Intelligent distribution method and device for heating furnace of fully-closed vacuum isothermal forging system
By using an intelligent distribution method in a fully enclosed vacuum isothermal forging system, the problem of coarse grains caused by the drop in billet temperature in traditional forging is solved, achieving efficient and intelligent heating furnace distribution and ensuring superplastic forming of billets.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUIZHOU ANDA AVIATION FORGING
- Filing Date
- 2024-12-26
- Publication Date
- 2026-06-23
AI Technical Summary
In traditional near-isothermal forging, the die cannot be heated to the same high temperature as the billet, which causes the billet temperature to drop rapidly and easily forms coarse grains in the surface area, affecting superplastic forming.
A fully enclosed vacuum isothermal forging system is adopted. The system obtains the property data of the billet and the heating furnace through an intelligent distribution device. The heating furnace is automatically distributed in a vacuum environment using a heating furnace distribution model to ensure that the temperature of the mold and the billet are consistent, improve the transfer efficiency, and avoid the formation of coarse grains.
It achieves efficient docking between the heating furnace and the billet in a vacuum environment, reduces human error, improves the level of intelligence, ensures superplastic forming of the billet, and extends the service life of the equipment.
Smart Images
Figure CN119681191B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of high-end intelligent device manufacturing, and in particular to an intelligent distribution method and device for heating furnace in a fully enclosed vacuum isothermal forging system. Background Technology
[0002] Near isothermal forging refers to heating the billet and the die to similar temperatures and forging at a relatively low strain rate.
[0003] Because near-isothermal forging can improve material properties, machining accuracy and surface quality, and can adapt to complex shapes and high strength requirements, it is now frequently used for forging aerospace components.
[0004] Traditional near-isothermal forging cannot achieve superplastic forming of the billet because the mold cannot be heated to the same high temperature as the billet. Summary of the Invention
[0005] This application provides a method and apparatus for intelligent allocation of heating furnaces in a fully enclosed vacuum isothermal forging system. This method can improve the transfer efficiency during billet heating, avoid the problem of coarse grains easily forming on the surface due to the drop in billet temperature, and automatically allocate the corresponding heating furnaces to different billets, thereby improving the intelligence level of the fully enclosed vacuum isothermal forging system.
[0006] In a first aspect, this application provides an intelligent furnace allocation method for a fully enclosed vacuum isothermal forging system. This method is applied to an intelligent allocation device within the fully enclosed vacuum isothermal forging system. The fully enclosed vacuum isothermal forging system also includes multiple furnaces operating in a vacuum environment and an intelligent robot that transfers billets between these furnaces. The method includes: acquiring attribute data of the billet to be allocated and performance data of an idle furnace; the idle furnace being one of the multiple furnaces in an idle state; determining the target furnace for heating the billet based on the attribute data of the billet to be allocated, the performance data of the idle furnace, and a furnace allocation model; wherein the furnace allocation model is used to predict the furnace for heating the billet based on the billet attribute data and the furnace performance data; and controlling the intelligent robot to transfer the billet to be allocated from the originally filled furnace to the target furnace.
[0007] The intelligent furnace allocation method for the fully enclosed vacuum isothermal forging system provided in this application includes multiple furnaces in a vacuum environment. These furnaces can heat the billet in a vacuum environment, which facilitates direct connection between the furnaces and the billet vacuum forging unit without breaking the vacuum, thereby improving transfer efficiency, avoiding the formation of coarse grains in the surface area due to the drop in billet temperature, and helping the target billet to achieve superplastic forming.
[0008] Furthermore, in the intelligent furnace allocation method of the fully enclosed vacuum isothermal forging system provided in this application, the intelligent allocation device can determine the target furnace for heating the billet to be allocated based on the attribute data of the billet to be allocated, the performance data of the idle furnace, and the furnace allocation model. Compared with the traditional manual furnace allocation method, it can avoid incorrect allocation caused by insufficient experience or negligence of the staff, provide more scientific and accurate allocation results, reduce interference from human factors, reduce safety risks caused by operational errors, and improve the intelligence level of the fully enclosed vacuum isothermal forging system.
[0009] Optionally, the attribute data includes: the size, material, weight of the billet, and heating process requirements; the performance data includes: the power of the heating furnace, the running time, the heating efficiency, and the record of the decrease in airtightness during the heating process.
[0010] Optionally, the method further includes updating the target heating furnace from an idle state to an occupied state.
[0011] In this way, when the intelligent distribution device distributes heating furnaces to other billets, it can avoid heating furnaces that have already distributed billets, thereby reducing the amount of calculation and avoiding heating furnace distribution conflicts.
