 10 and / or the blank heating chamber 20.

[0041] The process of heating the blank 30 using the above-mentioned vacuum isothermal forging blank heating furnace 100 is as follows: open the furnace door 12, clamp the blank 30 by the robot and put it into the middle position of the tray 14 in the blank placement chamber 10, and then clamp the blank 30 by the three-jaw chuck 16 to center it on the tray 14 or the tray 17 (or make the center of the blank 30 the same as the center of the tray 17). Close the furnace door 12, evacuate the vacuum isothermal forging blank heating furnace 100, release the three-jaw chuck 16 after the vacuum degree reaches the preset vacuum degree threshold, and the push rod 18 pushes the tray 17 and the blank 30 on the tray 17 to rise into the blank heating chamber 20. The blank 30 is completely placed in the billet heating chamber 20 for heating. After the billet 30 is heated to the required heating temperature, the push rod 18 descends to return the billet 30 to its original position on the tray 14, and the vacuum gate 13 is opened. The blank 30 is fed to the blank placement chamber 10 through the feeding robot ( Figure 2 (not shown) the blank 30 is fed into the vacuum forging chamber 19 for forging.

[0042] The intelligent control device 200 may be an electronic device with computing and processing functions such as a computer or server wirelessly connected to the vacuum isothermal forging billet heating furnace 100; or the intelligent control device 200 may also be a control unit disposed on the vacuum isothermal forging billet heating furnace 100 and wiredly connected to specific components of the vacuum isothermal forging billet heating furnace 100. The present application embodiment does not limit this.

[0043] The intelligent control device 200 can be used to control the lift rate of the push rod in the vacuum isothermal forging billet heating furnace 100. The specific process can be referred to the intelligent control method of the lift rate of the push rod in the vacuum isothermal forging billet heating furnace provided in the following embodiment, which will not be repeated here.

[0044] The execution subject of the intelligent control method for the rise rate of the push rod of the vacuum isothermal forging billet heating furnace provided in the embodiment of the present application is an intelligent control device (such as the above-mentioned intelligent control device 200). Optionally, the execution subject of the intelligent control method for the rise rate of the push rod of the vacuum isothermal forging billet heating furnace can also be a processor (such as a central processing unit (CPU)) in the aforementioned intelligent control device; or, the execution subject can also be a software system installed in the aforementioned intelligent control device for executing the intelligent control method; or, the execution subject can also be a functional module in the aforementioned intelligent control device for executing the intelligent control method, etc. The embodiment of the present application does not limit this.

[0045] For the sake of simplicity, the following is an introduction using the intelligent control device as the executor of the method for intelligent control of the rise rate of the push rod of the vacuum isothermal forging billet heating furnace provided in the embodiment of the present application.

[0046] Figure 3 The figure is a flow chart of the intelligent control method of the push rod rising rate of the vacuum isothermal forging blank heating furnace provided in the embodiment of the present application. Figure 3 As shown, the method includes the following steps: S101, obtaining property information of the blank to be heated.

[0047] Among them, the attribute information of the blank to be heated includes: material, mass, size, first ratio, and second ratio. The first ratio is the ratio of the height of the blank to be heated to the area of ​​the bottom surface (or the contact surface with the tray). The second ratio is the ratio of the size of the bottom surface of the blank to be heated in the first direction to the size in the second direction. The first direction and the second direction are perpendicular to each other, and the intersection of the first direction and the second direction is the center of the bottom surface of the blank to be heated. For example, taking the bottom surface of the blank to be heated as a rectangle as an example, the first direction and the second direction can be understood as the length direction and width direction of the bottom surface of the blank to be heated.

[0048] As an example, the intelligent control device may include an input-output interface, which can be connected to a mouse, a keyboard, or a touch screen. The intelligent control device can receive property information of the heated blank input by a staff through a mouse, a keyboard, or a touch screen through the input-output interface.

[0049] As another example, the intelligent control device may be communicatively connected with a device or platform storing the property information of the blank, and the intelligent control device may receive the property information of the blank to be heated sent from these devices or platforms.

[0050] S102, determining a target rising rate corresponding to the blank to be heated based on the attribute information and a preset push rod rising rate intelligent control model.

[0051] The push rod rising rate intelligent control model is used to predict the rising rate of the push rod when driving the blank according to the property information of the blank. The specific training process of the push rod rising rate intelligent control model can be referred to the following embodiment, which will not be repeated here.