[0012] Optionally, the method further includes: counting the prediction frequency of multiple heating furnaces being predicted as target heating furnaces by the heating furnace allocation model within a preset statistical period; and outputting maintenance prompt information for idle heating furnaces based on the existence of idle heating furnaces with prediction frequencies less than a frequency threshold among the multiple heating furnaces.
[0013] In the intelligent allocation method for heating furnaces in the fully enclosed vacuum isothermal forging system provided in this application, the intelligent allocation device can count the prediction frequency of multiple heating furnaces being predicted as target heating furnaces by the heating furnace allocation model within a preset statistical period. Idle heating furnaces with low prediction frequencies or even 0 may have defects that require maintenance. The intelligent allocation device can output maintenance prompt information for idle heating furnaces based on the existence of idle heating furnaces with prediction frequencies less than the frequency threshold among multiple heating furnaces. This timely prompts staff to maintain the idle heating furnaces, which can prevent potential failures and extend the service life of the heating furnace equipment.
[0014] Optionally, the heating furnace allocation model is trained by: obtaining a training sample set; the training sample set includes multiple training samples; each training sample includes attribute data of the training billet, performance data of the training heating furnace, and heating furnace label; and training a preset neural network based on the training sample set to obtain the heating furnace allocation model.
[0015] Optionally, the preset neural network includes a backpropagation (BP) neural network or a convolutional neural network (CNN).
[0016] Secondly, this application provides an intelligent furnace distribution device for a fully enclosed vacuum isothermal forging system. The fully enclosed vacuum isothermal forging system also includes multiple furnaces in a vacuum environment and an intelligent robot that transfers billets between the multiple furnaces. The intelligent distribution device includes: an acquisition module and a processing module; the acquisition module acquires attribute data of the billet to be distributed and performance data of the idle furnaces; the idle furnaces are the furnaces that are in an idle state among the multiple furnaces; the processing module determines the identifier of the target furnace corresponding to the billet to be distributed based on the attribute data of the billet to be distributed, the performance data of the idle furnaces, and the furnace distribution model; wherein, the furnace distribution model is used to predict the identifier of the furnace corresponding to the billet to be heated based on the attribute data of the billet and the performance data of the furnaces; and controls the intelligent robot to transfer the billet to be distributed from the originally filled furnace to the target furnace.
[0017] Optionally, the attribute data includes: the size, material, weight of the billet, and heating process requirements; the performance data includes: the power of the heating furnace, the running time, the heating efficiency, and the record of the decrease in airtightness during the heating process.
[0018] Optionally, the processing module is also used to update the target heating furnace from an idle state to an occupied state.
[0019] Optionally, the acquisition module is also used to count the prediction frequency of multiple heating furnaces being predicted as target heating furnaces by the heating furnace allocation model within a preset statistical period; the processing module is also used to output maintenance prompt information for idle heating furnaces based on the existence of idle heating furnaces among the multiple heating furnaces whose prediction frequency is less than the frequency threshold.
[0020] 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 data of the training billet, performance data of the training heating furnace, and heating furnace label; the processing module is also used to train a preset neural network based on the training sample set to obtain a heating furnace allocation model.
[0021] Optionally, the preset neural network includes a backpropagation (BP) neural network or a convolutional neural network (CNN).
[0022] Thirdly, this application provides an intelligent distribution device for the heating furnace of a fully enclosed vacuum isothermal forging system. The fully enclosed vacuum isothermal forging system further includes multiple heating furnaces in a vacuum environment and an intelligent robot for transferring billets in the multiple heating furnaces. The intelligent distribution device includes a processor and a memory. The memory stores instructions executable by the processor. When the processor is configured to execute the instructions, the intelligent distribution device enables the intelligent distribution device to perform the method described in the first aspect above.
[0023] Fourthly, this application provides a readable storage medium, comprising: software instructions; when the software instructions are executed in an intelligent allocation device, causing the intelligent allocation device to perform the method described in the first aspect above.
[0024] Fifthly, this application provides a computer program product, comprising: computer instructions; when the computer instructions are executed in an intelligent allocation device, causing the intelligent allocation device to perform the method described in the first aspect above.
[0025] The beneficial effects of the second to fifth aspects mentioned above can be referred to the first aspect, and will not be repeated here. Attached Figure Description
[0026] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0027] Figure 1 A top-view schematic diagram of the composition of the fully enclosed vacuum isothermal forging system provided in the embodiments of this application;
[0028] Figure 2 A schematic flowchart illustrating the intelligent furnace distribution method for a fully enclosed vacuum isothermal forging system provided in this application embodiment;
[0029] Figure 3 A schematic diagram of the composition of the intelligent distribution device for the heating furnace in the fully enclosed vacuum isothermal forging system provided in this application embodiment;
[0030] Figure 4 This is a schematic diagram of the composition of an intelligent distribution device for a heating furnace in another fully enclosed vacuum isothermal forging system provided in this application embodiment. Detailed Implementation
[0031] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0032] It should be noted that in the embodiments of this application, the words "exemplarily" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplarily" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplarily" or "for example" is intended to present the relevant concepts in a specific manner.
[0033] To facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish the same or similar items with essentially the same function and effect. Those skilled in the art can understand that the terms "first" and "second" are not intended to limit the quantity or execution order.
[0034] Near isothermal forging refers to heating the billet and the die to similar temperatures and forging at a relatively low strain rate.
[0035] Because near-isothermal forging can improve material properties, machining accuracy and surface quality, and can adapt to complex shapes and high strength requirements, it is now frequently used for forging aerospace components.
[0036] Traditional near-isothermal forging cannot achieve superplastic forming of the billet because the mold cannot be heated to the same high temperature as the billet.
[0037] Based on this, this application provides a method and apparatus for intelligent allocation of heating furnaces in a fully enclosed vacuum isothermal forging system. This method can heat the mold to the same high temperature as the billet and improve the transfer efficiency during billet heating. It avoids the problem of coarse grains easily forming in the surface area due to the drop in billet temperature, thereby solving the problem of superplastic forming of billet and mold under isothermal conditions. Furthermore, it can automatically allocate corresponding heating furnaces to different billets, thereby improving the intelligence level of the fully enclosed vacuum isothermal forging system.
[0038] The following description is provided in conjunction with the accompanying drawings.
[0039] Figure 1 This is a top-view schematic diagram of the composition of the fully enclosed vacuum isothermal forging system provided in an embodiment of this application. Figure 1 As shown, the fully enclosed vacuum isothermal forging system may include: a billet vacuum heating unit 100, a billet vacuum forging unit 200, a vacuum pumping unit 300, and an intelligent distribution device 400.
[0040] The vacuum heating unit 100 includes a vacuum tunnel 11. Multiple heating furnaces 12 can be installed on each side of the vacuum tunnel 11 along its length. Figure 1(The example shown is of three furnaces on each side: furnace 1, furnace 2, furnace 3, furnace 4, furnace 5, and furnace 6). Each furnace 12 is equipped with a rack 14 for placing billets 13.
[0041] Each heating furnace 12 may be equipped with a heating device. Figure 1 (Not shown in the image), this heating device can be used to heat the blank 13 placed in the material rack 14.
[0042] In some embodiments, the heating device in the heating furnace 12 may have a communication connection (e.g., wired or wireless connection) with the intelligent distribution device 400, which can receive drive signals from the intelligent distribution device 400 to drive the heating device to start or stop heating.
[0043] A track 15 is laid along the entire length of the vacuum tunnel 11, and an intelligent robot 16 for clamping the billet 13 is placed on the track 15. The intelligent robot 16 can slide back and forth along the track 15.
[0044] Each heating furnace 12 is provided with an openable sliding gate 17 on the side wall of the vacuum tunnel 11 (or on the side closer to the intelligent robot 16).
[0045] In some embodiments, a drive device may be provided on the sliding gate 17. Figure 1 (Not shown in the image). The drive device can have a communication connection with the intelligent distribution device 400 (e.g., a wired or wireless connection). The drive device can be used to receive drive signals from the intelligent distribution device 400, thereby driving the sliding gate 17 to open (e.g., open to a certain degree or fully open) or close.
[0046] As an example, the drive device may include a reduction gear and a drive motor. The drive device includes a driving gear and a driven rack, and an output gear is provided on the output shaft of the drive motor. The driving gear of the drive device meshes with the output gear of the drive motor, and the driven rack is fixed to the sliding gate 17, with the driving gear meshing with the driven rack. The drive motor can be used to receive drive signals from the intelligent distribution device 400 and rotate forward or backward according to the drive signals, thereby driving the sliding gate 17 to open or close via the drive device.
[0047] Each heating furnace 12 is also equipped with an openable furnace door 12a on its outer side (or the side away from the intelligent robot 16). During loading, the operator can place the billet 13 from the outside into the material rack 14 of each heating furnace 12 through the furnace door 12a.
[0048] The blank vacuum forging unit 200 may include a forging press 21, a vacuum forging chamber 22, and a connecting gate 23.