[0052] S103, controlling the ejector pin to drive the blank to be heated into the blank heating chamber at a target ascending rate.

[0053] As an example, the mandrel can be driven to rise or fall by a driving motor. In this case, the intelligent control device can control the rising rate of the mandrel by changing the control signal of the driving motor.

[0054] As another example, the push rod can also be driven up or down by a hydraulic system. In this case, the intelligent control device can specifically control the rising rate of the push rod by changing the opening of the regulating valve to adjust the flow of hydraulic oil entering the hydraulic cylinder.

[0055] In the method for intelligently controlling the rising rate of the mandrel of the vacuum isothermal forging billet heating furnace provided in the embodiment of the present application, the vacuum isothermal forging billet heating furnace includes a billet placement chamber and a billet heating chamber arranged above the billet placement chamber, and the mandrel in the billet placement chamber can lift and drive the billet placed in the tray to enter the billet heating chamber through the lower port of the billet heating chamber, and the billet heating chamber can be used to heat the billet in a vacuum environment. In this way, it is convenient for the billet heating furnace to directly dock with the vacuum forging chamber without breaking the vacuum, thereby improving the transfer efficiency, avoiding the rapid drop in billet temperature leading to the formation of coarse grains in the surface area of ​​the billet, and making it easy for the billet to achieve superplastic forming.

[0056] Furthermore, in the method for intelligent control of the push rod rising rate of the vacuum isothermal forging billet heating furnace provided in the embodiment of the present application, the intelligent control device can determine the target rising rate corresponding to the billet to be heated based on the attribute information and the preset push rod rising rate intelligent control model, and control the push rod to drive the billet to be heated into the billet heating chamber at the target rising rate. Compared with the fixed rising rate in the related art, the present application can control the rise of the push rod at different rising rates for billets with different attribute information. When the attribute information of the billet changes, the control strategy can be adaptively adjusted to adapt to different billet changes, thereby improving the heating and forging efficiency.

[0057] The specific process of the above S102 is introduced below.

[0058] In some possible embodiments, the intelligent control device may input the original features in the attribute information into the push rod rising rate intelligent control model to obtain the target rising rate output by the push rod rising rate intelligent control model.

[0059] In some other possible embodiments, the intelligent control device may also perform feature engineering on the features in the attribute information, and then input the features after feature engineering into the mandrel rise rate intelligent control model to obtain the target rise rate output by the mandrel rise rate intelligent control model. In this case, the above S102 may specifically include the following steps: Step 1a: construct a new feature and add attribute information according to the attribute information of the blank to be heated, and obtain the attribute information of the newly added feature.

[0060] Optionally, the newly created feature may include at least one of the following: a product of the mass and the first ratio, a product of the mass and the second ratio, a first irregularity coefficient, a second irregularity coefficient, and a size difference rate.

[0061] The first ratio is the ratio of the height of the blank to be heated to the bottom area.

[0062] The second ratio is the ratio of the size of the bottom surface of the blank to be heated in the first direction to the size of the bottom surface in the second direction. The first direction and the second direction are perpendicular to each other, and the intersection of the first direction and the second direction is the center of the bottom surface of the blank to be heated.

[0063] When the first ratio is greater than the first ratio threshold, the first irregularity coefficient is 1; when the first ratio threshold is less than the first ratio threshold, the first irregularity coefficient is 0. The first ratio threshold may be preset in the intelligent control device. For example, the first ratio threshold may be set to 1.5, 2, 2.5 or 3, etc. The embodiment of the present application does not limit the specific value of the first ratio threshold.

[0064] When the second ratio is greater than the second ratio threshold, the second irregularity coefficient is 1; when the second ratio threshold is less than the second ratio threshold, the second irregularity coefficient is 0. The second ratio threshold can be preset in the intelligent control device. For example, the second ratio threshold can be set to 5, 6, 7 or 8. The embodiment of the present application does not limit the specific value of the second ratio threshold.

[0065] The size difference rate is determined based on the ratio of the first value to the second value, wherein the first value is the absolute value of the difference between the size (or length) in the first direction and the size (or length) in the second direction of the bottom surface of the heated blank, and the second value is the sum of the size in the first direction and the size in the second direction of the bottom surface of the heated blank.