[0049] After the billet 13 is heated in the heating furnace 12, it can be taken out of the heating furnace 12 by the intelligent robot 16 and clamped to the connecting gate 23. The intelligent robot 16 can open the connecting gate 23 and load the billet 13 into the mold in the vacuum forging chamber 22, and then forging is performed by the forging press 21.
[0050] In some embodiments, a heating device may also be provided in the vacuum forging chamber 22, which can heat the mold in the vacuum forging chamber 22, and the heating temperature of the mold is the same as the heating temperature of the billet 13.
[0051] The vacuum pumping unit 300 may include a Roots pump and a diffusion pump, and is connected to each of the heating furnace 12, vacuum tunnel 11 and vacuum forging chamber 22 via vacuum pipes.
[0052] The vacuum unit 300 can be used to evacuate each heating furnace 12, vacuum tunnel 11, and vacuum forging chamber 22. In this case, after the vacuum unit 300 evacuates each heating furnace 12 and vacuum tunnel 11, each heating furnace 12 can also be understood as being in a vacuum environment. The opening and closing of the sliding gate 17 will not cause the heating furnace 12 to break the vacuum, but the opening of the furnace door 12a will cause the heating furnace 12 to break the vacuum. Therefore, after evacuating the heating furnace 12 and vacuum tunnel 11, if it is necessary to open the furnace door 12a of a certain heating furnace 12 for loading or unloading, the sliding gate 17 must be closed first to prevent the vacuum tunnel 11 and other heating furnaces 12 from breaking the vacuum.
[0053] In some embodiments, the vacuum unit 300 may further include a vacuum sensor that can be used to measure the vacuum level at each of the heating furnace 12, vacuum tunnel 11 and vacuum forging chamber 22.
[0054] The intelligent distribution device 400 can be used to automatically control all operations of the vacuum heating unit 100, the billet vacuum forging unit 200, and the vacuum pumping unit 300, and to allocate corresponding heating furnaces to different billets. The specific process can be referred to the intelligent distribution method of heating furnaces in the fully enclosed vacuum isothermal forging system provided in the following embodiment, and will not be repeated here.
[0055] The intelligent distribution method for the heating furnace of the fully enclosed vacuum isothermal forging system provided in this application embodiment is executed by an intelligent distribution device (such as the intelligent distribution device 400 described above). Optionally, the intelligent distribution method for the heating furnace of the fully enclosed vacuum isothermal forging system may also be the processor (e.g., a central processing unit, CPU) in the aforementioned intelligent distribution device; or, the execution subject may also be a software system installed in the aforementioned intelligent distribution device for executing the intelligent distribution method; or, the execution subject may also be a functional module in the aforementioned intelligent distribution device for executing the intelligent distribution method, etc. This application embodiment does not impose any limitations on this.
[0056] For simplicity, the following description will take the intelligent distribution device as the execution subject of the intelligent distribution method for the heating furnace of the fully enclosed vacuum isothermal forging system provided in the embodiments of this application.
[0057] Figure 2 This is a schematic flowchart illustrating the intelligent furnace distribution method for a fully enclosed vacuum isothermal forging system provided in this application embodiment. Figure 2 As shown, the method includes the following steps:
[0058] S101. Obtain the attribute data of the billet to be assigned and the performance data of the idle heating furnace.
[0059] Among them, an idle heating furnace is a heating furnace that is in an idle state among multiple heating furnaces. For example, each heating furnace is also equipped with a pressure sensor on the material rack. The intelligent distribution device can obtain the pressure signal collected by the pressure sensor and determine whether there is a billet on the material rack based on the pressure signal. The heating furnace with billets on the material rack is identified as occupied, and the heating furnace without billets on the material rack is identified as idle.
[0060] Optionally, the attribute data may include: the dimensions, material, weight of the billet, and heating process requirements.
[0061] Optionally, performance data may include: furnace power, operating time (or the duration of operation), heating efficiency, and records of airtightness degradation during the heating process.
[0062] In one possible implementation, the intelligent allocation device may include an input / output interface, such as a mouse, keyboard, or touchscreen display. The intelligent allocation device can receive attribute data of the blank to be allocated from the operator via the input / output interface.
[0063] In another possible implementation, the intelligent allocation device can also communicate with other devices or platforms, and can receive attribute data of the billets to be allocated from other devices or platforms.
[0064] In one possible implementation, the power of the heating furnace can be directly determined based on the rated power indicated on the furnace nameplate, and the intelligent distribution device can receive the rated power input by the operator as the power of the heating furnace.
[0065] In one possible implementation, the intelligent distribution device may maintain an operation log for each heating furnace, which may include the furnace's operating time, heating efficiency, and records of airtightness degradation during the heating process.