[0066] For example, the size difference rate can be calculated by the following formula: Formula (1) In formula (1), Indicates the size difference ratio. Indicates the size of the bottom surface of the blank to be heated in the first direction. Indicates the dimension of the bottom surface of the blank to be heated in the second direction.

[0067] Step 2a, input the attribute information of the newly created feature into the push rod rising rate intelligent control model to obtain the target rising rate output by the push rod rising rate intelligent control model.

[0068] In the intelligent control method for the push rod rising rate of a vacuum isothermal forging billet heating furnace provided in an embodiment of the present application, the intelligent control device can perform feature engineering on the original features in the attribute information of the billet to be heated, extract meaningful new features that can help evaluate and predict the push rod rising rate for prediction, and further improve the accuracy of the push rod rising rate prediction.

[0069] In some embodiments, before the above S102, the intelligent control device may also obtain a trained intelligent control model of the mandrel rising rate.

[0070] In a possible implementation, the intelligent control device can directly obtain the trained mandrel rising rate intelligent control model from other devices.

[0071] For example, the intelligent control device can obtain the trained push rod rising rate intelligent control model from other devices by downloading or transferring from an intermediate medium.

[0072] In another possible implementation, the intelligent control device can also train itself to obtain the mandrel rising rate intelligent control model. In this case, before the above S102, the method can also include the following steps: Step 1b: Obtain a training sample set.

[0073] The training sample set includes multiple training samples, and each training sample includes attribute information and a rising rate label of a training blank.

[0074] Step 2b: Train the initial model based on the training sample set to obtain an intelligent control model for the lift rate of the mandrel.

[0075] Optionally, the initial model may specifically be a multilayer perceptron (MLP) model or a convolutional neural network (CNN) model, etc. The embodiment of the present application does not limit the specific type of the initial model.

[0076] As an example, the MLP model can be composed of an input layer, multiple hidden layers and an output layer, and the neurons are nonlinearly transformed through the activation function to learn the complex mapping relationship between the features in the attribute information and the rising rate of the top rod.

[0077] As another example, the intelligent control device can use an encoder to encode the features in the attribute information to obtain a feature matrix, and then use the convolution kernel in the CNN model to slide on the feature matrix to perform a convolution operation to automatically extract the features in the feature matrix. The pooling layer in the CNN model can downsample the features extracted by the convolution layer. After feature extraction and compression in multiple convolutional layers and pooling layers, the features can enter the fully connected layer, which can integrate all the previously extracted features and map these features to the output space through the fully connected relationship between neurons to obtain the predicted value of the top rod rising rate.

[0078] Optionally, the intelligent control device can directly input the training samples (the original features in them) into the initial model for training.

[0079] For example, as described above, the training sample set may include multiple training samples. The intelligent control device may input one or more training samples into the initial model each time to obtain the predicted rising rate output by the initial model, and then compare the predicted rising rate with the rising rate label in the training sample, calculate the loss function, and then adjust the parameters in the initial model according to the loss function until the model convergence conditions are met to obtain the intelligent control model of the push rod rising rate.

[0080] Optionally, the model convergence condition may include: the number of times the training sample is input into the initial model reaches a number threshold, and / or the prediction error of the initial model is less than an error threshold.

[0081] The number threshold may be preset in the intelligent control device. For example, the number threshold may be set to 500 times, 1000 times, or 10000 times, etc. The embodiment of the present application does not limit the specific value of the number threshold. The error threshold may be preset in the intelligent control device. For example, the error threshold may be set to 3%, 5%, or 8%, etc. The embodiment of the present application does not limit the specific value of the error threshold.

[0082] Optionally, the intelligent control device may also perform feature engineering processing on the original features in the training samples and then input them into the initial model for training. In this case, the above step 2b may specifically include the following steps: Step 2.1b: construct a new feature based on the attribute information of the training sample and add it to the training sample to obtain a training sample set with the new feature added.

[0083] Step 2.1b can refer to the above-mentioned intelligent control device to perform feature engineering processing on the features in the attribute information, and then input the features after feature engineering processing into the intelligent control model of the push rod rising rate to obtain the target rising rate output by the intelligent control model of the push rod rising rate. The process is described in the process and will not be repeated here.

[0084] Step 2.2b: Input the training samples in the training sample set with the newly created features into the initial model for training to obtain the intelligent control model of the mandrel rising rate.