[0066] For example, an intelligent distribution device can control a heating furnace to start or stop heating. When controlling a heating furnace to start heating, the intelligent distribution device can simultaneously start a timer to record the duration of heating from start to stop, thus obtaining the duration of one heating cycle. By accumulating the duration of multiple heating cycles, the running time of the heating furnace can be obtained.
[0067] For example, intelligent distribution devices can also record the actual cumulative energy consumption and the theoretical cumulative energy consumption of the heating tasks performed over a period of time (such as within a week, a month, or a quarter), and calculate the heating efficiency based on the actual cumulative energy consumption and the theoretical cumulative energy consumption.
[0068] For example, each heating furnace can also be equipped with a vacuum sensor. The intelligent distribution device can determine whether the airtightness has decreased during the heating process based on the changes in the data detected by the vacuum sensor, and obtain a record of the decrease in airtightness during the heating process.
[0069] S102. Based on the attribute data of the billet to be assigned, the performance data of the idle heating furnace, and the heating furnace allocation model, determine the target heating furnace corresponding to the billet to be assigned.
[0070] The furnace allocation model is used to predict the appropriate furnace (or its identifier) for a given billet based on its attribute data and performance data. The specific training process for the furnace allocation model can be found in the following embodiments and will not be repeated here.
[0071] As an example, the intelligent allocation device can input the attribute data of the billet to be allocated and the performance data of the idle heating furnace into the heating furnace allocation model, obtain the identifier of the target heating furnace output by the heating furnace allocation model, and determine the target heating furnace based on the identifier.
[0072] S103. Control the intelligent robot to transfer the billet to be distributed from the original filling heating furnace to the target heating furnace.
[0073] For example, an intelligent distribution device can control the opening of the sliding gate of the original heating furnace and the sliding gate of the target heating furnace, and then control an intelligent robot to transfer the billet to be distributed from the original filling heating furnace to the target heating furnace.
[0074] The intelligent furnace allocation method for the fully enclosed vacuum isothermal forging system provided in this application embodiment includes multiple furnaces in a vacuum environment. These furnaces can heat the billet in a vacuum environment. This facilitates direct connection between the furnaces and the billet vacuum forging unit without breaking the vacuum, thereby improving transfer efficiency and preventing the billet temperature drop from causing coarse grains to form in the surface area, which helps the target billet achieve superplastic forming.
[0075] Furthermore, in the intelligent allocation method for heating furnaces in the fully enclosed vacuum isothermal forging system provided in this application embodiment, the intelligent allocation device can determine the target heating furnace corresponding to the heating of the billet to be allocated based on the attribute data of the billet to be allocated, the performance data of the idle heating furnace, and the heating furnace allocation model. Compared with the traditional manual allocation method, it can avoid incorrect allocation caused by insufficient experience or negligence of the staff, provide more scientific and accurate allocation results, reduce interference from human factors, reduce safety risks caused by operational errors, and improve the intelligence level of the fully enclosed vacuum isothermal forging system.
[0076] In some possible embodiments, after the billet to be allocated is transferred to the target heating furnace, or after the target heating furnace is determined but before the transfer action is performed, the intelligent allocation device may also update the target heating furnace from an idle state to an occupied state.
[0077] In this way, when the intelligent distribution device distributes heating furnaces to other billets, it can avoid heating furnaces that have already distributed billets, thereby reducing the amount of calculation and avoiding heating furnace distribution conflicts.
[0078] In some possible embodiments, the intelligent allocation device can also count the frequency of heating furnace allocation and identify idle heating furnaces with lower allocation frequencies for prompt maintenance. In this case, the method may also include the following steps:
[0079] Step 1a: Count the prediction frequency of multiple heating furnaces being predicted as the target heating furnace by the heating furnace allocation model within a preset statistical period.
[0080] The preset statistical period can be pre-set by staff in the intelligent allocation device. For example, the preset statistical period can be set to one day, one week, one month, or three months, etc. This application embodiment does not limit the specific duration of the preset statistical period.
[0081] Step 2a: Based on the existence of idle heating furnaces among multiple heating furnaces with a predicted frequency lower than the frequency threshold, output maintenance prompt information for the idle heating furnaces.
[0082] The frequency threshold can also be preset by staff in the intelligent allocation device. For example, the frequency threshold can be set to three, five, or ten times, etc. This application embodiment does not limit the specific value of the frequency threshold.
[0083] Optionally, if the predicted frequency of the heating furnace exceeds a frequency threshold, the intelligent distribution device may not output maintenance prompts.
[0084] It should be noted that when the predicted frequency of the heating furnace equals the frequency threshold, the intelligent allocation device may output maintenance prompts for the heating furnace, or it may not output maintenance prompts for the heating furnace. This application embodiment does not impose any limitations on this.