[0085] The specific process of step 2.2b can refer to the process of directly inputting the training samples into the initial model for training, which will not be repeated here.

[0086] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to realize the above functions, the intelligent control device includes a hardware structure and / or software module corresponding to the execution of each function. It should be easy to realize that the technical goals in this field are combined with the units and algorithm steps of each example described in the embodiments disclosed in this article, and the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technical goals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0087] In an exemplary embodiment, the present application also provides an intelligent control device for a vacuum isothermal forging billet heating furnace. Figure 4 This is a schematic diagram of the composition of the intelligent control device of the vacuum isothermal forging blank heating furnace provided in the embodiment of the present application. Figure 4 As shown, the intelligent control device includes: an acquisition module 401 and a processing module 402 .

[0088] The acquisition module 401 is used to acquire the property information of the blank to be heated.

[0089] Processing module 402 is used to determine the target rising rate corresponding to the blank to be heated based on the attribute information and a preset push rod rising rate intelligent control model; wherein the push rod rising rate intelligent control model is used to predict the rising rate of the push rod when driving the blank to be heated according to the attribute information of the blank; and control the push rod to drive the blank to be heated into the blank heating chamber according to the target rising rate.

[0090] In some possible embodiments, the attribute information includes: material, mass, size, a first ratio, and a second ratio; wherein the first ratio is the ratio of the height of the blank to be heated to the bottom area; the second ratio is the ratio of the size of the bottom surface of the blank to be heated in the first direction to the size in the second direction; the first direction and the second direction are perpendicular to each other, and the intersection of the first direction and the second direction is the center of the bottom surface of the blank to be heated.

[0091] In some other possible embodiments, the processing module 402 is specifically used to construct a new feature and add attribute information based on the attribute information of the blank to be heated, so as to obtain the attribute information of the newly added feature; the attribute information of the newly added feature is input into the intelligent control model of the push rod rising rate, so as to obtain the target rising rate output by the intelligent control model of the push rod rising rate.

[0092] In some other possible embodiments, the newly created feature includes at least one of the following: the product of the mass and the first ratio, the product of the mass and the second ratio, the first irregularity coefficient, the second irregularity coefficient, and the size difference rate; wherein the first ratio is the ratio of the height of the billet to be heated to the bottom area; the second ratio is the ratio of the size of the bottom surface of the billet to be heated in the first direction to the size of the bottom surface in the second direction; the first direction and the second direction are perpendicular to each other, and the intersection of the first direction and the second direction is the center of the bottom surface of the billet to be heated; when the first ratio is greater than the first ratio threshold, the first irregularity coefficient is 1; when the first ratio threshold is less than the first ratio threshold, the first irregularity coefficient is 0; when the second ratio is greater than the second ratio threshold, the second irregularity coefficient is 1; when the second ratio threshold is less than the second ratio threshold, the second irregularity coefficient is 0; the size difference rate is determined based on the ratio of the first value to the second value; the first value is the absolute value of the difference between the size of the bottom surface of the billet to be heated in the first direction and the size in the second direction; the second value is the sum of the size of the bottom surface of the billet to be heated in the first direction and the size in the second direction.

[0093] In some other possible embodiments, the acquisition module 401 is also used to acquire a training sample set; the training sample set includes multiple training samples; each training sample includes attribute information and a rising rate label of the training blank; the processing module 402 is also used to train the initial model based on the training sample set to obtain an intelligent control model of the push rod rising rate.

[0094] In some other possible embodiments, the processing module 402 is specifically used to construct a new feature based on the attribute information of the training sample and add it to the training sample to obtain a training sample set with the new feature added; the training samples in the training sample set with the new feature added are input into the initial model for training to obtain an intelligent control model of the push rod rising rate.

[0095] It should be noted that Figure 4 The division of modules in the example is schematic and is only a logical function division. There may be other division methods in actual implementation. For example, two or more functions may be integrated into one processing module. The above integrated modules may be implemented in the form of hardware or software function modules.

[0096] In an exemplary embodiment, the embodiment of the present application also provides an intelligent control device for a vacuum isothermal forging billet heating furnace in the form of a physical device. Figure 5 A schematic diagram of another intelligent control device for a vacuum isothermal forging blank heating furnace provided in an embodiment of the present application. Figure 5 As shown, the intelligent control device includes: a processor 40 , a memory 50 , a communication line 60 , a communication interface 70 , and an input / output interface 80 .