[0085] As an example, the intelligent distribution device can communicate with the staff's terminal device and send maintenance reminders for the heating furnace to the staff's terminal device.
[0086] As another example, each heating furnace can be equipped with a status indicator light. The intelligent distribution device can control the status indicator light at the idle heating furnace to display a preset light color to indicate that the idle heating furnace needs maintenance.
[0087] In the intelligent allocation method for heating furnaces in a fully enclosed vacuum isothermal forging system provided in this application embodiment, the intelligent allocation device can count the prediction frequency of multiple heating furnaces being predicted as target heating furnaces by the heating furnace allocation model within a preset statistical period. Idle heating furnaces with low prediction frequencies or even 0 may have defects that require maintenance. The intelligent allocation device can output maintenance prompt information for idle heating furnaces based on the existence of idle heating furnaces with prediction frequencies less than the frequency threshold among multiple heating furnaces. This timely prompts staff to maintain the idle heating furnaces, which can prevent potential failures and extend the service life of the heating furnace equipment.
[0088] In some possible embodiments, prior to S102 described above, the intelligent allocation device may also acquire the trained furnace allocation model.
[0089] In one possible implementation, the intelligent dispensing device can directly obtain the trained furnace dispensing model from other devices.
[0090] For example, the intelligent distribution device can obtain the trained furnace distribution model from other devices by downloading or transferring it through an intermediate storage medium.
[0091] In another possible implementation, the intelligent allocation device can also train a pre-defined neural network based on a training sample set to obtain a furnace allocation model. In this case, the method may further include the following steps:
[0092] Step 1b: Obtain the training sample set.
[0093] The training sample set includes multiple training samples, each of which includes attribute data of the training billet, performance data of the training furnace, and a furnace label. The furnace label can also be understood as an identifier for the furnace that heats the training billet, given the aforementioned attribute data and performance data. The training furnace can be the same as the furnace in a fully enclosed vacuum isothermal forging system, or it can be a furnace other than the furnace in a fully enclosed vacuum isothermal forging system; this embodiment does not impose any limitations on this.
[0094] Step 2b: Train the preset neural network based on the training sample set to obtain the heating furnace allocation model.
[0095] Optionally, the preset neural network may specifically be a back-propagation (BP) neural network or a convolutional neural network (CNN), etc. This application embodiment does not limit the specific type of preset neural network.
[0096] For example, as mentioned above, the training sample set may include multiple training samples. In this case, the intelligent allocation device can input one or more training samples into a preset neural network for training each time, obtain the predicted label output by the preset neural network, calculate the loss function based on the furnace label in the training samples and the preset label, adjust the parameters in the preset neural network according to the loss function, and repeat the training until the preset iteration stopping condition is reached.
[0097] Optionally, the preset iteration stopping condition may include: the number of times the intelligent allocation device inputs the training samples into the preset neural network reaches a threshold, and / or, the error between the predicted label output by the preset neural network and the heating furnace label in the training samples is less than an error threshold.
[0098] The number of attempts threshold can be preset by the staff in the intelligent allocation device. For example, the number of attempts threshold can be set to 500, 1000, or 5000, etc. This application embodiment does not limit the specific value of the number of attempts threshold. The error threshold can also be preset by the staff in the intelligent allocation device. For example, the error threshold can be set to 5%, 10%, or 15% (the percentage of prediction errors), etc. This application embodiment does not limit the specific number of errors.
[0099] The foregoing mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, the intelligent allocation device may include hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Technical objectives may be implemented using different methods for each specific application to achieve the described functions, but such implementation should not be considered beyond the scope of this application.
[0100] In an exemplary embodiment, this application also provides an intelligent distribution device for the heating furnace of a fully enclosed vacuum isothermal forging system. Figure 3 This is a schematic diagram illustrating the composition of the intelligent distribution device for the heating furnace in the fully enclosed vacuum isothermal forging system provided in this application embodiment. Figure 3 As shown, the intelligent allocation device includes an acquisition module 301 and a processing module 302.
[0101] The acquisition module 301 is used to acquire the attribute data of the billet to be allocated and the performance data of the idle heating furnace; the idle heating furnace is the heating furnace that is in an idle state among multiple heating furnaces;
[0102] The processing module 302 is used to determine the target heating furnace for heating the billet to be assigned based on the attribute data of the billet to be assigned, the performance data of the idle heating furnace, and the heating furnace allocation model; wherein, the heating furnace allocation model is used to predict the heating furnace for heating the billet to be assigned based on the attribute data of the billet and the performance data of the heating furnace; and to control the intelligent robot to transfer the billet to be assigned from the originally filled heating furnace to the target heating furnace.