[0097] The processor 40 , the memory 50 , the communication interface 70 and the input / output interface 80 may be connected via a communication line 60 .

[0098] The processor 40 is used to execute the instructions stored in the memory 50 to implement the intelligent control method of the push rod rising rate of the vacuum isothermal forging billet heating furnace provided in the above-mentioned embodiment of the present application. The processor 40 can be a CPU, a general-purpose processor network processor (network processor, NP), a digital signal processor (digital signal processing, DSP), a microprocessor, a microcontroller (micro control unit, MCU) / single-chip microcomputer / single-chip microcomputer, a programmable logic device (programmable logic device, PLD) or any combination thereof. The processor 40 can also be any other device with processing functions, such as a circuit, a device or a software module, which is not limited in the embodiments of the present application. In one example, the processor 40 may include one or more CPUs, such as Figure 4 As an optional implementation, the intelligent control device may include multiple processors, for example, in addition to the processor 40, it may also include a processor 90 ( Figure 4 ) is shown by the dotted line as an example.

[0099] The memory 50 is used to store instructions. For example, the instructions may be computer programs. Optionally, the memory 50 may be a read-only memory (ROM) or other types of static storage devices that can store static information and / or instructions, or a random access memory (RAM) or other types of dynamic storage devices that can store information and / or instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage devices, etc., and the embodiments of the present application are not limited to this.

[0100] It should be noted that the memory 50 may exist independently of the processor 40, or may be integrated with the processor 40. The memory 50 may be located inside the intelligent control device, or may be located outside the intelligent control device, which is not limited in the embodiment of the present application.

[0101] The communication line 60 is used to transmit information between the components included in the intelligent control device.

[0102] The communication interface 70 is used to communicate with other devices or other communication networks. The other communication networks may be Ethernet, radio access network (RAN), wireless local area network (WLAN), etc. The communication interface 70 may be a module, a circuit, a transceiver or any device capable of achieving communication.

[0103] The input / output interface 80 is used to realize human-computer interaction between the user and the intelligent control device, for example, to realize action interaction or information interaction between the user and the intelligent control device.

[0104] Exemplarily, the input / output interface 80 may be a mouse, a keyboard, a display screen, or a touch display screen, etc. Action interaction or information interaction between a user and the intelligent control device may be achieved through a mouse, a keyboard, a display screen, or a touch display screen, etc.

[0105] It should be noted that Figure 5 The structure shown in the figure does not constitute a limitation on the intelligent control device. Figure 5 In addition to the components shown, the intelligent control device may include more or fewer components than shown, or a combination of certain components, or a different arrangement of components.

[0106] In an exemplary embodiment, the embodiment of the present application further provides a computer program product, which includes computer instructions. When the computer instructions are executed in an intelligent control device, the intelligent control device implements the method in the aforementioned method embodiment.

[0107] In an exemplary embodiment, the present application also provides a readable storage medium, which includes software instructions. When the software instructions are executed in the intelligent control device, the intelligent control device implements the method in the aforementioned method embodiment. The computer-readable storage medium can be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0108] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer-executable instructions. When the computer-executable instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer-executable instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer-executable instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center.

[0109] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other changes to the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in a claim. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0110] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary illustrations of the present application as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0111] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent control method for the rising rate of the mandrel of a vacuum isothermal forging billet heating furnace, characterized in that: The method is applied to an intelligent control device of a vacuum isothermal forging billet heating furnace; the vacuum isothermal forging billet heating furnace further comprises a billet placement chamber and a billet heating chamber arranged above the billet placement chamber; the billet heating chamber is connected to the billet placement chamber through a lower end opening; A tray for placing the blanks is provided in the blank placement chamber, and a liftable ejector rod is installed at the bottom of the tray; the ejector rod is used to lift and drive the blanks placed in the tray to enter or leave the blank heating chamber through the lower end opening of the blank heating chamber; The blank heating chamber is used to heat the blank in a vacuum environment; The method comprises: Obtaining property information of the blank to be heated; Based on the attribute information and a preset push rod rising rate intelligent control model, a target rising rate corresponding to the blank to be heated is determined; wherein the push rod rising rate intelligent control model is used to predict the rising rate of the push rod when driving the blank to rise and fall according to the attribute information of the blank; The ejector rod is controlled to drive the blank to be heated into the blank heating chamber according to the target rising rate.

2. The method according to claim 1, characterized in that The attribute information includes: material, quality, size, first ratio, and second ratio; Among them, the first ratio is the ratio of the height of the blank to be heated to the bottom area; the second ratio is the ratio of the size of the bottom surface of the blank to be heated in the first direction to the size in the second direction; the first direction and the second direction are perpendicular to each other, and the intersection of the first direction and the second direction is the center of the bottom surface of the blank to be heated.

3. The method according to claim 1, characterized in that The step of determining a target rising rate corresponding to the blank to be heated based on the attribute information and a preset push rod rising rate intelligent control model includes: Constructing a new feature according to the attribute information of the blank to be heated and adding the attribute information to obtain the attribute information of the new feature; The attribute information of the newly added feature is input into the push rod rising rate intelligent control model to obtain the target rising rate output by the push rod rising rate intelligent control model.

4. The method according to claim 3, characterized in that The newly created feature includes at least one of the following: a product of mass and a first ratio, a product of mass and a second ratio, a first irregularity coefficient, a second irregularity coefficient, and a size difference rate; Wherein, the first ratio is the ratio of the height of the blank to be heated to the bottom area; the second ratio is the ratio of the size of the bottom surface of the blank to be heated in the first direction to the size in the second direction; the first direction and the second direction are perpendicular to each other, and the intersection of the first direction and the second direction is the center of the bottom surface of the blank to be heated; When the first ratio is greater than a first ratio threshold, the first irregularity coefficient is 1; when the first ratio threshold is less than the first ratio threshold, the first irregularity coefficient is 0; When the second ratio is greater than a second ratio threshold, the second irregularity coefficient is 1; when the second ratio threshold is less than the second ratio threshold, the second irregularity coefficient is 0; The dimensional difference rate is determined based on the ratio of the first value to the second value; the first value is the absolute value of the difference between the size of the bottom surface of the blank to be heated in the first direction and the size in the second direction; the second value is the sum of the size of the bottom surface of the blank to be heated in the first direction and the size in the second direction.

5. The method according to claim 1, characterized in that The intelligent control model of the mandrel rising rate is trained in the following way: Acquire a training sample set; the training sample set includes a plurality of training samples; each of the training samples includes attribute information and a rise rate label of a training blank; The initial model is trained based on the training sample set to obtain the mandrel rising rate intelligent control model.

6. The method according to claim 5, characterized in that The initial model is trained based on the training sample set to obtain the mandrel rising rate intelligent control model, including: Constructing a new feature according to the attribute information of the training sample and adding it to the training sample to obtain a training sample set with the new feature added; The training samples in the training sample set with the newly created features added are input into the initial model for training to obtain the mandrel rising rate intelligent control model.

7. An intelligent control device for a vacuum isothermal forging blank heating furnace, characterized in that: The vacuum isothermal forging billet heating furnace further comprises a billet placement chamber and a billet heating chamber arranged above the billet placement chamber; the billet heating chamber is connected to the billet placement chamber through a lower end opening; The blank placement chamber is provided with a tray for placing blanks, and a liftable push rod is installed at the bottom of the tray; the push rod is used to lift and drive the blank placed in the tray to enter or leave the blank heating chamber through the lower end opening of the blank heating chamber; the blank heating chamber is used to heat the blank in a vacuum environment; The intelligent control device comprises: an acquisition module and a processing module; The acquisition module is used to acquire the property information of the blank to be heated; The processing module is used to determine the target rising rate corresponding to the blank to be heated based on the attribute information and a preset push rod rising rate intelligent control model; wherein the push rod rising rate intelligent control model is used to predict the rising rate of the push rod when driving the blank to be heated up and down according to the attribute information of the blank; and control the push rod to drive the blank to be heated into the blank heating chamber according to the target rising rate.

8. An intelligent control device for a vacuum isothermal forging blank heating furnace, characterized in that: include: Processor and memory; The memory stores instructions executable by the processor; When the processor is configured to execute the instructions, the intelligent control device implements the method according to any one of claims 1 to 6.

9. A readable storage medium, characterized in that: include: Software instructions; When the software instructions are executed in the intelligent control device, the intelligent control device implements the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that include: Computer instructions; When the computer instructions are executed in the intelligent control device, the intelligent control device implements the method according to any one of claims 1 to 6.

Images