[0103] In some possible embodiments, the attribute data includes: billet size, material, weight, and heating process requirements; performance data includes: furnace power, operating time, heating efficiency, and records of airtightness degradation during the heating process.
[0104] In other possible embodiments, the processing module 302 is also configured to update the target heating furnace from an idle state to an occupied state.
[0105] In some other possible embodiments, the acquisition module 301 is further configured to count the prediction frequency of multiple heating furnaces being predicted as target heating furnaces by the heating furnace allocation model within a preset statistical period; the processing module 302 is further configured to output maintenance prompt information for idle heating furnaces based on the existence of idle heating furnaces among the multiple heating furnaces whose prediction frequency is less than the frequency threshold.
[0106] In some other possible embodiments, the acquisition module 301 is further configured to acquire a training sample set; the training sample set includes multiple training samples; each training sample includes attribute data of the training billet, performance data of the training heating furnace, and heating furnace label; the processing module 302 is further configured to train a preset neural network based on the training sample set to obtain a heating furnace allocation model.
[0107] In some other possible embodiments, the preset neural network includes a backpropagation (BP) neural network or a convolutional neural network (CNN).
[0108] It should be noted that, Figure 3 The module division shown is illustrative and represents only one logical functional division; in actual implementation, other division methods are possible. For example, two or more functions can be integrated into a single processing module. These integrated modules can be implemented in hardware or as software functional units.
[0109] In an exemplary embodiment, this application also provides an intelligent distribution device for the heating furnace of a fully enclosed vacuum isothermal forging system. Figure 4 This is a schematic diagram illustrating the composition of an intelligent distribution device for a heating furnace in another fully enclosed vacuum isothermal forging system provided in this application embodiment. Figure 4 As shown, the intelligent distribution device includes: a processor 10, a memory 20, a communication line 30, a communication interface 40, and an input / output interface 50.
[0110] The processor 10, memory 20, communication interface 40, and input / output interface 50 can be connected via communication line 30.
[0111] The processor 10 is used to execute instructions stored in the memory 20 to implement the intelligent furnace allocation method for the fully enclosed vacuum isothermal forging system provided in the above embodiments of this application. The processor 10 can be a CPU, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller (MCU) / single-chip microcomputer / microcontroller, a programmable logic device (PLD), or any combination thereof. The processor 10 can also be any other device with processing capabilities, such as a circuit, device, or software module; this application embodiment does not limit this. In one example, the processor 10 may include one or more CPUs, for example... Figure 3CPU0 and CPU1 in the configuration. As an optional implementation, the intelligent allocation device may include multiple processors; for example, in addition to processor 10, it may also include processor 60. Figure 3 (The example shown is a dashed line).
[0112] The memory 20 is used to store instructions. For example, the instructions may be computer programs. Optionally, the memory 20 may be a read-only memory (ROM) or other type of static storage device that can store static information and / or instructions; it may also be a random access memory (RAM) or other type of dynamic storage device that can store information and / or instructions; it may also be an electrically erasable programmable read-only memory (EEPROM), a CD-ROM or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, etc. The embodiments of this application do not limit this.
[0113] It should be noted that the memory 20 can exist independently of the processor 10 or it can be integrated with the processor 10. The memory 20 can be located inside or outside the intelligent allocation device, and this application embodiment does not impose any restrictions on this.
[0114] Communication line 30 is used to transmit information between the components included in the intelligent distribution device.
[0115] Communication interface 40 is used to communicate with other devices or other communication networks. These other communication networks can be Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc. Communication interface 40 can be a module, circuit, transceiver, or any device capable of enabling communication.
[0116] Input / output interface 50 is used to enable human-computer interaction between the user and the intelligent distribution device. This includes actions, text, or voice interaction between the user and the intelligent distribution device.
[0117] For example, the input / output interface 50 can be a physical keyboard or a touch screen. The physical keyboard or touch screen enables motion or text interaction between the user and the intelligent distribution device.
[0118] It should be noted that, Figure 4The structure shown does not constitute a limitation on the intelligent distribution device, except Figure 4 In addition to the components shown, the intelligent dispensing device may include more or fewer components than illustrated, or combinations of certain components, or different arrangements of components.
[0119] In an exemplary embodiment, this application also provides a computer program product including computer instructions; when the computer instructions are executed in an intelligent allocation device, the intelligent allocation device performs the method described in the foregoing method embodiments.
[0120] In an exemplary embodiment, this application also provides a readable storage medium comprising software instructions. When the software instructions are executed in an intelligent allocation device, the intelligent allocation device causes the intelligent allocation device to implement the method described in the foregoing method embodiments. The computer-readable storage medium may be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.
[0121] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer-executable instructions. When these computer-executable instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. 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. For example, computer-executable instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.
[0122] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.
[0123] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.
[0124] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
Claims
1. A method for intelligent furnace distribution in a fully enclosed vacuum isothermal forging system, characterized in that, The method is applied to the intelligent distribution device of a fully enclosed vacuum isothermal forging system, which also includes multiple heating furnaces in a vacuum environment and intelligent robots that transfer billets in the multiple heating furnaces. The method includes: Acquire the attribute data of the billet to be assigned and the performance data of the idle heating furnace; the idle heating furnace is the heating furnace that is in an idle state among multiple heating furnaces; the attribute data includes: the size, material, weight of the billet, and heating process requirements; the performance data includes: the power of the heating furnace, running time, heating efficiency, and records of airtightness decrease during the heating process; Based on the attribute data of the billet to be allocated, the performance data of the idle heating furnace, and the heating furnace allocation model, the target heating furnace corresponding to heating the billet to be allocated is determined; wherein, the heating furnace allocation model is used to predict the heating furnace corresponding to the billet to be heated based on the attribute data of the billet and the performance data of the heating furnace. The intelligent robot is controlled to transfer the billet to be distributed from the original filling furnace to the target furnace; The prediction frequency of the multiple heating furnaces being predicted as the target heating furnace by the heating furnace allocation model within a preset statistical period is counted. Based on the existence of an idle heating furnace among the multiple heating furnaces with a predicted frequency lower than the frequency threshold, maintenance prompt information for the idle heating furnace is output.
2. The method according to claim 1, characterized in that, The method further includes: Update the target heating furnace from idle to occupied.
3. The method according to claim 1, characterized in that, The furnace allocation model was trained in the following way: Obtain a training sample set; the training sample set includes multiple training samples; each training sample includes attribute data of the training billet, performance data of the training heating furnace, and heating furnace labels; The preset neural network is trained based on the training sample set to obtain the heating furnace allocation model.
4. The method according to claim 3, characterized in that, The preset neural network includes a backpropagation (BP) neural network or a convolutional neural network (CNN).
5. An intelligent distribution device for a heating furnace in a fully enclosed vacuum isothermal forging system, characterized in that, The fully enclosed vacuum isothermal forging system also includes multiple heating furnaces in a vacuum environment, and intelligent robots that transfer billets in multiple heating furnaces; The intelligent allocation device includes: an acquisition module and a processing module; The acquisition module acquires the attribute data of the billet to be allocated and the performance data of the idle heating furnace; the idle heating furnace is the heating furnace that is in an idle state among multiple heating furnaces; the attribute data includes: the size, material, weight of the billet, and heating process requirements; the performance data includes: the power of the heating furnace, the running time, the heating efficiency, and the record of the decrease in airtightness during the heating process; The processing module determines the identifier of the target heating furnace corresponding to the billet to be allocated, based on the attribute data of the billet to be allocated, the performance data of the idle heating furnace, and the heating furnace allocation model. The heating furnace allocation model is used to predict the identifier of the heating furnace corresponding to the billet to be heated based on the billet's attribute data and the heating furnace's performance data. The module controls the intelligent robot to transfer the billet to be allocated from the originally loaded heating furnace to the target heating furnace. It counts the prediction frequency of multiple heating furnaces being predicted as target heating furnaces by the heating furnace allocation model within a preset statistical period. Based on the existence of idle heating furnaces among the multiple heating furnaces with prediction frequencies less than a frequency threshold, it outputs maintenance prompt information for the idle heating furnaces.
6. An intelligent distribution device for a heating furnace in a fully enclosed vacuum isothermal forging system, characterized in that, The fully enclosed vacuum isothermal forging system also includes multiple heating furnaces in a vacuum environment, and intelligent robots that transfer billets in multiple heating furnaces; The intelligent allocation device includes: a processor and a memory; The memory stores instructions that the processor can execute; When the processor is configured to execute the instructions, the intelligent allocation device implements the method as described in any one of claims 1-4.
7. A readable storage medium, characterized in that, include: Software instructions; When the software instructions are executed in the intelligent allocation device, the intelligent allocation device causes the intelligent allocation device to implement the method as described in any one of claims 1-4.
8. A computer program product, characterized in that, include: Computer instructions; When the computer instructions are executed in the intelligent allocation device, the intelligent allocation device causes the intelligent allocation device to perform the method as described in any one of claims 1-4.